Dissertations / Theses on the topic 'Motion data'
To see the other types of publications on this topic, follow the link: Motion data.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Motion data.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Kröger, Viktor. "Classification in Functional Data Analysis : Applications on Motion Data." Thesis, Umeå universitet, Institutionen för matematik och matematisk statistik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-184963.
Abstract:
Anterior cruciate knee ligament injuries are common and well known, especially amongst athletes.These injuries often require surgeries and long rehabilitation programs, and can lead to functionloss and re-injuries (Marshall et al., 1977). This work aims to explore the possibility of applyingsupervised classification on knee functionality, using different types of models, and testing differentdivisions of classes. The data used is gathered through a performance test, where individualsperform one-leg hops with motion sensors attached to their bodies. The obtained data representsthe position over time, and is considered functional data.With functional data analysis (FDA), a process can be analysed as a continuous function of time,instead of being reduced to finite data points. FDA includes many useful tools, but also somechallenges. A functional observation can for example be differentiated, a handy tool not found inthe multivariate tool-box. The speed, and acceleration, can then be calculated from the obtaineddata. How to define "similarity" is, on the other hand, not as obvious as with points. In this work,an FDA-approach is taken on classifying knee kinematic data, from a long-term follow-up studyon knee ligament injuries.This work studies kernel functional classifiers, and k-nearest neighbours models, and performssignificance tests on the model accuracy, using re-sampling methods. Additionally, depending onhow similarity is defined, the models can distinguish different features of the data. Attempts atutilising more information through incorporation of ensemble-methods, does not exceed the singlemodels it is created from. Further, it is shown that classification on optimised sub-domains, canbe superior to classifiers using the full domain, in terms of predictive power.Främre korsbandsskador är vanliga och välkända skador, speciellt bland idrottsutövare. Skadornakräver ofta operationer och långa rehabiliteringsprogram, och kan leda till funktionell nedsättningoch återskador (Marshall et al., 1977). Målet med det här arbetet är att utforska möjligheten attklassificera knän utifrån funktionalitet, där utfallet är känt. Detta genom att använda olika typerav modeller, och genom att testa olika indelningar av grupper. Datat som används är insamlatunder ett prestandatest, där personer hoppat på ett ben med rörelsesensorer på kroppen. Deninsamlade datan representerar position över tid, och betraktas som funktionell data.Med funktionell dataanalys (FDA) kan en process analyseras som en kontinuerlig funktion av tid,istället för att reduceras till ett ändligt antal datapunkter. FDA innehåller många användbaraverktyg, men även utmaningar. En funktionell observation kan till exempel deriveras, ett händigtverktyg som inte återfinns i den multivariata verktygslådan. Hastigheten och accelerationen kandå beräknas utifrån den insamlade datan. Hur "likhet" är definierat, å andra sidan, är inte likauppenbart som med punkt-data. I det här arbetet används FDA för att klassificera knärörelsedatafrån en långtidsuppföljningsstudie av främre korsbandsskador.I detta arbete studeras både funktionella kärnklassificerare och k-närmsta grannar-metoder, och ut-för signifikanstest av modellträffsäkerheten genom omprovtagning. Vidare kan modellerna urskiljaolika egenskaper i datat, beroende på hur närhet definieras. Ensemblemetoder används i ett försökatt nyttja mer av informationen, men lyckas inte överträffa någon av de enskilda modellerna somutgör ensemblen. Vidare så visas också att klassificering på optimerade deldefinitionsmängder kange en högre förklaringskraft än klassificerare som använder hela definitionsmängden.
2
Tanco, L. Molina. "Human motion synthesis from captured data." Thesis, University of Surrey, 2002. http://epubs.surrey.ac.uk/844411/.
Abstract:
Animation of human motion is one of the most challenging topics in computer graphics. This is due to the large number of degrees of freedom of the body and to our ability to detect unnatural motion. Keyframing and interpolation remains the form of animation that is preferred by most animators because of the control and flexibility it provides. However this is a labour intensive process that requires skills that take years to acquire. Human motion capture techniques provide accurate measurement of the motion of a performer that can be mapped onto an animated character to provide strikingly natural animation. This raises the problem of how to allow an animator to modify captured movement to produce a desired animation whilst preserving the natural quality. This thesis introduces a new approach to the animation of human motion based on combining the flexibility of keyframing with the visual quality of motion capture data. In particular it addresses the problem of synthesising natural inbetween motion for sparse keyframes. This thesis proposes to obtain this motion by sampling high quality human motion capture data. The problem of keyframe interpolation is formulated as a search problem in a graph. This presents two difficulties: The complexity of the search makes it impractical for the large databases of motion capture required to model human motion. The second difficulty is that the global temporal structure in the data may not be preserved in the search. To address these difficulties this thesis introduces a layered framework that both reduces the complexity of the search and preserves the global temporal structure of the data. The first layer is a simplification of the graph obtained by clustering methods. This layer enables efficient planning of the search for a path between start and end keyframes. The second layer directly samples segments of the original motion data to synthesise realistic inbetween motion for the keyframes. A number of additional contributions are made including novel representations for human motion, pose similarity cost functions, dynamic programming algorithms for efficient search and quantitative evaluation methods. Results of realistic inbetween motion are presented with databases of up to 120 sequences (35000 frames). Key words: Human Motion Synthesis, Motion Capture, Character Animation, Graph Search, Clustering, Unsupervised Learning, Markov Models, Dynamic Programming.
3
Miller, Iain. "Finding associations in motion capture data." Thesis, University of the West of Scotland, 2013. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.729427.
4
Gonzalez, Rojas Paloma (Paloma Francisca). "Space and motion : data based rules of public space pedestrian motion." Thesis, Massachusetts Institute of Technology, 2015. http://hdl.handle.net/1721.1/99288.
Abstract:
Thesis: S.M., Massachusetts Institute of Technology, Department of Architecture, 2015.Title as it appears in MIT Commencement Exercises program, June 5, 2015: Space and motion : the case of pedestrian in public spaces. Cataloged from PDF version of thesis.
Includes bibliographical references (pages 106-107).
The understanding of space relies on motion, as we experience space by crossing it. While in motion we sense the environment in time, interacting with space. The vision of this thesis is to incorporate people's motion into architecture design process, enabled by technology. Simulation tools that introduce human motion into the design process in early stages are rare to nonexistent. Available tools are typically used for deterministically visualizing figures and simulating pedestrians with the goal of analyzing emergency exits or egress. Such simulations are built without consideration for non-goal oriented interaction with space; this presents a gap for design. Additionally, simulations are generally governed by assumptions regarding people's motion behavior or by analogous models such as collision avoidance methods. However, the use of data from people can elucidate spatial behavior. Advancements in depth camera sensors and computer vision algorithms have eased the task of tracking human movements to millimetric precision. This thesis proposes two main ideas: creating statistics from people's motion data for grounding simulations and measuring such motion in relation to space, developing a Space- Motion Metric. This metric takes pedestrian motion and spatial features as input, seeks actions composed by speed, time, gestures, direction, shape and scale. The actions are elaborated as Space-Motion Rules through substantial data analysis. The non-prescriptive combination of the rules generates a non-deterministic behavior focused on design. This research maps, quantifies, and formulates pedestrian motion correlation with space and questions the role of data for projecting what space could be.
by Paloma Gonzalez Rojas.
S.M.
5
Williams, Ben H. "Extracting motion primitives from natural handwriting data." Thesis, University of Edinburgh, 2009. http://hdl.handle.net/1842/3221.
Abstract:
Humans and animals can plan and execute movements much more adaptably and reliably than current computers can calculate robotic limb trajectories. Over recent decades, it has been suggested that our brains use motor primitives as blocks to build up movements. In broad terms a primitive is a segment of pre-optimised movement allowing a simplified movement planning solution. This thesis explores a generative model of handwriting based upon the concept of motor primitives. Unlike most primitive extraction studies, the primitives here are time extended blocks that are superimposed with character specific offsets to create a pen trajectory. This thesis shows how handwriting can be represented using a simple fixed function superposition model, where the variation in the handwriting arises from timing variation in the onset of the functions. Furthermore, it is shown how handwriting style variations could be due to primitive function differences between individuals, and how the timing code could provide a style invariant representation of the handwriting. The spike timing representation of the pen movements provides an extremely compact code, which could resemble internal spiking neural representations in the brain. The model proposes an novel way to infer primitives in data, and the proposed formalised probabilistic model allows informative priors to be introduced providing a more accurate inference of primitive shape and timing.
6
Rogers, Bennett Lee. "Query-by-example for motion capture data." Thesis, Massachusetts Institute of Technology, 2007. http://hdl.handle.net/1721.1/42255.
Abstract:
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2007.Includes bibliographical references (p. 57-58).
Motion capture datasets are employed widely in animation research and industry, however there currently exists no efficient way to index and search this data for diversified use. Motion clips are generally searched by filename or keywords, neither of which incorporates knowledge of actions in the clip aside from those listed in the descriptions. We present a method for indexing and searching a large database of motion capture clips that allows for fast insertion and query-by-example. Over time, more motions can be added to the index, incrementally increasing its value. The result is a tool that reduces the amount of time spent gathering new data for motion applications, and increases the utility of existing motion clips.
by Bennett Lee Rogers.
S.M.
7
Wang, Zhao. "Motion capture data processing, retrieval and recognition." Thesis, Bournemouth University, 2018. http://eprints.bournemouth.ac.uk/31038/.
Abstract:
Character animation plays an essential role in the area of featured film and computer games. Manually creating character animation by animators is both tedious and inefficient, where motion capture techniques (MoCap) have been developed and become the most popular method for creating realistic character animation products. Commercial MoCap systems are expensive and the capturing process itself usually requires an indoor studio environment. Procedural animation creation is often lacking extensive user control during the generation progress. Therefore, efficiently and effectively reusing MoCap data can brings significant benefits, which has motivated wider research in terms of machine learning based MoCap data processing. A typical work flow of MoCap data reusing can be divided into 3 stages: data capture, data management and data reusing. There are still many challenges at each stage. For instance, the data capture and management often suffer from data quality problems. The efficient and effective retrieval method is also demanding due to the large amount of data being used. In addition, classification and understanding of actions are the fundamental basis of data reusing. This thesis proposes to use machine learning on MoCap data for reusing purposes, where a frame work of motion capture data processing is designed. The modular design of this framework enables motion data refinement, retrieval and recognition. The first part of this thesis introduces various methods used in existing motion capture processing approaches in literature and a brief introduction of relevant machine learning methods used in this framework. In general, the frameworks related to refinement, retrieval, recognition are discussed. A motion refinement algorithm based on dictionary learning will then be presented, where kinematical structural and temporal information are exploited. The designed optimization method and data preprocessing technique can ensure a smooth property for the recovered result. After that, a motion refinement algorithm based on matrix completion is presented, where the low-rank property and spatio-temporal information is exploited. Such model does not require preparing data for training. The designed optimization method outperforms existing approaches in regard to both effectiveness and efficiency. A motion retrieval method based on multi-view feature selection is also proposed, where the intrinsic relations between visual words in each motion feature subspace are discovered as a means of improving the retrieval performance. A provisional trace-ratio objective function and an iterative optimization method are also included. A non-negative matrix factorization based motion data clustering method is proposed for recognition purposes, which aims to deal with large scale unsupervised/semi-supervised problems. In addition, deep learning models are used for motion data recognition, e.g. 2D gait recognition and 3D MoCap recognition. To sum up, the research on motion data refinement, retrieval and recognition are presented in this thesis with an aim to tackle the major challenges in motion reusing. The proposed motion refinement methods aim to provide high quality clean motion data for downstream applications. The designed multi-view feature selection algorithm aims to improve the motion retrieval performance. The proposed motion recognition methods are equally essential for motion understanding. A collection of publications by the author of this thesis are noted in publications section.
8
Hosseini, Babak [Verfasser]. "Interpretable analysis of motion data / Babak Hosseini." Bielefeld : Universitätsbibliothek Bielefeld, 2021. http://d-nb.info/1237815509/34.
9
Larsson, Albin. "MC.d.o.t : Motion capture data och dess tillgänglighet." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2014. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-9622.
Abstract:
Hårdvara kan bli gammal, program kan sluta utvecklas, filer som skapats från sådan hårdvara respektive mjukvara kan bli oanvändbara med tiden. Samt att hålla ordning på många individuella filer kan i längden bli jobbigt för användare. Med en databasorienterad lagrinsgslösning kan olika API:er användas för att göra data kompatibel med flera olika verktyg och program, samt att det kan användas för att skapa en centraliserad lösning för att enkelt hålla ordning på information. Bland databaser finns det två primära grupperingar: SQL och NoSQL. Detta arbete ämnar undersöka vilken typ som passar för att hantera motion capture data. Tester har utförts på SQLs MySQL och NoSQLs Neo4j. Neo4j som är specialiserad för att hantera data som motion capture data. Resultatet från testningarna är förvånande nog att MySQL hanterar motion capture data bättre än Neo4j. Ytterligare arbeten för att undersöka fler varianter av databaser för en mer komplett bild föreslås.
10
Svensson, Niclas. "Structure from Motion with Unstructured RGBD Data." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-302553.
Abstract:
This thesis covers the topic of depth- assisted Structure from Motion (SfM). When performing classic SfM, the goal is to reconstruct a 3D scene using only a set of unstructured RGB images. What is attempted to be achieved in this thesis is adding the depth dimension to the problem formulation, and consequently create a system that can receive a set of RGBD images. The problem has been addressed by modifying an already existing SfM pipeline and in particular, its Bundle Adjustment (BA) process. Comparisons between the modified framework and the baseline framework resulted in conclusions regarding the impact of the modifications. The results show mainly two things. First of all, the accuracy of the framework is increased in most situations. The difference is the most significant when the captured scene only is covered from a small sector. However, noisy data can cause the modified pipeline to decrease in performance. Secondly, the run time of the framework is significantly reduced. A discussion of how to modify other parts of the pipeline is covered in the conclusion of the report.Följande examensarbete behandlar ämnet djupassisterad Struktur genom Rörelse (eng. SfM). Vid klassisk SfM är målet att återskapa en 3D scen, endast med hjälp av en sekvens av oordnade RGB bilder. I djupassiterad SfM adderas djupinformationen till problemformulering och följaktligen har ett system som kan motta RGBD bilder skapats. Problemet har lösts genom att modifiera en befintlig SfM- mjukvara och mer specifikt dess Buntjustering (eng. BA). Resultatet från den modifierade mjukvaran jämförs med resultatet av originalutgåvan för att dra slutsatser rådande modifikationens påverkan på prestandan. Resultaten visar huvudsakligen två saker. Först och främst, den modifierade mjukvaran producerar resultat med högre noggrannhet i de allra flesta fall. Skillnaden är som allra störst när bilderna är tagna från endast en liten sektor som omringar scenen. Data med brus kan dock försämra systemets prestanda aningen jämfört med orginalsystemet. För det andra, så minskar exekutionstiden betydligt. Slutligen diskuteras hur mjukvaran kan vidareutvecklas för att ytterligare förbättra resultaten.
11
Segelstad, Johan. "Layering animation principles on motion capture data : Surpass the limitations of motion capture." Thesis, Luleå tekniska universitet, Institutionen för konst, kommunikation och lärande, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-74636.
Abstract:
This thesis deals with the use of Disney's twelve animation principles in relation to Motion Capture. The purpose of the work was to investigate whether animation principles can be applied to finished motion capture animations to surpass the limitations of motion capture by using animation layers, where each added layer is a new principle. To investigate this, motion capture data was retrieved with various movements from Mixamo, which was then imported into Maya where various animation principles were applied with the help of Maya animation layers. The result of this research will answer the following… Is it possible to surpass the limitations of motion capture by layering disney's animation principles on motion captured animations in Maya with the use of animation layers?
12
Röder, Tido. "Similarity, retrieval, and classification of motion capture data." [S.l.] : [s.n.], 2006. http://deposit.ddb.de/cgi-bin/dokserv?idn=983632332.
13
Brunner, Seth A. "Improved Computer-Generated Simulation Using Motion Capture Data." BYU ScholarsArchive, 2014. https://scholarsarchive.byu.edu/etd/4182.
Abstract:
Ever since the first use of crowds in films and videogames there has been an interest in larger, more efficient and more realistic simulations of crowds. Most crowd simulation algorithms are able to satisfy the viewer from a distance but when inspected from close up the flaws in the individual agent's movements become noticeable. One of the bigger challenges faced in crowd simulation is finding a solution that models the actual movement of an individual in a crowd. This paper simulates a more realistic crowd by using individual motion capture data as well as traditional crowd control techniques to reach an agent's desired goal. By augmenting traditional crowd control algorithms with the use of motion capture data for individual agents, we can simulate crowds that mimic more realistic crowd motion, while maintaining real-time simulation speed.
14
Dai, Chengxin. "Exploring Data Quality of Weigh-In-Motion Systems." PDXScholar, 2013. https://pdxscholar.library.pdx.edu/open_access_etds/1018.
Abstract:
This research focuses on the data quality control methods for evaluating the performance of Weigh-In-Motion (WIM) systems on Oregon highways. This research identifies and develops a new methodology and algorithm to explore the accuracy of each station's weight and spacing data at a corridor level, and further implements the Statistical Process Control (SPC) method, finite mixture model, axle spacing error rating method, and data flag method in published research to examine the soundness of WIM systems. This research employs the historical WIM data to analyze sensor health and compares the evaluation results of the methods. The results suggest the new triangulation method identified most possible WIM malfunctions that other methods sensed, and this method unprecedentedly monitors the process behavior with controls of time and meteorological variables. The SPC method appeared superior in differentiating between sensor noises and sensor errors or drifts, but it drew wrong conclusions when accurate WIM data reference was absent. The axle spacing error rating method cannot check the essential weight data in special cases, but reliable loop sensor evaluation results were arrived at by employing this multiple linear regression model. The results of the data flag method and the finite mixed model results were not accurate, thus they could be used as additional tools to complement the data quality evaluation results. Overall, these data quality analysis results are the valuable sources for examining the early detection of system malfunctions, sensor drift, etc., and allow the WIM operators to correct the situation on time before large amounts of measurement are lost.
15
Müglich, Marcel. "Motion Feature Extraction of Video and Movie Data." Thesis, KTH, Numerisk analys, NA, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-214030.
Abstract:
Since the Video on Demand market grows at a fast rate in terms of available content and user numbers, the task arises to match personal relevant content to each individual user. This problem is tackled by implementing a recommondation system which finds relevant content by automatically detecting patterns in the individual user’s behaviour. To find such patterns, either collaborative filtering, which evaluates patterns of user groups to draw conclusions about a single user’s preferences, or content based strategies can be applied. Those content strategies analyze the watched movies of the individual user and extract quantifiable information from them. This information can be utilized to find relevant movies with similar features. The focus of this thesis lies on the extraction of motion features from movie and video data. Three feature extraction methods are presented and evaluated which classify camera movement, estimate the motion intensity and detect film transitions.VOD-marknaden (Video på begäran) är en växande marknad, dels i mängden tillgängligt innehåll samt till antalet användare. Det skapar en utmaning att matcha personligt relevant innehåll för varje enskild användare. Utmaningen hanteras genom att implementera ett rekommendationssystem som hittar relevant innehåll genom att automatiskt identifiera mönster i varje användaren beteende. För att hitta sådana mönster används i vanliga fall Collaborative filtering; som utvärderar mönster utifrån grupper av flera användare och kors- rekommenderar produkter mellan dem utan att ta nämnvärd hänsyn till produktens innehåll. (De som har köpt X har också köpt Y) Ett alternativ till detta är att tillämpa en innehållsbaserad strategi. Innehållsbaserade strategier analyserar den faktiska video-datan i de produkter som har konsumerats av en enskild användare med syfte att därifrån extrahera kvantifierbar information. Denna information kan användas för att hitta relevanta filmer med liknande videoinnehåll. Inriktningen för denna avhandling berör utvinning av kamerarörelsevektorer från film- och videodata. Tre extraktionsmetoder presenteras och utvärderas för att klassificera kamerans rörelse, kamerarörelsen intensitet och för att detektera scenbyten.
16
Peressutti, Devis. "Motion modelling for respiratory motion estimation in minimally invasive cardiac interventions using intraprocedure ultrasound data." Thesis, King's College London (University of London), 2014. https://kclpure.kcl.ac.uk/portal/en/theses/motion-modelling-for-respiratory-motion-estimation-in-minimally-invasive-cardiac-interventions-using-intraprocedure-ultrasound-data(b23f01f8-9246-4230-a76d-8c38594fd8dc).html.
Abstract:
Respiratory motion of the heart limits the utility of image-guided cardiac interventions, causing misalignments between the pre-procedure information used for guidance and the intra-procedure moving anatomy and instruments. As a result, the guidance can be misleading, compromising the accuracy and success of the intervention. Respiratory motion models have been proposed to estimate and correct for respiratory motion, but to date their clinical uptake has been very limited due to a lack of accuracy and robustness, and the interruptions that they typically introduce into the clinical work flow. The scope of this project was to devise methods to address these limitations and foster the clinical translation of respiratory motion models. A novel Bayesian respiratory motion model was developed in the first part of the project. The Bayesian framework enables the combination of the robustness of a pre-procedure motion model derived from Magnetic Resonance Imaging with the intraprocedure information provided by 3D echography (echo) images. The main novelties of the approach lie in its probabilistic formulation and its ability to adapt to variable breathing patterns. The Bayesian motion model was further evaluated using live 2D echo images, proving to be accurate using both 2D and 3D echo images. Furthermore, a new motion model-driven echo acquisition framework was developed to acquire 2D echo images that automatically compensates for respiratory motion. The second part of the project addressed the limitations associated with the dynamic calibration scan used to derive the motion model, the acquisition of which causes interruptions to the clinical work flow. A personalisation framework for population based motion models that uses anatomical features to predict cardiac respiratory motion was developed. Results show an average value for the 50th and 95th quantiles of the estimation error of 1:6mm and 4:7mm respectively, without the need for a subject-specific dynamic calibration scan. Finally, the above mentioned parts were combined to produce a personalised Bayesian motion model. The technique is accurate and does not significantly complicate the clinical workflow, thus making it suitable for clinical uptake.
17
Howard, Matthew. "Learning control policies from constrained motion." Thesis, University of Edinburgh, 2009. http://hdl.handle.net/1842/3972.
Abstract:
Many everyday human skills can be framed in terms of performing some task subject to constraints imposed by the task or the environment. Constraints are usually unobservable and frequently change between contexts. In this thesis, we explore the problem of learning control policies from data containing variable, dynamic and non-linear constraints on motion. We show that an effective approach for doing this is to learn the unconstrained policy in a way that is consistent with the constraints. We propose several novel algorithms for extracting these policies from movement data, where observations are recorded under different constraints. Furthermore, we show that, by doing so, we are able to learn representations of movement that generalise over constraints and can predict behaviour under new constraints. In our experiments, we test the algorithms on systems of varying size and complexity, and show that the novel approaches give significant improvements in performance compared with standard policy learning approaches that are naive to the effect of constraints. Finally, we illustrate the utility of the approaches for learning from human motion capture data and transferring behaviour to several robotic platforms.
18
Nar, Selim. "A Virtual Human Animation Tool Using Motion Capture Data." Master's thesis, METU, 2008. http://etd.lib.metu.edu.tr/upload/12609683/index.pdf.
Abstract:
In this study, we developed an animation tool to animate 3D virtual characters. The tool offers facilities to integrate motion capture data with a 3D character mesh and animate the mesh by using Skeleton Subsurface Deformation and Dual Quaternion Skinning Methods. It is a compact tool, so it is possible to distribute, install and use the tool with ease.
This tool can be used to illustrate medical kinematic gait data for educational purposes. For validation, we obtained medical motion capture data from two separate sources and animated a 3D mesh model by using this data. The animations are presented to physicians for evaluation. The results show that the tool is sufficient in displaying obvious gait patterns of the patients.
The tool provides interactivity for inspecting the movements of patient from different angles and distances. We animate anonymous virtual characters which provide anonymity of the patient.
19
Wills, Joshua J. "Data analysis methods for motion segmentation and material reflectance." Connect to a 24 p. preview or request complete full text in PDF format. Access restricted to UC campuses, 2006. http://wwwlib.umi.com/cr/ucsd/fullcit?p3211281.
Abstract:
Thesis (Ph. D.)--University of California, San Diego, 2006.Title from first page of PDF file (viewed June 7, 2006). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references (p. 104-112).
20
O'Neill, Jennifer K. "Backdriving a full motion simulator using flight recorder data." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape3/PQDD_0015/MQ53325.pdf.
21
Hesse, Nikolas [Verfasser], and Ulrich [Akademischer Betreuer] Hofmann. "Unobtrusive medical infant motion analysis from RGB-D data." Freiburg : Universität, 2019. http://d-nb.info/121195675X/34.
22
Das, Mitali. "Motion within music : the analysis of multivariate MIDI data." Thesis, University of York, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.367466.
23
Basuki, Herry. "Generating novel animations of avatars using human motion data /." Leeds : University of Leeds, School of Computer Studies, 2003. http://www.leeds.ac.uk/cgi-bin/library/compst.pl?CAT=BSC&FILE=200304/basuki.pdf.
24
Foster, Matthew. "Reconstruction and motion estimation of sparsely sampled ionospheric data." Thesis, University of Bath, 2009. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.503658.
Abstract:
This thesis covers two main areas which are related to the mapping and examination of the ionosphere. The first examines the performance and specific nuances of various state-of-the-art interpolation methods with specific application to mapping the ionosphere. This work forms the most widely scoped examination of interpolation technique for ionospheric imaging to date, and includes the introduction of normalised convolution techniques to geophysical data. In this study, adaptive-normalised convolution was found to perform well in ionospheric electron content mapping, and the popular technique, kriging was found to have problems which limit its usefulness. The second, is the development and examination of automatic data-driven motion estimation methods for use on ionospheric electron content data. Particular emphasis is given to storm events, during which characteristic shapes appear and move across the North Pole. This is a particular challenge, as images covering this region tend to have a very-low resolution. Several motion estimation methods are developed and applied to such data, including methods based on optical flow, correlation and boundarycorrespondence. Correlation and relaxation labelling based methods are found to perform reasonably, and boundary based methods based on shape-context matching are found to perform well, when coupled with a regularisation stage. Overall, the techniques examined and developed here will help advance the process of examining the features and morphology of the ionosphere, both during storms and quiet times.
25
Arvedson, Tilde, and Anna Lundemo. "Analysing and classifying wheelchair movements from motion capture data." Thesis, KTH, Skolan för teknikvetenskap (SCI), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-167132.
Abstract:
This is a project that describes a part of the development of a tool intended for wheelchair users in their learning process of new and important movements in everyday life and in sports. The process began with an investigation, with the help of people with wheelchair experience, of which movements that were considered important and which were considered useful in sports and in everyday life. The project was first focused on improving the technical skills of athletes practicing wheelchair sports. After studies and discussions it however changed focus, to also deal with obstacles in everyday life and to help people using wheelchairs to learn more everyday movements. After practical workshops, a mechanical analysis of the wheelchair was made. Some types of movement patterns, such as balancing on the rear wheels and turning, was considered essential to study and the goal was also to get information about for example the speed and acceleration of the wheelchair. This was to be analysed in real time and then sonified in later steps. We developed a code torecognize and assess these movements, which is the product of the project.Detta är ett projekt som beskriver en del av utvecklingsprocessen för ett verktyg ämnat för rullstolsåkare i deras inlärningsprocess av nya och viktiga rörelser i vardagen och i sportsammanhang. Processen började med en undersökning, med hjälp av rullstolsburna,av vilka rörelser som ansågs svåra och vilka som ansågs använd bara inom sport och i vardagen. Projektet var först inriktat mot att förbättra tekniken hos idrottsutövare inom rullstolssporter. Efter undersökningar och diskussioner bytte det dock senare bana, till att även handla om hinder i vardagen och att hjälpa rullstolsåkare att lära sig vardagligare rörelser. Efter praktiska workshops gjordes en mekanisk analys av rullstolen. Vissa typer av rörelsemönster, till exempel balansering på bakhjul och sväng, ansågs vara viktiga att studera och målet var även att få information om till exempel rullstolens hastighet och acceleration. Detta skulle analyseras i realtid för att sedan sonifieras i senare steg. Vi utvecklade en kod för att känna igen och bedöma dessa rörelser, vilket är produkten av projektet.
26
Cheng, Yafeng. "Functional regression analysis and variable selection for motion data." Thesis, University of Newcastle upon Tyne, 2016. http://hdl.handle.net/10443/3150.
Abstract:
Modern technology o ers us highly evolved data collection devices. They allow us to observe data densely over continua such as time, distance, space and so on. The observations are normally assumed to follow certain continuous and smooth underline functions of the continua. Thus the analysis must consider two important properties of functional data: infinite dimension and the smoothness. Traditional multivariate data analysis normally works with low dimension and independent data. Therefore, we need to develop new methodology to conduct functional data analysis. In this thesis, we first study the linear relationship between a scalar variable and a group of functional variables using three di erent discrete methods. We combine this linear relationship with the idea from least angle regression to propose a new variable selection method, named as functional LARS. It is designed for functional linear regression with scalar response and a group of mixture of functional and scalar variables. We also propose two new stopping rules for the algorithm, since the conventional stopping rules may fail for functional data. The algorithm can be used when there are more variables than samples. The performance of the algorithm and the stopping rules is compared with existed algorithms by comprehensive simulation studies. The proposed algorithm is applied to analyse motion data including scalar response, more than 200 scalar covariates and 500 functional covariates. Models with or without functional variables are compared. We have achieved very accurate results for this complex data particularly the models including functional covariates. The research in functional variable selection is limited due to its complexity and onerous computational burdens. We have demonstrated that the proposed functional LARS is a very e cient method and can cope with functional data very large dimension. The methodology and the idea have the potential to be used to address other challenging problems in functional data analysis.
27
Dragan, Stephen P. "Motion generation and data acquisition for a rotational process rheometer." Thesis, McGill University, 1989. http://digitool.Library.McGill.CA:80/R/?func=dbin-jump-full&object_id=61893.
28
Julià, Ferré Ma Carme. "Missing Data Matrix Factorization Addressing the Structure from Motion Problem." Doctoral thesis, Universitat Autònoma de Barcelona, 2008. http://hdl.handle.net/10803/5785.
Abstract:
Aquest treball es centra en la factorització de matrius per obtenir l'Estructura a partir del Moviment (SFM). La idea és descomposar la matriu de trajectòries en la matriu de moviment, que conté la posició relativa càmera-objecte a cada frame, i la matriu de forma, que conté les coordenades 3D dels punts característics. Aquesta factorització es pot obtenir utilitzant que la matriu de trajectòries té un rang reduït. En particular, si les trajectòries pertanyen a un únic objecte rígid, la matriu té com a molt rang 4. Tot i que s'han proposat diverses tècniques per tractar el problema de les matrius amb forats, aquestes poden no donar resultats correctes quan el percentatge de forats a la matriu és molt gran. Proposem un esquema multiresolució iteratiu per poder tractar aquests casos amb molts elements buits a la matriu de trajectòries. L'esquema proposat consisteix en considerar submatrius amb un percentatge de forats reduït. Seguidament, els forats d'aquestes matrius són emplenats aplicant un mètode de factorització. L'objectiu final és obtenir millors resultats aplicant un mètode de factorització a la matriu emplenada amb l'esquema proposat, enlloc d'aplicar-lo a la matriu inicial, que presenta un elevat percentatge de forats. En el cas de matrius de trajectòries corresponents a punts característics que pertanyen a diversos objectes, les tècniques de factorització no es poden aplicar directament per
obtenir el moviment i la forma de cada objecte, ja que les trajectòries no estan ordenades per objectes. A més a més, s'ha de tenir en compte un altre problema: l'estimació del rang de la matriu de trajectòries. El problema és que amb forats, el rang de la matriu no pot ser calculat directament. Per altra banda, com que hi ha múltiples objectes, és difícil d'estimar-lo, sense utilitzar informació com ara nombre d'objectes o tipus de moviment d'aquests. Presentem una tècnica per estimar el rang d'una matriu de trajectòries amb forats. La idea és que, si les trajectòries pertanyen a objectes rígids, la freqüència espectral de la matriu de trajectòries inicial no hauria de variar un cop la matriu ha estat emplenada. Els forats de la matriu són emplenats amb un mètode de factorització, considerant diferents valors per al rang de la matriu. Al mateix temps, el rang de la matriu de trajectòries és estimat fent servir una mesura que compara la freqüència espectral de cada matriu emplenada amb la de la matriu inicial. El proper pas consisteix en segmentar les trajectòries segons el seu moviment. Finalment, qualsevol tècnica d'Estructura a partir de Moviment per a un únic objecte pot ser aplicada per trobar el moviment i la forma de cada objecte.
Intentem aplicar la metodologia proposada per al problema de l'Estructura a partir de Moviment a d'altres aplicacions, no només dins el camp de la visió per computador. En particular, l'objectiu és adaptar els mètodes Alternats per poder aplicar-los a diferents problemes de dimensionalitat reduïda. Una de les possibles aplicacions és la fotometria: la idea és recuperar la reflectància i les normals a la superfície i la direcció de la llum en cada imatge, a partir d'imatges obtingudes sota diferents condicions de llum. En una segona aplicació, l'objectiu és adaptar els mètodes Alternats per poder omplir els forats en una matriu de dades provinents d'expressions de gens. Aquestes matrius són generades amb la informació que proporcionen els DNA microarrays. Finalment, els mètodes Alternats són aplicats a matrius de dades de sistemes de recomanació, molt usats en E-commerce. Aquestes matrius contenen puntuacions que els usuaris han donat a certs productes. La idea és predir les puntuacions que un usuari concret donaria a altres productes, utilitzant la informació emmagatzemada en el sistema.
This work is focused on the missing data matrix factorization addressing the Structure from Motion (SFM) problem. The aim is to decompose a matrix of feature point trajectories into the motion and shape matrices, which contain the relative camera-object motion and the 3D positions of tracked feature points, respectively. This decomposition can be found by using the fact that the matrix of trajectories has a reduced rank. Although several techniques have been proposed to tackle this problem, they may give undesirable results when the percentage of missing data is high. An iterative multiresolution scheme is presented to deal with matrices with high percentages of missing data. Experimental results show the viability of the proposed approach.
In the multiple objects case, factorization techniques can not be directly applied to obtain the SFM of every object, since trajectories are not sorted into different objects. Furthermore, another problem should be faced out: the estimation of the rank of the matrix of trajectories. The problem is that, in this case, the rank of the matrix of trajectories is not bounded, since any prior knowledge about the number of objects nor about their motion is used. This problem becomes more difficult with missing data, since singular values can not be computed to estimate the rank. A technique to estimate the rank of a missing data matrix of trajectories is presented. The good performance of the proposed technique is empirically shown considering sequences with both, synthetic and real data. Once the rank is estimated and the matrix of trajectories is full, the motion segmentation of trajectories is computed. Finally, any factorization technique for the single object case gives the shape and motion of every object.
In addition to the SFM problem, this thesis also shows other applications that can be addressed by means of factorization techniques. Concretely, the Alternation technique, which is used through the thesis, is adapted to address each particular problem. The first proposed application is the photometric stereo: the goal is to recover the reflectance and surface normals and the light source direction at each frame, from a set of images taken under different lighting conditions. In a second application, the aim is to fill in missing data in gene expression matrices by using the Alternation technique. Finally, the Alternation technique is adapted to be applied in recommender systems, widely considered in E-commerce. For each application, experimental results are given in order to show the good performance of the proposed Alternation-based strategy.
29
Gong, Wenjuan. "3D Motion Data aided Human Action Recognition and Pose Estimation." Doctoral thesis, Universitat Autònoma de Barcelona, 2013. http://hdl.handle.net/10803/116189.
Abstract:
En aquest treball s’explora el reconeixement d’accions humanes i l'estimació de la seva postura en seqüències d'imatges. A diferència de les tècniques tradicionals d’aprenentatge a partir d’imatges 2D o vídeo amb la sortida anotada, en aquesta Tesi abordem aquest objectiu amb la informació de moviment 3D capturat, que ens ajudar a tancar el llaç entre les característiques 2D de la imatge i les interpretacions sobre el moviment humà.En este trabajo se exploran el reconocimiento de acciones humanas y la estimación de su postura en secuencias de imágenes. A diferencia de las técnicas tradicionales de aprendizaje a partir de imágenes 2D o vídeo con la salida anotada, en esta Tesis abordamos este objetivo con la información de movimiento 3D capturado, que nos ayudar a cerrar el lazo entre las caracteríssticas 2D de la imagen y las interpretaciones sobre el movimiento humano.
In this work, we explore human action recognition and pose estimation problems. Different from traditional works of learning from 2D images or video sequences and their annotated output, we seek to solve the problems with additional 3D motion capture information, which helps to fill the gap between 2D image features and human interpretations.
30
Bystam, Fredrik. "Improving motion tracking using gyroscope data in Augmented Reality applications." Thesis, KTH, Datorseende och robotik, CVAP, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166186.
Abstract:
As commissioned by Bontouch AB, this project contains the attempt to create an Augmented Reality application for smartphones, where a parcel is visualised in order for a user to get a comprehensive image of the parcel size. The main focus of the project was to create an eectively running en- gine that can process images for computer vision, in order to determine the pose of the smartphone camera. The experi- ment explored the possibilities of using gyroscope measure- ments between input images in order to formulate valid as- sumptions of upcoming images using homographies. These assumptions were meant to unburden the computer vision engine, creating very high performance. The ultimate goal of the engine was to track the motion of a known reference object in the image, with high precision. The proposed method performed adequately, improving reliability of the motion tracking algorithms. The resulting mobile application, run on an iPhone 5S, could perform camera pose estimation at up to 60 times per second, at a video camera feed resolution of 1280x720 pixels. This high performance resulted in a very stable rendition of the parcel.Som ett uppdrag från Bontouch AB innehåller det här pro- jektet ett försök att skapa en Augmented Reality-applikation för smartphones, där postpaket ska visualiseras för att ge användare en förstärkt bild av paketets storlek. Huvudfo- kus i projektet var att bygga en eektiv motor som kan behandla bilder för datorseende, för att beräkna positionen och riktningen på mobilkameran. Experimentet utforskade möjligheterna för att använda gyroskopdata mellan bilder för att formulera giltiga antaganden hos kommande bilder med hjälp av homografier. Dessa antaganden vad ämna- de att avlasta motorn för datorseende, för att åstadkomma hög prestanda. Målet var att motorn skulle följa rörelsen hos ett givet referensobjekt i bilden, och att göra det med hög precision. Den föreslagna metoden presterade tillräckligt, och för- bättrade pålitligheten hos algoritmerna för att följa objek- tets rörelser. Mobilapplikationen som byggdes, och kördes på iPhone 5S, kunde beräkna kamerans position of riktning upp till 60 gånger per sekund, när videokameran försåg mo- torn med bilder med 1280x720 pixlars upplösning. Den höga prestandan resulterade i en väldigt stabil bild av paketet.
31
Rakowski, Michael D. "Bridge evaluation using in-service and weigh-in-motion data." Access to citation, abstract and download form provided by ProQuest Information and Learning Company; downloadable PDF file, 184 p, 2009. http://proquest.umi.com/pqdweb?did=1654493661&sid=2&Fmt=2&clientId=8331&RQT=309&VName=PQD.
32
Kendrick, Connah. "Markerless facial motion capture : deep learning approaches on RGBD data." Thesis, Manchester Metropolitan University, 2018. http://e-space.mmu.ac.uk/622357/.
Abstract:
Facial expressions are a series of fast, complex and interconnected movement that causes an array of deformations, such as stretching, compressing and folding of the skin. Identifying expression is a natural process in human vision, but due to the diversity of faces, it has many challenges for computer vision. Research in markerless facial motion capture using single Red Green Blue (RGB) camera has gained popularity due to the wide access of the data, such as from mobile phones. The motivation behind this work is much of the existing work attempts to infer the 3-Dimensional (3D) data from 2-Dimensional (2D) images, such as in motion capture multiple 2D cameras are calibration to allow some depth prediction. Whereas, the inclusion of Red Green Blue Depth (RGBD) sensors that give ground truth depth data could gain a better understanding of the human face and how expressions are visualised. The aim of this thesis is to investigate and develop novel methods of markerless facial motion capture, where the focus is on the inclusions of RGBD data to provide 3D data. The contributions are: A tool to aid in the annotation of 3D facial landmarks; A novel neural network that demonstrate the ability of predicting 2D and 3D landmarks by merging RGBD data; Working application that demonstrates complex deep learning network on portable handheld devices; A review of existing methods of denoising fine detail in depth maps using neural networks; A network for the complete analysis of facial landmarks and expressions in 3D. The 3D annotator was developed to overcome the issues of relying on existing 3D modelling software, which made feature identification difficult. The technique of predicting 2D and 3D with auxiliary information, allowed high accuracy 3D landmarking, without the need for full model generation. Also, it outperformed other recent techniques of landmarking. The networks running on the handheld devices show as a proof of concept that even without much optimisation, a complex task can be performed in near real-time. Denoising Time of Flight (ToF) depth maps, showed much more complexity than the tradition RGB denoising, where we reviewed and applied an array of techniques to the task. The full facial analysis showed that when neural networks perform on a wide range of related task for auxiliary information allow for deep understanding of the overall task. The research for facial processing is vast, but still with many new problems and challenges to face and improve upon. While RGB cameras are used widely, we see the inclusion of high accuracy and cost-effective depth sensing device available. The new devices allow better understanding of facial features and expression. By using and merging RGB data, the area of facial landmarking, and expression intensity recognition can be improved.
33
Betancourt, Michelle Renee. "Modeling Peak Ground Acceleration (PGA) From Collected Strong Motion Data." OpenSIUC, 2016. https://opensiuc.lib.siu.edu/theses/1861.
Abstract:
The main focus of this thesis is to effectively estimate levels of peak ground acceleration (PGA) during a seismic event for a given site. This will be achieved by applying regression analysis via a mixed model methodology to data collected from previously recorded seismic events collected from the PEER Strong Motion Database using a program written in MATLAB. The basic mixed model combines both fixed and random effect terms. Two models are analyzed and compared based on varying combinations of predictor variables, such as magnitude, distance, shear wave velocity, and site class. While the primary objective of this thesis solely examines the modeling of PGA, the same methodology can be applied in predicting other ground motion intensity parameters such as Peak Ground Velocity (PGV) or the spectral ordinate at a given vibration period.
34
Kulkarni, Amey S. "Motion Segmentation for Autonomous Robots Using 3D Point Cloud Data." Digital WPI, 2020. https://digitalcommons.wpi.edu/etd-theses/1370.
Abstract:
Achieving robot autonomy is an extremely challenging task and it starts with developing algorithms that help the robot understand how humans perceive the environment around them. Once the robot understands how to make sense of its environment, it is easy to make efficient decisions about safe movement. It is hard for robots to perform tasks that come naturally to humans like understanding signboards, classifying traffic lights, planning path around dynamic obstacles, etc. In this work, we take up one such challenge of motion segmentation using Light Detection and Ranging (LiDAR) point clouds. Motion segmentation is the task of classifying a point as either moving or static. As the ego-vehicle moves along the road, it needs to detect moving cars with very high certainty as they are the areas of interest which provide cues to the ego-vehicle to plan it's motion. Motion segmentation algorithms segregate moving cars from static cars to give more importance to dynamic obstacles. In contrast to the usual LiDAR scan representations like range images and regular grid, this work uses a modern representation of LiDAR scans using permutohedral lattices. This representation gives ease of representing unstructured LiDAR points in an efficient lattice structure. We propose a machine learning approach to perform motion segmentation. The network architecture takes in two sequential point clouds and performs convolutions on them to estimate if 3D points from the first point cloud are moving or static. Using two temporal point clouds help the network in learning what features constitute motion. We have trained and tested our learning algorithm on the FlyingThings3D dataset and a modified KITTI dataset with simulated motion.
35
Zhang, Yuning. "Unsupervised Motion Artifact Detection in Wrist-Measured Electrodermal Activity Data." University of Toledo / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1501876131092933.
36
Hakl, Henri. "Structure-from-motion for enclosed environments." Thesis, Link to the online version, 2007. http://hdl.handle.net/10019.1/1195.
37
Mott, Ryan. "Music in motion : the synthesis of album design and motion graphics for downloadable music /." Online version of thesis, 2009. http://hdl.handle.net/1850/10942.
38
Delgado, Reyes Lourdes Marielle. "Evaluating motion processing algorithms for use with fNIRS data from young children." Thesis, University of Iowa, 2015. https://ir.uiowa.edu/etd/5929.
Abstract:
Motion artifacts are often a significant component of the measured signal in functional near-infrared spectroscopy (fNIRS) experiments. A variety of methods have been proposed to address this issue, including principal component analyses (PCA), Kalman filtering, correlation-based signal improvement (CBSI), wavelet filtering, spline interpolation, and autoregressive algorithms. The efficacy of these techniques has been compared using simulated data; however, our understanding of how these techniques fare when dealing with task-based cognitive data is limited. Recently, Brigadoi et al. (2014) quantitatively compared 6 motion correction techniques in a sample of adult data measured during a simple cognitive task. Wavelet filtering showed the most promise as an optimal technique for motion correction. Because fNIRS is often used with infants and young children, it is critical to evaluate the effectiveness of motion correction techniques directly with data from these age groups. Here we examined which techniques are most effective with data from young children. The efficacy of each technique was compared quantitatively using objective metrics related to the physiological properties of the hemodynamic response using two different sets of parameters to ensure maximum retention of included trials. Results showed that targeted PCA (tPCA) and CBSI retained a higher number of trials. These techniques also performed well in direct head-to-head comparisons with the other approaches using both quantitative metrics and a qualitative assessment. The CBSI technique corrected many of the artifacts present in our data; however, this technique was highly influenced by the parameters used to detect motion. The tPCA technique, by contrast, was robust across changes in parameters while also performing well across all comparison metrics. We conclude, therefore, that tPCA is an effective technique for the correction of motion artifacts in fNIRS data from young children.
39
Bányay, Dániel. "MLSurf : Surfer Motion Characterization Using Machine Learning Techniques." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-264921.
Abstract:
Wave surfing is a popular sport that requires minimal financial investment, while it can still be enjoyable from the very first attempt. At the same time, the demand for smart devices that enhance the experience of doing sports by analyzing and evaluating the activities is growing. For surf sport, there are some solutions that are able to collect statistics about activities being done during a surf session, but none of them is able to recognize specific maneuvers that are performed during wave riding. The goal of this Master Thesis is to improve a currently existing surf activity monitoring solution by extending it with the ability to identify the two most common surf maneuvers during a wave riding session, namely cutback and snap. The solution is using the user’s smartphone to collect IMU sensor data and feed it to a classification pipeline. The implemented algorithm takes raw sensor data as an input, performs various preprocessing steps, splits the input stream into segments, extracts features from these segments and feed them into a hierarchical classification tree. The implemented pipeline is able to classify non-maneuver, cutback and snap segments with 78% accuracy on a self-collected dataset.Vågsurfing är en populär sport som kräver minimala finansiella investeringar, medan det kan vara roligt från första början. Samtidigt växer efterfrågan på smarta enheter som förbättrar sportupplevelsen genom att analysera och utvärdera aktiviteterna. För surfsport finns det några lösningar som kan samla in data om aktiviteter som utförs under en surfsession, men ingen av dem kan känna igen specifika manövrar som utförs under vågsurfing. Målet med denna uppsats är att förbättra en befintlig lösning för surfaktivitetsövervakning genom att utöka den med förmågan att identifiera de två vanligaste surfmanövren nämligen cutback och snap. Lösningen använder användarens smartphone för att samla IMU-sensordata och mata dem till en klassificeringspipeline. Den implementerade algoritmen tar råa sensordata som input, utför olika förbehandlingssteg, segmenterar input-strömmen, extraherar funktioner från dessa segment och matar in dem i ett hierarkiskt klassificeringsträd. Den implementerade pipeline kan klassificera non-maneuver-, cutback- och snapsegment med 78% noggrannhet på ett självsamlat dataset.
40
Bailer, Christian [Verfasser]. "New Data Based Matching Strategies for Visual Motion Estimation / Christian Bailer." München : Verlag Dr. Hut, 2020. http://d-nb.info/1219321559/34.
41
De, Wet Dirk Pieter Gerhardus. "Post-calibration and quality management of weigh-in-motion traffic data." Thesis, Stellenbosch : University of Stellenbosch, 2010. http://hdl.handle.net/10019.1/4205.
Abstract:
Thesis (MScEng (Process Engineering))--University of Stellenbosch, 2010.Thesis presented in fulfilment of the requirements for the degree of Master of Science in Engineering at Stellenbosch University
ENGLISH ABSTRACT: Weigh-in-motion (WIM) scales are installed on various higher order South African roads to provide traffic loading information for pavement design, strategic planning and law enforcement using a scientific approach. The two most respected international guideline documents for WIM systems are the American ASTM E1318 Standard and the COST 323 European Specification, yet neither are fully suited to be applied to local WIM systems. The author developed a post-calibration method for WIM data, called the Truck Tractor (TT) Method, to correct the magnitude of recorded axle loads in retrospect. It incorporates a series of powerful data quality checks. The TT Method is robust, accurate and adequately simple to be used on a routine basis. The TT Method uses the truck tractor loads of articulated 6- and 7-axle trucks with single steering- and double driving axles – these vehicle are called Eligible Trucks. Only Eligible Trucks with average axle loads between 6.5 t and 8.5 t are used in the calibration process – these vehicles are called Selected Trucks. A calibration factor, kTT, is determined using a fully automated iterative procedure, and multiplied with all axle load measurements to produce data for which the average truck tractor load of Selected Trucks, TTT, is equal to 21.8 t. The TT Method can be used for WIMs in various operating environments and is not sensitive to the extent of miss-calibration of a WIM, clipping of sensors owing to poor lane discipline or different extents of loading on different routes. The TT Method includes a series of data quality checks that can be used on a routine basis. They are summarised as follows: - The standard deviation of truck tractor loads for Selected Trucks, STTT, should always be below 2.0 t, but preferably below 1.9 t. - The standard deviation of front axle loads for Selected Trucks, SFTT, should always be below 0.9 t, but preferably below 0.8 t. - The post-calibration factor from the TT Method, kTT, should be between 0.9 and 1.1. The factor for any month should not deviate by more than 3% from the moving average of the previous five months. - The average of front axle loads of Selected Trucks, FTT, should be between 5.6 t and 6.6 t; the exact values are influenced by load transfer between the steering and driving axles. - A procedure was formulated using the Front axle / Truck tractor Ratio, FTR, to identify the percentage of Eligible Trucks that in all probability clipped the sensor. The percentage of these records must be below 10 %, but preferably below 6 %. The TT Method has the potential to significantly improve WIM data collection in South Africa. The calibration module of the TT Method, i.e. the procedure to calculate kTT, has already been accepted by SANRAL. Most of the data quality checking concepts associated with the TT Method were also accepted, although their threshold values are still being refined.
AFRIKAANSE OPSOMMING: Weeg-in-beweging (“weigh-in-motion”, WIM) skale word op talle hoë orde paaie in Suid- Afrika gebruik om op wetenskaplike wyse verkeersinligting te verskaf wat gebruik word vir plaveiselontwerp, strategiese beplanning en wetstoepassing met betrekking tot oorlading. Nie een van die twee vooraanstaande internasionale riglyne vir WIM sisteme, die ASTM E1318 Standaard en die COST 323 Europese Spesifikasie, is in geheel geskik vir Suid-Afrikaanse kondisies nie. Die outeur het ‘n unieke kalibrasie metode, genaamd die TT Metode, ontwikkel wat ’n reeks roetine kwaliteitsbeheertoetse vir WIM data insluit. Die TT Metode is eenvoudig, akkuraat en toepaslik vir ’n wye verskeidenheid WIM sisteme in Suid-Afrika. Die massa van trekkers van geartikuleerde 6- en 7-as vragmotors met enkel stuur- en dubbel dryf-aste en ’n gemiddelde asmassa tussen 6.5 en 8.5 ton (ook genoem Geselekteerde Vragmotors) word as verwysingsmassa gebruik. ’n Iteratiewe prosedure word gevolg vir die bepaling van die kalibrasie faktor, kTT. Dieselfde faktor word met alle asmassas in die data vir die analise periode vermenigvuldig, met die einddoel dat die gemiddelde trekker massa van die Geselekteerde Vragmotors, TTT, gedryf word na die teikenwaarde van 21.8 ton. Die TT Metode is ewe toepaslik ongeag die tipiese belading van trokke op ’n roete, hoe goed die WIM sisteem oorspronklik gekalibreer was of hoe goed laandissipline by die WIM sensor is. Die kwaliteitsbeheertoetse kan op ’n roetine basis toegepas word as deel van die uitvoering van WIM kalibrasie prosedure, en word soos volg saamgevat: - Die standaard afwyking van trekker massas van Geselekteerde Vragmotors, STTT, behoort altyd laer as 2.0 ton, maar verkieslik laer as 1.9 ton te wees. - Die standaard afwyking van voor-as massas van Geselekteerde Trokke, SFTT, behoort altyd laer as 0.9 ton, maar vekieslik laer as 0.8 ton te wees. - Die kalibrasiefaktor, kTT, moet verkieslik tussen 0.9 en 1.1 wees, en mag nie met meer as 3 % van die gemiddelde kTT vir die voorafgaande vyf maande verskil nie. - Die gemiddeld van voor-as massas van Geselekteerde Vragmotors, FTT, behoort tussen 5.6 ton en 6.6 ton te wees. Die presiese waarde hang af van die mate waartoe gewig tussen die voor-as en dubbel dryf-as oorgedra word weens dinamiese effekte op die trekker. - Die verhouding tussen die voor-as en dubbel dryf-as, bekend as die FTR, kan gebruik word as ‘n aanduiding of ’n trok weens swak laandissipline slegs gedeeltelik oor die WIM sensor gery het. Die persentasie gedeeltelike metings moet laer as 10%, maar verkieslik laer as 6 % wees. Die TT Metode het die potensiaal om die insameling en kwaliteit van verkeersdata deur middel van WIM sisteme noemenswaarding te verbeter. Die kalibrasie module van die TT Metode, m.a.w. die prosedure om kTT te bereken, is reeds deur SANRAL aanvaar. Die meeste van die kwaliteitsbeheerkonsepte wat met die TT Metode gepaard gaan is ook aanvaar, maar die drempelwaardes hiervoor word nog verfyn.
42
Shen, Yuping. "GEOMETRIC INVARIANCE IN THE ANALYSIS OF HUMAN MOTION IN VIDEO DATA." Doctoral diss., University of Central Florida, 2009. http://digital.library.ucf.edu/cdm/ref/collection/ETD/id/3157.
Abstract:
Human motion analysis is one of the major problems in computer vision research. It deals with the study of the motion of human body in video data from different aspects, ranging from the tracking of body parts and reconstruction of 3D human body configuration, to higher level of interpretation of human action and activities in image sequences. When human motion is observed through video camera, it is perspectively distorted and may appear totally different from different viewpoints. Therefore it is highly challenging to establish correct relationships between human motions across video sequences with different camera settings. In this work, we investigate the geometric invariance in the motion of human body, which is critical to accurately understand human motion in video data regardless of variations in camera parameters and viewpoints. In human action analysis, the representation of human action is a very important issue, and it usually determines the nature of the solutions, including their limits in resolving the problem. Unlike existing research that study human motion as a whole 2D/3D object or a sequence of postures, we study human motion as a sequence of body pose transitions. We also decompose a human body pose further into a number of body point triplets, and break down a pose transition into the transition of a set of body point triplets. In this way the study of complex non-rigid motion of human body is reduced to that of the motion of rigid body point triplets, i.e. a collection of planes in motion. As a result, projective geometry and linear algebra can be applied to explore the geometric invariance in human motion. Based on this formulation, we have discovered the fundamental ratio invariant and the eigenvalue equality invariant in human motion. We also propose solutions based on these geometric invariants to the problems of view-invariant recognition of human postures and actions, as well as analysis of human motion styles. These invariants and their applicability have been validated by experimental results supporting that their effectiveness in understanding human motion with various camera parameters and viewpoints.Ph.D.
School of Electrical Engineering and Computer Science
Engineering and Computer Science
Computer Science PhD
43
Lundeen, Gregory N. "A comparison of ice drift motion from modeled and buoy data." Thesis, Monterey, California : Naval Postgraduate School, 1990. http://handle.dtic.mil/100.2/ADA246062.
Abstract:
Thesis (M.S. in Meteorology and Physical Oceanography)--Naval Postgraduate School, December 1990.Thesis Advisor(s): Bourke, Robert H. ; Morison, James. "December 1990." Description based on title screen as viewed on April 1, 2010. DTIC Identifier(s): Buoys, Sea Ice, Arctic Buoys, Ice Forecast, Arctic, Theses. Author(s) subject terms: PIPS, Sea Ice, Arctic Buoys, Ice Forecast, Arctic. Includes bibliographical references (p. 106-111). Also available in print.
44
Niu, Chaowei. "Patterns of motion in non-overlapping networks using vehicle tracking data." Thesis, Massachusetts Institute of Technology, 2010. http://hdl.handle.net/1721.1/58278.
Abstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2010.Cataloged from PDF version of thesis.
Includes bibliographical references (p. 121-131).
We present a systematic framework to learn motion patterns based on vehicle tracking data captured by multiple non-overlapping uncalibrated cameras. We assume that the tracks from individual cameras are available. We define the key problems related to the multi-camera surveillance system and present solutions to these problems: learning the topology of the network, constructing tracking correspondences between different views, learning the activity clusters over global views and finally detecting abnormal events. First, we present a weighted cross correlation model to learn the topology of the network without solving correspondence in the first place. We use estimates of normalized color and apparent size to measure similarity of object appearance between different views. This information is used to temporally correlated observations, allowing us to infer possible links between disjoint views, and to estimate the associated transition time. Based on the learned cross correlation coefficient, the network topology can be fully recovered. Then, we present a MAP framework to match two objects along their tracks from non overlapping camera views and discuss how the learned topology can reduce the correspondence search space dramatically. We propose to learn the color transformation in [iota][alpha][beta] space to compensate for the varying illumination conditions across different views, and learn the inter-camera time transition and the shape/size transformation between different views.
(cont.) After we model the correspondence probability for observations captured by different source/sinks, we adopt a probabilistic framework to use this correspondence probability in a principled manner. Tracks are assigned by estimating the correspondences which maximize the posterior probabilities (MAP) using the Hungarian algorithm. After establishing the correspondence, we have a set of stitched trajectories, in which elements from each camera can be combined with observations in multiple subsequent cameras generated by the same object. Finally, we show how to learn the activity clusters and detect abnormal activities using the mixture of unigram model with the stitched trajectories as input. We adopt a bag - of - words presentation, and present a Bayesian probabilistic approach in which trajectories are represented by a mixture model. This model can classify trajectories into different activity clusters, and gives representations of both new trajectories and abnormal trajectories.
by Chaowei Niu.
Ph.D.
45
Silva, Marco Jorge Tome da. "Simulation of human motion data using short-horizon model-predictive control." Thesis, Massachusetts Institute of Technology, 2008. http://hdl.handle.net/1721.1/43041.
Abstract:
Thesis (S.M.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2008.Includes bibliographical references (p. 52-56).
Many data-driven animation techniques are capable of producing high quality motions of human characters. Few techniques, however, are capable of generating motions that are consistent with physically simulated environments. Physically simulated characters, in contrast, are automatically consistent with the environment, but their motions are often unnatural because they are difficult to control. We present a model-predictive controller that yields natural motions by guiding simulated humans toward real motion data. During simulation, the predictive component of the controller solves a quadratic program to compute the forces for a short window of time into the future. These forces are then applied by a low-gain proportional-derivative component, which makes minor adjustments until the next planning cycle. The controller is fast enough for interactive systems such as games and training simulations. It requires no precomputation and little manual tuning. The controller is resilient to mismatches between the character dynamics and the input motion, which allows it to track motion capture data even where the real dynamics are not known precisely. The same principled formulation can generate natural walks, runs, and jumps in a number of different physically simulated surroundings.
by Marco da Silva.
S.M.
46
Nykvist, Joar. "Sonication in Kinesiophobia Therapy: Presenting Motion Capture Data as Mechanical Quantities." Thesis, KTH, Skolan för teknikvetenskap (SCI), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-211567.
Abstract:
Kinesiophobia is a severe limitation in its victims' lives, this paper is part of a larger study aiming to use motion capture combined with a reliable mechanical model to provide auditory feedback on a kinesiophobia victim's locomotion on a track designed to inspire movements relevant for rehabilitation. This paper focuses on creating a theoretical model with a foundation in the biomechanics eld and uses it to establish programming logic that facilitates sonication methods used on the recorded motion data. Motion capture is a widely used technique and a lot of research has been done on how to use it, this paper brings up examples of skeleton gen-eration and movement categorization. Nonetheless, there is no precedent using quantities entirely based on rigid body coordinates for the sonication of motion data as a possible segment in kinesiophobia therapy. The mechanical quantities that were analyzed in this study are based solely on travelled distances and their derivatives to minimize the customization need for dierent subjects. Functions calculating the quantities of interest based on a motion capture stream were written in MatLab and programatically run from a script in Java, where the data was stored. A swift tool for analyzing valuable motion quantities in real time was developed and tested successfully, the full procedure is disclosed along with suggested improvements and an evaluation of its strengths and drawbacks.
47
Aslan, David. "Lagring av Motion Capture Data i NoSQL-databser : Undersökning av CouchDB." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-11095.
Abstract:
Motion capture data behöver lagra på ett eller annat sätt lagra detta med databas skulle innebära väldigt många fördelar. Den används på många olika sätt och i olika branscher därmed skulle innebära en stor förändring. Det finns två olika kategorier av databaser SQL databaser och NoSQL databaser, dem databaser som kommer testas är relationsbaserade MySQL och dokumentbaserade CouchDB med en prototyp som utvecklas för att utföra dessa tester. Testerna påvisar att CouchDB är bättre databaslösningen vid lagringen av motion capture data. Men ytterligare arbete skulle kunna utföra flera tester som påvisar att läsning av motion capture data från databaserna kan ske i realtid. Mätningar från experimentet bevisar att CouchDB är den snabbare på att lagra Motion Capture data. I framtida arbete skulle arbetet kunna införas i filmbranschen och bli effektivt genom att använda mindre hårddiskutrymme och minska kostnaderna.
48
Chung, Hing-yip Ronald, and 鍾興業. "Fast motion estimation with search center prediction." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1999. http://hub.hku.hk/bib/B31220721.
49
Holm, Malin, Christoffer Roepstorff, and Martin Svedberg. "Validering av Inertial Measurment Units som insamlare av data för drivande av OpenSim-modell." Thesis, Uppsala universitet, Institutionen för teknikvetenskaper, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-175937.
Abstract:
The purpose of this paper is to investigate the possibility of replacing data from highspeed filming (Qualisys motion capture) with data from Inertial Measurement Units (X-io technologies), when used to run a model of torso and pelvis in OpenSim. Qualisys motion capture data is used as the golden standard to validate the result visually and with Bland-Altman plots. In order to obtain comparable data experiments are conducted where both methods of collecting data are used simultaneously. Data from the IMU's then need to be processed in Matlab before it can be used to run the OpenSim modell. Several Matlab programs rotate the IMU data to a static reference frame, filter and integrate it, then create viritual markers that correspond to Qualisys' optical markers. The conclusion is that using IMU as a method for collecting data can replace Qualisys in some applications, but not in ones that require high precision. However, this paper only begins the examination of IMU's and there are most likely improvements to be made.
50
Taboada, Sophie. "Multi-Agent Motion Planning with Signal Temporal Logic Constraints." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-292870.
Abstract:
Motion planning algorithms allow us to define a sequence of configurations to guide robots from a starting point to an ending goal while considering the environment’s and the robot’s constraints. As all robots and circumstances are different, motion planning can be adapted to fit into the system’s specifications and the user’s preferences. Temporal Logic (TL) has been used to enable the implementation of more complex missions. In this work, we are interested in using TL to establish the affiliation between robots in a multi-robot system, as well as their affiliation with features in the workspace. More specifically, Signal Temporal Logic (STL) is used to guide motion planning into respecting certain preferences linked to the robot’s motion behavior. In fact, user’s preferences are translated into STL formulas, that need to be respected by the motion planning. To achieve this, RRT* sampling-based algorithm is used to study the free space and to identify the best trajectory with the help of a cost analysis of all possible trajectories found. Here, RRT* is adapted to fit into multi-robot systems and to allow the simultaneous planning of trajectories for multiple robots. The robustness metric of STL quantifies the respect trajectories have for STL formulas and influences the cost function of the RRT*. The impact the robustness has on the cost function is responsible for the selection of trajectories with more respect for the STL formulas. The proposed multi-agent motion planning is tested in simulations with environments containing multiple obstacles and robots. To demonstrate the impact STL has on motion planning, a comparison is made between the trajectories extracted with and without the use of STL. These simulations include specific scenarios and different numbers of robots to test the developed algorithm. They deliver asymptotically optimal solutions. Finally, we conduct some hardware experiments up until four robots to present how the developed motion planning can be implemented in real life.Rörelseplaneringsalgoritmer låter oss definiera en sekvens av konfigurationer för att guida robotar från en startposition till en slutposition medan vi tar hänsyn till robotens och miljöns begränsningar. Eftersom alla robotar och omständigheter är olika kan rörelseplanering anpassas för att passa systemets specifikationer och användarens preferenser. Temporal Logik (TL) har använts för att möjliggöra implementationer av mer komplexa uppdrag. I detta arbete är vi intresserade av att använda TL för att fastställa anslutningen mellan robotar i ett multirobotsystem, samt mellan dessa robotar och egenskaper i deras arbetsmiljö. Mer specifikt används signaltemporär logik (eng: Signal Temporal Logic) (STL) för att anpassa rörelseplanering till att respektera vissa preferenser länkade till robotens rörelsebeteende. Faktum är att användarpreferenser översätts till STL-formler som behöver respekteras av rörelseplaneringen. För att uppnå detta används den samplingsbaserade algoritmen RRT* för att studera den fria ytan och för att identifiera den bästa rörelsebanan med hjälp av en kostanalys av alla funna möjliga rörelsebanor. Här anpassas RRT* för multirobotsystem och för att tillåta planering av rörelsebanor för flera robotar samtidigt. Robushetsmåttet för STL kvantifierar respekten som banorna har för STL-formler och påverkar RRT*: s kostnadsfunktion. Påverkan som robustheten har på kostfunktionen är ansvarig för valet av rörelsebanor som till högre grad respekterar STL-formlerna. Den föreslagna röresleplaneringen för flera agenter (eng: multi-agent) testas i simuleringar av miljöer med flera hinder och robotar. För att demonstrera vilken inverkan STL har på rörelseplanering görs en jämförelse mellan rörelsebanor som ges med och utan användning av STL. Dessa simuleringar inkluderar specifika scenarion och olika antal robotar för att testa den utvecklade algoritmen. De levererar asymptotiskt optimala lösningar. Slutligen genomför vi hårdvaruexperiment upp till och med fyra robotar för att presentera hur den framtagna rörelseplaneringsalgoritmen kan implementeras i verkligheten.