Dissertations / Theses on the topic 'Visual analysis'
To see the other types of publications on this topic, follow the link: Visual analysis.
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 'Visual analysis.'
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
Davis, Myers Abraham. "Visual vibration analysis." Thesis, Massachusetts Institute of Technology, 2016. http://hdl.handle.net/1721.1/107330.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2016.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 109-113).
This dissertation shows how regular cameras can be used to record and analyze the vibrations of visible objects. Through careful temporal analysis, we relate subtle changes in video to the vibrations of recorded surfaces, and use that information to reason about the physical properties of objects and the forces that drive their motion. We explore several applications of our approach to extracting vibrations from video - using it to recover sound from distant surfaces, estimate the physical properties of visible objects, and even predict how objects will respond to new, previously unseen forces. Our work impacts a variety of fields, ranging from computer vision, to long-distance structural health monitoring and nondestructive testing, surveillance, and even visual effects for film. By imaging the vibrations of objects, we offer cameras as low-cost vibration sensors with dramatically higher spatial resolution than the devices traditionally used in engineering. In doing so, we turn every camera into a powerful tool for vibration analysis, and provide an exciting new way to image the world.
by Myers Abraham Davis (Abe Davis)
Ph. D.
2
Shah, Neet. "Visual Field Analysis for Functional Visual Loss." Thesis, The University of Arizona, 2018. http://hdl.handle.net/10150/626887.
Full text
3
Larsson, Petter. "Automatic Visual Behavior Analysis." Thesis, Linköping University, Department of Electrical Engineering, 2002. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-1980.
Full textAbstract:
This work explores the possibilities of robust, noise adaptive and automatic segmentation of driver eye movements into comparable quantities as defined in the ISO 15007 and SAE J2396 standards for in-vehicle visual demand measurements. Driver eye movements have many potential applications, from the detection of driver distraction, drowsiness and mental workload, to the optimization of in-vehicle HMIs. This work focuses on SeeingMachines head and eye-tracking system SleepyHead (or FaceLAB), but is applicable to data from other similar eye-tracking systems. A robust and noise adaptive hybrid algorithm, based on two different change detection protocols and facts about eye-physiology, has been developed. The algorithm has been validated against data, video transcribed according to the ISO/SAE standards. This approach was highly successful, revealing correlations in the region of 0.999 between analysis types i.e. video transcription and the analysis developed in this work. Also, a real-time segmentation algorithm, with a unique initialization fefature, has been developed and validated based on the same approach.
This work enables real-time in-vehicle systems, based on driver eye-movements, to be developed and tested in real driving conditions. Furthermore, it has augmented FaceLAB by providing a tool that can easily be used when analysis of eye movements are of interest e.g. HMI and ergonomics studies, analysis of warnings, driver workload estimation etc.
4
Machado, Vinícius Fritzen. "Visual soccer match analysis." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2016. http://hdl.handle.net/10183/144074.
Full textAbstract:
Futebol é um esporte fascinante que capta a atenção de milhões de pessoas no mundo. Equipes de futebol profissionais, bem como os meios de comunicação, têm um profundo interesse na análise de partidas de futebol. Análise estatística é a abordagem mais usada para descrever um jogo de futebol, no entanto, muitas vezes eles não conseguem captar a evolução do jogo e as mudanças de estratégias que aconteceram. Neste trabalho, apresentamos Visual Soccer Match Analysis (VSMA), uma ferramenta para a compreensão dos diferentes aspectos relacionados com a evolução de um jogo de futebol. A nossa ferramenta recebe como entrada as coordenadas de cada jogador durante o jogo, bem como os eventos associados. Apresentamos um design visual que permite identificar rapidamente padrões relevantes em jogo. A abordagem foi desenvolvida em conjunto com colegas da área da educação física com experiência em análise de futebol. Validamos a utilidade da nossa abordagem utilizando dados de várias partidas, juntamente com avaliações de especialistas.Soccer is a fascinating sport that captures the attention of millions of people in the world. Professional soccer teams, as well as the broadcasting media, have a deep interest in the analysis of soccer matches. Statistical summaries are the most-used approach to describe a soccer match. However, they often fail to capture the evolution of the game and changes of strategies that happen. In this work, we present the Visual Soccer Match Analysis (VSMA) system, a tool for understanding the different aspects associated with the evolution of a soccer match. Our tool receives as input the coordinates of each player throughout the match and related events. We present a visual design that allows to quickly identify relevant patterns in the match. Our approach was developed in conjunction with colleagues from the physical education field with expertise in soccer analysis. We validated the system utility using several matches together with expert evaluations.
5
Yang, Di. "Analysis guided visual exploration of multivariate data." Worcester, Mass. : Worcester Polytechnic Institute, 2007. http://www.wpi.edu/Pubs/ETD/Available/etd-050407-005925/.
Full text
6
McAulay, Ian Charles. "Visual descriptors : a design tool for visual impact analysis." Thesis, University of Plymouth, 1988. http://hdl.handle.net/10026.1/2401.
Full textAbstract:
This study is concerned with the development of a practical and effective form of computer-aided analysis of the visual impact of building development in rural areas. Its contribution is fourfold. Firstly, a conceptual model has been developed for the process of seeing in the context of visual impact analysis. Secondly, a mathematical model for a consistent series of visual descriptors has been devised. Thirdly, a suitable design tool has been devised to make use of visual descriptors in visual impact analysis. Fourthly, visual descriptors have actually been implemented as computer software. The concept of visual impact analysis is defined and placed within the wider context of landscape research. The problems faced by a designer in the context of visual impact analysis are identified and the concept of a 'design tool' is introduced and defined. A number of existing computer software packages, intended or used for visual impact analysis, are reviewed critically. The concept of 'visual descriptors' as measures to be used by designers is introduced and examined critically. A conceptual model is presented for the process of seeing in the context of visual impact analysis. A range of possible measures for use as visual descriptors is presented and developed further into a series of precise definitions. A method of implementing visual descriptors is presented together with formal algorithms for the derivation of eight visual descriptors. A software package incorporating these descriptors is presented and verification and case studies of its use carried out. Visual descriptors, as implemented, are assessed for their effectiveness as a design tool for visual impact analysis.
7
Ardila, Jimenez Silvia. "Analysis of visual responses in the mouse early visual pathway." Thesis, Imperial College London, 2016. http://hdl.handle.net/10044/1/43376.
Full textAbstract:
Many animals, including humans, rely on visual input to guide their behaviour and interact with their environment. The study of the visual system is prevalent in neuroscience, however, given the highly complex nature of the brain, we are yet to understand the full functionality of the system. In this study, we set out to explore different aspects of visual processing in the mouse early visual pathway, and how they compare to those in other mammals. In this thesis, we study two major brain structures in the early visual pathway, the dorsal lateral geniculate nucleus (dLGN) in the thalamus, and the primary visual area (V1 or area 17) in the cortex. We aim to explore 3 different aspects of visual information processing in these areas. Firstly, the functional response characteristics of single neurons in the visual thalamus. Secondly, whether additional communication channels are used in thalamo-cortical interactions in the mouse. And lastly, the correlation of behaviour within neuronal population activity in visual cortex. We use data from two different experimental paradigms. One involves an anaesthetised preparation, recording extracellular potentials from the visual thalamus in isolation, or from the visual thalamus and the primary visual cortex simultaneously. The second involves an awake preparation in which animals were trained on a 'Go'/'NoGo' discrimination task and extracellular potentials were recorded from the primary visual cortex during behaviour. This project combines time-series analysis and information theoretical methods to analyse high dimensional multi-electrode array recordings. In addition to the analysis of experimental data, we also explore the practical and methodological implications of measuring communication through cross-frequency coupling and propose an alternative method to measure this phenomenon.
8
Maushagen, Jan. "Visual Analysis of Publication Networks." Thesis, Linnéuniversitetet, Institutionen för datavetenskap (DV), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-27487.
Full textAbstract:
This thesis documents the development of a web-application attacking the problem of visualization of co-authorship networks. The visualization encompasses several views.Each of them shows different aspects of the data which is loaded from Academic Archive Online (DiVa), a library system which holds all publications released in the Linnaeus University. To detect relationships among authors, a new interactive layout for Node-Link Diagrams was developed which shows publications, authors and corresponding organizations (faculties, departments) in a radial manner. This Network-View is connected to another view showing the attributes (year, type) of the publications. In development, particular emphasis was placed on a rich support of user interaction in order to equip the user with a tool that allows graphical and explorative analysis of the underlying data.
9
Tresadern, Phil. "Visual analysis of articulated motion." Thesis, University of Oxford, 2002. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.436970.
Full text
10
Turkmani, Aseel. "Visual analysis of viseme dynamics." Thesis, University of Surrey, 2008. http://epubs.surrey.ac.uk/804944/.
Full textAbstract:
Face-to-face dialogue is the most natural mode of communication between humans. The combination of human visual perception of expression and perception in changes in intonation provides semantic information that communicates idea, feelings and concepts. The realistic modelling of speech movements, through automatic facial animation, and maintaining audio-visual coherence is still a challenge in both the computer graphics and film industry.
11
Purdie, Cameron L. "Computer aided visual impact analysis." Thesis, University of Strathclyde, 1993. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.385519.
Full text
12
Pålsson, Nicholas. "Guiding the viewer using visual components : Eye-tracking for visual analysis." Thesis, Luleå tekniska universitet, Institutionen för konst, kommunikation och lärande, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-74563.
Full textAbstract:
Are there ways to assess the objective value of the image? By first breaking down visual components and visual structure that are commonly used in image construction, this report will try to predict how a audience chooses to view an image. Through eye-tracking technology using a webcam to track the subjects' eye movement, these visual components validation will be tested. The result is presented as heatmaps; which illustrate the point of attention of the audience. The result is then compared with a hypothesis that was compiled in preparation for the examination. The result of the survey shows that potential off using eye-tracking for analysis, though the technology of using a web camera might not be the most suitable.
13
Jancsary, Dennis, Markus Höllerer, and Renate Meyer. "Critical analysis of visual and multimodal texts." SAGE, 2016. http://epub.wu.ac.at/6126/1/Dennis_etal_2016_SAGE%2Dcritical%2Danalysis.pdf.
Full text
14
Costa, Patrícia Folgado Bargado. "Análise visual da paisagem. Caso de Estudo: concelho de Almada." Master's thesis, ISA, 2010. http://hdl.handle.net/10400.5/3111.
Full textAbstract:
Mestrado em Arquitectura Paisagista - Instituto Superior de AgronomiaThe interest for the subject, “Visual Analysis of the Landscape in the Municipality of Almada”, emerged from the perception that projects don´t generally meet the needs of the populations, but instead they meet the personal preferences of the designer. The aim of this work is to introduce public opinion as a tool in the design process. Although the general public doesn´t possess the technical knowledge, making the intervention of the designer essential, they do possess the practical knowledge of the dynamics, needs and the most valuable assets of the landscape that surrounds the areas where they live or work. As a case study I chose the Municipality of Almada, from which I took the seven most representative photos and then elaborated an inquiry to its population. In an inquiry, these pictures were to be ordered by preference by the inquired, asking them to make the visual analysis of the municipality and revealing what kind of landscapes they most and least like. It was possible to conclude that although the urban expansion engulfed the natural landscape, involving the population in an insalubrious environment, people still prefer landscapes with natural elements, like water or vegetation. Landscapes with cultural heritage are also of great importance, for they represent the identity of the population or of the nation itself.
15
Ferm, Andreas. "Visual attention analysis using eyetracker data." Thesis, Linköpings universitet, Institutionen för teknik och naturvetenskap, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-95333.
Full textAbstract:
Little research has been done on the task of how a person searches for images when presented with a set of images, typically those presented by image search engines. By investigating the properties we might be able to present the images in a different manner to ease the users search for the image he/she is looking for. The work was performed at Chiba University under the supervision of Norimichi Tsumura and Reiner Lenz. I created an experimental platform which first showed a target image and then a 7 × 4 grid in which the users task would be to locate the target image. The experiment data was recorded with a NAC EMR-8B eyetracker that saved the data as both a video and serial data stream. The data was later used to extract certain characteristics for different image sets, like how the eye fixates, and how different image sets affect the scan. The initial place where the user started his/her search was dependent on where the user previously was fixating. It was also more probable that subsequent fixations were placed in a close proximity to the previous fixation. My results also show that the search task was slightly faster when images where placed with a high contrast between neighboring images, i.e. dark images next to bright ones etc.
16
Mannan, Sabira Khanam. "The visual analysis of complex scenes." Thesis, Imperial College London, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.321654.
Full text
17
Wilson, Andrew David. "Learning visual behavior for gesture analysis." Thesis, Massachusetts Institute of Technology, 1995. http://hdl.handle.net/1721.1/62924.
Full text
18
Chung, HaeYong. "Designing Display Ecologies for Visual Analysis." Diss., Virginia Tech, 2015. http://hdl.handle.net/10919/52042.
Full textAbstract:
The current proliferation of connected displays and mobile devices from smart phones and tablets to wall-sized displays presents a number of exciting opportunities for information visualization and visual analytics. When a user employs heterogeneous displays collaboratively to achieve a goal, they form what is known as a display ecology. The display ecology enables multiple displays to function in concert within a broader technological environment to accomplish tasks and goals. However, since information and tasks are scattered and disconnected among separate displays, one of the inherent challenges associated with visual analysis in display ecologies is enabling users to seamlessly coordinate and subsequently connect and integrate information across displays. This research primarily addresses these challenges through the creation of interaction and visualization techniques and systems for display ecologies in order to support sensemaking with visual analysis.
This dissertation explores essential visual analysis activities and design considerations for visual analysis in order to inform the new design of display ecologies for visual analysis. Based on identified design considerations, we then designed and developed two visual analysis systems. First, VisPorter supports intuitive gesture interactions for sharing and integrating information in a display ecology. Second, the Spatially Aware Visual Links (SAViL) presents a cross-display visual link technique capable of guiding the user's attention to relevant information across displays. It also enables the user to visually connect related information over displays in order to facilitate synthesizing information scattered over separate displays and devices. The various aspects associated with the techniques described herein help users to transform and empower the multiple displays in a display ecology for enhanced visual analysis and sensemaking.Ph. D.
19
Oikonomopoulos, Antonios. "Spatiotemporal visual analysis of human actions." Thesis, Imperial College London, 2010. http://hdl.handle.net/10044/1/5871.
Full textAbstract:
In this dissertation we propose four methods for the recognition of human activities. In all four of them, the representation of the activities is based on spatiotemporal features that are automatically detected at areas where there is a significant amount of independent motion, that is, motion that is due to ongoing activities in the scene. We propose the use of spatiotemporal salient points as features throughout this dissertation. The algorithms presented, however, can be used with any kind of features, as long as the latter are well localized and have a well-defined area of support in space and time. We introduce the utilized spatiotemporal salient points in the first method presented in this dissertation. By extending previous work on spatial saliency, we measure the variations in the information content of pixel neighborhoods both in space and time, and detect the points at the locations and scales for which this information content is locally maximized. In this way, an activity is represented as a collection of spatiotemporal salient points. We propose an iterative linear space-time warping technique in order to align the representations in space and time and propose to use Relevance Vector Machines (RVM) in order to classify each example into an action category. In the second method proposed in this dissertation we propose to enhance the acquired representations of the first method. More specifically, we propose to track each detected point in time, and create representations based on sets of trajectories, where each trajectory expresses how the information engulfed by each salient point evolves over time. In order to deal with imperfect localization of the detected points, we augment the observation model of the tracker with background information, acquired using a fully automatic background estimation algorithm. In this way, the tracker favors solutions that contain a large number of foreground pixels. In addition, we perform experiments where the tracked templates are localized on specific parts of the body, like the hands and the head, and we further augment the tracker’s observation model using a human skin color model. Finally, we use a variant of the Longest Common Subsequence algorithm (LCSS) in order to acquire a similarity measure between the resulting trajectory representations, and RVMs for classification. In the third method that we propose, we assume that neighboring salient points follow a similar motion. This is in contrast to the previous method, where each salient point was tracked independently of its neighbors. More specifically, we propose to extract a novel set of visual descriptors that are based on geometrical properties of three-dimensional piece-wise polynomials. The latter are fitted on the spatiotemporal locations of salient points that fall within local spatiotemporal neighborhoods, and are assumed to follow a similar motion. The extracted descriptors are invariant in translation and scaling in space-time. Coupling the neighborhood dimensions to the scale at which the corresponding spatiotemporal salient points are detected ensures the latter. The descriptors that are extracted across the whole dataset are subsequently clustered in order to create a codebook, which is used in order to represent the overall motion of the subjects within small temporal windows.Finally,we use boosting in order to select the most discriminative of these windows for each class, and RVMs for classification. The fourth and last method addresses the joint problem of localization and recognition of human activities depicted in unsegmented image sequences. Its main contribution is the use of an implicit representation of the spatiotemporal shape of the activity, which relies on the spatiotemporal localization of characteristic ensembles of spatiotemporal features. The latter are localized around automatically detected salient points. Evidence for the spatiotemporal localization of the activity is accumulated in a probabilistic spatiotemporal voting scheme. During training, we use boosting in order to create codebooks of characteristic feature ensembles for each class. Subsequently, we construct class-specific spatiotemporal models, which encode where in space and time each codeword ensemble appears in the training set. During testing, each activated codeword ensemble casts probabilistic votes concerning the spatiotemporal localization of the activity, according to the information stored during training. We use a Mean Shift Mode estimation algorithm in order to extract the most probable hypotheses from each resulting voting space. Each hypothesis corresponds to a spatiotemporal volume which potentially engulfs the activity, and is verified by performing action category classification with an RVM classifier.
20
RIZVI, SYED TAHIR HUSSAIN. "Visual Analysis Algorithms for Embedded Systems." Doctoral thesis, Politecnico di Torino, 2018. http://hdl.handle.net/11583/2707423.
Full textAbstract:
The main contribution of this thesis is the design and development of an optimized framework to realize the deep neural classifiers on the embedded platforms. Deep convolutional networks exhibit unmatched performance in image classification. However, these deep classifiers demand huge computational power and memory storage. That is an issue on embedded devices due to limited onboard resources. The computational demand of neural networks mainly stems from the convolutional layers. A significant improvement in performance can be obtained by reducing the computational complexity of these convolutional layers, making them realizable on embedded platforms.
In this thesis, we proposed a CUDA (Compute Unified Device Architecture)-based accelerated scheme to realize the deep architectures on the embedded platforms by exploiting the already trained networks. All required functions and layers to replicate the trained neural networks were implemented and accelerated using concurrent resources of embedded GPU. Performance of our CUDA-based proposed scheme was significantly improved by performing convolutions in the transform domain. This matrix multiplication based convolution was also compared with the traditional approach to analyze the improvement in inference performance.
The second part of this thesis focused on the optimization of the proposed framework. The flow of our CUDA-based framework was optimized using unified memory scheme and hardware-dependent utilization of computational resources. The proposed flow was evaluated over three different image classification networks on Jetson TX1 embedded board and Nvidia Shield K1 tablet. The performance of proposed GPU-only flow was compared with its sequential and heterogeneous versions. The results showed that the proposed scheme brought the higher performance and enabled the real-time image classification on the embedded platforms with lesser storage requirements. These results motivated us towards the realization of useful real-time classification and recognition problems on the embedded platforms.
Finally, we utilized the proposed framework to realize the neural network-based automatic license plate recognition (ALPR) system on a mobile platform. This highly-precise and computationally demanding system was deployed by simplifying the flow of trained deep architecture developed for powerful desktop and server environments. A comparative analysis of computational complexity, recognition accuracy and inference performance was performed.
21
PATTI, DENIS. "Visual Analysis Algorithms for Embedded Systems." Doctoral thesis, Politecnico di Torino, 2018. http://hdl.handle.net/11583/2709452.
Full textAbstract:
Visual search systems are very popular applications, but on-line versions in 3G wireless environments suffer from network constraint like unstable or limited bandwidth that entail latency in query delivery, significantly degenerating the user’s experience. An alternative is to exploit the ability of the newest mobile devices to perform heterogeneous activities, like not only creating but also processing images. Visual feature extraction and compression can be performed on on-board Graphical Processing Units (GPUs), making smartphones capable of detecting a generic object (matching) in an exact way or of performing a classification activity.
The latest trends in visual search have resulted in dedicated efforts in MPEG standardization, namely the MPEG CDVS (Compact Descriptor for Visual Search) standard. CDVS is an ISO/IEC standard used to extract a compressed descriptor.
As regards to classification, in recent years neural networks have acquired an impressive importance and have been applied to several domains. This thesis focuses on the use of Deep Neural networks to classify images by means of Deep learning.
Implementing visual search algorithms and deep learning-based classification on embedded environments is not a mere code-porting activity. Recent embedded devices are equipped with a powerful but limited number of resources, like development boards such as GPGPUs. GPU architectures fit particularly well, because they allow to execute more operations in parallel, following the SIMD (Single Instruction Multiple Data) paradigm. Nonetheless, it is necessary to make good design choices for the best use of available hardware and memory.
For visual search, following the MPEG CDVS standard, the contribution of this thesis is an efficient feature computation phase, a parallel CDVS detector, completely implemented on embedded devices supporting the OpenCL framework. Algorithmic choices and implementation details to target the intrinsic characteristics of the selected embedded platforms are presented and discussed. Experimental results on several GPUs show that the GPU-based solution is up to 7× faster than the
CPU-based one. This speed-up opens new visual search scenarios exploiting entire real-time on-board computations with no data transfer.
As regards to the use of Deep convolutional neural networks for off-line image classification, their computational and memory requirements are huge, and this is an issue on embedded devices. Most of the complexity derives from the convolutional layers and in particular from the matrix multiplications they entail. The contribution of this thesis is a self-contained implementation to image classification providing common layers used in neural networks. The approach relies on a heterogeneous CPU-GPU scheme for performing convolutions in the transform domain. Experimental results show that the heterogeneous scheme described in this thesis boasts a 50× speedup over the CPU-only reference and outperforms a GPU-based reference by 2×, while slashing the power consumption by nearly 30%.
22
Santarcangelo, Vito. "Visual Behavior Analysis in Retail Scenario." Doctoral thesis, Università di Catania, 2018. http://hdl.handle.net/10761/4135.
Full textAbstract:
The retail world is today highly competitive and has seen its logics completely revolutionized by the introduction of e-commerce that have prompted a reaction from the retail market, requiring greater attention to the consumer. We therefore moved from the world of traditional marketing (generic flyer) to that of 1to1 marketing (specific attention to the customer, profiling and personalization of the assortment offer). In this context the need arises to introduce innovative tools that can allow the physical sales spaces to be kept competitive, interacting more with the customer in order to create a more relevant commercial proposal. As a consequence, the computer vision represented one of the possible means to carry out the behavioral analysis of the consumer useful for dynamically adapting the assortment proposal.
DOOH (Digital Out Of Home) in its most widespread form of interactive point-of sale kiosks is one of the best tools to get in touch with the customer, create a synergy with him, listen to his needs in order to improve the offer, the level of service and therefore customer satisfaction. Next to DOOH, it is necessary to introduce further and time-continuous monitoring tools, which map the entire customer's shopping experience into the point of sale. For this purpose the egocentric vision is introduced through the use of cam narratives on board the trolleys, which allow a timely story of the consumer, called Visual Market Basket Analysis (evolution of Market Basket Analysis), which generates process functional alerts to the improvement of
the service offered. The story of these approaches is provided in this PhD thesis, which tells the three-year course carried out, its experiments and possible future developments.
This study has been conducted thanks to the support of Centro Studi S.r.l., a sister company of a privately owned consumer goods distribution company called Orizzonti Holding Group, located in southern Italy. The study has been implemented through an industrial application approach, in a real context (Futura Supermarkets). Consequently, the PhD thesis has considered the typical difficulties of a challenging environment, starting from the creation and acquisition of a dataset to the integration of the approach in the current business processes.
23
Leite, Roger Almeida. "PhenoVis : a visual analysis tool to phenological phenomena." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2015. http://hdl.handle.net/10183/115181.
Full textAbstract:
Phenology studies recurrent periodic phenomena of plants and their relationship to environmental conditions. Monitoring forest ecosystems using digital cameras allows the study of several phenological events, such as leaf expansion or leaf fall. Since phenological phenomena are cyclic, the comparative analysis of successive years is capable of identifying interesting variation on annual patterns. However, the number of images collected rapidly gets significant since the goal is to compare data from several years. Instead of performing the analysis over images, experts prefer to use derived statistics (such as average values). We propose PhenoVis, a visual analytics tool that provides insightful ways to analyze phenological data. The main idea behind PhenoVis is the Chronological Percentage Maps (CPMs), a visual mapping that offers a summary view of one year of phenological data. CPMs are highly customizable, encoding more information about the images using a pre-defined histogram, a mapping function that translates histogram values into colors, and a normalized stacked bar chart to display the results. PhenoVis supports different color encodings, visual pattern analysis over CPMs, and similarity searches that rank vegetation patterns found at various time periods. Results for datasets comprising data of up to nine consecutive years show that PhenoVis is capable of finding relevant phenological patterns along time. Fenologia estuda os fenômenos recorrentes e periódicos que ocorrem com as plantas. Estes podem vir a ser relacionados com as condições ambientais. O monitoramento de florestas, através de câmeras, permite o estudo de eventos fenológicos como o crescimento e queda de folhas. Uma vez que os fenômenos fenológicos são cíclicos, análises comparativas de anos sucessivos podem identificar variações interessantes no comportamento destes. No entanto, o número de imagens cresce rapidamente para que sejam comparadas lado a lado. PhenoVis é uma ferramenta para análise visual que apresenta formas para analisar dados fenológicos através de comparações estatísticas (preferência dos especialistas) derivadas dos valores dos pixels destas imagens. A principal ideia por trás de PhenoVis são os mapas percentuais cronológicos (CPMs), um mapeamento visual com uma visão resumida de um período de um ano de dados fenológicos. CPMs são personalizáveis e conseguem representar mais informações sobre as imagens do que um gráfico de linha comum. Isto é possível pois o processo envolve o uso de histogramas pré-definidos, um mapeamento que transforma valores em cores e um empilhamento dos mapas de percentagem que visa a criação da CPM. PhenoVis suporta diferentes codificações de cores e análises de padrão visual sobre as CPMs. Pesquisas de similaridade ranqueiam padrões parecidos encontrados nos diferentes anos. Dados de até nove anos consecutivos mostram que PhenoVis é capaz de encontrar padrões fenológicos relevantes ao longo do tempo.
24
Cerutti, Lisa. "Visual grounded analysis : developing and testing a method for preliminary visual research." Thesis, London Metropolitan University, 2017. http://repository.londonmet.ac.uk/1471/.
Full textAbstract:
Approaching a new design project by performing preliminary visual research is a common practice in educational and studio settings, particularly in Jewellery and Fashion Design. Collecting images around a given subject or theme - for better understanding its visual traits, or for future reference - could be seen as the counterpart, in visual terms, of a literature search. However, ‘visual research’ is an expression often used rather vaguely for indicating a spectrum of unstructured methodological approaches, whose procedures and underlying assumptions tend to remain unexplained, undisclosed or unquestioned in everyday studio practice. When creative practice becomes an integral part of academic research, though, there is an increased need for rigor and explicitness regarding every aspect about it, including all the work preliminary to it. This research aims to develop and test a systematic method for conducting and documenting visual research in the preliminary stages of the design process, contributing to new knowledge in the form of a new visual method, also applicable as a design tool. A reflection on the vagueness and implicitness of the Intuitive Approach (IA) to visual research adopted in the initial stage of this PhD motivated the search for an alternative method that could make transparent and rigorous the taken-for-granted, subjective assumptions behind the research initially conducted. The iterative and data-driven nature of the IA oriented the methodological quest towards established qualitative approaches in the Social Sciences, focusing on Emergent Methods and Grounded Theory. By translating and adapting some of their procedures to suit a visual context, a new method, Grounded Visual Analysis (GVA), has been developed and tested, revealing its suitability for achieving a higher degree of explicitness and systematicity in the process of data collection and analysis, and increasing the richness of the visual patterns elicited from the data, thus their potential for stimulating reflective practice. The development of GVA is offered as the major contribution to knowledge of this research, together with its application on a practical case as the demonstration of its double functioning, either as a reflective method for conducting visual research in the preparatory phase of the design process, and as a design tool for stimulating the generation of new ideas and design briefs.
25
Chan, Y. M. "Depth perception in visual images." Thesis, University of Brighton, 1987. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.380238.
Full text
26
Economou, Dorothy. "Photos in the News: appraisal analysis of visual semiosis and verbal-visual intersemiosis." University of Sydney, 2009. http://hdl.handle.net/2123/5740.
Full textAbstract:
Doctor of Philosophy (PhD)This thesis concerns the intersection of social semiotic theory and critical discourse analysis (CDA), applying systemic-functional (SF) theory to verbal-visual news media texts. The aim of the thesis is to develop social semiotic descriptions of visual meaning in order to facilitate analyses of evaluative stance in visual-verbal text. The texts studied are ‘factual’ daily broadsheet news photos and prominent visual-verbal ‘displays’ that incorporate these photos alongside headlines and captions. Such displays introduce investigative stories on the front page of broadsheet weekly news reviews and are referred to in the thesis as ‘standout’ texts. They are significant because they may also be read as independent texts and play a critical role in positioning a wide readership on the issues investigated in the story. The SF system of verbal appraisal was used in this thesis to develop a corresponding system of visual appraisal. The process involved applying general appraisal options to a corpus of news photos and proceeding to further delicacy in a repeated cycle of analysis and system-building. Once refined in this way the system was applied alongside the verbal appraisal system to account for evaluation in verbal-visual standouts. In the thesis four Australian and four Greek standouts introducing stories on asylum seekers were analysed in order to explore the potential for variation and the impact of context on evaluative meaning choices. The thesis contributes insights into SF theory, media discourse and CDA. The visual systems developed allow appraisal analysis to be extended to images and to verbalvisual texts. Visual appraisal analysis in the thesis provides new evidence for the ideological and evaluative power of news photos. Verbal-visual appraisal analysis shows how each semiotic contributes to evaluative meaning, and to its accumulation and spread across a text. In respect to media discourse, the thesis also provides evidence for the ‘standout’ as an orbital verbal-visual news genre. The comparison of evaluative stance in two sets of standouts demonstrates consistent editorial choices in texts within each context and contrasts across the two sites. The Australian texts display more evaluative complexity, greater emphasis on entertainment and offer two different stances, aligning a diverse target audience. The Greek texts are more straightforward and construct a single stance, aligning a narrower audience. By identifying the semiotic choices involved in the evaluative positioning of readers by visual-verbal texts, the thesis can contribute to more informed and reflective practice. Thus, as well as making theoretical advances, the findings have relevance for journalism and education at a time when the impact of images is changing our conception of literacy.
27
Parameswaran, Vasudev. "View-invariance in visual human motion analysis." College Park, Md. : University of Maryland, 2004. http://hdl.handle.net/1903/1408.
Full textAbstract:
Thesis (Ph. D.) -- University of Maryland, College Park, 2004.Thesis research directed by: Computer Science. Title from t.p. of PDF. Includes bibliographical references. Published by UMI Dissertation Services, Ann Arbor, Mich. Also available in paper.
28
Liu, Zhicheng. "Network-based visual analysis of tabular data." Diss., Georgia Institute of Technology, 2012. http://hdl.handle.net/1853/43687.
Full textAbstract:
Tabular data is pervasive in the form of spreadsheets and relational databases. Although tables often describe multivariate data without explicit network semantics, it may be advantageous to explore the data modeled as a graph or network for analysis. Even when a given table design conveys some static network semantics, analysts may want to look at multiple networks from different perspectives, at different levels of abstraction, and with different edge semantics.
This dissertation is motivated by the observation that a general approach for performing multi-dimensional and multi-level network-based visual analysis on multivariate tabular data is necessary. We present a formal framework based on the relational data model that systematically specifies the construction and transformation
of graphs from relational data tables. In the framework, a set of relational operators provide the basis for rich expressive power for network modeling.
Powered by this relational algebraic framework, we design and implement a visual analytics system called Ploceus. Ploceus supports flexible construction and transformation of networks through a direct manipulation interface, and integrates dynamic network manipulation with visual exploration for a seamless analytic experience.
29
Sedlmair, Michael. "Visual Analysis of In-Car Communication Networks." Diss., lmu, 2010. http://nbn-resolving.de/urn:nbn:de:bvb:19-124488.
Full text
30
Rehm, Frank. "Visual data analysis in air traffic management /." Köln : DLR, 2007. http://diglib.uni-magdeburg.de/Dissertationen/2007/frarehm.htm.
Full text
31
Al-Sowaidi, Faraj. "Visual analysis of the decay of pears." Virtual Press, 1988. http://liblink.bsu.edu/uhtbin/catkey/724953.
Full textAbstract:
This creative project explored the visual characteristics of the transitions found in the decay of the pear. The project consisted of oil paintings, watercolors and prints. I found that what is normally viewed as ugly can be visually stimulating or actually beautiful. These images were produced to communicate the visual changes which occure with the characteristics of the fruit through the passage of time.Department of Art
32
Chen, Da. "The visual analysis of complex natural phenomena." Thesis, University of Bath, 2017. https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.760925.
Full textAbstract:
Optical flow estimation or dense motion estimation for dynamic natural phenomena (water, smoke, fire, etc.) is a significant open problem in Computer Vision. Assumptions such as brightness constancy cannot be relied upon, as natural phenomena scenes contain lots of non- rigid motion, blurred motion, etc. Current approaches tend to be either general, giving poor results, or else be specialised in one phenomenon and therefore fail to generalise well. The literature would benefit from a general solution, and such a solution could be found useful in a diverse set of application areas. In this thesis, we prove that a skeleton based feature can guide the standard optical flow pipeline to obtain state-of-the-art motion results. We also demonstrate that this result can be applied in different applications such as video segmentation, slow motion, etc. First, we describe an approach to estimating dense motion for dynamic phenomena that is simple and can be extended to a wide range of phenomena. The key to our approach is to replace local assumptions such as brightness constancy with the global assumption in which characteristic topographic maps change subtly. This leads to a global sparse motion estimation, which upgrades to dense estimation for final motion results, as suggested in our experiments, are state-of-the-art. We demonstrate the method using lab-based and consumer-level video obtained from our dataset, public dataset and the Internet. Second, the motion result is applied on a slow motion application which contains fewer artefacts than the state-of-the-art commercial software Adobe AfterEffect 2017 CC. Third, we embed the motion result and the skeleton feature in a video segmentation pipeline and outperform the state-of-the-art video segmentation methods including the method which is specially designed for natural phenomena. Fourth, we introduce a dataset containing two types of sequences i.e., sequences based on a 6-sync cameras system and sequences with 88 different kinds of dynamic textures with a single view camera lab set-up. Fifth, since semi-transparent case often happens in natural phenomena, a closed form solution for layer separation is also proposed.
33
Sokolov, Michael Adam. "Visual motion : algorithms for analysis and application." Thesis, Massachusetts Institute of Technology, 1990. http://hdl.handle.net/1721.1/70173.
Full text
34
Simoncelli, Eero Peter. "Distributed representation and analysis of visual motion." Thesis, Massachusetts Institute of Technology, 1993. http://hdl.handle.net/1721.1/12590.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1993.Includes bibliographical references (leaves 171-179).
by Eero Peter Simoncelli.
Ph.D.
35
Sullivan, Terry. "The Cluster Hypothesis: A Visual/Statistical Analysis." Thesis, University of North Texas, 2000. https://digital.library.unt.edu/ark:/67531/metadc2444/.
Full textAbstract:
By allowing judgments based on a small number of exemplar documents to be applied to a larger number of unexamined documents, clustered presentation of search results represents an intuitively attractive possibility for reducing the cognitive resource demands on human users of information retrieval systems. However, clustered presentation of search results is sensible only to the extent that naturally occurring similarity relationships among documents correspond to topically coherent clusters. The Cluster Hypothesis posits just such a systematic relationship between document similarity and topical relevance. To date, experimental validation of the Cluster Hypothesis has proved problematic, with collection-specific results both supporting and failing to support this fundamental theoretical postulate.
The present study consists of two computational information visualization experiments, representing a two-tiered test of the Cluster Hypothesis under adverse conditions. Both experiments rely on multidimensionally scaled representations of interdocument similarity matrices. Experiment 1 is a term-reduction condition, in which descriptive titles are extracted from Associated Press news stories drawn from the TREC information retrieval test collection. The clustering behavior of these titles is compared to the behavior of the corresponding full text via statistical analysis of the visual characteristics of a two-dimensional similarity map. Experiment 2 is a dimensionality reduction condition, in which inter-item similarity coefficients for full text documents are scaled into a single dimension and then rendered as a two-dimensional visualization; the clustering behavior of relevant documents within these unidimensionally scaled representations is examined via visual and statistical methods.
Taken as a whole, results of both experiments lend strong though not unqualified support to the Cluster Hypothesis. In Experiment 1, semantically meaningful 6.6-word document surrogates systematically conform to the predictions of the Cluster Hypothesis. In Experiment 2, the majority of the unidimensionally scaled datasets exhibit a marked nonuniformity of distribution of relevant documents, further supporting the Cluster Hypothesis.
Results of the two experiments are profoundly question-specific. Post hoc analyses suggest that it may be possible to predict the success of clustered searching based on the lexical characteristics of users' natural-language expression of their information need.
36
Karthikeyan, Nithesh Chandher. "Analysis of visual political communication on YouTube." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-447660.
Full textAbstract:
Though images are ubiquitous in everyday life and have always been part of politics, research on the visual aspects of political communication recently gained momentum, especially with the rise of social media. This opens up a platform to analyze the role of visuals in communicating political ideas. Images are a key part of the communication process, shaping peoples’ attitudes and policy preferences on political ideas. Generally iconic themes dominate representation of political ideas, for example iconic themes like polar bears represent the issues of climate change and environmental policies. This thesis focuses on finding such distant iconic themes in visuals of growing social media platforms like YouTube using deep learning. The initial analysis revealed the poor performance of the existing state-of-the-art networks on image classification in detecting the simple iconic theme of Polar bear in visuals. This arises a need for a new approach to improve the performance in detecting visual themes. The thesis proposes a method to develop a custom network by transferring the knowledge of the state-of-the-art networks using transfer learning. The result shows that the custom network has a better recall on predicting Polar bears than the state-of-the-art networks and the impact of training methods on predicting visualthemes on YouTube data.
37
Bulusu, Prakash. "DIVA-Data warehouse Interface for Visual Analysis." [Gainesville, Fla.] : University of Florida, 2003. http://purl.fcla.edu/fcla/etd/UFE0000655.
Full text
38
Ess, Andreas. "Visual urban scene analysis by moving platforms." Konstanz Hartung-Gorre, 2009. http://d-nb.info/998626767/04.
Full text
39
Vohra, Neeru Rani. "Three dimensional statistical graphs, visual cues and clustering." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp03/MQ56213.pdf.
Full text
40
Janicke, Susan Beth. "Visual Arts and Chronic Pain: Thematic Analysis to the Artistic Statements of Visual Artists." ScholarWorks, 2015. http://scholarworks.waldenu.edu/dissertations/1689.
Full textAbstract:
The relief of pain is an essential element of nursing practice. Nursing has begun to successfully use art to assess and reduce pain among hospitalized children, surgical patients, and oncology patients. Structured art projects have been used to provide distraction from pain and patient drawings have allowed nurses to assess pain. This project employed grounded theory and thematic analysis to uncover significant concepts in the artists' statements. The Roy adaptation model and Saunders' total pain theory provided the project theoretical framework. The artistic statements and the art of chronic pain patients were examined using thematic analysis to identify recurrent themes. This project explored the insights to chronic pain in the adult patient as evidenced in the posted work. The project also considered how the content of the posted artistic statements informed individual nursing practice and facilitated the reduction of pain in the adult patient suffering from chronic pain. Emergent concepts were used to develop artistic nursing interventions. Suggested modification of nursing practice included drawing as a tool in pain assessment, exploring the meaning of color choices, encouraging mask making, providing distraction, and using art to identify spiritual distress. The proposed nursing actions will allow more effective communication of pain, provide meaningful distraction, intervene in spiritual distress, and encourage creation of an artistic product. Expected outcomes include more effective pain control, greater patient autonomy, and reduced healthcare costs. The application of this new knowledge and skill will make a difference in the lives of chronic pain patients and will therefore promote positive social change.
41
Ren, Reede. "Audio-visual football video analysis, from structure detection to attention analysis." Thesis, Connect to e-thesis. Move to record for print version, 2008. http://theses.gla.ac.uk/77/.
Full textAbstract:
Thesis (Ph.D.) - University of Glasgow, 2008.Ph.D. thesis submitted to the Faculty of Information and Mathematical Sciences, Department of Computing Science, University of Glasgow, 2008. Includes bibliographical references. Print version also available.
42
Zhou, Hong. "Visual clustering in parallel coordinates and graphs /." View abstract or full-text, 2009. http://library.ust.hk/cgi/db/thesis.pl?CSED%202009%20ZHOU.
Full text
43
Jain, Varun. "Visual Observation of Human Emotions." Thesis, Université Grenoble Alpes (ComUE), 2015. http://www.theses.fr/2015GRENM006/document.
Full textAbstract:
Cette thèse a pour sujet le développement de méthodes et de techniques permettant d'inférer l'état affectif d'une personne à partir d'informations visuelles. Plus précisement, nous nous intéressons à l'analyse d'expressions du visage, puisque le visage est la partie la mieux visible du corps, et que l'expression du visage est la manifestation la plus évidente de l'affect. Nous étudions différentes théories psychologiques concernant affect et émotions, et différentes facons de représenter et de classifier les émotions d'une part et la relation entre expression du visage et émotion sousjacente d'autre part. Nous présentons les dérivées Gaussiennes multi-échelle en tant que descripteur dímages pour l'estimation de la pose de la tête, pour la détection de sourire, puis aussi pour la mesure de l'affect. Nous utilisons l'analyse en composantes principales pour la réduction de la dimensionalité, et les machines à support de vecteur pour la classification et la regression. Nous appliquons cette même architecture, simple et efficace, aux différents problèmes que sont l'estimation de la pose de tête, la détection de sourire, et la mesure d'affect. Nous montrons que non seulement les dérivées Gaussiennes multi-échelle ont une performance supérieure aux populaires filtres de Gabor, mais qu'elles sont également moins coûteuses en calculs. Lors de nos expérimentations nous avons constaté que dans le cas d'un éclairage partiel du visage les dérivées Gaussiennes multi-échelle ne fournissent pas une description d'image suffisamment discriminante. Pour résoudre ce problème nous combinons des dérivées Gaussiennes avec des histogrammes locaux de type LBP (Local Binary Pattern). Avec cette combinaison nous obtenons des résultats à la hauteur de l'état de l'art pour la détection de sourire dans le base d'images GENKI qui comporte des images de personnes trouvées «dans la nature» sur internet, et avec la difficile «extended YaleB database». Pour la classification dans la reconnaissance de visage nous utilisons un apprentissage métrique avec comme mesure de similarité une distance de Minkowski. Nous obtenons le résultat que les normes L1 and L2 ne fournissent pas toujours la distance optimale; cet optimum est souvent obtenu avec une norme Lp où p n'est pas entier. Finalement, nous développons un système multi-modal pour la détection de dépressions nerveuses, avec en entrée des informations audio et vidéo. Pour la détection de mouvements intra-faciaux dans les données vidéo nous utilisons de descripteurs de type LBP-TOP (Local Binary Patterns -Three Orthogonal Planes), alors que nous utilisons des trajectoires denses pour les mouvements plus globaux, par exemple de la tête ou des épaules. Nous avons trouvé que les descripteurs LBP-TOP encodés avec des vecteurs de Fisher suffisent pour dépasser la performance de la méthode de reférence dans la compétition «Audio Visual Emotion Challenge (AVEC) 2014». Nous disposons donc d'une technique effective pour l'evaluation de l'état dépressif, technique qui peut aisement être étendue à d'autres formes d'émotions qui varient lentement, comme l'humeur (mood an Anglais)In this thesis we focus on the development of methods and techniques to infer affect from visual information. We focus on facial expression analysis since the face is one of the least occluded parts of the body and facial expressions are one of the most visible manifestations of affect. We explore the different psychological theories on affect and emotion, different ways to represent and classify emotions and the relationship between facial expressions and underlying emotions. We present the use of multiscale Gaussian derivatives as an image descriptor for head pose estimation, smile detection before using it for affect sensing. Principal Component Analysis is used for dimensionality reduction while Support Vector Machines are used for classification and regression. We are able to employ the same, simple and effective architecture for head pose estimation, smile detection and affect sensing. We also demonstrate that not only do multiscale Gaussian derivatives perform better than the popular Gabor Filters but are also computationally less expensive to compute. While performing these experiments we discovered that multiscale Gaussian derivatives do not provide an appropriately discriminative image description when the face is only partly illuminated. We overcome this problem by combining Gaussian derivatives with Local Binary Pattern (LBP) histograms. This combination helps us achieve state-of-the-art results for smile detection on the benchmark GENKI database which contains images of people in the "wild" collected from the internet. We use the same description method for face recognition on the CMU-PIE database and the challenging extended YaleB database and our results compare well with the state-of-the-art. In the case of face recognition we use metric learning for classification, adopting the Minkowski distance as the similarity measure. We find that L1 and L2 norms are not always the optimum distance metrics and the optimum is often an Lp norm where p is not an integer. Lastly we develop a multi-modal system for depression estimation with audio and video information as input. We use Local Binary Patterns -Three Orthogonal Planes (LBP-TOP) features to capture intra-facial movements in the videos and dense trajectories for macro movements such as the movement of the head and shoulders. These video features along with Low Level Descriptor (LLD) audio features are encoded using Fisher Vectors and finally a Support Vector Machine is used for regression. We discover that the LBP-TOP features encoded with Fisher Vectors alone are enough to outperform the baseline method on the Audio Visual Emotion Challenge (AVEC) 2014 database. We thereby present an effective technique for depression estimation which can be easily extended for other slowly varying aspects of emotions such as mood
44
Ventura, Royo Carles. "Visual object analysis using regions and local features." Doctoral thesis, Universitat Politècnica de Catalunya, 2016. http://hdl.handle.net/10803/398407.
Full textAbstract:
The first part of this dissertation focuses on an analysis of the spatial context in semantic image segmentation. First, we review how spatial context has been tackled in the literature by local features and spatial aggregation techniques. From a discussion about whether the context is beneficial or not for object recognition, we extend a Figure-Border-Ground segmentation for local feature aggregation with ground truth annotations to a more realistic scenario where object proposals techniques are used instead. Whereas the Figure and Ground regions represent the object and the surround respectively, the Border is a region around the object contour, which is found to be the region with the richest contextual information for object recognition. Furthermore, we propose a new contour-based spatial aggregation technique of the local features within the object region by a division of the region into four subregions. Both contributions have been tested on a semantic segmentation benchmark with a combination of free and non-free context local features that allows the models automatically learn whether the context is beneficial or not for each semantic category.
The second part of this dissertation addresses the semantic segmentation for a set of closely-related images from an uncalibrated multiview scenario. State-of-the-art semantic segmentation algorithms fail on correctly segmenting the objects from some viewpoints when the techniques are independently applied to each viewpoint image. The lack of large annotations available for multiview segmentation do not allow to obtain a proper model that is robust to viewpoint changes. In this second part, we exploit the spatial correlation that exists between the different viewpoints images to obtain a more robust semantic segmentation. First, we review the state-of-the-art co-clustering, co-segmentation and video segmentation techniques that aim to segment the set of images in a generic way, i.e. without considering semantics. Then, a new architecture that considers motion information nd provides a multiresolution segmentation is proposed for the co-clustering framework nd outperforms state-of-the-art techniques for generic multiview segmentation. Finally, the proposed multiview segmentation is combined with the semantic segmentation results giving a method for automatic resolution selection and a coherent semantic multiview segmentation.La primera part de la tesi es focalitza en l'anàlisi del context espacial en la segmentació semàntica d'imatges. En primer lloc, revisem com s'ha tractat el context espacial en la literatura per mitjà de descriptors locals i tècniques d'agregació espacial. A partir de la discussió sobre si el context és beneficial o no per al reconeixement d'objectes, extenem una segmentació en objecte, contorn i fons per a l'agregació espacial de descriptors locals amb annotacions a un escenari més realístic on s'utilitzen hipòtesis de localitzacions d'objectes enlloc d'annotacions. Mentres que les regions corresponen a objecte i fons representes aquestes àrees respectives de la imatge, el contorn és una regió al voltant de l'objecte, la qual ha resultat ser la regió més rica amb informació contextual per al reconeixement d'objectes. A més a més, proposem una nova tècnica d'agregació espacial dels descriptors locals de l'interior de l'objecte amb una divisió d'aquesta regió en 4 subregions. Ambdues contribucions han estat verificades en un benchmark de segmentació semàntica amb la combinació de descriptors locals dependents i independents del context que permet que els models automàticament aprenguin si el context és beneficiós o no per a cada categoria semàntica. La segona part de la tesi aborda el problema de segmentació semàntica per a un conjunt d'imatges relacionades en un escenari multi-vista sense calibració. Els algorismes de l'estat de l'art en segmentació semàntica fallen en segmentar correctament els objects dels diferents punts de vista quan les tècniques són aplicades de forma independent a cadascun dels punts de vista. La manca d'un nombre elevat d'annotacions disponibles per a segmentació multi-vista no permet obtenir un model que sigui robust als canvis de vista. En aquesta segona part, explotem la correlació espacial existent entre els diferents punts de vista per obtenir una segmentació semàntica més robusta. En primer lloc, revisem les tècniques de l'estat de l'art en co-agrupament, co-segmentació i segmentació de vídeo que tenen per objectiu segmentar el conjunt d'imatges de forma genèrica, és a dir, sense considerar la semàntica. A continuació, proposem una nova arquitectura de co-agrupament que considera informació de moviment i proveeix una segmentació amb múltiples resolucions i millora les tècniques de l'estat de l'art en segmentació genèrica multi-vista. Finalment, la segmentació multivista proposada és combinada amb els resultats de la segmentació semàntica donant lloc a un mètode per a una selecció automàtica de la resolució i una segmentació semàntica multi-vista coherent.
45
Hall, Tonya A. "Patient satisfaction : a visual analysis using Trellis Graphics." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 1998. http://handle.dtic.mil/100.2/ADA355903.
Full textAbstract:
Thesis (M.S. in Operations Research) Naval Postgraduate School, September 1998."September 1998." Thesis advisor(s): Samuel E. Buttrey. Includes bibliographical references (p. 67-68). Also available online.
46
Van, den Bergh Michael. "Visual body pose analysis for human-computer interaction." Konstanz Hartung-Gorre, 2010. http://d-nb.info/1000839370/04.
Full text
47
Kostkevicius, Björn. "Visual Analysis of Author Impacts and Bibliometric Data." Thesis, Linnéuniversitetet, Institutionen för datavetenskap, fysik och matematik, DFM, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-18632.
Full textAbstract:
AbstractThis thesis is about the visual analysis of author impact and other bibliometric data such as an authorspublication history. It utilizes Publish or Perish as a data source, which is a search tool to find thisbibliometric data. Bibliometric data is a concept within Bibliometrics with which to find and definenotable publications, to draw a number of different conclusions, such as how much impact an authorhas had in a given field. To do this we use information visualization techniques. InformationVisualization is a field of science about increasing insight and understanding of raw data. It does this byresearching on details of human cognition and perception and how data itself is modeled, and bycategorizing and developing new ways to encode and interact with data visually.Since Publish or Perish only gives its information as a raw text feed, and do not allow for anyreal comparisons between authors, this thesis tries to rectify this by introducing a web basedvisualization tool to analyze this data. The data itself consists of a number of scientifically definedindexes which measures an author's impact in his given field, an overview of his publication history,and some general bibliometric data.
48
Haga, Thorsten. "Visual Analysis of Swedish Research Council's Project Database." Thesis, Linnéuniversitetet, Institutionen för datavetenskap, fysik och matematik, DFM, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-21681.
Full textAbstract:
A human can understand data visualizations easier than reading the source .The goal of this thesis is to support the user with an application to fulfill this problem, so he is able to cope with the data and also filter it for his interests. This thesis aims to visualize projects of the Swedish Research Council (Vetenskapsrådet) supported by the latest web technologies. The visualizations, which will be created from the projects, are interactive, so the user is able to select a single university and their faculties by years and other categories. The application is quite transparent, so it is conceivable that it also fits in most organisations or firms who want to analyse their departments project budgets.The web application is built with the newest Hypertext Markup Language Standard (HTML5) and Cascading Style Sheets (CSS3). A large part of the application was programmed with the help of the new Toolkitfrom the Google family which is called Google Web Toolkit.
49
Ižo, Tomáš 1979. "Visual attention models for far-field scene analysis." Thesis, Massachusetts Institute of Technology, 2007. http://hdl.handle.net/1721.1/40314.
Full textAbstract:
Thesis (Ph. D.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2007.This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
Includes bibliographical references (p. 141-146).
The amount of information available to an intelligent monitoring system is simply too vast to process in its entirety. One way to address this issue is by developing attentive mechanisms that recognize parts of the input as more interesting than others. We apply this concept to the domain of far-field activity analysis by addressing the problem of determining where to look in a scene in order to capture interesting activity in progress. We pose the problem of attention as an unsupervised learning problem, in which the task is to learn from long-term observation a model of the usual pattern of activity. Such a statistical scene model then makes it possible to detect and attend to examples of unusual activity. We present two data-driven scene modeling approaches. In the first, we model the pattern of individual observations (instances) of moving objects at each scene location as a mixture of Gaussians. In the second approach, we model the pattern of sequences of observations -- tracks -- by grouping them into clusters.We employ a similarity measure that combines comparisons of multiple attributes -- such as size, position, and velocity -- in a principled manner so that only tracks that are spatially similar and have similar attributes at spatially corresponding points are grouped together. We group the tracks using spectral clustering and represent the scene model as a mixture of Gaussians in the spectral embedding space. New examples of activity can be efficiently classified by projection into the embedding space. We demonstrate clustering and unusual activity detection results on a week of activity in the scene (about 40,000 moving object tracks) and show that human perceptual judgments of unusual activity are well-correlated with the statistical model. The human validation suggests that the track-based anomaly detection framework would perform well as a classifier for unusual events. To our knowledge, our work is the first to evaluate a statistical scene modeling and anomaly detection framework against human judgments.
by Tomáš Ižo.
Ph.D.
50
Kassel, Jan-Frederik [Verfasser]. "On intelligible multimodal visual analysis / Jan-Frederik Kassel." Hannover : Gottfried Wilhelm Leibniz Universität Hannover, 2020. http://d-nb.info/1220422258/34.
Full text