Artykuły w czasopismach: „Object matching”

1

Li, Stan Z. "Bayesian object matching." Journal of Applied Statistics 25, no. 3 (June 1998): 425–43. http://dx.doi.org/10.1080/02664769823142.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

2

Leme, Luiz André P., Daniela F. Brauner, Karin K. Breitman, Marco A. Casanova, and Alexandre Gazola. "Matching object catalogues." Innovations in Systems and Software Engineering 4, no. 4 (October 31, 2008): 315–28. http://dx.doi.org/10.1007/s11334-008-0070-3.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

3

Klami, Arto. "Bayesian object matching." Machine Learning 92, no. 2-3 (April 30, 2013): 225–50. http://dx.doi.org/10.1007/s10994-013-5357-4.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

4

Koning, Arno, and Johan Wagemans. "Detection of Symmetry and Repetition in One and Two Objects." Experimental Psychology 56, no. 1 (January 2009): 5–17. http://dx.doi.org/10.1027/1618-3169.56.1.5.

Pełny tekst źródła

Streszczenie:

Symmetry is usually easier to detect within a single object than in two objects (one-object advantage), while the reverse is true for repetition (two-objects advantage). This interaction between regularity and number of objects could reflect an intrinsic property of encoding spatial relations within and across objects or it could reflect a matching strategy. To test this, regularities between two contours (belonging to a single object or two objects) had to be detected in two experiments. Projected three-dimensional (3-D) objects rotated in depth were used to disambiguate figure-ground segmentation and to make matching based on simple translations of the two-dimensional (2-D) contours unlikely. Experiment 1 showed the expected interaction between regularity and number of objects. Experiment 2 used two-objects displays only and prevented a matching strategy by also switching the positions of the two objects. Nevertheless, symmetry was never detected more easily than repetition in these two-objects displays. We conclude that structural coding, not matching strategies, underlies the one-object advantage for symmetry and the two-objects advantage for repetition.

Style APA, Harvard, Vancouver, ISO itp.

5

Auclair-Ouellet, Noémie, Marion Fossard, Joël Macoir, and Robert Laforce. "The Nonverbal Processing of Actions Is an Area of Relative Strength in the Semantic Variant of Primary Progressive Aphasia." Journal of Speech, Language, and Hearing Research 63, no. 2 (February 26, 2020): 569–84. http://dx.doi.org/10.1044/2019_jslhr-19-00271.

Pełny tekst źródła

Streszczenie:

Purpose Better performance for actions compared to objects has been reported in the semantic variant of primary progressive aphasia (svPPA). This study investigated the influence of the assessment task (naming, semantic picture matching) over the dissociation between objects and actions. Method Ten individuals with svPPA and 17 matched controls completed object and action naming tests, and object and action semantic picture matching tests. Performance was compared between the svPPA and control groups, within the svPPA group, and for each participant with svPPA versus the control group individually. Results Compared to controls, participants with svPPA were impaired on object and action naming, and object and action semantic picture matching. As a group, participants with svPPA had an advantage for actions over objects and for semantic picture matching tests over naming tests. Eight participants had a better performance for actions compared to objects in naming, with three showing a significant difference. Nine participants had a better performance for actions compared to objects in semantic picture matching, with six showing a significant difference. For objects, semantic picture matching was better than naming in nine participants, with five showing a significant difference. For actions, semantic picture matching was better than naming in all 10 participants, with nine showing a significant difference. Conclusion The nonverbal processing of actions, as assessed with a semantic picture matching test, is an area of relative strength in svPPA. Clinical implications for assessment planning and interpretation and theoretical implications for current models of semantic cognition are discussed.

Style APA, Harvard, Vancouver, ISO itp.

6

Guo, Lei, Ningdong Song, Jindong Hu, Huiyan Han, Xie Han, and Fengguang Xiong. "Focusing 3D Small Objects with Object Matching Set Abstraction." Applied Sciences 15, no. 8 (April 9, 2025): 4121. https://doi.org/10.3390/app15084121.

Pełny tekst źródła

Streszczenie:

Currently, 3D object detection methods fail to detect small objects due to the fewer effective points of small objects. It is a significant challenge to reduce the loss of information of points in representation learning. To this end, we propose an effective 3D detection method with object matching set abstraction (OMSA). We observe that key points are lost during feature learning with multiple set abstraction layers, especially for downsampling and queries. Therefore, we present a novel sampling module named focus-based sampling, which raises the sampling probability of small objects. In addition, we design a multi-scale cube query to match the small objects with a close geometric alignment. Our comprehensive experimental evaluations on the KITTI 3D benchmark demonstrate significant performance improvements in 3D object detection. Notably, the proposed framework exhibits competitive detection accuracy for small objects (pedestrians and cyclists). Through an ablation study, we verify that each module contributes to the performance enhancement and demonstrate the robustness of the method against the balance factor.

Style APA, Harvard, Vancouver, ISO itp.

7

Ulrich, Markus, Patrick Follmann, and Jan-Hendrik Neudeck. "A comparison of shape-based matching with deep-learning-based object detection." tm - Technisches Messen 86, no. 11 (November 26, 2019): 685–98. http://dx.doi.org/10.1515/teme-2019-0076.

Pełny tekst źródła

Streszczenie:

AbstractMatching, i. e. determining the exact 2D pose (e. g., position and orientation) of objects, is still one of the key tasks in machine vision applications like robot navigation, measuring, or grasping an object. There are many classic approaches for matching, based on edges or on the pure gray values of the template. In recent years, deep learning has been utilized mainly for more difficult tasks where the objects of interest are from many different categories with high intra-class variations and classic algorithms are failing. In this work, we compare one of the latest deep-learning-based object detectors with classic shape-based matching. We evaluate the methods both on a matching dataset as well as an object detection dataset that contains rigid objects and is thus also suitable for shape-based matching. We show that for datasets of this type, where rigid objects appear with rigid transformations, shape-based matching still outperforms recent object detectors regarding runtime, robustness, and precision if only a single template image per object is used. On the other hand, we show that for the application of object detection, the deep-learning-based approach outperforms the classic approach if annotated data is used for training. Ultimately, the choice of the best suited approach depends on the conditions and requirements of the application.

Style APA, Harvard, Vancouver, ISO itp.

8

Flusser, Jan. "Object matching by means of matching likelihood coefficients." Pattern Recognition Letters 16, no. 9 (September 1995): 893–900. http://dx.doi.org/10.1016/0167-8655(95)00032-c.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

9

Zhu, Daoye, Chengqi Cheng, Weixin Zhai, Yihang Li, Shizhong Li, and Bo Chen. "Multiscale Spatial Polygonal Object Granularity Factor Matching Method Based on BPNN." ISPRS International Journal of Geo-Information 10, no. 2 (February 13, 2021): 75. http://dx.doi.org/10.3390/ijgi10020075.

Pełny tekst źródła

Streszczenie:

Spatial object matching is one of the fundamental technologies used for updating and merging spatial data. This study focused mainly on the matching optimization of multiscale spatial polygonal objects. We proposed a granularity factor evaluation index that was developed to promote the recognition ability of complex matches in multiscale spatial polygonal object matching. Moreover, we designed the granularity factor matching model based on a backpropagation neural network (BPNN) and designed a multistage matching workflow. Our approach was validated experimentally using two topographical datasets at two different scales: 1:2000 and 1:10,000. Our results indicate that the granularity factor is effective both in improving the matching score of complex matching and reducing the occurrence of missing matching, and our matching model is suitable for multiscale spatial polygonal object matching, with a high precision and recall reach of 97.2% and 90.6%.

Style APA, Harvard, Vancouver, ISO itp.

10

BHANDARKAR, SUCHENDRA M. "A SURFACE FEATURE ATTRIBUTED HYPERGRAPH REPRESENTATION FOR 3-D OBJECT RECOGNITION." International Journal of Pattern Recognition and Artificial Intelligence 09, no. 06 (December 1995): 869–909. http://dx.doi.org/10.1142/s0218001495000365.

Pełny tekst źródła

Streszczenie:

A surface feature hypergraph (SFAHG) representation is proposed for the recognition and localization of three-dimensional objects. The hypergraph representation is shown to be viewpoint independent thus resulting in substantial savings in terms of memory for the object model database. The resulting hypergraph matching algorithm integrates both, relational and the rigid pose constraint in a consistent unified manner. The matching algorithm is also shown to have a polynomial order of complexity even in multiple-object scenes with instances of objects partially occluding each other. An algorithm for incrementally constructing the hypergraph representation of an object model from range images of the object taken from different viewpoints is also presented. The hypergraph matching and the hypergraph construction algorithms are shown to be capable of correcting errors in the initial segmentation of the range image. The hypergraph construction algorithm and the matching algorithm are tested on range images of scenes containing multiple three-dimensional objects with partial occlusion.

Style APA, Harvard, Vancouver, ISO itp.

11

Yang, Yingpeng. "A Stereo Matching System." International Journal of Advanced Pervasive and Ubiquitous Computing 5, no. 2 (April 2013): 1–8. http://dx.doi.org/10.4018/japuc.2013040101.

Pełny tekst źródła

Streszczenie:

Determination of the depth of the image feature distinctive automation and other industries of machine vision and computer vision technology in everyday life are becoming increasingly popular. Some techniques have been proposed to extract from the current depth of a 2D image of the feature, which defines a particular object or structure of the information. In many cases, these techniques are automatic, such as a suitable carrier moving average depth identify objects placed in the 2D image. For this intensive depth cues to solve two stereo matching algorithm using a machine learning algorithm. Other methods, relative to the camera based on the motion of the object have been proposed and analyzed by estimating the optical flow calculation depth map. The method of dense and sparse three-dimensional surface of the object to provide the three-dimensional information. This paper discusses the evaluation of the depth cues, through intensive two standard fast algorithm for real-time stereo image matching algorithm.

Style APA, Harvard, Vancouver, ISO itp.

12

Loghin, Mihai-Adrian. "3D Deformable Object Matching Using Graph Neural Networks." Studia Universitatis Babeș-Bolyai Informatica 69, no. 1 (June 10, 2024): 21–40. http://dx.doi.org/10.24193/subbi.2024.1.02.

Pełny tekst źródła

Streszczenie:

Considering the current advancements in computer vision it can be observed that most of it is focused on two-dimensional imagery. This includes problems such as classification, regression, and the lesser-known object matching problem. While object matching ca be viewed as a solved problem in a two-dimensional space, for a three-dimensional space there is a long way to go, especially for non-rigid objects. The problem is focused on matching a given object to a target object. We propose a solution based on Graph Neural Networks that tries to generalize over multiple objects at once, based on self-attention and cross-attention blocks for the network. To test our solution, we utilised five convolutional operators for the layers of the model. The convolutional operators we compared included GCNConv, ChebConv, SAGEConv, TAGConv, and FeaStConv. This paper aims to find the best operators for our architecture and the task. Our approach obtained favourable results for predicting the barycentric weights for the model, while struggling to predict the triangle indexes. The best results were obtained for the models using GCNConv, for the triangles index prediction and FeaStConv for the barycentric coordinates prediction. Keywords: graph neural networks, object matching, 3D objects, deformable objects.

Style APA, Harvard, Vancouver, ISO itp.

13

Iwata, Tomoharu, Tsutomu Hirao, and Naonori Ueda. "Unsupervised Cluster Matching via Probabilistic Latent Variable Models." Proceedings of the AAAI Conference on Artificial Intelligence 27, no. 1 (June 30, 2013): 445–51. http://dx.doi.org/10.1609/aaai.v27i1.8558.

Pełny tekst źródła

Streszczenie:

We propose a probabilistic latent variable model for unsupervised cluster matching, which is the task of finding correspondences between clusters of objects in different domains. Existing object matching methods find one-to-one matching. The proposed model finds many-to-many matching, and can handle multiple domains with different numbers of objects. The proposed model assumes that there are an infinite number of latent vectors that are shared by all domains, and that each object is generated using one of the latent vectors and a domain-specific linear projection. By inferring a latent vector to be used for generating each object, objects in different domains are clustered in shared groups, and thus we can find matching between clusters in an unsupervised manner. We present efficient inference procedures for the proposed model based on a stochastic EM algorithm. The effectiveness of the proposed model is demonstrated with experiments using synthetic and real data sets.

Style APA, Harvard, Vancouver, ISO itp.

14

Newell, F. N. "Searching for Objects in the Visual Periphery: Effects of Orientation." Perception 25, no. 1_suppl (August 1996): 110. http://dx.doi.org/10.1068/v96l1111.

Pełny tekst źródła

Streszczenie:

Previous studies have found that the recognition of familiar objects is dependent on the orientation of the object in the picture plane. Here the time taken to locate rotated objects in the periphery was examined. Eye movements were also recorded. In all experiments, familiar objects were arranged in a clock face display. In experiment 1, subjects were instructed to locate a match to a central, upright object from amongst a set of randomly rotated objects. The target object was rotated in the frontoparallel plane. Search performance was dependent on rotation, yielding the classic ‘M’ function found in recognition tasks. When matching a single object in periphery, match times were dependent on the angular deviations between the central and target objects and showed no advantage for the upright (experiment 2). In experiment 3 the central object was shown in either the upright rotation or rotated by 120° from the upright. The target object was similarly rotated given four different match conditions. Distractor objects were aligned with the target object. Search times were faster when the centre and target object were aligned and also when the centre object was rotated and the target was upright. Search times were slower when matching a central upright object to a rotated target object. These results suggest that in simple tasks matching is based on image characteristics. However, in complex search tasks a contribution from the object's representation is made which gives an advantage to the canonical, upright view in peripheral vision.

Style APA, Harvard, Vancouver, ISO itp.

15

Cui, Zhoujuan, Yuqi Dai, Yiping Duan, and Xiaoming Tao. "Joint Object Detection and Multi-Object Tracking Based on Hypergraph Matching." Applied Sciences 14, no. 23 (November 28, 2024): 11098. http://dx.doi.org/10.3390/app142311098.

Pełny tekst źródła

Streszczenie:

Addressing the challenges in online multi-object tracking algorithms under complex scenarios, where the independence among feature extraction, object detection, and data association modules leads to both error accumulation and the difficulty of maintaining visual consistency for occluded objects, we have proposed an end-to-end multi-object tracking method based on hypergraph matching (JDTHM). Initially, a feature extraction and object detection module is introduced to achieve preliminary localization and description of the objects. Subsequently, a deep feature aggregation module is designed to extract temporal information from historical tracklets, amalgamating features from object detection and feature extraction to enhance the consistency between the current frame features and the tracklet features, thus preventing identity swaps and tracklet breaks caused by object detection loss or distortion. Finally, a data association module based on hypergraph matching is constructed, integrating with object detection and feature extraction into a unified network, transforming the data association problem into a hypergraph matching problem between the tracklet hypergraph and the detection hypergraph, thereby achieving end-to-end model optimization. The experimental results demonstrate that this method has yielded favorable qualitative and quantitative analysis results on three multi-object tracking datasets, thereby validating its effectiveness in enhancing the robustness and accuracy of multi-object tracking tasks.

Style APA, Harvard, Vancouver, ISO itp.

16

Koning, Arno, and Rob Van Lier. "Object-based connectedness facilitates matching." Perception & Psychophysics 65, no. 7 (October 2003): 1094–102. http://dx.doi.org/10.3758/bf03194836.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

17

Jain, A. K., Yu Zhong, and S. Lakshmanan. "Object matching using deformable templates." IEEE Transactions on Pattern Analysis and Machine Intelligence 18, no. 3 (March 1996): 267–78. http://dx.doi.org/10.1109/34.485555.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

18

Yang, Cong, Oliver Tiebe, Kimiaki Shirahama, and Marcin Grzegorzek. "Object matching with hierarchical skeletons." Pattern Recognition 55 (July 2016): 183–97. http://dx.doi.org/10.1016/j.patcog.2016.01.022.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

19

Karma, I. Gede Made, and I. Ketut Darma. "Application of feature-based image matching method as an object recognition method." Bulletin of Electrical Engineering and Informatics 14, no. 2 (April 1, 2025): 1073–79. https://doi.org/10.11591/eei.v14i2.8803.

Pełny tekst źródła

Streszczenie:

In everyday life, objects are recognized based on the suitability of their characteristics to familiar objects. A feature matching process occurs when recognizing objects. This concept is what we want to apply and test in this research. Because various factors can influence the level of accuracy and success of an image matching method, the first step taken is to improve the accuracy level of the image matching method used. There are three feature-based image matching methods, which are implemented as object recognition methods. These three methods are the result of modifications of the image matching function method, normalized 2D cross correlation method and point feature matching which were later named PICMatch, NCMatch and FBMatch. As image matching methods, these three modified methods show performance with a success rate above 95%. However, when applied as an object recognition method, both individually and combined, the three methods only have a maximum accuracy of 7%. These results are obtained by matching the samples using one of the methods with the best match rate, in the order of application of the PICMatch, NCMatch, and FBMatch methods.

Style APA, Harvard, Vancouver, ISO itp.

20

Nassar, Ahmed Samy, Sébastien Lefèvre, and Jan Dirk Wegner. "Multi-View Instance Matching with Learned Geometric Soft-Constraints." ISPRS International Journal of Geo-Information 9, no. 11 (November 18, 2020): 687. http://dx.doi.org/10.3390/ijgi9110687.

Pełny tekst źródła

Streszczenie:

We present a new approach for matching urban object instances across multiple ground-level images for the ultimate goal of city-scale mapping of objects with high positioning accuracy. What makes this task challenging is the strong change in view-point, different lighting conditions, high similarity of neighboring objects, and variability in scale. We propose to turn object instance matching into a learning task, where image-appearance and geometric relationships between views fruitfully interact. Our approach constructs a Siamese convolutional neural network that learns to match two views of the same object given many candidate image cut-outs. In addition to image features, we propose utilizing location information about the camera and the object to support image evidence via soft geometric constraints. Our method is compared to existing patch matching methods to prove its edge over state-of-the-art. This takes us one step closer to the ultimate goal of city-wide object mapping from street-level imagery to benefit city administration.

Style APA, Harvard, Vancouver, ISO itp.

21

Nishina, S., and T. Inui. "Differential Effect of Object Complexity on 2-D and 3-D Matching Processes." Perception 26, no. 1_suppl (August 1997): 290. http://dx.doi.org/10.1068/v970308.

Pełny tekst źródła

Streszczenie:

Previously, we found that two matching processes work in parallel when an object is recognised from unknown viewpoints: the 2-dimensional (2-D) and the 3-dimensional (3-D) matching process. These processes were shown to differ in several respects, including recognition speed, generalisation range, and learning ability. We have now examined the effect of the complexity of an object on these two matching processes. We performed a recognition experiment where the subjects had to compare two sequentially presented images. The stimuli were objects that had different numbers of segments, presented for either 1.5 s (short condition) or 3.0 s (long condition). The different presentation times enabled us to separate the two processes, as 3-D matching requires a longer processing time. We adopted the ability to generalise from a known view as a measure of the performance of each process. Under the ‘short’ condition, the generalisation range for objects of high complexity was almost the same as that for objects of low complexity. Under the ‘long’ condition, however, the ranges for objects differing in complexity were significantly different. Our interpretation is that the effect of complexity was mainly associated with the 3-D matching process. The matching performed by the 2-D process under a shorter duration may be a simple image-to-image matching without recourse to the 3-D structure of the object.

Style APA, Harvard, Vancouver, ISO itp.

22

Lawson, Rebecca, Glyn W. Humphreys, and Derrick G. Watson. "Object Recognition under Sequential Viewing Conditions: Evidence for Viewpoint-Specific Recognition Procedures." Perception 23, no. 5 (May 1994): 595–613. http://dx.doi.org/10.1068/p230595.

Pełny tekst źródła

Streszczenie:

In many computational approaches to vision it has been emphasised that object recognition involves the encoding of view-independent descriptions prior to matching to a stored object model, thus enabling objects to be identified across different retinal projections. In contrast, neurophysiological studies suggest that image descriptions are matched to less abstract, view-specific representations, resulting in more efficient access to stored object knowledge for objects presented from a view similar to a stored viewpoint. Evidence favouring a primary role for view-specific object descriptions in object recognition is reported. In a series of experiments employing line drawings of familiar objects, the effects of depth rotation upon the efficiency of object recognition were investigated. Subjects were required to identify an object from a sequence of very briefly presented pictures. The results suggested that object recognition is based upon the matching of image descriptions to view-specific stored representations, and that priming effects under sequential viewing conditions are strongly influenced by the visual similarity of different views of objects.

Style APA, Harvard, Vancouver, ISO itp.

23

Li, Yongdong, Liang Qu, Guiyan Cai, Guoan Cheng, Long Qian, Yuling Dou, Fengqin Yao, and Shengke Wang. "Video Object Counting With Scene-Aware Multi-Object Tracking." Journal of Database Management 34, no. 3 (April 20, 2023): 1–13. http://dx.doi.org/10.4018/jdm.321553.

Pełny tekst źródła

Streszczenie:

The critical challenge of video object counting is to avoid counting the same object multiple times in different frames. By comparing the appearance and motion feature information of the detection results, the authors use the multi-object tracking method to assign an independent ID number to each object. From the time the ID tag is obtained until the end of the video, each object is counted only once. However, even minor amounts of image noise can cause irreversible changes in feature information, resulting in severe tracking drifts. This paper introduces the concept of scene awareness and addresses unreasonable ID assignment caused by unreliable feature matching in the context of region division. Through the macro analysis of the scene, the authors define the region (called the transition region) where the number of objects can increase or decrease and require that all ID assignments for new objects and ID deletions for existing objects take place only in the transition region. Because the actual number of objects in the non-transition region is constant, they rematch unmatched objects with existing IDs in the region (called ID relocation) because changes in object ID are caused by feature matching failure. In this paper, the authors create algorithms for dynamically generating transition regions, detecting object increases and decreases, and relocating object IDs. Experimental results show that the method effectively improves the accuracy of video object counting.

Style APA, Harvard, Vancouver, ISO itp.

24

Tan, Qifan, Xuqi Yang, Cheng Qiu, Wenzhuo Liu, Yize Li, Zhengxia Zou, and Jing Huang. "Graph-Based Target Association for Multi-Drone Collaborative Perception Under Imperfect Detection Conditions." Drones 9, no. 4 (April 11, 2025): 300. https://doi.org/10.3390/drones9040300.

Pełny tekst źródła

Streszczenie:

Multi-drone collaborative perception aims to address single-drone viewpoint limitations. The existing matching and association methods based on visual features and spatial topology rely heavily on detection, making it challenging to associate targets under imperfect detection conditions. To address this issue, a Graph-Based Target Association Network (GTA-Net) is proposed to utilize graph matching to associate the key objects before affine transforming and matching both detected and undetected targets. The Key Object Detection Network (KODN) finds the key object that is more likely to be a True Positive and more important. The Graph Feature Network (GFN) treats the key objects as graph nodes and extracts the graph feature. The Association Module utilizes graph matching to associate the top-k-like matching objects and iterable affine transformation to associate all objects. The experiment results show that our method achieved a 42% accuracy improvement on the public dataset. The ablation experiments under imperfect detection simulation demonstrate robust performance.

Style APA, Harvard, Vancouver, ISO itp.

25

Wang, Yanli, Zhipeng Dong, Mi Wang, and Yi Ding. "Adaptive Orientation Object-Detection Method for Large-scale Remote Sensing Images Based on Multi-scale Block Fusion." Photogrammetric Engineering & Remote Sensing 91, no. 1 (January 1, 2025): 27–34. https://doi.org/10.14358/pers.24-00036r1.

Pełny tekst źródła

Streszczenie:

Object detection is crucial to extracting and analyzing information autonomously from high-resolution remote sensing images (HRSIs). To address ideal blocking for large-scale HRSI object detection, this study uses a novel adaptive orientation object-detection method for large-scale HRSIs based on multi-scale block fusion. An adaptive orientation object-detection framework based on a convolutional neural network is applied to detect diverse objects of large-scale HRSIs through different block scales; average precision (AP) values of diverse object-detection results are calculated at different block scales. Then, block scales matching the largest AP values of diverse objects are determined based on statistical results of the AP values of the diverse object at different block scales. Finally, object-detection results at block scales matching the largest AP values of diverse objects are fused by the non-maximum suppression algorithm to achieve large-scale HRSI object-detection results. Experimental findings reveal that the proposed method is better than any single block-scale object-detection method, resulting in satisfactory large-scale HRSI object-detection results.

Style APA, Harvard, Vancouver, ISO itp.

26

Yu, Hang, Jiulu Gong, and Derong Chen. "Object Detection Using Multi-Scale Balanced Sampling." Applied Sciences 10, no. 17 (September 1, 2020): 6053. http://dx.doi.org/10.3390/app10176053.

Pełny tekst źródła

Streszczenie:

Detecting small objects and objects with large scale variants are always challenging for deep learning based object detection approaches. Many efforts have been made to solve these problems such as adopting more effective network structures, image features, loss functions, etc. However, for both small objects detection and detecting objects with various scale in single image, the first thing should be solve is the matching mechanism between anchor boxes and ground-truths. In this paper, an approach based on multi-scale balanced sampling(MB-RPN) is proposed for the difficult matching of small objects and detecting multi-scale objects. According to the scale of the anchor boxes, different positive and negative sample IOU discriminate thresholds are adopted to improve the probability of matching the small object area with the anchor boxes so that more small object samples are included in the training process. Moreover, the balanced sampling method is proposed for the collected samples, the samples are further divided and uniform sampling to ensure the diversity of samples in training process. Several datasets are adopted to evaluate the MB-RPN, the experimental results show that compare with the similar approach, MB-RPN improves detection performances effectively.

Style APA, Harvard, Vancouver, ISO itp.

27

Ko, K. H., T. Maekawa, N. M. Patrikalakis, H. Masuda, and F. E. Wolter. "Shape Intrinsic Properties for Free-Form Object Matching." Journal of Computing and Information Science in Engineering 3, no. 4 (December 1, 2003): 325–33. http://dx.doi.org/10.1115/1.1633277.

Pełny tekst źródła

Streszczenie:

Despite extensive research and rapid increase of computing power, free-form object matching still remains a challenging problem in CAD/CAM areas. In this paper, various object features are discussed, and matching methods which use these features are introduced along with robust computational algorithms for umbilical points and intrinsic wireframes. The similarity of matched objects is assessed with three proposed tests. Each algorithm is demonstrated with examples.

Style APA, Harvard, Vancouver, ISO itp.

28

Bethmann, F., and T. Luhmann. "Semi-Global Matching in Object Space." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-3/W2 (March 10, 2015): 23–30. http://dx.doi.org/10.5194/isprsarchives-xl-3-w2-23-2015.

Pełny tekst źródła

Streszczenie:

Semi-Global Matching (SGM) is a widespread algorithm for image matching which is used for very different applications, ranging from real-time applications (e.g. for generating 3D data for driver assistance systems) to aerial image matching. Originally developed for stereo-image matching, several extensions have been proposed to use more than two images within the matching process (multi-baseline matching, multi-view stereo). These extensions still perform the image matching in (rectified) stereo images and combine the pairwise results afterwards to create the final solution. This paper proposes an alternative approach which is suitable for the introduction of an arbitrary number of images into the matching process and utilizes image matching by using non-rectified images. The new method differs from the original SGM method mainly in two aspects: Firstly, the cost calculation is formulated in object space within a dense voxel raster by using the grey (or colour) values of all images instead of pairwise cost calculation in image space. Secondly, the semi-global (path-wise) minimization process is transferred into object space as well, so that the result of semi-global optimization leads to index maps (instead of disparity maps) which directly indicate the 3D positions of the best matches. Altogether, this yields to an essential simplification of the matching process compared to multi-view stereo (MVS) approaches. After a description of the new method, results achieved from two different datasets (close-range and aerial) are presented and discussed.

Style APA, Harvard, Vancouver, ISO itp.

29

Zhang, Peng, Qingyang Jing, Xinlei Zhao, Lijia Dong, Weimin Lei, Wei Zhang, and Zhaonan Lin. "A Multi-Object Tracking Approach Combining Contextual Features and Trajectory Prediction." Electronics 12, no. 23 (November 21, 2023): 4720. http://dx.doi.org/10.3390/electronics12234720.

Pełny tekst źródła

Streszczenie:

Aiming to solve the problem of the identity switching of objects with similar appearances in real scenarios, a multi-object tracking approach combining contextual features and trajectory prediction is proposed. This approach integrates the motion and appearance features of objects. The motion features are mainly used for trajectory prediction, and the appearance features are divided into contextual features and individual features, which are mainly used for trajectory matching. In order to accurately distinguish the identities of objects with similar appearances, a context graph is constructed by taking the specified object as the master node and its neighboring objects as the branch nodes. A preprocessing module is applied to exclude unnecessary connections in the graph model based on the speed of the historical trajectory of the object, and to distinguish the features of objects with similar appearances. Feature matching is performed using the Hungarian algorithm, based on the similarity matrix obtained from the features. Post-processing is performed for the temporarily unmatched frames to obtain the final object matching results. The experimental results show that the approach proposed in this paper can achieve the highest MOTA.

Style APA, Harvard, Vancouver, ISO itp.

30

S., S., Vibu Krishnan S., Mathan Raj Kumar, Ashok .., and M. Janakiraman. "Object Detection Using Deep Learning." Journal of Cognitive Human-Computer Interaction 6, no. 1 (2023): 32–38. http://dx.doi.org/10.54216/jchci.060103.

Pełny tekst źródła

Streszczenie:

Object recognition is an important task in computer vision that involves identifying the objects such as digital images or videos. This research paper provides a comprehensive review of the different techniques and applications of object recognition. The paper first discusses the basic concepts of object recognition, including feature extraction and matching, classification, and detection. Next, the paper reviews the different techniques for object recognition, such as template matching, PCA-based recognition, and deep learning-based recognition. The paper then presents an overview of the different applications of object recognition, including image and video classification, object tracking, face recognition, and autonomous driving. Finally, the paper ends with a discussion of the difficulties and likely new paths for object recognition.

Style APA, Harvard, Vancouver, ISO itp.

31

Kang, Seok-Hoon, and Joon-Sang Park. "Aligned Matching: Improving Small Object Detection in SSD." Sensors 23, no. 5 (February 26, 2023): 2589. http://dx.doi.org/10.3390/s23052589.

Pełny tekst źródła

Streszczenie:

Although detecting small objects is critical in various applications, neural network models designed and trained for generic object detection struggle to do so with precision. For example, the popular Single Shot MultiBox Detector (SSD) tends to perform poorly for small objects, and balancing the performance of SSD across different sized objects remains challenging. In this study, we argue that the current IoU-based matching strategy used in SSD reduces the training efficiency for small objects due to improper matches between default boxes and ground truth objects. To address this issue and improve the performance of SSD in detecting small objects, we propose a new matching strategy called aligned matching that considers aspect ratios and center-point distance in addition to IoU. The results of experiments on the TT100K and Pascal VOC datasets show that SSD with aligned matching detected small objects significantly better without sacrificing performance on large objects or requiring extra parameters.

Style APA, Harvard, Vancouver, ISO itp.

32

Van Brandt, Seppe, Kamil Yavuz Kapusuz, Joryan Sennesael, Sam Lemey, Patrick Van Torre, Jo Verhaevert, Tanja Van Hecke, and Hendrik Rogier. "Reliability Analysis and Optimization of a Reconfigurable Matching Network for Communication and Sensing Antennas in Dynamic Environments through Gaussian Process Regression." Sensors 24, no. 9 (April 24, 2024): 2689. http://dx.doi.org/10.3390/s24092689.

Pełny tekst źródła

Streszczenie:

During the implementation of the Internet of Things (IoT), the performance of communication and sensing antennas that are embedded in smart surfaces or smart devices can be affected by objects in their reactive near field due to detuning and antenna mismatch. Matching networks have been proposed to re-establish impedance matching when antennas become detuned due to environmental factors. In this work, the change in the reflection coefficient at the antenna, due to the presence of objects, is first characterized as a function of the frequency and object distance by applying Gaussian process regression on experimental data. Based on this characterization, for random object positions, it is shown through simulation that a dynamic environment can lower the reliability of a matching network by up to 90%, depending on the type of object, the probability distribution of the object distance, and the required bandwidth. As an alternative to complex and power-consuming real-time adaptive matching, a new, resilient network tuning strategy is proposed that takes into account these random variations. This new approach increases the reliability of the system by 10% to 40% in these dynamic environment scenarios.

Style APA, Harvard, Vancouver, ISO itp.

33

Djuric, Nemanja, Mihajlo Grbovic, and Slobodan Vucetic. "Convex Kernelized Sorting." Proceedings of the AAAI Conference on Artificial Intelligence 26, no. 1 (September 20, 2021): 893–99. http://dx.doi.org/10.1609/aaai.v26i1.8314.

Pełny tekst źródła

Streszczenie:

Kernelized sorting is a method for aligning objects across two domains by considering within-domain similarity, without a need to specify a cross-domain similarity measure. In this paper we present the Convex Kernelized Sorting method where, unlike in the previous approaches, the cross-domain object matching is formulated as a convex optimization problem, leading to simpler optimization and global optimum solution. Our method outputs soft alignments between objects, which can be used to rank the best matches for each object, or to visualize the object matching and verify the correct choice of the kernel. It also allows for computing hard one-to-one alignments by solving the resulting Linear Assignment Problem. Experiments on a number of cross-domain matching tasks show the strength of the proposed method, which consistently achieves higher accuracy than the existing methods.

Style APA, Harvard, Vancouver, ISO itp.

34

Harley, Heidi E. "WAU! Identifying complex objects with an acoustic flashlight?" Journal of the Acoustical Society of America 151, no. 4 (April 2022): A107. http://dx.doi.org/10.1121/10.0010802.

Pełny tekst źródła

Streszczenie:

A Hawaiian bunker, a bearded and barefoot entrepreneur, some dolphins, and an electrical engineer: A starter recipe for one of the most productive dolphin biosonar researchers in world history? Sound unlikely? Overstated? Apocryphal? And yet… Thirty years with Whit inspired us to investigate a dolphin’s use of wholistic shape matching versus “flashlight” object-parts-focused matching. Our stimuli were 3 3-object sets (Sets W, A,U). Objects within sets varied on shape alone made with identical PVC parts, but PVC parts varied between sets. In Condition Shape, experienced dolphin Calvin matched objects based on shape within sets (matching W1Snail to W1Snail) in a 3-alternative echoic matching-to-sample task: mean accuracy across 12 18-trial sessions/set: Set W: 37%, Set A: 44%, Set U: 39%, chance = 33%. In Condition Parts/NoShape, Calvin performed untrained transfer tests with same-parts/different-shape objects as sample-match pairs within alternative arrays of objects from different sets with different parts (sample W1Snail matched to W2StingRay with alternatives A2Trumpet and U2Whale). Mean accuracy in ten transfer sessions/set (WAU1 to WAU2: 47%, WAU2-WAU3: 48%, WAU3-WAU1: 39%) was above-chance and comparable to Condition Shape even though shape information was absent for matching in this parts-focused condition. Calvin’s narrow echolocation beam may have emphasized object parts versus wholistic shape.

Style APA, Harvard, Vancouver, ISO itp.

35

Noda, Mitsuru. "Imagery and Perceptual Basis of Matching Tasks in Young Children." Perceptual and Motor Skills 107, no. 2 (October 2008): 419–38. http://dx.doi.org/10.2466/pms.107.2.419-438.

Pełny tekst źródła

Streszczenie:

Object identification in perceptual tests may include constituents of mental rotation. A matching-to-sample task was conducted with same or different objects to look for evidence of rotation. Elementary schoolchildren (6 to 8 years old) in Grades 1 to 4 ( N = 264) participated, using the inclined Flags Test and the Water Level Test to ensure that children can use kinematic imagery for the Flags Test even if they used static imagery for the Water Level Test. Performance on the inclined Flags Test varied by age group. Use of implicit mental rotation of the inclined object was inferred in recognition. Also, children at the pre-operational stage showed a rotational effect, i.e., they could transform the object by turning it, thereby confirming kinematic imagery is used from age 6. As a consequence, solving both rotation tasks may require not only recognition of object frames but also objects internal to the frame.

Style APA, Harvard, Vancouver, ISO itp.

36

Doi, Kento, Ryuhei Hamaguchi, Yusuke Iwasawa, Masaki Onishi, Yutaka Matsuo, and Ken Sakurada. "Detecting Object-Level Scene Changes in Images with Viewpoint Differences Using Graph Matching." Remote Sensing 14, no. 17 (August 27, 2022): 4225. http://dx.doi.org/10.3390/rs14174225.

Pełny tekst źródła

Streszczenie:

We developed a robust object-level change detection method that could capture distinct scene changes in an image pair with viewpoint differences. To achieve this, we designed a network that could detect object-level changes in an image pair. In contrast to previous studies, we considered the change detection task as a graph matching problem for two object graphs that were extracted from each image. By virtue of this, the proposed network more robustly detected object-level changes with viewpoint differences than existing pixel-level approaches. In addition, the network did not require pixel-level change annotations, which have been required in previous studies. Specifically, the proposed network extracted the objects in each image using an object detection module and then constructed correspondences between the objects using an object matching module. Finally, the network detected objects that appeared or disappeared in a scene using the correspondences that were obtained between the objects. To verify the effectiveness of the proposed network, we created a synthetic dataset of images that contained object-level changes. In experiments on the created dataset, the proposed method improved the F1 score of conventional methods by more than 40%. Our synthetic dataset will be available publicly online.

Style APA, Harvard, Vancouver, ISO itp.

37

Peng, Mengkang, and Narendra K. Gupta. "Invariant and Occluded Object Recognition Based on Graph Matching." International Journal of Electrical Engineering & Education 32, no. 1 (January 1995): 31–38. http://dx.doi.org/10.1177/002072099503200104.

Pełny tekst źródła

Streszczenie:

Invariant and occluded object recognition based on graph matching The paper describes an algorithm for object recognition using neural network. The objects may be occluded and may have any changes in position, orientation and scale. The paper aims to generate project ideas for the final year students at the university and also to provide a basis for further research.

Style APA, Harvard, Vancouver, ISO itp.

38

Chantara, Wisarut, Ji-Hun Mun, Dong-Won Shin, and Yo-Sung Ho. "Object Tracking using Adaptive Template Matching." IEIE Transactions on Smart Processing and Computing 4, no. 1 (February 28, 2015): 1–9. http://dx.doi.org/10.5573/ieiespc.2015.4.1.001.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

39

Robeson, Brendan, Mohammadreza Javanmardi, and Xiaojun Qi. "Object tracking using temporally matching filters." IET Computer Vision 15, no. 4 (March 30, 2021): 245–57. http://dx.doi.org/10.1049/cvi2.12040.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

40

Ke, Wei, and Ka-Hou Chan. "Pattern Matching Based on Object Graphs." IEEE Access 9 (2021): 159313–25. http://dx.doi.org/10.1109/access.2021.3128575.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

41

Dryden, Ian L., and Gary Walker. "Highly Resistant Regression and Object Matching." Biometrics 55, no. 3 (September 1999): 820–25. http://dx.doi.org/10.1111/j.0006-341x.1999.00820.x.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

42

Zhu, Jie, Shufang Wu, Xizhao Wang, Guoqing Yang, and Liyan Ma. "Multi‐image matching for object recognition." IET Computer Vision 12, no. 3 (January 3, 2018): 350–56. http://dx.doi.org/10.1049/iet-cvi.2017.0261.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

43

Zhou, Chuan, and Gurdeep S. Hura. "Matching Object Structure Using Petri Nets." IFAC Proceedings Volumes 31, no. 15 (June 1998): 65–70. http://dx.doi.org/10.1016/s1474-6670(17)40530-1.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

44

Penn, Michal, and Moshe Tennenholtz. "Constrained multi-object auctions and -matching." Information Processing Letters 75, no. 1-2 (July 2000): 29–34. http://dx.doi.org/10.1016/s0020-0190(00)00073-9.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

45

Bunke, Horst. "Graph matching for visual object recognition." Spatial Vision 13, no. 2-3 (2000): 335–40. http://dx.doi.org/10.1163/156856800741153.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

46

Su, Ching-Liang. "Manufacture Automation: Model and Object Recognition by Using Object Position Auto Locating Algorithm and Object Comparison Model." JALA: Journal of the Association for Laboratory Automation 5, no. 2 (April 2000): 61–65. http://dx.doi.org/10.1016/s1535-5535-04-00062-0.

Pełny tekst źródła

Streszczenie:

This research uses the geometry matching technique to identify the different objects. The object is extracted from the background. The second moment 6 is used to find the orientation and the center point of the extracted object. Since the second moment can find the orientations and the center point of the object, the perfect object and the test object can be aligned to the same orientation. Furthermore, these two images can be shifted to the same centroid. After this, the perfect object can be subtracted from the test face. By using the subtracted result, the objects can be classified. The techniques used in this research can very accurately classify different objects.

Style APA, Harvard, Vancouver, ISO itp.

47

Li, Wen-Jing, and Tong Lee. "Object recognition and articulated object learning by accumulative Hopfield matching." Pattern Recognition 35, no. 9 (September 2002): 1933–48. http://dx.doi.org/10.1016/s0031-3203(01)00158-3.

Pełny tekst źródła

Style APA, Harvard, Vancouver, ISO itp.

48

Lawson, Rebecca. "An Investigation into the Cause of Orientation-Sensitivity in Haptic Object Recognition." Seeing and Perceiving 24, no. 3 (2011): 293–314. http://dx.doi.org/10.1163/187847511x579052.

Pełny tekst źródła

Streszczenie:

AbstractObject orientation influences visual and haptic recognition differently. This could be caused by the two modalities accessing different object representations or it could be due to differences in how each modality acquires information. These two alternatives were investigated using sequential haptic matching tasks. Matches presented the same object twice. Mismatches presented two similarly-shaped objects. Objects were either both placed at the same orientation or were rotated 90° in depth from each other. Experiment 1 manipulated exploration time to test if longer durations weakened orientation-sensitivity by allowing orientation-invariant representations to be extracted. This hypothesis was not supported. Experiment 2 investigated whether the same-orientation advantage resulted from general spatial or motor action cueing rather than the involvement of orientation-specific object representations. To distinguish between these two possibilities, people did a secondary task interleaved within the matching task. They reported the orientation of a fork or spoon which was presented in between the first and second objects. The main axis of the fork/spoon was the same as that of the final object, equating spatial and motor cueing across the same-orientation and orientation-change conditions. Nevertheless, matching remained orientation-sensitive. Together these results suggest that there are separate visual and haptic stored, orientation-specific perceptual representations of objects.

Style APA, Harvard, Vancouver, ISO itp.

49

Mettes, Pascal, William Thong, and Cees G. M. Snoek. "Object Priors for Classifying and Localizing Unseen Actions." International Journal of Computer Vision 129, no. 6 (April 19, 2021): 1954–71. http://dx.doi.org/10.1007/s11263-021-01454-y.

Pełny tekst źródła

Streszczenie:

AbstractThis work strives for the classification and localization of human actions in videos, without the need for any labeled video training examples. Where existing work relies on transferring global attribute or object information from seen to unseen action videos, we seek to classify and spatio-temporally localize unseen actions in videos from image-based object information only. We propose three spatial object priors, which encode local person and object detectors along with their spatial relations. On top we introduce three semantic object priors, which extend semantic matching through word embeddings with three simple functions that tackle semantic ambiguity, object discrimination, and object naming. A video embedding combines the spatial and semantic object priors. It enables us to introduce a new video retrieval task that retrieves action tubes in video collections based on user-specified objects, spatial relations, and object size. Experimental evaluation on five action datasets shows the importance of spatial and semantic object priors for unseen actions. We find that persons and objects have preferred spatial relations that benefit unseen action localization, while using multiple languages and simple object filtering directly improves semantic matching, leading to state-of-the-art results for both unseen action classification and localization.

Style APA, Harvard, Vancouver, ISO itp.

50

Eckes, Christian, Jochen Triesch, and Christoph von der Malsburg. "Analysis of Cluttered Scenes Using an Elastic Matching Approach for Stereo Images." Neural Computation 18, no. 6 (June 2006): 1441–71. http://dx.doi.org/10.1162/neco.2006.18.6.1441.

Pełny tekst źródła

Streszczenie:

We present a system for the automatic interpretation of cluttered scenes containing multiple partly occluded objects in front of unknown, complex backgrounds. The system is based on an extended elastic graph matching algorithm that allows the explicit modeling of partial occlusions. Our approach extends an earlier system in two ways. First, we use elastic graph matching in stereo image pairs to increase matching robustness and disambiguate occlusion relations. Second, we use richer feature descriptions in the object models by integrating shape and texture with color features. We demonstrate that the combination of both extensions substantially increases recognition performance. The system learns about new objects in a simple one-shot learning approach. Despite the lack of statistical information in the object models and the lack of an explicit background model, our system performs surprisingly well for this very difficult task. Our results underscore the advantages of view-based feature constellation representations for difficult object recognition problems.

Style APA, Harvard, Vancouver, ISO itp.

Artykuły w czasopismach na temat „Object matching”

Utwórz poprawne odniesienie w stylach APA, MLA, Chicago, Harvard i wielu innych