Filters








10,091 Hits in 9.6 sec

Superpixel Tensor Pooling for Visual Tracking using Multiple Midlevel Visual Cues Fusion

Chong Wu, Le Zhang, Jiawang Cao, Hong Yan
2019 IEEE Access  
To validate the proposed method, we compare it with state-of-the-art methods on 24 sequences with multiple visual tracking challenges.  ...  Then the incremental positive and negative subspaces learning is performed.  ...  INCREMENTAL POSITIVE AND NEGATIVE SUBSPACES LEARNING The update and learning scheme used in SPTPT is based on the incremental subspace learning [27] .  ... 
doi:10.1109/access.2019.2946939 fatcat:iv5mxdk26bgqzkuc6scrjr3zmy

Robust Visual Tracking via Inverse Nonnegative Matrix Factorization [article]

Fanghui Liu, Tao Zhou, Keren Fu, Irene Y.H. Gu, Jie Yang
2016 arXiv   pre-print
The establishment of robust target appearance model over time is an overriding concern in visual tracking.  ...  In this paper, we propose an inverse nonnegative matrix factorization (NMF) method for robust appearance modeling.  ...  Nonnegative Matrix Factorization (NMF) has recently been applied to visual tracking, some variety work includes Orthogonal Projective NMF Tracker [8] , Constraint Online NMF Tracker [9] and Constrained  ... 
arXiv:1509.06003v3 fatcat:wthnginibnfntnfzxztud7qkqu

Incremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking [article]

Xi Li and Anthony Dick and Chunhua Shen and Anton van den Hengel and Hanzi Wang
2012 arXiv   pre-print
Visual tracking usually requires an object appearance model that is robust to changing illumination, pose and other factors encountered in video.  ...  The 3D-DCT is based on a set of cosine basis functions, which are determined by the dimensions of the 3D signal and thus independent of the input video data.  ...  ACKNOWLEDGMENTS This work is supported by ARC Discovery Project (DP1094764). All correspondence should be addressed to X. Li.  ... 
arXiv:1207.3389v2 fatcat:7b5jb2itdngxnlzkqox3qdbzbq

Online Robust Non-negative Dictionary Learning for Visual Tracking

Naiyan Wang, Jingdong Wang, Dit-Yan Yeung
2013 2013 IEEE International Conference on Computer Vision  
In particular, we propose an online robust non-negative dictionary learning algorithm for updating the object templates so that each learned template can capture a distinctive aspect of the tracked object  ...  This paper studies the visual tracking problem in video sequences and presents a novel robust sparse tracker under the particle filter framework.  ...  Conclusion and Future Work In this paper, we have proposed a novel visual tracking method based on robust non-negative dictionary learning.  ... 
doi:10.1109/iccv.2013.87 dblp:conf/iccv/WangWY13 fatcat:kcrf5dsbvzh4fkftwy3e3jkz6i

Incremental tensor biased discriminant analysis: A new color-based visual tracking method

Jing Wen, Xinbo Gao, Yuan Yuan, Dacheng Tao, Jie Li
2010 Neurocomputing  
Considering the influence of the environment changing on the tracking, the biased discriminant analysis (BDA) is extended to the tensor biased discriminant analysis (TBDA) for distinguishing the object  ...  Most existing color-based tracking algorithms utilize the statistical color information of the object as the tracking clues, without maintaining the spatial structure within a single chromatic image.  ...  This research was supported by the National Natural Science Foundation of China (60771068, 60702061, 60832005), the Open Project Program of the National Laboratory of Pattern Recognition (NLPR) in China  ... 
doi:10.1016/j.neucom.2009.10.013 fatcat:6x75tbprmzcwfbihllpj2ho46a

Incremental Learning of 3D-DCT Compact Representations for Robust Visual Tracking

Xi Li, Anthony Dick, Chunhua Shen, Anton van den Hengel, Hanzi Wang
2013 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we focus on how to construct an effective DCT-based object representation for robust visual tracking.  ...  Based on incremental principal component analysis, IPCA constructs an eigenspace-based observation model for visual tracking.  ... 
doi:10.1109/tpami.2012.166 pmid:22868649 fatcat:lq72kei4rnd3lflt7wvkdow52m

A survey of appearance models in visual object tracking

Xi Li, Weiming Hu, Chunhua Shen, Zhongfei Zhang, Anthony Dick, Anton Van Den Hengel
2013 ACM Transactions on Intelligent Systems and Technology  
In particular, this survey takes a module-based architecture that enables readers to easily grasp the key points of visual object tracking.  ...  Despite extensive research on this topic, it still suffers from difficulties in handling complex object appearance changes caused by factors such as illumination variation, partial occlusion, shape deformation  ...  For instance, build a DADAM based on incremental Fisher linear discriminant analysis (IFLDA).  ... 
doi:10.1145/2508037.2508039 fatcat:uwptu4nkmbhjvib5szoafjhg3i

Tracking Using Online Feature Selection and a Local Generative Model

T. E. Woodley, B. Stenger, R. Cipolla
2007 Procedings of the British Machine Vision Conference 2007  
Discriminative classifiers based on feature extraction have classically either prepared a fixed prior model by training offline, or continually adapted their classification parameters to any apparent appearance  ...  The generative model exhibits the properties of non-negativity, localization and orthogonality.  ...  The target estimate is used as Local non-negative matrix factorization Non-negative matrix factorization (NMF) is a method for finding a lower dimensional representation of data.  ... 
doi:10.5244/c.21.86 dblp:conf/bmvc/WoodleySC07 fatcat:6co2k2frbrdlhdsl7xusfv3j7i

A Survey of Appearance Models in Visual Object Tracking [article]

Xi Li, Weiming Hu, Chunhua Shen, Zhongfei Zhang, Anthony Dick, Anton van den Hengel
2013 arXiv   pre-print
In particular, this survey takes a module-based architecture that enables readers to easily grasp the key points of visual object tracking.  ...  Second, the existing statistical modeling schemes for tracking-by-detection are reviewed according to their model-construction mechanisms: generative, discriminative, and hybrid generative-discriminative  ...  For instance, build a DADAM based on incremental Fisher linear discriminant analysis (IFLDA).  ... 
arXiv:1303.4803v1 fatcat:tx333ej63faufnxffjttac4jxq

Graph mode-based contextual kernels for robust SVM tracking

Xi Li, Anthony Dick, Hanzi Wang, Chunhua Shen, Anton van den Hengel
2011 2011 International Conference on Computer Vision  
Finally, this contextual kernel is embedded into SVMs for robust tracking. Experimental results on challenging videos demonstrate the effectiveness and robustness of the proposed tracker.  ...  In this paper, we propose a visual tracker based on support vector machines (SVMs), for which a novel graph mode-based contextual kernel is designed to effectively capture the higher-order contextual information  ...  IPCA uses incremental principal component analysis to construct the eigenspace-based observation model for visual tracking.  ... 
doi:10.1109/iccv.2011.6126364 dblp:conf/iccv/LiDWSH11 fatcat:7irp5yeg7jhujoetzjus3ptn7e

Table of contents

2017 IEEE Transactions on Cybernetics  
Cong 3827 Graph Regularized Non-Negative Low-Rank Matrix Factorization for Image Clustering . . . . . . . . . . . . X. Li, G. Cui, and Y.  ...  Kyriakoulis 3772 Trifocal Tensor-Based Adaptive Visual Trajectory Tracking Control of Mobile Robots . . . . . . . . . . J. Chen, B. Jia, and K.  ... 
doi:10.1109/tcyb.2017.2752019 fatcat:hq7k7uwnnje2niicnwwc2bhmza

Online Tracking and Reacquisition Using Co-trained Generative and Discriminative Trackers [chapter]

Qian Yu, Thang Ba Dinh, Gérard Medioni
2008 Lecture Notes in Computer Science  
A discriminative classifier is implemented as an online support vector machine, which is trained to focus on recent appearance variations.  ...  Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion.  ...  The visual results are shown in Figure 4 , where the tracked objects and part of negative In experiments, we frequently find that the co-trained tracker has better self-awareness of current tracking  ... 
doi:10.1007/978-3-540-88688-4_50 fatcat:6wos6btplncgxiq5iqxo5lm4sm

Robust Tracking via Weighted Online Extreme Learning Machine [article]

Jing Zhang, Huibing Wang, Yonggong Ren
2018 arXiv   pre-print
The tracking method based on the extreme learning machine (ELM) is efficient and effective.  ...  Finally, the forgetting factor is used to strengthen the robustness for changing of the classification distribution with time.  ...  Our method based on discriminating model is a robust tracking method.  ... 
arXiv:1807.10211v1 fatcat:rnvym72lwfhrvinmtb63frq6pm

Online Multi-Modal Robust Non-Negative Dictionary Learning for Visual Tracking

Xiang Zhang, Naiyang Guan, Dacheng Tao, Xiaogang Qiu, Zhigang Luo, Wen-Bo Du
2015 PLoS ONE  
In this paper, we propose an online multi-modal robust non-negative dictionary learning (OMRNDL) algorithm to overcome this deficiency.  ...  OMRNDL incrementally learns the dictionary and the coefficient of each particle by using multiplicative update rules to respectively guarantee their non-negativity constraints.  ...  Acknowledgments This work is sponsored by scientific research plan project of National University of Defense Technology (NO. JC13-06-01) and National Natural Science Foundation of China (NO.  ... 
doi:10.1371/journal.pone.0124685 pmid:25961715 pmcid:PMC4427315 fatcat:foao36zxbnefhmjt2kcirts2vy

Real-Time Compressive Tracking [chapter]

Kaihua Zhang, Lei Zhang, Ming-Hsuan Yang
2012 Lecture Notes in Computer Science  
It is a challenging task to develop effective and efficient appearance models for robust object tracking due to factors such as pose variation, illumination change, occlusion, and motion blur.  ...  In this paper, we propose a simple yet effective and efficient tracking algorithm with an appearance model based on features extracted from the multi-scale image feature space with data-independent basis  ...  Concluding Remarks In this paper, we proposed a simple yet robust tracking algorithm with an appearance model based on non-adaptive random projections that preserve the structure of original image space  ... 
doi:10.1007/978-3-642-33712-3_62 fatcat:u77rbj2swvca7kuww26rjkthay
« Previous Showing results 1 — 15 out of 10,091 results