# 16.6 Tracking of Moving Objects and Matching in Sequences

Chapter Contents (Back)
Sequences. Tracking. Motion, Tracking. There should be some mention of the much older basic tracking effort (e.g. spots, etc.).

Martin, W.N., and Aggarwal, J.K.,
Computer Analysis of Dynamic Scenes Containing Curvilinear Figures,
PR(11), No. 3, 1979, pp. 169-178.
Elsevier DOI Represent the curves in polar form - arc length vs. angle. From these there are pieces of curves, match the curves. Assume that the scenes are motion sequences so that the changes are position and occlusions / separations.

Aggarwal, J.K., and Duda, R.O.,
Computer Analysis of Moving Polygonal Images,
TC(24), No. 10, October 1975, pp. 966-976. BibRef 7510 CMetImAly77(271-282). Motion, Tracking. Motivated by cloud motions assumes: properly registered, clouds not rapidly changing, and 1 layer at a time. Information in joint motion - to avoid problems and obtain generality: idealized model no distinguishing features of the planes (image is union of several planes.). Given a sequence find linear and angular velocities and decompose scene into component figures. Noise free; pair vertices in 2 images - using true and false vertices; use info from previous image; acute vertex => "true" vertex, i.e., on an object; obtuse => any kind; cluster on velocity of true vertices; heuristic: no guarantee that matches are globally optimal; no processes for backtracking. BibRef

Chow, W.K., and Aggarwal, J.K.,
Computer Analysis of Planar Curvilinear Moving Images,
TC(26), No. 2, February 1977, pp. 179-185. Eliminates assumptions in Aggarwal & Duda (
See also Computer Analysis of Moving Polygonal Images. ), i.e., - curved objects, multiple topological changes, but no holes; all objects known before motion analysis; no occlusion for first 2 views; white on black background objects; noise, stable velocity, i.e., low acceleration; heterogeneous collection of objects; edges; descriptors - invariant to rotation and translation area, modified principal axes (major/minor axes); matches new image with current model to get update model, if fails then match with prediction; extension match boundaries rather than descriptors. BibRef 7702

Roach, J.W., and Aggarwal, J.K.,
Computer Tracking of Objects Moving in Space,
PAMI(1), No. 2, April 1979, pp. 127-135. BibRef 7904
Earlier:
Computer Tracking of Three Dimensional Objects,
PRAI-78(7-9). Detect movement of 3-D convex blocks in 2-D images. Use evidence from T-junctions for occlusions. BibRef

Aggarwal, J.K., Davis, L.S., and Martin, W.N.,
Correspondence Processes in Dynamic Scene Analysis,
PIEEE(69), No. 5, May 1981, pp. 562-572. BibRef 8105

Thompson, W.B., Lechleider, P., and Stuck, E.R.,
Detecting Moving Objects Using the Rigidity Constraint,
PAMI(15), No. 2, February 1993, pp. 162-166.
IEEE DOI Not really tracking, more motion detection. Compute the motion of the camera compared to the background. Moving objects are the points that do not correspond. BibRef 9302

Nichol, D.[David], Fiebig, M.[Merrilyn],
Image Segmentation and Matching Using the Binary Object Forest,
IVC(9), No. 3, June 1991, pp. 139-149.
Elsevier DOI BibRef 9106

Nichol, D.[David], Fiebig, M.[Merrilyn],
Tracking Multiple Moving Objects by Binary Object Forest Segmentation,
IVC(9), No. 6, December 1991, pp. 362-371.
Elsevier DOI BibRef 9112

Lowe, D.G.[David G.],
Robust Model-Based Motion Tracking Through the Integration of Search and Estimation,
IJCV(8), No. 2, August 1992, pp. 113-122.
Springer DOI BibRef 9208
And: UBCTR-92-11, May 1992. Handle both measurement and motion errors that occur in following the sequence. BibRef

Cox, I.J.,
A Review of Statistical Data Association Techniques for Motion Correspondence,
IJCV(10), No. 1, February 1993, pp. 53-66.
Springer DOI Survey, Tracking. Techniques that came from target tracking work. BibRef 9302

Cowart, A.E.[Alan E.], Snyder, W.E.[Wesley E.], and Ruedger, W.H.[W. Howard],
The Detection of Unresolved Targets Using the Hough Transform,
CVGIP(21), No. 2, February 1983, pp. 222-238.
Elsevier DOI Hough, Motion. BibRef 8302

Mirmehdi, M., Ellis, T.J.,
Parallel Approach to Tracking Edge Segments in Dynamic Scenes,
IVC(11), No. 1, January-February 1993, pp. 35-48.
Elsevier DOI Parallel processors (transputers) applied to tracking problem. BibRef 9301

Ellis, T.J., Mirmehdi, M., and Dowling, G.R.,
Tracking Image Features Using a Parallel Computational Model,
SPIE(1708), Applications of Artificial Intelligence X: Machine vision and Robots, 1992, pp. 172-183. Implementation using transputers. BibRef 9200

Zhang, Z.Y.[Zheng-You],
Token Tracking in a Cluttered Scene,
IVC(12), No. 2, March 1994, pp. 110-120.
Elsevier DOI BibRef 9403
And: INRIARR-2072, October 1993. BibRef
Earlier:
Strategies for Tracking Tokens in a Cluttered Scene,
BMVC93(I. 205-216).
PDF File. Uses a beam search. BibRef

Snijder, H.P.[Henk Philip], van Leeuwen, C.[Cees],
A Minimal Architecture for Detecting Object Location and Motion,
PR(27), No. 11, November 1994, pp. 1463-1473.
Elsevier DOI BibRef 9411

Sharp, N.G.[Nigel G.], Hancock, E.R.[Edwin R.],
Feature Tracking by Multiframe Relaxation,
IVC(13), No. 8, October 1995, pp. 637-644.
Elsevier DOI BibRef 9510
Earlier: BMVC94(xx-yy).
PDF File. 9409
BibRef

Bruckstein, A.M., Holt, R.J., Netravali, A.N.,
How to Catch a Crook,
JVCIR(5), 1994, pp. 273-281. BibRef 9400

Bruckstein, A.M., Holt, R.J., Netravali, A.N.,
How to Track a Flying Saucer,
JVCIR(7), No. 2, June 1996, pp. 196-204. 9607
BibRef

Choate, W.C.[William Clay], Talluri, R.K.[Rajendra K.],
Method of inferring sensor attitude through multi-feature tracking,
US_Patent5,647,015, Jul 8, 1997
And: US_Patent5,870,486, Feb 9, 1999
And: A2, A1:
Target Tracking and Range Estimation Using an Image Sequence,
WACV92(84-91).
IEEE DOI BibRef

Habib, A.,
Motion Parameter Estimation by Tracking Stationary 3-Dimensional Straight Lines in Image Sequences,
PandRS(53), No. 3, June 1998, pp. 174-182. 9807
BibRef

Zatelli, P.,
Measurement and Tracking of Circle Centers for Geotechnic Applications,
PandRS(53), No. 3, June 1998, pp. 183-191. 9807
BibRef

Heimes, F., Nagel, H.H.,
Real Time Tracking of Intersections in Image Sequences of a Moving Camera,
EngAAI(11), No. 2, April 1998, pp. 215-227. 9807
BibRef

Jung, S.K., Wohn, K.Y.,
A Model Based 3-D Tracking of Rigid Objects from a Sequence of Multiple Perspective Views,
PRL(19), No. 5-6, April 1998, pp. 499-512. 9808
BibRef

Sanders-Reed, J.N.[John N.],
Maximum Likelihood Detection of Unresolved Moving Targets,
AeroSys(34), No.3, July, 1998, pp. xx-yy.
WWW Link. Faint target detection and tracking. BibRef 9807

Toyama, K.[Kentaro], Hager, G.D.[Gregory D.],
Incremental Focus of Attention for Robust Vision-Based Tracking,
IJCV(35), No. 1, November 1999, pp. 45-63.
Earlier:
Incremental Focus of Attention for Robust Visual Tracking,
CVPR96(189-195).
IEEE DOI Tracking.
HTML Version. And
PS File. BibRef
Earlier:
Tracker Fusion for Robustness in Visual Feature Tracking,
SPIE(2569), pp. 38-49. Photonics East, October 1995.
PS File. Code, Tracking. Code:

Toyama, K.[Kentaro],
Handling Tradeoffs Between Precision and Robustness with Incremental Focus of Attention for Visual Tracking,
AAAI-Fall96(142-147). Symposium on Flexible Computation.
HTML Version. And
PS File. BibRef 9600

Erdem, Ç.E., Tekalp, A.M., Sankur, B.,
Video object tracking with feedback of performance measures,
CirSysVideo(13), No. 4, April 2003, pp. 310-324.
IEEE Abstract. 0301
BibRef
Earlier: A1, A3, A2:
Non-Rigid Object Tracking using Performance Evaluation Measures as Feedback,
CVPR01(II:323-330).
IEEE DOI 0110
BibRef

Erdem, C.E.[Cigdem Eroglu],
Video object segmentation and tracking using region-based statistics,
SP:IC(22), No. 10, November 2007, pp. 891-905.
Elsevier DOI 0711
Object tracking; Active contours; Histogram matching; Curve evolution; Defocus; Selective focus BibRef

Erdem, C.E.[C. Eroglu], Sankur, B., Tekalp, A.M.,
Performance Measures for Video Object Segmentation and Tracking,
IP(13), No. 7, July 2004, pp. 937-951.
IEEE DOI 0406
BibRef
Earlier: A1, A3, A2:
Metrics for Performance Evaluation of Video Object Segmentation and Tracking Without Ground-truth,
ICIP01(II: 69-72).
IEEE DOI 0108
BibRef

Williams, O., Blake, A., Cipolla, R.,
Sparse Bayesian Learning for Efficient Visual Tracking,
PAMI(27), No. 8, August 2005, pp. 1292-1304.
IEEE Abstract. 0506
BibRef
Earlier:
A sparse probabilistic learning algorithm for real-time tracking,
ICCV03(353-360).
IEEE DOI 0311
BibRef

Maggio, E.[Emilio], Cavallaro, A.[Andrea],
Video Tracking: Theory and Practice,
WileyApril 2011 ISBN: 978-0-470-74964-7
HTML Version. Buy this book: Video Tracking: Theory and Practice 1010
BibRef

Nawaz, T.[Tahir], Poiesi, F.[Fabio], Cavallaro, A.[Andrea],
Measures of Effective Video Tracking,
IP(23), No. 1, January 2014, pp. 376-388.
IEEE DOI 1402
BibRef
And:
Assessing tracking assessment measures,
ICIP14(441-445)
IEEE DOI 1502
Area measurement object tracking BibRef

Easson, G., de Lozier, S., Momm, H.,
Estimating Speed and Direction of Small Dynamic Targets through Optical Satellite Imaging,
RS(2), No. 5, May 2010, pp. 1331-1347.
BibRef

Salti, S., Cavallaro, A., di Stefano, L.[Luigi],
Adaptive Appearance Modeling for Video Tracking: Survey and Evaluation,
IP(21), No. 10, October 2012, pp. 4334-4348.
IEEE DOI 1209
BibRef

Fan, J., Shen, X., Wu, Y.,
What Are We Tracking: A Unified Approach of Tracking and Recognition,
IP(22), No. 2, February 2013, pp. 549-560.
IEEE DOI 1302
BibRef

Seo, J., Kim, S.D.,
Visual Target TRACTOR: Tracker and Detector,
CirSysVideo(25), No. 5, May 2015, pp. 761-775.
IEEE DOI 1505

Granstrom, K., Natale, A., Braca, P., Ludeno, G., Serafino, F.,
Gamma Gaussian Inverse Wishart Probability Hypothesis Density for Extended Target Tracking Using X-Band Marine Radar Data,
GeoRS(53), No. 12, December 2015, pp. 6617-6631.
IEEE DOI 1512
geophysical techniques BibRef

Millefiori, L.M., Braca, P., Willett, P.,
Consistent Estimation of Randomly Sampled Ornstein-Uhlenbeck Process Long-Run Mean for Long-Term Target State Prediction,
SPLetters(23), No. 11, November 2016, pp. 1562-1566.
IEEE DOI 1609
covariance analysis BibRef

Vivone, G., Millefiori, L.M., Braca, P., Willett, P.,
Performance Assessment of Vessel Dynamic Models for Long-Term Prediction Using Heterogeneous Data,
GeoRS(55), No. 11, November 2017, pp. 6533-6546.
IEEE DOI 1711
Radar tracking, Synthetic aperture radar, Uncertainty, maritime surveillance, ornstein-Uhlenbeck (OU) process. BibRef

Gao, Y.[Yun], Zhou, H.[Hao], Zhang, X.J.[Xue-Jie],
Enhanced fast compressive tracking based on adaptive measurement matrix,
IET-CV(9), No. 6, 2015, pp. 857-863.
compressed sensing BibRef

Wang, X.[Xin], Shen, S.Q.[Si-Qiu], Ning, C.[Chen], Zhang, Y.Z.[Yu-Zhen], Lv, G.F.[Guo-Fang],
Robust object tracking based on local discriminative sparse representation,
JOSA-A(34), No. 4, April 2017, pp. 533-544.
Digital image processing BibRef

Zeng, F., Huang, Z., Ji, Y.,
Discriminative Bag-of-Words-Based Adaptive Appearance Model for Robust Visual Tracking,
SPLetters(24), No. 6, June 2017, pp. 907-911.
IEEE DOI 1705
Adaptation models, Computational modeling, Deformable models, Indexes, Robustness, Signal processing algorithms, Visualization, Adaptive appearance model, discriminative bag-of-words (DBoW), visual, tracking BibRef

Chan, S.X.[Si-Xian], Zhou, X.L.[Xiao-Long], Li, J.W.[Jun-Wei], Chen, S.Y.[Sheng-Yong],
Adaptive Compressive Tracking based on Locality Sensitive Histograms,
PR(72), No. 1, 2017, pp. 517-531.
Elsevier DOI 1708
Compressive tracking BibRef

Zheng, Y.H.[Yu-Hui], Liu, X.Y.[Xin-Yan], Xiao, B.[Bin], Cheng, X.[Xu], Wu, Y.[Yi], Chen, S.Y.[Sheng-Yong],
Multi-Task Convolution Operators with Object Detection for Visual Tracking,
CirSysVideo(32), No. 12, December 2022, pp. 8204-8216.
IEEE DOI 2212
Target tracking, Correlation, Feature extraction, Convolutional neural networks, Visualization, multi-task learning BibRef

Wang, H.Q.[Hong-Qing], Xu, T.F.[Ting-Fa], Guo, J.[Jie], Rao, Z.T.[Zhi-Tao], Shi, G.K.[Guo-Kai],
Withdrawn: Incremental subspace and probability mask constrained tracking in smart and autonomous systems,
PR(72), No. 1, 2017, pp. 473-483.
Elsevier DOI 1708
BibRef
And: Withdrawn - premature publication. PR(76), No. 1, 2018, pp. 764.
Elsevier DOI 1801
Smart and autonomous systems BibRef

Guo, Q., Feng, W., Zhou, C., Pun, C.M., Wu, B.,
Structure-Regularized Compressive Tracking With Online Data-Driven Sampling,
IP(26), No. 12, December 2017, pp. 5692-5705.
IEEE DOI 1710
Haar transforms, discriminative feature generation, object localization, online data-driven sampling, rich local structural information, structural regularization, BibRef

Yu, Y.H.[Yuan-Hao], Wu, Q.S.[Qing-Song], Kirubarajan, T., Uehara, Y.[Yasuo],
Robust discriminative tracking via structured prior regularization,
IVC(69), No. 1, 2018, pp. 68-80.
Elsevier DOI 1712
Visual tracking BibRef

Wang, Y.[Yong], Luo, X.B.[Xin-Bin], Fu, S.[Shan], Hu, S.Q.[Shi-Qiang],
Context multi-task visual object tracking via guided filter,
SP:IC(62), 2018, pp. 117-128.
Elsevier DOI 1802
BibRef
Earlier: A1, A2, A4, Only: ICIP17(4332-4336)
IEEE DOI 1803
BibRef
And: A1, A2, A4, Only:
Robust object tracking via multi-task based collaborative model,
ICIP17(1132-1136)
IEEE DOI 1803
Visual object tracking, Context information, Multi-task sparse learning, Guided filter, Alternating direction method of multipliers BibRef

Wang, Y.[Yong], Luo, X.B.[Xin-Bin], Ding, L.[Lu], Hu, S.Q.[Shi-Qiang],
Multi-task based object tracking via a collaborative model,
JVCIR(55), 2018, pp. 698-710.
Elsevier DOI 1809
Collaborative model, Alternating direction method of multipliers, Discriminative model BibRef

Wang, W.[Wei], Wang, C.P.[Chun-Ping], Liu, S.[Si], Zhang, T.Z.[Tian-Zhu], Cao, X.C.[Xiao-Chun],
Robust Target Tracking by Online Random Forests and Superpixels,
CirSysVideo(28), No. 7, July 2018, pp. 1609-1622.
IEEE DOI 1807
Adaptation models, Computational modeling, Robustness, Target tracking, Training, Vision tracking, superpixels BibRef

Huang, J.[Jing], Wang, S.Z.[Shi-Zheng], Guo, M.H.[Meng-Han], Chen, S.S.[Shou-Shun],
Event-Guided Structured Output Tracking of Fast-Moving Objects Using a CeleX Sensor,
CirSysVideo(28), No. 9, September 2018, pp. 2413-2417.
IEEE DOI 1809
Issues of blur and large displacements. Tracking, Robot sensing systems, Support vector machines, Cameras, Computational efficiency, Lighting, Search problems, support vector machine (SVM) BibRef

Liu, G.,
Robust Visual Tracking via Smooth Manifold Kernel Sparse Learning,
MultMed(20), No. 11, November 2018, pp. 2949-2963.
IEEE DOI 1810
Target tracking, Kernel, Manifolds, Machine learning, Covariance matrices, Robustness, Visualization, visual tracking BibRef

Xue, W.L.[Wan-Li], Xu, C.[Chao], Feng, Z.Y.[Zhi-Yong],
Robust Visual Tracking via Multi-Scale Spatio-Temporal Context Learning,
CirSysVideo(28), No. 10, October 2018, pp. 2849-2860.
IEEE DOI 1811
Target tracking, Feature extraction, Visualization, Image color analysis, Context, Automobiles, Visual tracking, salient sample BibRef

Choi, J.[Janghoon], Kwon, J.[Junseok], Lee, K.M.[Kyoung Mu],
Real-time visual tracking by deep reinforced decision making,
CVIU(171), 2018, pp. 10-19.
Elsevier DOI 1812
Visual tracking, Object tracking, Deep learning, Reinforcement learning BibRef

Choi, J.[Janghoon], Kwon, J.[Junseok], Lee, K.M.[Kyoung Mu],
Deep Meta Learning for Real-Time Target-Aware Visual Tracking,
ICCV19(911-920)
IEEE DOI 2004
feature extraction, image matching, image motion analysis, image representation, Real-time systems BibRef

de Ath, G., Everson, R.,
Visual Object Tracking: The Initialisation Problem,
CRV18(142-149)
IEEE DOI 1812
Feature extraction, Support vector machines, Image segmentation, Image color analysis, Adaptation models, Kernel, Visualization BibRef

Wang, Q., Yuan, C., Wang, J., Zeng, W.,
Learning Attentional Recurrent Neural Network for Visual Tracking,
MultMed(21), No. 4, April 2019, pp. 930-942.
IEEE DOI 1903
Target tracking, Visualization, Computational modeling, Recurrent neural networks, Correlation, Hidden Markov models, attention model BibRef

Xiu, C.[Chunbo], Chai, Z.H.[Zuo-Hong],
Target tracking based on the cognitive associative network,
IET-IPR(13), No. 3, February 2019, pp. 498-505.
BibRef

Zhang, T.[Tiansa], Huo, C.L.[Chun-Lei], Zhou, Z.Q.A.[Zhi-Qi-Ang], Wang, B.[Bo],
IEICE(E102-D), No. 3, March 2019, pp. 684-687.
BibRef

Qi, Y.K.[Yuan-Kai], Zhang, S.P.[Sheng-Ping], Qin, L.[Lei], Huang, Q.M.[Qing-Ming], Yao, H.X.[Hong-Xun], Lim, J.W.[Jong-Woo], Yang, M.H.[Ming-Hsuan],
Hedging Deep Features for Visual Tracking,
PAMI(41), No. 5, May 2019, pp. 1116-1130.
IEEE DOI 1904
Target tracking, Visualization, Feature extraction, Correlation, Computer science, Robustness, Visual tracking, Siamese network BibRef

Zhang, J.[Jing], Ren, Y.G.[Yong-Gong], Zhang, D.[Danyi],
Marrying tracking with ELM: A Metric constraint guided multiple features fusion method,
PRL(120), 2019, pp. 82-88.
Elsevier DOI 1904
Object tracking, Multi-view fusion, Extreme learning machine, Metric constraint BibRef

Shen, W.C.[Wei-Chao], Wu, Y.W.[Yu-Wei], Yuan, J.S.[Jun-Song], Duan, L.Y.[Ling-Yu], Zhang, J.[Jian], Jia, Y.D.[Yun-De],
Robust Distracter-Resistive Tracker via Learning a Multi-Component Discriminative Dictionary,
CirSysVideo(29), No. 7, July 2019, pp. 2012-2028.
IEEE DOI 1907
Dictionaries, Visualization, Feature extraction, Machine learning, Robustness, Target tracking, Convolutional codes, Visual tracking, multi-object tracking BibRef

Fang, Z.W.[Zhi-Wen], Cao, Z.G.[Zhi-Guo], Xiao, Y.[Yang], Gong, K.C.[Kai-Cheng], Yuan, J.S.[Jun-Song],
MAT: Multianchor Visual Tracking With Selective Search Region,
Cyber(52), No. 7, July 2022, pp. 7136-7150.
IEEE DOI 2207
Target tracking, Tracking, Visualization, Search problems, Proposals, Predictive models, Histograms, Anchor proposal, anchor selection, selective search region BibRef

Zhang, B.[Bobin], Shao, X.Y.[Xiu-Yan], Chen, W.[Wei], Bi, F.M.[Fang-Ming], Fang, W.D.[Wei-Dong], Sun, T.F.[Tong-Feng], Tang, C.G.[Chao-Gang],
Visual tracking based on robust appearance model,
IVC(89), 2019, pp. 211-221.
Elsevier DOI 1909
Visual tracking, Semi-supervised linear kernel classifier, Fisher vectors, Similarity, Pollution handle BibRef

Abdelpakey, M.H.[Mohamed H.], Shehata, M.S.[Mohamed S.],
DP-Siam: Dynamic Policy Siamese Network for Robust Object Tracking,
IP(29), 2020, pp. 1479-1492.
IEEE DOI 1911
Real-time systems, Target tracking, Reinforcement learning, Object tracking, Training, Visualization, Heating systems, reinforcement learning BibRef

Lu, X.K.[Xian-Kai], Tang, F.H.[Fu-Hui], Huo, H.[Hong], Fang, T.[Tao],
Learning channel-aware deep regression for object tracking,
PRL(127), 2019, pp. 103-109.
Elsevier DOI 1911
Object tracking, Channel-aware, Deep regression BibRef

Jiang, Y.F.[Yi-Fan], Han, D.K.[David K.], Ko, H.S.[Han-Seok],
Relay dueling network for visual tracking with broad field-of-view,
IET-CV(13), No. 7, Octomber 2019, pp. 615-622.
BibRef

Zha, Y.F.[Yu-Fei], Wu, M.[Min], Qiu, Z.L.[Zhu-Ling], Yu, W.S.[Wang-Sheng],
Visual tracking based on semantic and similarity learning,
IET-CV(13), No. 7, Octomber 2019, pp. 623-631.
BibRef

Lv, Y.Q.[Yun-Qiu], Liu, K.[Kai], Cheng, F.[Fei], Li, W.[Wei],
Visual tracking with tree-structured appearance model for online learning,
IET-IPR(13), No. 12, October 2019, pp. 2106-2115.
Deep learning during tracking is expensive. BibRef

Wang, Y.[Yong], Hu, S.Q.[Shi-Qiang], Wu, S.D.[Shan-Dong],
Object tracking based on Huber loss function,
VC(35), No. 11, November 2018, pp. 1641-1654.
BibRef

Guo, Q., Han, R., Feng, W., Chen, Z., Wan, L.,
Selective Spatial Regularization by Reinforcement Learned Decision Making for Object Tracking,
IP(29), 2020, pp. 2999-3013.
IEEE DOI 2002
Target tracking, Visualization, Correlation, Object tracking, Clutter, Complexity theory, Visual object tracking, reinforcement learning BibRef

Li, K., Kong, Y., Fu, Y.,
Visual Object Tracking Via Multi-Stream Deep Similarity Learning Networks,
IP(29), 2020, pp. 3311-3320.
IEEE DOI 2002
Deep learning, visual tracking BibRef

Liang, Z., Shen, J.,
Local Semantic Siamese Networks for Fast Tracking,
IP(29), 2020, pp. 3351-3364.
IEEE DOI 2002
Visual object tracking, Siamese deep network, local feature representation BibRef

Bi, Y.[Yin], Chadha, A.[Aaron], Abbas, A.[Alhabib], Bourtsoulatze, E.[Eirina], Andreopoulos, Y.F.[Yi-Fannis],
Graph-Based Spatio-Temporal Feature Learning for Neuromorphic Vision Sensing,
IP(29), 2020, pp. 9084-9098.
IEEE DOI 2009
BibRef
Earlier:
Graph-Based Object Classification for Neuromorphic Vision Sensing,
ICCV19(491-501)
IEEE DOI 2004
Represent visual information as sequences of asynchronous discrete events. convolutional neural nets, graph theory, Task analysis, Cameras, Neuromorphics, Sensors, Lighting, Labeling, Feature extraction, Neuromorphic vision sensing, human action recognition. image classification, image representation, image sequences BibRef

Zhang, L., Lan, J., Li, X.R.,
Performance Evaluation of Joint Tracking and Classification,
SMCS(51), No. 2, February 2021, pp. 1149-1163.
IEEE DOI 2101
Target tracking, Probability density function, Estimation error, Indexes, Performance evaluation, Credibility, joint tracking and classification (JTC) BibRef

Zhu, H., Han, Y., Wang, Y., Yuan, G.,
Hybrid Cascade Filter With Complementary Features for Visual Tracking,
SPLetters(28), 2021, pp. 86-90.
IEEE DOI 2101
Observers, Visualization, Feature extraction, Robustness, Information filters, Target tracking, visual tracking BibRef

Lu, X.K.[Xian-Kai], Ma, C.[Chao], Ni, B.B.[Bing-Bing], Yang, X.K.[Xiao-Kang],
Adaptive Region Proposal With Channel Regularization for Robust Object Tracking,
CirSysVideo(31), No. 4, April 2021, pp. 1268-1282.
IEEE DOI 2104
Target tracking, Correlation, Proposals, Visualization, Estimation, Object tracking, Adaptive region proposals, robust object tracking BibRef

Lu, X.K.[Xian-Kai], Ma, C.[Chao], Shen, J.B.[Jian-Bing], Yang, X.K.[Xiao-Kang], Reid, I.D.[Ian D.], Yang, M.H.[Ming-Hsuan],
Deep Object Tracking With Shrinkage Loss,
PAMI(44), No. 5, May 2022, pp. 2386-2401.
IEEE DOI 2204
Target tracking, Visualization, Training, Benchmark testing, Object tracking, Data models, Correlation, Data imbalance, Siamese tracking BibRef

Qu, H.F.[Hui-Fang], Yang, F.[Fuwen], Han, Q.L.[Qing-Long], Zhang, Y.L.[Yi-Lian],
Distributed H8-Consensus Filtering for Attitude Tracking Using Ground-Based Radars,
Cyber(51), No. 7, July 2021, pp. 3767-3778.
IEEE DOI 2106
Spaceborne radar, Radar tracking, Network topology, Switches, Estimation, Sun, Attitude-rate, distributed H8-consensus filtering, switching topology BibRef

Wu, W.T.[Wen-Tao], Peng, Z.[Zhouhua], Wang, D.[Dan], Liu, L.[Lu], Han, Q.L.[Qing-Long],
Network-Based Line-of-Sight Path Tracking of Underactuated Unmanned Surface Vehicles With Experiment Results,
Cyber(52), No. 10, October 2022, pp. 10937-10947.
IEEE DOI 2209
Kinetic theory, Kinematics, Uncertainty, Observers, Tracking loops, Target tracking, Electrical engineering, Event-trigger, unmanned surface vehicle (USV) BibRef

Zhang, Y.P.[Yu-Ping], Ma, B.[Bo], Wu, J.H.[Jia-Hao], Huang, L.H.[Liang-Hua], Shen, J.B.[Jian-Bing],
Capturing Relevant Context for Visual Tracking,
MultMed(23), 2021, pp. 4232-4244.
IEEE DOI 2112
Target tracking, Visualization, Task analysis, Feature extraction, Object tracking, Benchmark testing, visual object tracking BibRef

Jiang, H.N.[Hao-Nan], Cai, Y.L.[Yuan-Li], Yu, Z.H.[Zhen-Hua],
Observability Metrics for Single-Target Tracking With Bearings-Only Measurements,
SMCS(52), No. 2, February 2022, pp. 1065-1077.
IEEE DOI 2201
Observability, Target tracking, Radar tracking, Geometry, Linear programming, Bearings-only tracking (BOT), trajectory optimization BibRef

Wang, S.[Shuai], Sheng, H.[Hao], Yang, D.[Da], Zhang, Y.[Yang], Wu, Y.[Yubin], Wang, S.Z.[Si-Zhe],
Extendable Multiple Nodes Recurrent Tracking Framework with RTU++,
IP(31), 2022, pp. 5257-5271.
IEEE DOI 2208
Tracking, Proposals, Feature extraction, Manuals, Trajectory, Filtering algorithms, Benchmark testing, Multi-object tracking, simulated data BibRef

Wang, S.[Shuai], Sheng, H.[Hao], Zhang, Y.[Yang], Wu, Y.[Yubin], Xiong, Z.[Zhang],
A General Recurrent Tracking Framework without Real Data,
ICCV21(13199-13208)
IEEE DOI 2203
Training, Tracking, Manuals, Benchmark testing, Motion and tracking, Efficient training and inference methods, Video analysis and understanding BibRef

Hou, Y.[Yueen], Luo, Z.J.[Zhi-Jian], Deng, J.M.[Jia-Ming], Gao, Y.Z.[Yan-Zeng], Huang, K.[Kekun], Li, W.G.[Wei-Guang],
Attention meets involution in visual tracking,
JVCIR(90), 2023, pp. 103746.
Elsevier DOI 2301
A recently-proposed model called involution uses kernels differing in spatial extent but sharing across channels, making it possible to take advantage of both convolution and attention. Visual tracking, Involution, Attention BibRef

Yu, E.[En], Li, Z.L.[Zhuo-Ling], Han, S.D.[Shou-Dong], Wang, H.W.[Hong-Wei],
RelationTrack: Relation-Aware Multiple Object Tracking With Decoupled Representation,
MultMed(25), 2023, pp. 2686-2697.
IEEE DOI 2307
Feature extraction, Transformers, Trajectory, Target tracking, Optimization, Object tracking, Training, Decoupling representation, transformer encoder BibRef

Lee, S.H.[Seong-Ho], Park, D.H.[Dae-Hyeon], Bae, S.H.[Seung-Hwan],
Decode-MOT: How Can We Hurdle Frames to Go Beyond Tracking-by-Detection?,
IP(32), 2023, pp. 4378-4392.
IEEE DOI 2308
Tracking, Detectors, Object tracking, Complexity theory, Task analysis, Feature extraction, Self-supervised learning, hierarchical association BibRef

Nakka, K.K.[Krishna Kanth], Salzmann, M.[Mathieu],
Universal, Transferable Adversarial Perturbations for Visual Object Trackers,
Springer DOI 2304
BibRef

Zou, Z.J.[Zhuo-Jun], Hao, J.[Jie], Shu, L.[Lin],
Online Feature Classification and Clustering for Transformer-based Visual Tracker,
ICPR22(3514-3521)
IEEE DOI 2212
Knowledge engineering, Visualization, Process control, Optimization methods, Quality control, Filtering algorithms, Feature Clustering BibRef

Cui, Y.[Yutao], Jiang, C.[Cheng], Wang, L.M.[Li-Min], Wu, G.S.[Gang-Shan],
MixFormer: End-to-End Tracking with Iterative Mixed Attention,
CVPR22(13598-13608)
IEEE DOI 2210
Location awareness, Target tracking, Pipelines, Stacking, Transformer cores, Feature extraction, Transformers, Video analysis and understanding BibRef

Cao, Z.[Ziang], Huang, Z.Y.[Zi-Yuan], Pan, L.[Liang], Zhang, S.W.[Shi-Wei], Liu, Z.[Ziwei], Fu, C.H.[Chang-Hong],
TCTrack: Temporal Contexts for Aerial Tracking,
CVPR22(14778-14788)
IEEE DOI 2210
Visualization, Convolution, Benchmark testing, Feature extraction, Transformers, Autonomous aerial vehicles, Robot vision, Motion and tracking BibRef

Fu, Z.H.[Zhi-Hong], Liu, Q.J.[Qing-Jie], Fu, Z.[Zehua], Wang, Y.H.[Yun-Hong],
STMTrack: Template-free Visual Tracking with Space-time Memory Networks,
CVPR21(13769-13778)
IEEE DOI 2111
Visualization, Target tracking, Codes, Adaptive systems, Benchmark testing, Boosting BibRef

Wu, H., Li, W., Li, W., Liu, G.,
A Real-time Robust Approach for Tracking UAVs in Infrared Videos,
Anti-UAV20(4448-4455)
IEEE DOI 2008
Target tracking, Drones, Feature extraction, Cameras, Robustness, Correlation BibRef

Wang, Z., Zhao, Z., Su, F.,
Real-time Tracking with Stabilized Frame,
Anti-UAV20(4431-4438)
IEEE DOI 2008
Target tracking, Cameras, Real-time systems, Robustness, Object tracking, Streaming media BibRef

Dunnhofer, M., Martinel, N., Foresti, G.L.[Gian Luca], Micheloni, C.[Christian],
Visual Tracking by Means of Deep Reinforcement Learning and an Expert Demonstrator,
VOT19(2290-2299)
IEEE DOI 2004
learning (artificial intelligence), object tracking, video signal processing, visual tracking, expert demonstrator, deep reinforcement learning BibRef

Chen, B.X., Tsotsos, J.,
Fast Visual Object Tracking using Ellipse Fitting for Rotated Bounding Boxes,
VOT19(2281-2289)
IEEE DOI 2004
Code, Tracking.
WWW Link. image segmentation, object tracking, ellipse fitting, real-time visual object tracking, Ellipse Fitting BibRef

Cevikalp, H.[Hakan], Saribas, H.[Hasan], Benligiray, B., Kahvecioglu, S.,
Visual Object Tracking by Using Ranking Loss,
VOT19(2271-2280)
IEEE DOI 2004
filtering theory, learning (artificial intelligence), neural nets, object detection, object tracking, target tracking, deep neural network classifier BibRef

Ma, D., Wu, X.,
Learning Cascaded Context-Aware Framework for Robust Visual Tracking,
VisDrone19(28-36)
IEEE DOI 2004
image representation, learning (artificial intelligence), object detection, object tracking, ubiquitous computing, cascaded structure BibRef

Xu, D., Wu, L., Jian, M., Wang, Q.,
Visual Tracking by Combining the Structure-Aware Network and Spatial-Temporal Regression,
ICPR18(1912-1917)
IEEE DOI 1812
Visualization, Feature extraction, Strain, Training, Logic gates, Proposals, Task analysis, spatial and temporal regression, LSTM, object deformation BibRef

Delforouzi, A., Tabatabaei, S.A.H., Shirahama, K., Grzegorzek, M.,
Unknown object tracking in 360-degree camera images,
ICPR16(1798-1803)
IEEE DOI 1705
Cameras, Detectors, Image resolution, Object tracking, Robot vision systems, Shape BibRef

Sugaya, Y.[Yasuyuki], Matsushita, Y.[Yuichi], Kanatani, K.[Kenichi],
Removing Mistracking of Multibody Motion Video Database Hopkins155,
BMVC13(xx-yy).
Results:
WWW Link. Point features for multibody motion. BibRef

Gu, Y.[Yang],
Effective Motion Tracking Using Known and Learned Actuation Models,
CMU-CS-08-137, June 2008 BibRef 0806 Ph.D.Thesis, June 2008
HTML Version. BibRef

Rosten, E.[Edward], Drummond, T.W.[Tom W.],
Fusing Points and Lines for High Performance Tracking,
ICCV05(II: 1508-1515).
IEEE DOI 0510
Deal with large changes. BibRef

Steger, C.T.[Carsten T.],
On the Calculation of Arbitrary Moments of Polygons,
TRFGBV-96-05, Forschungsgruppe Bildverstehen (FG BV), Informatik IX, Technische Universität München, October 1996.
HTML Version. BibRef 9610

Steger, C.T.[Carsten T.],
On the Calculation of Moments of Polygons,
TRFGBV-96-04, Forschungsgruppe Bildverstehen (FG BV), Informatik IX, Technische Universität München, August 1996.
HTML Version. BibRef 9608

Gardner, W.F., and Lawton, D.T.,
Shape and Motion from Linear Features,
DARPA93(1091-1095). Generate the structure from sequence of linear features. BibRef 9300

Chapter on Motion -- Feature-Based, Long Range, Motion and Structure Estimates, Tracking, Surveillance, Activities continues in
Long Sequence Matching and Motion .

Last update:Aug 31, 2023 at 09:37:21