Abstract
In recent years, visual object tracking has become a very active research area. An increasing number of tracking algorithms are being proposed each year. It is because tracking has wide applications in various real-world problems such as human-computer interaction, autonomous vehicles, robotics, surveillance, and security just to name a few. In the current study, we review latest trends and advances in the tracking area and evaluate the robustness of different trackers based on the feature extraction methods. The first part of this work includes a comprehensive survey of the recently proposed trackers. We broadly categorize trackers into Correlation Filter based Trackers (CFTs) and Non-CFTs. Each category is further classified into various types based on the architecture and the tracking mechanism. In the second part of this work, we experimentally evaluated 24 recent trackers for robustness and compared handcrafted and deep feature based trackers. We observe that trackers using deep features performed better, though in some cases a fusion of both increased performance significantly. To overcome the drawbacks of the existing benchmarks, a new benchmark Object Tracking and Temple Color (OTTC) has also been proposed and used in the evaluation of different algorithms. We analyze the performance of trackers over 11 different challenges in OTTC and 3 other benchmarks. Our study concludes that Discriminative Correlation Filter (DCF) based trackers perform better than the others. Our study also reveals that inclusion of different types of regularizations over DCF often results in boosted tracking performance. Finally, we sum up our study by pointing out some insights and indicating future trends in the visual object tracking field.
- Marjan Abdechiri, Karim Faez, and Hamidreza Amindavar. 2017. Visual object tracking with online weighted chaotic multiple instance learning. Neurocomputing 247 (2017), 16--30. Google ScholarDigital Library
- Radhakrishna Achanta, Appu Shaji, Kevin Smith, Aurelien Lucchi, Pascal Fua, and Sabine Süsstrunk. 2012. SLIC superpixels compared to state-of-the-art superpixel methods. IEEE TPAMI 34, 11 (2012), 2274--2282. Google ScholarDigital Library
- Amit Adam, Ehud Rivlin, and Ilan Shimshoni. 2006. Robust fragments-based tracking using the integral histogram. In Proceedings of the CVPR. IEEE. Google ScholarDigital Library
- Jake K. Aggarwal and Lu Xia. 2014. Human activity recognition from 3D data: A review. Pattern Recognition Letters 48 (2014), 70--80.Google ScholarCross Ref
- Ahmad Ali, Abdul Jalil, Jianwei Niu, Xiaoke Zhao, Saima Rathore, Javed Ahmed, and Muhammad Aksam Iftikhar. 2016. Visual object tracking—Classical and contemporary approaches. FCS 10, 1 (2016), 167--188. Google ScholarDigital Library
- Saad Ali and Mubarak Shah. 2010. Human action recognition in videos using kinematic features and multiple instance learning. IEEE TPAMI 32, 2 (2010), 288--303. Google ScholarDigital Library
- M. Sanjeev Arulampalam, Simon Maskell, Neil Gordon, and Tim Clapp. 2002. A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. IEEE TSP 50, 2 (2002), 174--188. Google ScholarDigital Library
- Boris Babenko, M. H. Yang, and Serge Belongie. 2009. Visual tracking with online multiple instance learning. In Proceedings of the CVPR. IEEE, 983--990.Google ScholarCross Ref
- Boris Babenko, M. H. Yang, and Serge Belongie. 2011. Robust object tracking with online multiple instance learning. IEEE TPAMI 33, 8 (2011), 1619--1632. Google ScholarDigital Library
- Bing Bai, Bineng Zhong, Gu Ouyang, Pengfei Wang, Xin Liu, Ziyi Chen, and Cheng Wang. 2018. Kernel correlation filters for visual tracking with adaptive fusion of heterogeneous cues. Neurocomputing 286 (2018), 109--120. Google ScholarDigital Library
- Jerome Berclaz, Francois Fleuret, Engin Turetken, and Pascal Fua. 2011. Multiple object tracking using k-shortest paths optimization. IEEE TPAMI 33, 9 (2011), 1806--1819. Google ScholarDigital Library
- L. Bertinetto, J. Valmadre, S. Golodetz, O. Miksik, and P Torr. 2016. Staple complementary learners for realtime tracking. In Proceedings of the CVPR. IEEE.Google Scholar
- Luca Bertinetto, Jack Valmadre, João F. Henriques, Andrea Vedaldi, and Philip H. S. Torr. 2016. Fully-convolutional Siamese networks for object tracking. In Proceedings of the ECCVW. Springer, 850--865.Google Scholar
- R. S. Blum and Z. Liu. 2005. Multi-sensor image fusion and its applications. CRC press, Taylor 8 Francis Group.Google Scholar
- D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui. 2010. Visual object tracking using adaptive correlation filters. In Proceedings of the CVPR. IEEE.Google Scholar
- David S. Bolme, Bruce A. Draper, and J. Ross Beveridge. 2009. Average of synthetic exact filters. In Proceedings of the CVPR. IEEE, 2105--2112.Google Scholar
- Yuanfeng Zhou, Brekhna Brekhna, Arif Mahmood, and Caiming Zhang. 2017. Robustness analysis of superpixel algorithms to image blur, additive Gaussian noise, and impulse noise. J. Electron. Imag. 26, 6 (2017), 61604.Google Scholar
- B. Cai, X. Xu, X. Xing, K. Jia, J. Miao, and D. Tao. 2016. BIT: Biologically inspired tracker. IEEE TIP 25, 3 (2016), 1327--1339. Google ScholarDigital Library
- Kevin Cannons. 2008. A Review of Visual Tracking. Technical Report CSE-2008-07. Department of Computer Science Engineering, York University, Toronto, Canada.Google Scholar
- Kai Chen and Wenbing Tao. 2018. Once for all: A two-flow convolutional neural network for visual tracking. IEEE TCSVT 28, 12 (2018), 3377--3386.Google Scholar
- K. Chen, W. Tao, and S. Han. 2017. Visual object tracking via enhanced structural correlation filter. Elsevier Inf. Sci. 394 (2017), 232--245. Google ScholarDigital Library
- Wei Chen, Kaihua Zhang, and Qingshan Liu. 2016. Robust visual tracking via patch based kernel correlation filters with adaptive multiple feature ensemble. Neurocomputing 214 (2016), 607--617. Google ScholarDigital Library
- X. Chen, P. J. Flynn, and K. W. Bowyer. 2006. Fusion of infrared and range data: Multi-modal face images. In Proceedings of the ICB. Springer, 55--63. Google ScholarDigital Library
- Z. Chen, Z. Hong, and D. Tao. 2015. An experimental survey on correlation filter-based tracking. CoRR. Retrieved from abs/1509.05520).Google Scholar
- G. Chéron, I. Laptev, and C. Schmid. 2015. P-CNN: Pose-based CNN features for action recognition. In Proceedings of the ICCV. IEEE, 3218--3226. Google ScholarDigital Library
- Zhizhen Chi, Hongyang Li, Huchuan Lu, and M. H. Yang. 2017. Dual deep network for visual tracking. IEEE TIP 26, 4 (2017), 2005--2015. Google ScholarDigital Library
- J. Choi, H. J. Chang, S. Yun, T. Fischer, Y. Demiris, and J. Y. Choi. 2017. Attentional correlation filter network for adaptive visual tracking. In Proceedings of the CVPR. IEEE, 4828--4837.Google Scholar
- Jongwon Choi and Jin Young Choi. 2015. User interactive segmentation with partially growing random forest. In Proceedings of the ICIP. IEEE.Google ScholarDigital Library
- Jongwon Choi, Hyung Jin Chang, Jiyeoup Jeong, Yiannis Demiris, and Jin Young Choi. 2016. Visual tracking using attention-modulated disintegration and integration. In Proceedings of the CVPR. IEEE, 4321--4330.Google ScholarCross Ref
- J. Choi, J. Kwon, and K. M. Lee. 2017. Visual tracking by reinforced decision making. Retrieved from arXiv:1702.06291.Google Scholar
- S. Chopra, R. Hadsell, and Y. LeCun. 2005. Learning similarity metric discriminatively, with application face verification. In Proceedings of the CVPR. IEEE. Google ScholarDigital Library
- Zhen Cui, Shengtao Xiao, Jiashi Feng, and Shuicheng Yan. 2016. Recurrently target-attending tracking. In Proceedings of the CVPR. IEEE, 1449--1458.Google ScholarCross Ref
- M. Danelljan, G. Bhat, F. S. Khan, and M. Felsberg. 2017. ECO: Efficient convolution operators for tracking. In Proceedings of the CVPR. IEEE, 6931--6939.Google Scholar
- M. Danelljan, G. Häger, F. S. Khan, and M. Felsberg. 2017. Discriminative scale space tracking. IEEE TPAMI 39 (2017), 1561--1575.Google ScholarDigital Library
- M. Danelljan, G. Hager, F. S. Khan, and M. Felsberg. 2015. Convolutional features for correlation filter based tracking. In Proceedings of the ICCVW. IEEE. Google ScholarDigital Library
- M. Danelljan, G. Hager, F. S. Khan, and M. Felsberg. 2015. Learning spatially regularized correlation filters for tracking. In Proceedings of the ICCV. IEEE. Google ScholarDigital Library
- M. Danelljan, G. Hager, F. S. Khan, and M. Felsberg. 2016. Adaptive decontamination of the training set: A unified formulation for discriminative visual tracking. In Proceedings of the CVPR. IEEE, 1430--1438.Google Scholar
- M. Danelljan, A. Robinson, F. S. Khan, and M. Felsberg. 2016. Beyond correlation filters: Learning continuous convolution operators for visual tracking. In Proceedings of the ECCV. Springer.Google Scholar
- M. Danelljan, F. S. Khan, M. Felsberg, and J. Van de Weijer. 2014. Adaptive color attributes for real-time visual tracking. In Proceedings of the CVPR. IEEE. Google ScholarDigital Library
- A. Dosovitskiy, P. Fischer, E. Ilg, P. Hausser, C. Hazirbas, V. Golkov, P. Van der Smagt, D. Cremers, and T. Brox. 2015. Flownet: Learning optical flow with convolutional networks. In Proceedings of the ICCV. IEEE, 2758--2766. Google ScholarDigital Library
- Dawei Du, Honggang Qi, Wenbo Li, Longyin Wen, Qingming Huang, and Siwei Lyu. 2016. Online deformable object tracking based on structure-aware hyper-graph. TIP 25, 8 (2016), 3572--3584. Google ScholarDigital Library
- Dawei Du, Honggang Qi, Longyin Wen, Qi Tian, Qingming Huang, and Siwei Lyu. 2017. Geometric hypergraph learning for visual tracking. IEEE TC 47, 12 (2017), 4182--4195.Google Scholar
- Yong Du, Yun Fu, and Liang Wang. 2016. Representation learning of temporal dynamics for skeleton-based action recognition. IEEE TIP 25, 7 (2016), 3010--3022.Google Scholar
- Leila Essannouni, Elhassane Ibn-Elhaj, and Driss Aboutajdine. 2006. Fast cross-spectral image registration using new robust correlation. Springer JRTIP 1, 2 (2006), 123--129.Google Scholar
- H. Fan and H. Ling. 2017. Parallel tracking and verifying: A framework for real-time and high accuracy visual tracking. In Proceedings of the IEEE International Conference on Computer Vision. 5486--5494.Google Scholar
- Heng Fan and Haibin Ling. 2017. SANet: Structure-aware network for visual tracking. In Proceedings of the CVPRW. 2217--2224.Google ScholarCross Ref
- M. Farid, A. Mahmood, and S. Al Maadeed. 2019. Multi-focus image fusion using content adaptive blurring. Inf. Fusion 45 (2019), 96--112.Google ScholarCross Ref
- Pedro F. Felzenszwalb, Ross B. Girshick, David McAllester, and Deva Ramanan. 2010. Object detection with discriminatively trained part-based models. IEEE TPAMI 32, 9 (2010), 1627--1645. Google ScholarDigital Library
- Idir Filali, Mohand Saïd Allili, and Nadjia Benblidia. 2016. Multi-scale salient object detection using graph ranking and global--local saliency refinement. Elsevier Signal Proc. Image 47 (2016), 380--401. Google ScholarDigital Library
- David Forsyth. 2014. Object detection with discriminatively trained part-based models. Computer 47, 2 (2014), 6--7. Google ScholarDigital Library
- C. Gao, F. Chen, J. G. Yu, R. Huang, and N. Sang. 2017. Robust tracking using exemplar-based detectors. IEEE TCSVT 27, 2 (2017), 300--312. Google ScholarDigital Library
- C. Gao, H. Shi, J. G. Yu, and N. Sang. 2016. Enhancement of ELDA based on CNN and adaptive model update. Sensors 16, 4 (2016), 545.Google ScholarCross Ref
- Junyu Gao, Tianzhu Zhang, Xiaoshan Yang, and Changsheng Xu. 2017. Deep relative tracking. IEEE TIP 26, 4 (2017), 1845--1858. Google ScholarDigital Library
- J. Gao, T. Zhang, X. Yang, and C. Xu. 2018. P2t: Part-to-target tracking via deep regression learning. IEEE TIP 27, 6 (2018), 3074--3086.Google Scholar
- R. Girshick, J. Donahue, T. Darrell, and J. Malik. 2014. Rich feature hierarchies for accurate object detection and semantic segmentation. In Proceedings of the CVPR. IEEE, 580--587. Google ScholarDigital Library
- S. Gladh, M. Danelljan, F. S. Khan, and M. Felsberg. 2016. Deep motion features for visual tracking. In Proceedings of the ICPR. IEEE, 1243--1248.Google Scholar
- H. Gong, J. Sim, M. Likhachev, and J. Shi. 2011. Multi-hypothesis motion planning for visual object tracking. In Proceedings of the ICCV. IEEE, 619--626. Google ScholarDigital Library
- I. Goodfellow, J. P. Abadie, M. Mirza, B. Xu, D. W. Farley, S. Ozair, A. Courville, and Y. Bengio. 2014. Generative adversarial nets. In Proceedings of the Conference on NIPS. Google ScholarDigital Library
- A. Graves, A. R. Mohamed, and G. Hinton. 2013. Speech recognition with deep recurrent neural networks. In Proceedings of the ICASSP. IEEE, 6645--6649.Google Scholar
- S. Gu, Y. Zheng, and C. Tomasi. 2010. Efficient visual object tracking with online nearest neighbor classifier. In Proceedings of the ACCV. Springer. Google ScholarDigital Library
- M. Guillaumin, J. J. Verbeek, and C. Schmid. 2010. Multiple instance metric learning from automatically labeled bags of faces. In Proceedings of the ECCV. Springer, 634--647. Google ScholarDigital Library
- E. Gundogdu, A. Koc, B. Solmaz, R. I. Hammoud, and A. A. Alatan. 2016. Evaluation of feature channels for correlation-filter-based visual object tracking in infrared spectrum. In Proceedings of the CVPRW. IEEE, 290--298.Google Scholar
- Jie Guo, Tingfa Xu, Ziyi Shen, and Guokai Shi. 2017. Visual tracking via sparse representation with reliable structure constraint. IEEE SPL 24, 2 (2017), 146--150.Google Scholar
- Q. Guo, W. Feng, C. Zhou, R. Huang, L. Wan, and S. Wang. 2017. Learning dynamic Siamese network for visual tracking. In Proceedings of the ICCV. IEEE.Google Scholar
- B. Han, J. Sim, and H. Adam. 2017. Branchout: Regularization for online ensemble tracking with CNN. In Proceedings of the CVPR. IEEE, 521--530.Google Scholar
- S. Hare, S. Golodetz, A. Saffari, V. Vineet, M. M. Cheng, S. L. Hicks, and Philip H. S. Torr. 2016. Struck: Structured output tracking with kernels. IEEE TPAMI 38 (2016), 2096--2109. Google ScholarDigital Library
- Sam Hare, Amir Saffari, and Philip H. S. Torr. 2011. Struck: Structured output tracking with kernels. In Proceedings of the ICCV. Google ScholarDigital Library
- K. He, X. Zhang, S. Ren, and J. Sun. 2016. Deep residual learning for image recognition. In Proceedings of the CVPR. IEEE, 770--778.Google Scholar
- D. Held, S. Thrun, and S. Savarese. 2016. Learning to track at 100 fps with deep regression networks. In Proceedings of the ECCV. Springer, 749--765.Google Scholar
- J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. 2012. Exploiting the circulant structure of tracking-by-detection with kernels. In Proceedings of the ECCV. Springer, 702--715. Google ScholarDigital Library
- João F. Henriques, Rui Caseiro, Pedro Martins, and Jorge Batista. 2015. High-speed tracking with kernelized correlation filters. IEEE TPAMI 37, 3 (2015), 583--596.Google ScholarDigital Library
- Zhibin Hong, Zhe Chen, Chaohui Wang, Xue Mei, Danil Prokhorov, and Dacheng Tao. 2015. Multi-store tracker (muster): A cognitive psychology inspired approach to object tracking. In Proceedings of the CVPR. IEEE, 749--758.Google ScholarCross Ref
- Hongwei Hu, Bo Ma, Jianbing Shen, and Ling Shao. 2018. Manifold regularized correlation object tracking. IEEE TNNLS 29, 5 (2018), 1786--1795.Google Scholar
- C. Huang, S. Lucey, and D. Ramanan. 2017. Learning policies for adaptive tracking with deep feature cascades. In Proceedings of the ICCV. IEEE.Google Scholar
- W. Huang, R. Hu, C. Liang, W. Ruan, and B. Luo. 2017. Structural superpixel descriptor for visual tracking. In Proceedings of the IJCNN. IEEE, 3146--3152.Google Scholar
- X. Jia, H. Lu, and M. H. Yang. 2012. Visual tracking via adaptive structural local sparse appearance model. In Proceedings of the CVPR. IEEE, 1822--1829. Google ScholarDigital Library
- H. K. Galoogahi, A. Fagg, and S. Lucey. 2017. Learning background-aware correlation filters for visual tracking. In Proceedings of the ICCV. IEEE.Google Scholar
- H. K. Galoogahi, T. Sim, and S. Lucey. 2015. Correlation filters with limited boundaries. In Proceedings of the CVPR. IEEE, 4630--4638.Google Scholar
- Z. Kalal, J. Matas, and K. Mikolajczyk. 2010. Pn learning: Bootstrapping binary classifiers by structural constraints. In Proceedings of the CVPR. IEEE.Google Scholar
- Zdenek Kalal, Krystian Mikolajczyk, Jiri Matas.2012. Tracking-learning-detection. IEEE TPAMI 34, 7 (2012), 1409. Google ScholarDigital Library
- P. Karczmarek, A. Kiersztyn, W. Pedrycz, and M. Dolecki. 2017. An application of chain code-based local descriptor and its extension to face recognition. PR 65 (2017), 26--34. Google ScholarDigital Library
- A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, and L. F. Fei. 2014. Large-scale video classification with convolutional neural networks. In Proceedings of the CVPR. IEEE, 1725--1732. Google ScholarDigital Library
- Zulfiqar Hasan Khan, Irene Yu-Hua Gu, and Andrew G. Backhouse. 2011. Robust visual object tracking using multi-mode anisotropic mean shift and particle filters. IEEE TCSVT 21, 1 (2011), 74--87. Google ScholarDigital Library
- Matej Kristan, Roman Pflugfelder, Ale Leonardis, Jiri Matas, Fatih Porikli, Luka Cehovin, Georg Nebehay, Gustavo Fernandez, Toma Vojir, Adam Gatt, et al. 2013. The visual object tracking vot2013 challenge results. In Proceedings of the ICCVW. IEEE, 98--111. Google ScholarDigital Library
- Matej Kristan, Roman Pflugfelder, Ale Leonardis, Jiri Matas, Fatih Porikli, Luka Cehovin, Georg Nebehay, Gustavo Fernandez, Toma Vojir, Adam Gatt, et al. 2015. The visual object tracking VOT2014 challenge results. In Proceedings of the Computer Vision - ECCV 2014 Workshops, Agapito Lourdes Bronstein, M. Michael, and Rother Carsten (Eds.). Springer International Publishing, 191--217.Google ScholarCross Ref
- Matej Kristan, Roman Pflugfelder, Ale Leonardis, Jiri Matas, Fatih Porikli, Luka Cehovin, Georg Nebehay, Gustavo Fernandez, Toma Vojir, Adam Gatt, et al. 2015. The visual object tracking VOT2015 challenge results. In Proceedings of the IEEE International Conference on Computer Vision Workshop (ICCVW'15). 564--586. Google ScholarDigital Library
- Matej Kristan, Roman Pflugfelder, Ale Leonardis, Jiri Matas, Fatih Porikli, Luka Cehovin, Georg Nebehay, Gustavo Fernandez, Toma Vojir, Adam Gatt, et al. 2016. The visual object tracking VOT2016 challenge results. In Proceedings of the Computer Vision -- ECCV 2016 Workshops. Springer International Publishing, 777--823.Google ScholarCross Ref
- Matej Kristan, Roman Pflugfelder, Ale Leonardis, Jiri Matas, Fatih Porikli, Luka Cehovin, Georg Nebehay, Gustavo Fernandez, Toma Vojir, Adam Gatt, et al. 2017. The visual object tracking VOT2017 challenge results. In Proceedings of the IEEE International Conference on Computer Vision Workshops (ICCVW'17). 1949--1972.Google ScholarCross Ref
- Junseok Kwon and Kyoung Mu Lee. 2010. Visual tracking decomposition. In Proceedings of the CVPR. IEEE, 1269--1276.Google ScholarCross Ref
- L. L. Taixé, C. C. Ferrer, and K. Schindler. 2016. Learning by tracking: Siamese CNN for robust target association. In Proceedings of the CVPRW. IEEE, 33--40.Google Scholar
- L. L. Taixé, A. Milan, K. Schindler, D. Cremers, Ian Reid, and S. Roth. 2017. Tracking the trackers: An analysis of the state of the art in multiple object tracking. CoRR. Retrieved from abs/1704.02781.Google Scholar
- V. A. Laurense, J. Y. Goh, and J. C. Gerdes. 2017. Path-tracking for autonomous vehicles at the limit of friction. In Proceedings of the ACC. IEEE, 5586--5591.Google Scholar
- I. Leang, S. Herbin, B. Girard, and J. Droulez. 2018. On-line fusion of trackers for single-object tracking. PR 74 (2018), 459--473. Google ScholarDigital Library
- J. Lee, B. K. Iwana, S. Ide, and S. Uchida. 2016. Globally optimal object tracking with fully convolutional networks. CoRR. arXiv preprint arXiv:1612.08274Google Scholar
- Annan Li and Shuicheng Yan. 2014. Object tracking with only background cues. IEEE TCSVT 24, 11 (2014), 1911--1919.Google Scholar
- Fu Li, Xu Jia, Cheng Xiang, and Huchuan Lu. 2017. Visual tracking with structured patch-based model. IVC 60 (2017), 124--133. Google ScholarDigital Library
- F. Li, C. Tian, W. Zuo, L. Zhang, and M. H. Yang. 2018. Learning spatial-temporal regularized correlation filters tracking. In Proceedings of the CVPR. IEEE.Google Scholar
- Hanxi Li, Yi Li, and Fatih Porikli. 2016. Deeptrack: Learning discriminative feature representations online for robust visual tracking. IEEE TIP 25, 4 (2016), 1834--1848.Google Scholar
- Hanxi Li, Chunhua Shen, and Qinfeng Shi. 2011. Real-time visual tracking using compressive sensing. In Proceedings of the CVPR. IEEE, 1305--1312. Google ScholarDigital Library
- Meng Li and Howard Leung. 2016. Multiview skeletal interaction recognition using active joint interaction graph. IEEE TM 18, 11 (2016), 2293--2302. Google ScholarDigital Library
- P. Li, D. Wang, L. Wang, and H. Lu. 2018. Deep visual tracking: Review and experimental comparison. PR 76 (2018), 323--338. Google ScholarDigital Library
- X. Li, W. Hu, C. Shen, Z. Zhang, A. Dick, and A. Van den Hengel. 2013. A survey of appearance models in visual object tracking. ACM TIST 4, 4 (2013), 58. Google ScholarDigital Library
- Y. Li and J. Zhu. 2014. A scale adaptive kernel correlation filter tracker with feature integration. In Proceedings of the ECCVW. Springer, 254--265.Google Scholar
- Y. Li, J. Zhu, and S. C. H. Hoi. 2015. Reliable patch trackers: Robust visual tracking by exploiting reliable patches. In Proceedings of the CVPR. IEEE, 353--361.Google ScholarCross Ref
- Pengpeng Liang, Erik Blasch, and Haibin Ling. 2015. Encoding color information for visual tracking: Algorithms and benchmark. IEEE TIP 24, 12 (2015), 5630--5644.Google Scholar
- Q. Liu, X. Zhao, and Z. Hou. 2014. Survey of single-target visual tracking methods based on online learning. IET-CV 8, 5 (2014), 419--428.Google Scholar
- S. Liu, T. Zhang, X. Cao, and C. Xu. 2016. Structural correlation filter for robust visual tracking. In Proceedings of the CVPR. IEEE, 4312--4320.Google Scholar
- T. Liu, G. Wang, and Q. Yang. 2015. Real-time part-based visual tracking via adaptive correlation filters. In Proceedings of the CVPR. IEEE, 4902--4912.Google Scholar
- Songjiang Lou, Xiaoming Zhao, Yuelong Chuang, Haitao Yu, and Shiqing Zhang. 2016. Graph regularized sparsity discriminant analysis for face recognition. Neurocomputing 173 (2016), 290--297. Google ScholarDigital Library
- A. Lukežič, L. Zajc, and M. Kristan. 2018. Deformable parts correlation filters for robust visual tracking. IEEE TC 48, 6 (2018), 1849--1861.Google Scholar
- A. Lukežič, T. Vojíř, L. Čehovin, J. Matas, and M. Kristan. 2017. DCF with channel and spatial reliability. In Proceedings of the CVPR. IEEE.Google Scholar
- Chengwei Luo, Bin Sun, Qiao Deng, Zihao Wang, and Dengwei Wang. 2018. Comparison of different level fusion schemes for infrared-visible object tracking: An experimental survey. In Proceedings of the ICRAS. IEEE, 1--5.Google ScholarCross Ref
- C. Ma, J. B. Huang, X. Yang, and M. H. Yang. 2018. Robust visual tracking via hierarchical convolutional features. IEEE TPAMI (2018), 1--1.Google Scholar
- C. Ma, J. B. Huang, X. Yang, and M. H. Yang. 2015. Hierarchical convolutional features for visual tracking. In Proceedings of the ICCV. IEEE, 3074--3082. Google ScholarDigital Library
- Chao Ma, Jia-Bin Huang, Xiaokang Yang, and Ming-Hsuan Yang. 2018. Adaptive correlation filters with long-term and short-term memory for object tracking. IJCV 126, 8 (2018), 771--796. Google ScholarDigital Library
- Chao Ma, Xiaokang Yang, Chongyang Zhang, and M. H. Yang. 2015. Long-term correlation tracking. In Proceedings of the CVPR. IEEE, 5388--5396.Google Scholar
- L. Ma, J. Lu, J. Feng, and J. Zhou. 2015. Multiple feature fusion via weighted entropy for visual tracking. In Proceedings of the ICCV. 3128--3136. Google ScholarDigital Library
- H. K. Meena, K. K. Sharma, and S. D. Joshi. 2017. Improved facial expression recognition using graph sig. pro. IET EL 53, 11 (2017), 718--720.Google ScholarCross Ref
- Xue Mei and Haibin Ling. 2009. Robust visual tracking using â 1 minimization. In Proceedings of the ICCV. IEEE, 1436--1443.Google Scholar
- G. Mori, X. Ren, A. Efros, and J. Malik. 2004. Recovering human body configurations: Combining segmentation and recognition. In Proceedings of the CVPR. IEEE. Google ScholarDigital Library
- Matthias Mueller, Neil Smith, and Bernard Ghanem. 2017. Context-aware correlation filter tracking. In Proceedings of the CVPR. IEEE, 1387--1395.Google ScholarCross Ref
- H. Nam, M. Baek, and B. Han. 2016. Modeling and propagating CNNs in a tree structure for visual tracking. CoRR. Retrieved from abs/1608.07242.Google Scholar
- H. Nam and B. Han. 2016. Learning multi-domain convolutional neural networks for visual tracking. In Proceedings of the CVPR. IEEE, 4293--4302.Google Scholar
- Jifeng Ning, Jimei Yang, Shaojie Jiang, Lei Zhang, and M. H. Yang. 2016. Object tracking via dual linear structured SVM and explicit feature map. In Proceedings of the CVPR. IEEE, 4266--4274.Google Scholar
- W. Ouyang, X. Zeng, X. Wang, S. Qiu, P. Luo, Y. Tian, H. Li, S. Yang, Z. Wang, H. Li, K. Wang, J. Yan, C. C. Loy, and X. Tang. 2017. DeepID-net: Object detection with deformable part based convolutional neural networks. IEEE TPAMI 39, 7 (2017), 1320--1334.Google ScholarDigital Library
- Mustafa Ozuysal, Pascal Fua, and Vincent Lepetit. 2007. Fast keypoint recognition in ten lines of code. In Proceedings of the CVPR. IEEE, 1--8.Google ScholarCross Ref
- Jiyan Pan and Bo Hu. 2007. Robust occlusion handling in object tracking. In Proceedings of the CVPR. IEEE, 1--8.Google ScholarCross Ref
- Houwen Peng, Bing Li, Haibin Ling, Weiming Hu, Weihua Xiong, and Stephen J. Maybank. 2017. Salient object detection via structured matrix decomposition. IEEE TPAMI 39, 4 (2017), 818--832. Google ScholarDigital Library
- A. Prioletti, A. Møgelmose, P. Grisleri, M. M. Trivedi, A. Broggi, and T. B. Moeslund. 2013. Part-based pedestrian detection and feature-based tracking for driver assistance: real-time, robust algorithms, and evaluation. IEEE TITS 14, 3 (2013), 1346--1359. Google ScholarDigital Library
- Y. Qi, S. Zhang, L. Qin, H. Yao, Q. Huang, J. Lim, and M. H. Yang. 2016. Hedged deep tracking. In Proceedings of the CVPR. IEEE, 4303--4311.Google Scholar
- Lei Qin, Hichem Snoussi, and Fahed Abdallah. 2014. Object tracking using adaptive covariance descriptor and clustering-based model updating for visual surveillance. Sensors 14, 6 (2014), 9380--9407.Google ScholarCross Ref
- Deva Ramanan. 2013. Dual coordinate solvers for large-scale structural svms. Retrieved from arXiv:1312.1743.Google Scholar
- Madan Kumar Rapuru, Sumithra Kakanuru, Pallavi M. Venugopal, Deepak Mishra, and G. R. K. S. Subrahmanyam. 2017. Correlation-based tracker-level fusion for robust visual tracking. IEEE TIP 26, 10 (2017), 4832--4842.Google Scholar
- Mikel D. Rodriguez, Javed Ahmed, and Mubarak Shah. 2008. Action mach a spatio-temporal maximum average correlation height filter for action recognition. In Proceedings of the CVPR. IEEE, 1--8.Google ScholarCross Ref
- Adriana Romero, Carlo Gatta, and Gustau Camps-Valls. 2016. Unsupervised deep feature extraction for remote sensing image classification. IEEE TGRS 54, 3 (2016), 1349--1362.Google Scholar
- Marios Savvides, B. V. K. Vijaya Kumar, and Pradeep Khosla. 2002. Face verification using correlation filters. In Proceeding of the 3rd IEEE Automatic Identification Advanced Technologies. 56--61.Google Scholar
- F. Schroff, D. Kalenichenko, and J. Philbin. 2015. Facenet: A unified embedding for face recognition and clustering. In Proceedings of the CVPR. IEEE.Google Scholar
- Joan Severson. 2017. Human-digital media interaction tracking. US Patent No. 9,713,444.Google Scholar
- V. Sharma and K. Mahapatra. 2017. MIL-based visual tracking with kernel and scale adaptation. Sig. Pro.: Img. Comm. 53 (2017), 51--64. Google ScholarDigital Library
- K. Simonyan and A. Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. CoRR. Retrieved from abs/1409.1556.Google Scholar
- Arnold W. M. Smeulders, Dung M. Chu, Rita Cucchiara, Simone Calderara, Afshin Dehghan, and Mubarak Shah. 2014. Visual tracking: An experimental survey. IEEE TPAMI 36, 7 (2014), 1442--1468. Google ScholarDigital Library
- Y. Song, C. Ma, L. Gong, J. Zhang, R. Lau, and M. H. Yang. 2017. CREST convolutional residual learning for tracking. In Proceedings of the ICCV. IEEE.Google Scholar
- Yibing Song, Chao Ma, Xiaohe Wu, Lijun Gong, Linchao Bao, Wangmeng Zuo, Chunhua Shen, Lau Rynson, and Ming-Hsuan Yang. 2018. VITAL: Visual tracking via adversarial learning. In Proceedings of the CVPR. IEEE.Google ScholarCross Ref
- Yao Sui, Ziming Zhang, Guanghui Wang, Yafei Tang, and Li Zhang. 2016. Real-time visual tracking: Promoting the robustness of correlation filter learning. In Proceedings of the ECCV. Springer.Google ScholarCross Ref
- Ran Tao, Efstratios Gavves, and Arnold W. M. Smeulders. 2016. Siamese instance search for tracking. In Proceedings of the CVPR. IEEE, 1420--1429.Google Scholar
- Zhu Teng, Junliang Xing, Qiang Wang, Congyan Lang, Songhe Feng, and Yi Jin. 2017. Robust object tracking based on temporal and spatial deep networks. In Proceedings of the ICCV. IEEE, 1153--1162.Google ScholarCross Ref
- B. Tian, Q. Yao, Y. Gu, K. Wang, and Y. Li. 2011. Video processing techniques for traffic flow monitoring: A survey. In Proceedings of the ITSC. IEEE.Google Scholar
- Jack Valmadre, Luca Bertinetto, João F. Henriques, Andrea Vedaldi, and Philip H. S. Torr. 2017. End-to-end representation learning for correlation filter based tracking. In Proceedings of the CVPR, 5000--5008.Google Scholar
- Andrea Vedaldi and Karel Lenc. 2015. Matconvnet: Convolutional neural networks for MATLAB. In Proceedings of the ACMMM. ACM. Google ScholarDigital Library
- Sean Walker, Christopher Sewell, June Park, Prabu Ravindran, Aditya Koolwal, Dave Camarillo, and Federico Barbagli. 2017. Systems and methods for localizing, tracking, and/or controlling medical instruments. US Patent App. 15/466,565.Google Scholar
- Fan Wang, Yan Wu, Peng Zhang, Qingjun Zhang, and Ming Li. 2017. Unsupervised SAR image segmentation using ambiguity label information fusion in triplet Markov fields model. IEEE Geosci. Remote Sens. Lett. 14, 9 (2017), 1479--1483.Google ScholarCross Ref
- G. Wang, J. Wang, W. Tang, and N. Yu. 2017. Robust visual tracking with deep feature fusion. In Proceedings of the ICASSP. IEEE, 1917--1921.Google Scholar
- Jingjing Wang, Chi Fei, Liansheng Zhuang, and Nenghai Yu. 2016. Part-based multi-graph ranking for visual tracking. In Proceedings of the ICIP. IEEE.Google ScholarCross Ref
- Jun Wang, Weibin Liu, Weiwei Xing, and Shunli Zhang. 2017. Two-level superpixel and feedback-based visual object tracking. Neurocomputing 267 (2017), 581--596. Google ScholarDigital Library
- Lijun Wang, Huchuan Lu, and M. H. Yang. 2018. Constrained superpixel tracking. IEEE TC 48, 3 (2018), 1030--1041.Google Scholar
- L. Wang, W. Ouyang, X. Wang, and H. Lu. 2016. STCT: Sequentially training convolutional networks for visual tracking. In Proceedings of the CVPR. IEEE.Google Scholar
- M. Wang, Y. Liu, and Z. Huang. 2017. Large margin object tracking with circulant feature maps. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4021--4029.Google Scholar
- Q. Wang, J. Gao, J. Xing, M. Zhang, and W. Hu. 2017. DCFNet: Discriminant correlation filters network for visual tracking. CoRR. Retrieved from abs/1704.04057).Google Scholar
- Tao Wang and Haibin Ling. 2018. Gracker: A graph-based planar object tracker. IEEE TPAMI 40, 6 (2018), 1494--1501.Google ScholarCross Ref
- X. Wang, C. Li, B. Luo, and J. Tang. 2018. SINT++: Robust visual tracking via adversarial positive instance generation. In Proceedings of the CVPR. IEEE.Google Scholar
- Zhenjie Wang, Lijia Wang, and Hua Zhang. 2017. Patch-based multiple instance learning algorithm for object tracking. Comp. Int. and Neurosc. 2017 (2017). Google ScholarDigital Library
- Ronald J. Williams and David Zipser. 1989. A learning algorithm for continually running fully recurrent neural networks. MIT Press NC 1, 2 (1989), 270--280. Google ScholarDigital Library
- Jianxin Wu, Adebola Osuntogun, Tanzeem Choudhury, Matthai Philipose, and James M. Rehg. 2007. A scalable approach to activity recognition based on object use. In Proceedings of the ICCV. IEEE, 1--8.Google Scholar
- Yi Wu, Jongwoo Lim, and M. H. Yang. 2013. Online object tracking: A benchmark. In Proceedings of the CVPR. IEEE, 2411--2418. Google ScholarDigital Library
- Yi Wu, Jongwoo Lim, and M. H. Yang. 2015. Object tracking benchmark. IEEE TPAMI (2015), 1834--1848.Google Scholar
- Chao Xu, Wenyuan Tao, Zhaopeng Meng, and Zhiyong Feng. 2015. Robust visual tracking via online multiple instance learning with Fisher information. Elsevier PR 48, 12 (2015), 3917--3926. Google ScholarDigital Library
- Fan Yang, Huchuan Lu, and M. H. Yang. 2014. Robust superpixel tracking. IEEE TIP 23, 4 (2014), 1639--1651. Google ScholarDigital Library
- Honghong Yang, Shiru Qu, and Zunxin Zheng. 2018. Visual tracking via online discriminative multiple instance metric learning. Springer MTA 77, 4 (2018), 4113--4131.Google Scholar
- Hanxuan Yang, Ling Shao, Feng Zheng, Liang Wang, and Zhan Song. 2011. Recent advances and trends in visual tracking: A review. Neurocomputing 74, 18 (2011), 3823--3831. Google ScholarDigital Library
- Ming Yang, Ying Wu, and Gang Hua. 2009. Context-aware visual tracking. IEEE TPAMI 31, 7 (2009), 1195--1209. Google ScholarDigital Library
- M. Yang, Y. Wu, and S. Lao. 2006. Intelligent collaborative tracking by mining auxiliary objects. In Proceedings of the CVPR, Vol. 1. IEEE, 697--704. Google ScholarDigital Library
- Rui Yao, Qinfeng Shi, Chunhua Shen, Yanning Zhang, and Anton van den Hengel. 2017. Part-based robust tracking using online latent structured learning. IEEE TCSVT 27, 6 (2017), 1235--1248.Google Scholar
- D. Yeo, J. Son, B. Han, and J. H. Han. 2017. Superpixel-based tracking-by-segmentation using Markov chains. In Proceedings of the CVPR. IEEE, 511--520.Google Scholar
- Yang Yi, Yang Cheng, and Chuping Xu. 2018. Visual tracking based on hierarchical framework and sparse representation. Springer MTA 77, 13 (2018), 16267--16289. Google ScholarDigital Library
- Alper Yilmaz, Omar Javed, and Mubarak Shah. 2006. Object tracking: A survey. ACM Comput. Surv. 38 (2006), 13. Google ScholarDigital Library
- Alper Yilmaz, Xin Li, and Mubarak Shah. 2004. Contour-based object tracking with occlusion handling in video acquired using mobile cameras. IEEE TPAMI 26, 11 (2004), 1531--1536. Google ScholarDigital Library
- Qian Yu, Thang Ba Dinh, and Gérard Medioni. 2008. Online tracking and reacquisition using co-trained generative and discriminative trackers. In Proceedings of the ECCV. Springer, 678--691. Google ScholarDigital Library
- S. Yun, J. Choi, Y. Yoo, K. Yun, and J. Y. Choi. 2017. Action-decision net. for tracking with deep reinforcement learning. In Proceedings of the CVPR. IEEE.Google Scholar
- Sergey Zagoruyko and Nikos Komodakis. 2015. Learning to compare image patches via convolutional neural networks. In Proceedings of the CVPR. IEEE.Google ScholarCross Ref
- J. Zbontar and Y. LeCun. 2015. Computing the stereo matching cost with a convolutional neural network. In Proceedings of the CVPR. IEEE, 1592--1599.Google Scholar
- Baochang Zhang, Zhigang Li, Alessandro Perina, Alessio Del Bue, Vittorio Murino, and Jianzhuang Liu. 2017. Adaptive local movement modeling for robust object tracking. IEEE TCSVT 27, 7 (2017), 1515--1526.Google Scholar
- Cha Zhang, John C. Platt, and Paul A. Viola. 2006. Multiple instance boosting for object detection. In Proceedings of the Conference on NIPS. 1417--1424. Google ScholarDigital Library
- Da Zhang, Hamid Maei, Xin Wang, and Yuan-Fang Wang. 2017. Deep reinforcement learning for visual object tracking in videos. CoRR. Retrieved from abs/1701.08936.Google Scholar
- Jiaqi Zhang, Yao Deng, Zhenhua Guo, and Youbin Chen. 2016. Face recognition using part-based dense sampling local features. Neurocomputing 184 (2016), 176--187. Google ScholarDigital Library
- Kaihua Zhang, Qingshan Liu, Yi Wu, and M. H. Yang. 2016. Robust visual tracking via convolutional networks without training. IEEE TIP 25, 4 (2016), 1779--1792.Google Scholar
- L. Zhang, J. Varadarajan, P. Suganthan, N. Ahuja, and P. Moulin. 2017. Robust tracking using oblique random forests. In Proceedings of the CVPR. IEEE.Google Scholar
- M. Zhang, J. Xing, J. Gao, and W. Hu. 2015. Robust visual tracking using joint scale-spatial correlation filters. In Proceedings of the ICIP. IEEE, 1468--1472.Google Scholar
- Mengdan Zhang, Junliang Xing, Jin Gao, Xinchu Shi, Qiang Wang, and Weiming Hu. 2015. Joint scale-spatial correlation tracking with adaptive rotation estimation. In Proceedings of the ICCVW. IEEE, 32--40. Google ScholarDigital Library
- S. Zhang, H. Yao, X. Sun, and X. Lu. 2013. Sparse coding based visual tracking: Review and experimental comparison. PR 46, 7 (2013), 1772--1788. Google ScholarDigital Library
- T. Zhang, B. Ghanem, S. Liu, and N. Ahuja. 2012. Robust visual tracking via multi-task sparse learning. In Proceedings of the CVPR. IEEE, 2042--2049. Google ScholarDigital Library
- T. Zhang, B. Ghanem, S. Liu, C. Xu, and N. Ahuja. 2016. Robust tracking via exclusive context modeling. IEEE TC 46, 1 (2016), 51--63.Google Scholar
- T. Zhang, K. Jia, C. Xu, Y. Ma, and N. Ahuja. 2014. Partial occlusion handling for tracking via robust part matching. In Proceedings of the CVPR. IEEE. Google ScholarDigital Library
- T. Zhang, S. Liu, N. Ahuja, M. H. Yang, and B. Ghanem. 2015. Robust tracking via consistent low-rank sparse learning. IJCV 111, 2 (2015), 171--190. Google ScholarDigital Library
- T. Zhang, S. Liu, C. Xu, S. Yan, B. Ghanem, N. Ahuja, and M. H. Yang. 2015. Structural sparse tracking. In Proceedings of the CVPR. IEEE, 150--158.Google Scholar
- T. Zhang, C. Xu, and M. H. Yang. 2017. Multi-task correlation particle filter for robust object tracking. In Proceedings of the CVPR. IEEE, 4819--4827.Google Scholar
- Tianzhu Zhang, Changsheng Xu, and Ming-Hsuan Yang. 2019. Robust structural sparse tracking. IEEE TPAMI 41, 2 (2019), 473--486.Google ScholarDigital Library
- Wei Zhong, Huchuan Lu, and M. H. Yang. 2012. Robust object tracking via sparsity-based collaborative model. In Proceedings of the CVPR. IEEE. Google ScholarDigital Library
- B. Zhuang, L. Wang, and H. Lu. 2016. Visual tracking via shallow and deep collaborative model. Neurocomputing 218 (2016), 61--71. Google ScholarDigital Library
Index Terms
- Handcrafted and Deep Trackers: Recent Visual Object Tracking Approaches and Trends
Recommendations
Cooperative object tracking using dual‐pan–tilt–zoom cameras based on planar ground assumption
Pan–tilt–zoom (PTZ) cameras play an important role in visual surveillance system. Dual‐PTZ camera system is the simplest and most typical one. The superiority of this system lies in that it can obtain both large‐view information and high‐resolution local‐...
Recent advances on multicue object tracking: a survey
The performance of single cue object tracking algorithms may degrade due to complex nature of visual world and environment challenges. In recent past, multicue object tracking methods using single or multiple sensors such as vision, thermal, infrared, ...
Intelligent video surveillance system: 3-tier context-aware surveillance system with metadata
This paper presents an intelligent video surveillance system with the metadata rule for the exchange of analyzed information. We define the metadata rule for the exchange of analyzed information between intelligent video surveillance systems that ...
Comments