{"type":"ScholarlyArticle","title":"Unsupervised Learning based Jump-Diffusion Process for Object Tracking in Video Surveillance","authors":[{"name":"Xiaobai Liu","slug":"xiaobai-liu","given":"Xiaobai","family":"Liu","affiliation":"San Diego State University , San Diego , CA; XreLab Inc. , San Diego , CA"},{"name":"Donovan Lo","slug":"donovan-lo","given":"Donovan","family":"Lo","affiliation":"San Diego State University , San Diego , CA"},{"name":"Chau Thuan","slug":"chau-thuan","given":"Chau","family":"Thuan","affiliation":"San Diego State University , San Diego , CA"}],"abstract":"This paper presents a principled way for dealing with occlusions in visual tracking which is a long-standing issue in computer vision but largely remains unsolved. As the major innovation, we develop a learning-based jump-diffusion process to jointly track object locations  and estimate their visibility statuses over time. Our method employs in particular a set of jump dynamics to change object's visibility statuses and a set of diffusion dynamics to track objects in videos. Different from the traditional jump-diffusion process that stochastically generates dynamics, we utilize deep policy functions to determine the best dynamic at the present step and learn the optimal policies from raw videos using reinforcement learning methods.Our method is capable of tracking objects with severe occlusions in crowded scenes and thus recovers the complete trajectories of objects that undergo multiple interactions with others. We evaluate the proposed method on challenging video sequences and compare it to alternative methods. Significant improvements are obtained particularly for the videos including frequent interactions or occlusions.","doi":"10.24963/ijcai.2018/702","url":"https://ijcai.org/proceedings/2018/702","pdf":"https://ijcai.org/proceedings/2018/0702.pdf","markdown":"https://ijcai.org/proceedings/2018/702.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/702","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Uncertainty in AI","track":"Main track","number":702,"pages":{"first":5060,"last":5066},"keywords":["Computer Vision: Motion and Tracking","Uncertainty in AI: Bayesian Networks","Computer Vision: Statistical Methods and Machine Learning"],"videos":[],"references":[{"position":1,"raw":"[Andriyenko et al., 2012] Anton Andriyenko, Konrad Schindler, and Stefan Roth. Discrete-continuous opti- mization for multi-target tracking. In IEEE Conference on Computer Vision and Pattern Recognition, 2012.","title":"Discrete-continuous optimization for multi-target tracking","authors":"Anton Andriyenko, Konrad Schindler, Stefan Roth","year":"2012","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Berclaz et al., 2011] Jerome Berclaz, Francois Fleuret, En- gin Turetken, and Pascal Fua. Multiple object tracking using k-shortest paths optimization. IEEE transactions on pattern analysis and machine intelligence, 33(9):1806- 1819, 2011.","title":"Multiple object tracking using k-shortest paths optimization","authors":"Jerome Berclaz, Francois Fleuret, Engin Turetken, Pascal Fua","year":"2011","venue":"IEEE transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Caicedo and Lazebnik, 2015] Juan C Caicedo and Svetlana Lazebnik. Active object localization with deep reinforce- ment learning. In Proceedings of the IEEE International Conference on Computer Vision, pages 2488-2496, 2015.","title":"Active object localization with deep reinforcement learning","authors":"Lazebnik ; ] Caicedo, C Juan, Svetlana Caicedo, Lazebnik","year":"2015","venue":"Proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Deng et al., 2009] Jia Deng, Wei Dong, Richard Socher, Li- Jia Li, Kai Li, and Li Fei-Fei. Imagenet: A large-scale hierarchical image database. In Computer Vision and Pat- tern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 248-255. IEEE, 2009.","title":"Imagenet: A large-scale hierarchical image database","authors":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, Li Fei-Fei","year":"2009","venue":"Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ess et al., 2009] Andreas Ess, Konrad Schindler, Bastian Leibe, and Luc Van Gool. Improved multi-person tracking with active occlusion handling. In IEEE ICRA Workshop, 2009.","title":"Improved multi-person tracking with active occlusion handling","authors":"Andreas Ess, Konrad Schindler, Bastian Leibe, Luc Van Gool","year":"2009","venue":"IEEE ICRA Workshop","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ferryman and Shahrokni, 2009] James T Ferryman and Ali Shahrokni. Pets2009: Dataset and challenge. In IEEE International Workshop on Performance Evaluation of Tracking and Surveillance, 2009.","title":"Pets2009: Dataset and challenge","authors":"T James, Ali Ferryman, Shahrokni","year":"2009","venue":"IEEE International Workshop on Performance Evaluation of Tracking and Surveillance","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fleuret et al., 2008] Francois Fleuret, Jerome Berclaz, Richard Lengagne, and Pascal Fua. Multicamera people tracking with a probabilistic occupancy map. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 30(2):267-282, 2008.","title":"Multicamera people tracking with a probabilistic occupancy map","authors":"Francois Fleuret, Jerome Berclaz, Richard Lengagne, Pascal Fua","year":"2008","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Geiger et al., 2012] Andreas Geiger, Philip Lenz, and Raquel Urtasun. Are we ready for autonomous driving? the kitti vision benchmark suite. In IEEE Conference on Computer Vision and Pattern Recognition, 2012.","title":"Are we ready for autonomous driving? the kitti vision benchmark suite","authors":"Andreas Geiger, Philip Lenz, Raquel Urtasun","year":"2012","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Green, 1995] Peter J Green. Reversible jump markov chain monte carlo computation and bayesian model determina- tion. Biometrika, 82(4):711-732, 1995.","title":"Reversible jump markov chain monte carlo computation and bayesian model determination","authors":"J Peter, Green","year":"1995","venue":"Biometrika","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Grenander and Miller, 1994] Ulf Grenander and Michael I Miller. Representations of knowledge in complex systems. Journal of the Royal Statistical Society. Series B (Method- ological), pages 549-603, 1994.","title":"Representations of knowledge in complex systems","authors":"Miller Grenander, Ulf Grenander, Michael I Miller","year":"1994","venue":"Journal of the Royal Statistical Society. Series B (Methodological","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hamid Rezatofighi et al., 2015] Seyed Hamid Rezatofighi, Anton Milan, Zhen Zhang, Qinfeng Shi, Anthony Dick, and Ian Reid. Joint probabilistic data association revis- ited. In IEEE International Conference on Computer Vi- sion, 2015.","title":"Joint probabilistic data association revisited","authors":"Seyed Hamid Rezatofighi, Anton Milan, Zhen Zhang, Qinfeng Shi, Anthony Dick, Ian Reid","year":"2015","venue":"IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Han et al., 2004] Feng Han, Zhuowen Tu, and Song-Chun Zhu. Range image segmentation by an effective jump- diffusion method. IEEE Transactions on pattern analysis and machine intelligence, 26(9):1138-1153, 2004.","title":"Range image segmentation by an effective jumpdiffusion method","authors":"Han","year":"2004","venue":"IEEE Transactions on pattern analysis and machine intelligence","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Kasturi et al., 2009] Rangachar Kasturi, Dmitry Goldgof, Padmanabhan Soundararajan, Vasant Manohar, John Garofolo, Rachel Bowers, Matthew Boonstra, Valentina Korzhova, and Jing Zhang. Framework for performance evaluation of face, text, and vehicle detection and tracking in video: Data, metrics, and protocol. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(2):319- 336, 2009.","title":"Framework for performance evaluation of face, text, and vehicle detection and tracking in video: Data, metrics, and protocol","authors":"Kasturi","year":"2009","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Kim et al., 2015] Chanho Kim, Fuxin Li, Arridhana Cip- tadi, and James M Rehg. Multiple hypothesis tracking re- visited. In IEEE International Conference on Computer Vision, 2015.","title":"Multiple hypothesis tracking revisited","authors":"Kim","year":"2015","venue":"IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Leal-Taixé et al., 2014] Laura Leal-Taixé, Michele Fenzi, Alina Kuznetsova, Bodo Rosenhahn, and Silvio Savarese. Learning an image-based motion context for multiple peo- ple tracking. In IEEE Conference on Computer Vision and Pattern Recognition, 2014.","title":"Learning an image-based motion context for multiple people tracking","authors":"Laura Leal-Taixé, Michele Fenzi, Alina Kuznetsova, Bodo Rosenhahn, Silvio Savarese","year":"2014","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Milan et al., 2016] Anton Milan, Konrad Schindler, and Stefan Roth. Multi-target tracking by discrete-continuous energy minimization. IEEE Transactions on Pattern Anal- ysis and Machine Intelligence, 38(10):2054-2068, 2016.","title":"Multi-target tracking by discrete-continuous energy minimization","authors":"Anton Milan, Konrad Schindler, Stefan Roth","year":"2016","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Mnih et al., 2013] Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602, 2013.","title":"Playing atari with deep reinforcement learning","authors":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, Martin Riedmiller","year":"2013","venue":null,"doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Nam and Han, 2016] Hyeonseob Nam and Bohyung Han. Learning multi-domain convolutional neural networks for visual tracking. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4293- 4302, 2016.","title":"Hyeonseob Nam and Bohyung Han. Learning multi-domain convolutional neural networks for visual tracking","authors":"Nam, Han","year":"2016","venue":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pirsiavash et al., 2011] Hamed Pirsiavash, Deva Ramanan, and Charless C Fowlkes. Globally-optimal greedy algo- rithms for tracking a variable number of objects. In IEEE Conference on Computer Vision and Pattern Recognition, 2011.","title":"Globally-optimal greedy algorithms for tracking a variable number of objects","authors":"Hamed Pirsiavash, Deva Ramanan, Charless C Fowlkes","year":"2011","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Ren et al., 2015] Shaoqing Ren, Kaiming He, Ross Gir- shick, and Jian Sun. Faster r-cnn: Towards real-time object detection with region proposal networks. In Conference on Neural Information Processing Systems, 2015.","title":"Faster r-cnn: Towards real-time object detection with region proposal networks","authors":"Ren","year":"2015","venue":"Conference on Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Schaul et al., 2015] Tom Schaul, John Quan, Ioannis Antonoglou, and David Silver. Prioritized experience re- play. arXiv preprint arXiv:1511.05952, 2015.","title":"Prioritized experience replay","authors":"Tom Schaul, John Quan, Ioannis Antonoglou, David Silver","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Sutton and Barto, 1998] Richard S Sutton and Andrew G Barto. Reinforcement learning: An introduction, vol- ume 1. MIT press Cambridge, 1998.","title":"Reinforcement learning: An introduction","authors":"S Richard, Andrew G Sutton, Barto","year":"1998","venue":null,"doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Tang et al., 2014] Siyu Tang, Mykhaylo Andriluka, and Bernt Schiele. Detection and tracking of occluded people. International Journal of Computer Vision, 110(1):58-69, 2014.","title":"Detection and tracking of occluded people","authors":"Siyu Tang, Mykhaylo Andriluka, Bernt Schiele","year":"2014","venue":"International Journal of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Wang et al., 2016] Xinchao Wang, Engin Turetken, Fran- cois Fleuret, and Pascal Fua. Tracking interacting ob- jects using intertwined flows. IEEE Transaction on Pattern Analysis and Machine Intelligence, 38(11):2312-2326, 2016.","title":"Tracking interacting objects using intertwined flows","authors":"Wang","year":"2016","venue":"IEEE Transaction on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Williams, 1992] Ronald J Williams. Simple statistical gradient-following algorithms for connectionist reinforce- ment learning. Machine learning, 8(3-4):229-256, 1992.","title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","authors":"Williams Ronald","year":"1992","venue":"Machine learning","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wu et al., 2015] Yi Wu, Jongwoo Lim, and Ming-Hsuan Yang. Object tracking benchmark. IEEE Transactions on Pattern Analysis and Machine Intelligence, 37(9):1834- 1848, 2015.","title":"Object tracking benchmark","authors":"Yi Wu, Jongwoo Lim, Ming-Hsuan Yang","year":"2015","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Xiang et al., 2015] Yu Xiang, Alexandre Alahi, and Silvio Savarese. Learning to track: Online multi-object tracking by decision making. In IEEE International Conference on Computer Vision, 2015.","title":"Learning to track: Online multi-object tracking by decision making","authors":"Yu Xiang, Alexandre Alahi, Silvio Savarese","year":"2015","venue":"IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xu et al., 2013] Yuanlu Xu, Liang Lin, Wei-Shi Zheng, and Xiaobai Liu. Human re-identification by matching com- positional template with cluster sampling. In proceedings of the IEEE International Conference on Computer Vision, pages 3152-3159, 2013.","title":"Human re-identification by matching compositional template with cluster sampling","authors":"Yuanlu Xu, Liang Lin, Wei-Shi Zheng, Xiaobai Liu","year":"2013","venue":"proceedings of the IEEE International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xu et al., 2016] Yuanlu Xu, Xiaobai Liu, Yang Liu, and Song-Chun Zhu. Multi-view people tracking via hierarchi- cal trajectory composition. In IEEE Conference on Com- puter Vision and Pattern Recognition, 2016.","title":"Multi-view people tracking via hierarchical trajectory composition","authors":"Yuanlu Xu, Xiaobai Liu, Yang Liu, Song-Chun Zhu","year":"2016","venue":"IEEE Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Yilmaz et al., 2006] Alper Yilmaz, Omar Javed, and Mubarak Shah. Object tracking: A survey. Acm computing surveys (CSUR), 38(4):13, 2006.","title":"Object tracking: A survey","authors":"Alper Yilmaz, Omar Javed, Mubarak Shah","year":"2006","venue":"Acm computing surveys","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[Yoo et al., 2017] Sangdoo Yoo, Jongwon Yun, Youngjoon Choi, Kimin Yun, and Jin Young Choi. Action-decision networks for visual tracking with deep reinforcement learning. 2017.","title":"Action-decision networks for visual tracking with deep reinforcement learning","authors":"Yoo","year":"2017","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}