Abstract
Occlusion is known as one of the most challenging factors in long-term tracking because of its unpredictable shape. Existing works devoted into the design of loss functions, training strategies or model architectures, which are considered to have not directly touched the key point. Alternatively, we came up with a direct and natural idea that is discarding things that covers the target. We propose a novel occluder-aware representation learning framework to develop this idea. First, we design a local occluders detection module (LODM) to localize the occluders, which works on the principle that discriminates the non-noumenal part from a target based on the general knowledge of this category. An extra dataset and a clustering strategy is proposed to support this general knowledge. Second, we devise a feature reconstruction module to guide the occluder-aware representation learning. With the help of above methods, our localizing occluders tracker, called LOTracker, can learn an occluder-free representation and promote the performance that tracks with occlusion scenarios. Extensive experimental results show that our LOTracker achieves a state-of-the-art performance in multiple benchmarks such as LaSOT, VOTLT2018, VOTLT2019, and OxUvALT.
- [1] . 2016. Fully-convolutional Siamese networks for object tracking. In ECCV 2016, Vol. 9914. 850–865. Google Scholar
Cross Ref
- [2] . 2019. Learning discriminative model prediction for tracking. In Proc. ICCV.Google Scholar
- [3] . 2006. High toughness high hardness iron based PTAW weld materials. Materials Science and Engineering: A 428, 1 (2006), 116–123. Google Scholar
Cross Ref
- [4] . [n.d.]. AdderNet: Do we really need multiplications in deep learning?. In CVPR 2019.Google Scholar
- [5] . 2020. High-performance long-term tracking with meta-updater. In Proc. CVPR.Google Scholar
- [6] . [n.d.]. ECO: Efficient convolution operators for tracking. In CVPR 2017.Google Scholar
- [7] . 2011. Guest editorial - Advances in people tracking. Pattern Recognition Letters 32, 6 (2011), 866. Google Scholar
Digital Library
- [8] . 2017. Improved regularization of convolutional neural networks with cutout. CoRR abs/1708.04552 (2017).
arxiv:1708.04552 http://arxiv.org/abs/1708.04552Google Scholar - [9] . 2019. LaSOT: A high-quality benchmark for large-scale single object tracking. In Proc. CVPR. 5374–5383.Google Scholar
- [10] . 2019. GOT-10k: A large high-diversity benchmark for generic object tracking in the wild. IEEE Trans. Pattern Anal. Mach. Intell. (2019), 1–1. Google Scholar
Cross Ref
- [11] . 2020. GlobalTrack: A simple and strong baseline for long-term tracking. In Proc. AAAI.Google Scholar
- [12] . 2012. Tracking-learning-detection. IEEE Trans.Pattern Anal. Mach. Intell. 34, 7 (2012), 1409–1422. Google Scholar
Digital Library
- [13] . 2020. Compositional convolutional neural networks: A deep architecture with innate robustness to partial occlusion. In Proc. CVPR.Google Scholar
- [14] . 2019. Localizing occluders with compositional convolutional networks. In Proc. ICCV Workshops.Google Scholar
- [15] Matej Kristan, Jiri Matas, Ales Leonardis, Michael Felsberg, Roman Pflugfelder, Joni-Kristian Kamarainen, Luka Cehovin Zajc, Ondrej Drbohlav, Alan Lukezic, Amanda Berg, Abdelrahman Eldesokey, Jani Kapyla, Gustavo Fernandez, Abel Gonzalez-Garcia, Alireza Memarmoghadam, Andong Lu, Anfeng He, Anton Varfolomieiev, Antoni Chan, Ardhendu Shekhar Tripathi, Arnold Smeulders, Bala Suraj Pedasingu, Bao Xin Chen, Baopeng Zhang, Baoyuan Wu, Bi Li, Bin He, Bin Yan, Bing Bai, Bing Li, Bo Li, Byeong Hak Kim, and Byeong Hak Ki. The seventh visual object tracking VOT2019 challenge results. In Proc. ICCV.Google Scholar
- [16] . 2011. Learning occlusion with likelihoods for visual tracking. In Proc. ICCV. IEEE, 1551–1558.Google Scholar
- [17] . 2015. On-road pedestrian tracking across multiple driving recorders. IEEE Trans.Multimedia 17, 9 (2015), 1–1.Google Scholar
Digital Library
- [18] . 2019. SiamRPN++: Evolution of Siamese visual tracking with very deep networks. In Proc. CVPR.Google Scholar
- [19] . 2014. Microsoft COCO: Common objects in context. International Journal of Computer Vision (2014).Google Scholar
- [20] . 2018. FuCoLoT - A fully-correlational long-term tracker. In Proc. ACCV.Google Scholar
- [21] . 2018. Now you see me: Evaluating performance in long-term visual tracking. CoRR abs/1804.07056 (2018).
arxiv:1804.07056 http://arxiv.org/abs/1804.07056.Google Scholar - [22] . 2015. Long-term correlation tracking. In Proc. CVPR. IEEE Computer Society, 5388–5396. Google Scholar
Cross Ref
- [23] . [n.d.]. Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural network. In CVPR 2016.Google Scholar
- [24] . 2015. Clustering of static-adaptive correspondences for deformable object tracking. In Proc. CVPR. IEEE Computer Society, 2784–2791. Google Scholar
Cross Ref
- [25] . 2010. Multiple and variable target visual tracking for video-surveillance applications. Pattern Recognit. Lett. 31, 12 (2010), 1577–1590. Google Scholar
Digital Library
- [26] . 2015. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 3 (2015), 211–252. Google Scholar
Digital Library
- [27] . [n.d.]. Multiple people tracking by lifted multicut and person re-identification. In CVPR 2017.Google Scholar
- [28] . 2017. Robust visual tracking via collaborative motion and appearance model. IEEE Transactions on Industrial Informatics 13, 5 (2017), 2251–2259. Google Scholar
Cross Ref
- [29] . 2018. Long-term tracking in the wild: A benchmark. In Proceedings of the European Conference on Computer Vision (ECCV). 670–685.Google Scholar
Digital Library
- [30] . 2018. Long-term tracking in the wild: A benchmark. CoRR abs/1803.09502 (2018).
arXiv:1803.09502 http://arxiv.org/abs/1803.09502.Google Scholar - [31] . [n.d.]. SINT++: Robust visual tracking via adversarial positive instance generation. In CVPR 2018.Google Scholar
- [32] . 2018. Repulsion loss: Detecting pedestrians in a crowd.
arxiv:1711.07752 [cs.CV]Google Scholar - [33] . 2019. ‘Skimming-perusal’ tracking: A framework for real-time and robust long-term tracking. In Proc. ICCV.Google Scholar
- [34] . 2014. Partial occlusion handling for visual tracking via robust part matching. In Proc.CVPR. 1258–1265.Google Scholar
- [35] . 2018. Learning regression and verification networks for long-term visual tracking. CoRR abs/1809.04320 (2018).
arXiv:1809.04320 http://arxiv.org/abs/1809.04320Google Scholar - [36] . 2018. Distractor-aware Siamese networks for visual object tracking. CoRR abs/1808.06048 (2018).
arXiv:1808.06048 http://arxiv.org/abs/1808.06048.Google Scholar
Index Terms
Robust Long-Term Tracking via Localizing Occluders
Recommendations
Robust object tracking via multi-cue fusion
A long-term object tracking method based on calibrated binocular cameras by fusing information of the two channels and binocular geometry constraints is proposed.The stereo filter which is built based on the epipolar geometry of the binocular cameras is ...
Long-Term Tracking through Failure Cases
ICCVW '13: Proceedings of the 2013 IEEE International Conference on Computer Vision WorkshopsLong term tracking of an object, given only a single instance in an initial frame, remains an open problem. We propose a visual tracking algorithm, robust to many of the difficulties which often occur in real-world scenes. Correspondences of edge-based ...
Robust tracking with adaptive appearance learning and occlusion detection
It is still challenging to design a robust and efficient tracking algorithm in complex scenes. We propose a new object tracking algorithm with adaptive appearance learning and occlusion detection in an efficient self-tuning particle filter framework. ...






Comments