10 April 2018 Robust visual tracking via multiple discriminative models with object proposals
Author Affiliations +
Proceedings Volume 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017); 106153X (2018) https://doi.org/10.1117/12.2302921
Event: Ninth International Conference on Graphic and Image Processing, 2017, Qingdao, China
Abstract
Model drift is an important reason for tracking failure. In this paper, multiple discriminative models with object proposals are used to improve the model discrimination for relieving this problem. Firstly, the target location and scale changing are captured by lots of high-quality object proposals, which are represented by deep convolutional features for target semantics. And then, through sharing a feature map obtained by a pre-trained network, ROI pooling is exploited to wrap the various sizes of object proposals into vectors of the same length, which are used to learn a discriminative model conveniently. Lastly, these historical snapshot vectors are trained by different lifetime models. Based on entropy decision mechanism, the bad model owing to model drift can be corrected by selecting the best discriminative model. This would improve the robustness of the tracker significantly. We extensively evaluate our tracker on two popular benchmarks, the OTB 2013 benchmark and UAV20L benchmark. On both benchmarks, our tracker achieves the best performance on precision and success rate compared with the state-of-the-art trackers.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Yuanqiang Zhang, Yuanqiang Zhang, Duyan Bi, Duyan Bi, Yufei Zha, Yufei Zha, Huanyu Li, Huanyu Li, Tao Ku, Tao Ku, Min Wu, Min Wu, Wenshan Ding, Wenshan Ding, Zunlin Fan, Zunlin Fan, } "Robust visual tracking via multiple discriminative models with object proposals", Proc. SPIE 10615, Ninth International Conference on Graphic and Image Processing (ICGIP 2017), 106153X (10 April 2018); doi: 10.1117/12.2302921; https://doi.org/10.1117/12.2302921
PROCEEDINGS
11 PAGES


SHARE
Back to Top