The Community for Technology Leaders
2018 24th International Conference on Pattern Recognition (ICPR) (2018)
Beijing, China
Aug. 20, 2018 to Aug. 24, 2018
ISSN: 1051-4651
ISBN: 978-1-5386-3789-0
pp: 1676-1682
Min Wu , Aeronautics and Astronautics Engineering College, Air Force Engineering University
Yufei Zha , Aeronautics and Astronautics Engineering College, Air Force Engineering University
Yuanqiang Zhang , Aeronautics and Astronautics Engineering College, Air Force Engineering University
Tao Ku , Aeronautics and Astronautics Engineering College, Air Force Engineering University
Lichao Zhang , Aeronautics and Astronautics Engineering College, Air Force Engineering University
Bin Chen , Aeronautics and Astronautics Engineering College, Air Force Engineering University
ABSTRACT
Similarity algorithms determine the location of the target by the similarity between the template and the candidate, the most similar candidate to the template is considered as the target in visual tracking. Similarity algorithms search the most similar candidate to the template as the current estimation for visual object. In practice, most trackers only take usage of the intra-class similarity, yet the inter-class semantic separability is ignored. In this paper, a joint identification-verification model is proposed to learn the similarity with the category attribute for visual tracking. This approach constructs the cost function both on the inter-class semantic separability and intra-class similarity, firstly. Then, the training dataset is fed into the network. To the end, the discriminative features are learned in the embedding space. During tracking phase, the template and candidates are fed into the network simultaneously. Thereforce, the target will be located correctly by the similarity metric between the template and candidates in the learned embedding space. We evaluate the proposed approach on the open benchmark: OTB50 and UAV123 dataset. A large number of experimental results show that the inter-class semantic separability can increase the discrimination for the similar distractors effectively, and bootstrap the tracking performances of the trackers based on the similarity learning.
INDEX TERMS
Target tracking, Visualization, Feature extraction, Semantics, Training, Neural networks
CITATION

M. Wu, Y. Zha, Y. Zhang, T. Ku, L. Zhang and B. Chen, "Joint Identification-Verification Model for Visual Tracking," 2018 24th International Conference on Pattern Recognition (ICPR), Beijing, China, 2018, pp. 1676-1682.
doi:10.1109/ICPR.2018.8545204
188 ms
(Ver 3.3 (11022016))