TY - GEN
T1 - Siamese Anchor Proposal Network for High-Speed Aerial Tracking
AU - Fu, Changhong
AU - Cao, Ziang
AU - Li, Yiming
AU - Ye, Junjie
AU - Feng, Chen
N1 - Funding Information:
This work is supported by the National Natural Science Foundation of China (No. 61806148) and the Natural Science Foundation of Shanghai (No. 20ZR1460100).
Publisher Copyright:
© 2021 IEEE
PY - 2021
Y1 - 2021
N2 - In the domain of visual tracking, most deep learning-based trackers highlight the accuracy but casting aside efficiency. Therefore, their real-world deployment on mobile platforms like the unmanned aerial vehicle (UAV) is impeded. In this work, a novel two-stage Siamese network-based method is proposed for aerial tracking, i.e., stage-1 for high-quality anchor proposal generation, stage-2 for refining the anchor proposal. Different from anchor-based methods with numerous pre-defined fixed-sized anchors, our no-prior method can 1) increase the robustness and generalization to different objects with various sizes, especially to small, occluded, and fast-moving objects, under complex scenarios in light of the adaptive anchor generation, 2) make calculation feasible due to the substantial decrease of anchor numbers. In addition, compared to anchor-free methods, our framework has better performance owing to refinement at stage-2. Comprehensive experiments on three benchmarks have proven the superior performance of our approach, with a speed of ∼200 frames/s.
AB - In the domain of visual tracking, most deep learning-based trackers highlight the accuracy but casting aside efficiency. Therefore, their real-world deployment on mobile platforms like the unmanned aerial vehicle (UAV) is impeded. In this work, a novel two-stage Siamese network-based method is proposed for aerial tracking, i.e., stage-1 for high-quality anchor proposal generation, stage-2 for refining the anchor proposal. Different from anchor-based methods with numerous pre-defined fixed-sized anchors, our no-prior method can 1) increase the robustness and generalization to different objects with various sizes, especially to small, occluded, and fast-moving objects, under complex scenarios in light of the adaptive anchor generation, 2) make calculation feasible due to the substantial decrease of anchor numbers. In addition, compared to anchor-free methods, our framework has better performance owing to refinement at stage-2. Comprehensive experiments on three benchmarks have proven the superior performance of our approach, with a speed of ∼200 frames/s.
UR - http://www.scopus.com/inward/record.url?scp=85109863391&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85109863391&partnerID=8YFLogxK
U2 - 10.1109/ICRA48506.2021.9560756
DO - 10.1109/ICRA48506.2021.9560756
M3 - Conference contribution
AN - SCOPUS:85109863391
T3 - Proceedings - IEEE International Conference on Robotics and Automation
SP - 510
EP - 516
BT - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE International Conference on Robotics and Automation, ICRA 2021
Y2 - 30 May 2021 through 5 June 2021
ER -