Tracker Meets Night: A Transformer Enhancer for UAV Tracking

被引:31
作者
Ye, Junjie [1 ]
Fu, Changhong [1 ]
Cao, Ziang [2 ]
An, Shan [3 ]
Zheng, Guangze [1 ]
Li, Bowen [1 ]
机构
[1] Tongji Univ, Sch Mech Engn, Shanghai 201804, Peoples R China
[2] Tongji Univ, Sch Automot Studies, Shanghai 201804, Peoples R China
[3] JD COM Inc, Tech & Data Ctr, Beijing 100108, Peoples R China
基金
中国国家自然科学基金;
关键词
Transformers; Task analysis; Feature extraction; Autonomous aerial vehicles; Visualization; Target tracking; Lighting; Aerial systems; applications; deep learning for visual perception; data sets for robotic vision; low-light enhancement; nighttime tracking; spatial-channel transformer; LIGHT;
D O I
10.1109/LRA.2022.3146911
中图分类号
TP24 [机器人技术];
学科分类号
080202 ; 1405 ;
摘要
Most previous progress in object tracking is realized in daytime scenes with favorable illumination. State-of-the-arts can hardly carry on their superiority at night so far, thereby considerably blocking the broadening of visual tracking-related unmanned aerial vehicle (UAV) applications. To realize reliable UAV tracking at night, a spatial-channel Transformer-based low-light enhancer (namely SCT), which is trained in a novel task-inspired manner, is proposed and plugged prior to tracking approaches. To achieve semantic-level low-light enhancement targeting the high-level task, the novel spatial-channel attention module is proposed to model global information while preserving local context. In the enhancement process, SCT denoises and illuminates nighttime images simultaneously through a robust non-linear curve projection. Moreover, to provide a comprehensive evaluation, we construct a challenging nighttime tracking benchmark, namely DarkTrack2021, which contains 110 challenging sequences with over 100 K frames in total. Evaluations on both the public UAVDark135 benchmark and the newly constructed DarkTrack2021 benchmark show that the task-inspired design enables SCT with significant performance gains for nighttime UAV tracking compared with other top-ranked low-light enhancers. Real-world tests on a typical UAV platform further verify the practicability of the proposed approach. The DarkTrack2021 benchmark and the code of the proposed approach are publicly available at https://github.com/vision4robotics/SCT.
引用
收藏
页码:3866 / 3873
页数:8
相关论文
共 38 条
[1]   Fully-Convolutional Siamese Networks for Object Tracking [J].
Bertinetto, Luca ;
Valmadre, Jack ;
Henriques, Joao F. ;
Vedaldi, Andrea ;
Torr, Philip H. S. .
COMPUTER VISION - ECCV 2016 WORKSHOPS, PT II, 2016, 9914 :850-865
[2]   Learning Discriminative Model Prediction for Tracking [J].
Bhat, Goutam ;
Danelljan, Martin ;
Van Gool, Luc ;
Timofte, Radu .
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, :6181-6190
[3]   HiFT: Hierarchical Feature Transformer for Aerial Tracking [J].
Cao, Ziang ;
Fu, Changhong ;
Ye, Junjie ;
Li, Bowen ;
Li, Yiming .
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, :15437-15446
[4]   Pre-Trained Image Processing Transformer [J].
Chen, Hanting ;
Wang, Yunhe ;
Guo, Tianyu ;
Xu, Chang ;
Deng, Yiping ;
Liu, Zhenhua ;
Ma, Siwei ;
Xu, Chunjing ;
Xu, Chao ;
Gao, Wen .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :12294-12305
[5]   Transformer Tracking [J].
Chen, Xin ;
Yan, Bin ;
Zhu, Jiawen ;
Wang, Dong ;
Yang, Xiaoyun ;
Lu, Huchuan .
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021, 2021, :8122-8131
[6]   Probabilistic Regression for Visual Tracking [J].
Danelljan, Martin ;
Van Gool, Luc ;
Timofte, Radu .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2020, :7181-7190
[7]  
Dosovitskiy A., 2021, INT C LEARNING REPRE
[8]   On the Visual-Based Safe Landing of UAVs in Populated Areas: A Crucial Aspect for Urban Deployment [J].
Gonzalez-Trejo, Javier ;
Mercado-Ravell, Diego ;
Becerra, Israel ;
Murrieta-Cid, Rafael .
IEEE ROBOTICS AND AUTOMATION LETTERS, 2021, 6 (04) :7902-7909
[9]   LIME: Low-Light Image Enhancement via Illumination Map Estimation [J].
Guo, Xiaojie ;
Li, Yu ;
Ling, Haibin .
IEEE TRANSACTIONS ON IMAGE PROCESSING, 2017, 26 (02) :982-993
[10]   Multi-Scale Progressive Fusion Network for Single Image Deraining [J].
Jiang, Kui ;
Wang, Zhongyuan ;
Yi, Peng ;
Chen, Chen ;
Huang, Baojin ;
Luo, Yimin ;
Ma, Jiayi ;
Jiang, Junjun .
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2020), 2020, :8343-8352