High speed long-term visual object tracking algorithm for real robot systems

被引:16
作者
Jiang, Muxi [1 ]
Li, Rui [1 ]
Liu, Qisheng [1 ]
Shi, Yingjing [1 ]
Tlelo-Cuautle, Esteban [2 ]
机构
[1] Univ Elect Sci & Technol China, Sch Automat Engn, Chengdu, Peoples R China
[2] INAOE, Dept Elect, Luis Enrique Erro 1, Mexico City 72840, DF, Mexico
基金
中国国家自然科学基金;
关键词
Long-term UAV tracking; Correlation filter; Drift correction; Target relocate; LOCALIZATION; FEATURES;
D O I
10.1016/j.neucom.2020.12.113
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Although many visual tracking algorithms have made many achievements in video sequences, they have not been confirmed to work well on the real robot systems with the unpredictable changes and limited computing capabilities. In order to face the complex practical conditions, including huge scale variation, occlusion and long-term task, this paper develops a CF-based long-term tracking algorithm. The main strategies are as follows. A novel confidence score is proposed to judge tracking reliability, and the track-ing drift is corrected to keep the target's long-term appearance. Furthermore, once the target is lost, it can be relocated by the multi-scale search. Our tracker performs favorably against other CF-based trackers with strong engineering applicability. Finally, experiments on the datasets and an UAV are carried out to verify the effectiveness for real robot systems.
引用
收藏
页码:268 / 284
页数:17
相关论文
共 50 条
[21]   RGB-T long-term tracking algorithm via local sampling and global proposals [J].
Jun, Liu ;
Luo Zhongqiang ;
Xiong Xingzhong .
SIGNAL IMAGE AND VIDEO PROCESSING, 2022, 16 (08) :2221-2229
[22]   RGB-T long-term tracking algorithm via local sampling and global proposals [J].
Liu Jun ;
Luo Zhongqiang ;
Xiong Xingzhong .
Signal, Image and Video Processing, 2022, 16 :2221-2229
[23]   Event-Driven Stereo Visual Tracking Algorithm to Solve Object Occlusion [J].
Camunas-Mesa, Luis A. ;
Serrano-Gotarredona, Teresa ;
Ieng, Sio-Hoi ;
Benosman, Ryad ;
Linares-Barranco, Bernabe .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2018, 29 (09) :4223-4237
[24]   Visual Object Tracking Algorithm Based on Hard Negative Mining and Adaptive Temporal Regularization [J].
Huang Y. ;
Li X. ;
Qi N. ;
Lu R. ;
Zhang S. .
Jiqiren/Robot, 2021, 43 (03) :350-363
[25]   Visual Tracking With Long-Short Term Based Correlation Filter [J].
Yang, Yuxiang ;
Xing, Weiwei ;
Zhang, Shunli ;
Gao, Limin ;
Yu, Qi ;
Che, Xiaoping ;
Lu, Wei .
IEEE ACCESS, 2020, 8 :20257-20269
[26]   Aerial Infrared Object Tracking via an improved Long-term Correlation Filter with optical flow estimation and SURF matching [J].
Wang, Xiaotian ;
Zhang, Kai ;
Zhang, Ximing ;
Li, Shaoyi ;
Yan, Jie .
INFRARED PHYSICS & TECHNOLOGY, 2021, 116
[27]   Long-term multiobject tracking using alternative correlation filters [J].
Baskurt, Kemal Batuhan ;
Samet, Refik .
TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, 2018, 26 (05) :2246-2259
[28]   Long-Term Target Tracking for UAV Based on Correlation Filter [J].
Xiao, Qiao ;
Zhang, Qinyu ;
Wu, Boqian ;
Han, Xiao ;
Wu, Xi .
COMMUNICATIONS, SIGNAL PROCESSING, AND SYSTEMS, 2019, 463 :2678-2685
[29]   Visual saliency detection approach for long-term ECG analysis [J].
Mukhopadhyay, Sourav Kumar ;
Krishnan, Sridhar .
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE, 2022, 213
[30]   A location-aware siamese network for high-speed visual tracking [J].
Zhou, Lifang ;
Ding, Xiang ;
Li, Weisheng ;
Leng, Jiaxu ;
Lei, Bangjun ;
Yang, Weibin .
APPLIED INTELLIGENCE, 2023, 53 (04) :4431-4447