UAV Complex-Scene Single-Target Tracking Based on Improved Re-Detection Staple Algorithm

被引:1
|
作者
Huang, Yiqing [1 ,2 ]
Huang, He [1 ,2 ]
Niu, Mingbo [3 ]
Miah, Md Sipon [3 ,4 ]
Wang, Huifeng [1 ]
Gao, Tao [5 ]
机构
[1] Changan Univ, Sch Elect & Control Engn, Xian 710064, Peoples R China
[2] Changan Univ, Xian Key Lab Intelligent Expressway Informat Fus &, Xian 710064, Peoples R China
[3] Changan Univ, IVR Low Carbon Res Inst, Sch Energy & Elect Engn, Xian 710064, Peoples R China
[4] Univ Carlos III Madrid, Dept Signal Theory & Commun, Madrid 28903, Spain
[5] Changan Univ, Sch Informat Engn, Xian 710064, Peoples R China
关键词
moth-flame optimization; re-detection; remote sensing; staple; target tracking; MOTH-FLAME OPTIMIZATION; CORRELATION FILTER; OBJECT;
D O I
10.3390/rs16101768
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
With the advancement of remote sensing technology, the demand for the accurate monitoring and tracking of various targets utilizing unmanned aerial vehicles (UAVs) is increasing. However, challenges such as object deformation, motion blur, and object occlusion during the tracking process could significantly affect tracking performance and ultimately lead to tracking drift. To address this issue, this paper introduces a high-precision target-tracking method with anomaly tracking status detection and recovery. An adaptive feature fusion strategy is proposed to improve the adaptability of the traditional sum of template and pixel-wise learners (Staple) algorithm to changes in target appearance and environmental conditions. Additionally, the Moth Flame Optimization (MFO) algorithm, known for its strong global search capability, is introduced as a re-detection algorithm in case of tracking failure. Furthermore, a trajectory-guided Gaussian initialization technique and an iteration speed update strategy are proposed based on sexual pheromone density to enhance the tracking performance of the introduced re-detection algorithm. Comparative experiments conducted on UAV123 and UAVDT datasets demonstrate the excellent stability and robustness of the proposed algorithm.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Target Re-detection and Tracking Based on Correlated Filter
    Wu, Yuqiu
    Li, Zhaohui
    Li, Dongmei
    PROCEEDINGS OF 2018 14TH IEEE INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING (ICSP), 2018, : 359 - 362
  • [2] Research on Motion Target Detection and Tracking Algorithm Based on Complex Scene
    Jin Xue-lian
    Yang Jian-hua
    Lu Wei
    2018 37TH CHINESE CONTROL CONFERENCE (CCC), 2018, : 3537 - 3540
  • [3] Long-time target tracking algorithm based on re-detection multi-feature fusion
    Qu, Junsuo
    Tang, Chenxue
    Zhang, Yuan
    Zhou, Kai
    Razi, Abolfazl
    IET CYBER-SYSTEMS AND ROBOTICS, 2022, 4 (01) : 38 - 50
  • [4] Long-term Tracking Algorithm Based on Dimensionality Reduction and Re-Detection
    Xia L.
    Zhang Y.
    Huang Y.
    Jia H.
    Zhang, Ya (zhangya@aust.edu.cn), 1600, Institute of Computing Technology (33): : 385 - 394
  • [5] Vision Based Target Tracking Algorithm in Natural Complex Scene
    Chang, Faliang
    Wang, Xiaolin
    Han, Jie
    Liu, Xue
    ICNC 2008: FOURTH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 6, PROCEEDINGS, 2008, : 213 - 217
  • [6] Long-term stable target tracking algorithm based on improved Staple
    Liao, Haoyu
    Li, Le
    Bai, Yongqiang
    2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 7094 - 7099
  • [7] Pedestrian target tracking of UAV platform based on improved TLD algorithm
    Zhou Bin
    Jin Ali
    Zhang Yu
    Zhang Yudi
    Zhao Mingdong
    AOPC 2022: OPTICAL SENSING, IMAGING, AND DISPLAY TECHNOLOGY, 2022, 12557
  • [8] An Improved Target Tracking Algorithm Based on Extended Kalman Filter for UAV
    Li, Yibing
    Jiu, Mingyang
    Sun, Qian
    Wang, Yansong
    PROCEEDINGS OF THE 2018 IEEE 7TH ASIA-PACIFIC CONFERENCE ON ANTENNAS AND PROPAGATION (APCAP), 2018, : 435 - 437
  • [9] Pedestrian target tracking of UAV platform based on improved TLD algorithm
    Zhou Bin
    Jin Ali
    Zhang Yu
    Zhang Yudi
    Zhao Mingdong
    INTERNATIONAL CONFERENCE ON OPTICAL AND PHOTONIC ENGINEERING, ICOPEN 2022, 2022, 12550
  • [10] Small-Target Complex-Scene Detection Method Based on Information Interworking High-Resolution Network
    Fu, Yongzhong
    Li, Xiufeng
    Hu, Zungang
    SENSORS, 2021, 21 (15)