基于V-CSK视频遥感卫星运动目标检测跟踪方法

doi:10.7523/j.issn.2095-6134.2021.03.013

中国科学院大学学报 ›› 2021, Vol. 38 ›› Issue (3): 392-401.DOI: 10.7523/j.issn.2095-6134.2021.03.013

基于V-CSK视频遥感卫星运动目标检测跟踪方法

黄萍萍^1,2, 王峰¹, 向俞明^1,2, 尤红建^1,2

1. 中国科学院空天信息研究院中国科学院空间信息处理与应用系统技术重点实验室, 北京 100190;
2. 中国科学院大学, 北京 100049

收稿日期:2019-11-07 修回日期:2020-07-13 发布日期:2021-05-17
通讯作者: 黄萍萍
基金资助:
中国科学院前沿科学重点研究计划（ZDBS-LY-JSC036）和国家自然科学基金（61901439）资助

Moving target detection and tracking of satellite videos based on V-CSK algorithm

HUANG Pingping^1,2, WANG Feng¹, XIANG Yuming^1,2, YOU Hongjian^1,2

1. Key Laboratory of Spatial Information Processing and Application System of CAS, AeroSpace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China

Received:2019-11-07 Revised:2020-07-13 Published:2021-05-17

摘要/Abstract

摘要： 视频遥感卫星在道路交通导航、军事动态监视、目标跟踪等方面具有众多应用，因此利用卫星视频实现运动目标实时检测跟踪备受关注。针对卫星视频中的运动目标检测跟踪问题，提出基于V-CSK算法的检测跟踪方法，该算法采用改进的ViBe检测算法，引入多重自定义阈值滤波算法获得运动目标中心区域，再根据中心位置均值原理与噪声距离判断原则提取目标中心坐标，并实现轨迹曲线估计和修正，最后利用CSK算法实现目标跟踪。基于3组卫星视频数据进行实验，同时引入目标检测和跟踪的对比实验作为参照。实验结果表明，V-CSK算法在卫星视频运动目标检测跟踪中具有良好的性能。

关键词: 视频遥感卫星, 运动目标检测, 跟踪, ViBe算法, CSK算法

Abstract: Video remote sensing satellite has many applications in road traffic navigation, military dynamic monitoring, target tracking and so on, so the use of satellite video to achieve real-time detection and tracking of moving targets is of great concern. Aiming at the problem of moving target detection and tracking in satellite video, this paper proposes a detection and tracking method based on V-CSK algorithm, which adopts improved ViBe detection algorithm, introduces multiple custom threshold filtering algorithm to obtain the center area of moving target, and then extracts the center coordinates of target according to the principle of center position mean and noise distance judgment, and realizes the estimation and repair of track curve. Finally, the target tracking is realized by CSK algorithm. The experiment is based on three groups of satellite video data, and the contrast experiment of target detection and tracking is introduced as a reference. The experimental results show that V-CSK algorithm has good performance in satellite video moving target detection and tracking.

Key words: video remote sensing satellite, moving object detection, tracking, ViBe algorithm, CSK algorithm

中图分类号:

TP751

黄萍萍, 王峰, 向俞明, 尤红建. 基于V-CSK视频遥感卫星运动目标检测跟踪方法[J]. 中国科学院大学学报, 2021, 38(3): 392-401.

HUANG Pingping, WANG Feng, XIANG Yuming, YOU Hongjian. Moving target detection and tracking of satellite videos based on V-CSK algorithm[J]. Journal of University of Chinese Academy of Sciences, 2021, 38(3): 392-401.

参考文献

[1] 刘韬. 国外视频卫星发展研究[J]. 国际太空, 2014, 36(9):50-56.
[2] 张过. 卫星视频处理与应用进展[J]. 应用科学学报, 2016, 34(4):361-370.
[3] 朱厉洪, 回征, 任德锋, 等. 视频成像卫星发展现状与启示[J]. 卫星应用, 2015, 6(10):23-28.
[4] 何胜皎. 视频序列中运动目标检测算法的研究[D].兰州:兰州理工大学, 2018.
[5] 韩露. 基于航拍图像的目标检测系统设计与实现[D]. 北京:北京理工大学, 2015.
[6] 孟琭, 杨旭. 目标跟踪算法综述[J]. 自动化学报, 2019, 45(7):1244-1260.
[7] 葛宝义, 左宪章, 胡永江. 视觉目标跟踪方法研究综述[J]. 中国图象图形学报, 2018, 23(8):1091-1107.
[8] 袁益琴. 遥感卫星视频图像车辆动态信息提取方法研究[D]. 北京:中国科学院大学(中国科学院遥感与数字地球研究所), 2017.
[9] Meng L F, Kerekes J P. Object tracking using high resolution satellite imagery[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(1):146-152.
[10] 吴佳奇,张过,汪韬阳,等. 结合运动平滑约束与灰度特征的卫星视频点目标跟踪[J]. 测绘学报, 2017, 46(9):1135-1146.
[11] Du B, Sun Y J, Cai S H, et al. Object tracking in satellite videos by fusing the kernel correlation filter and the three-frame-difference algorithm[J]. IEEE Geoscience and Remote Sensing Letters, 2018, 15(2):168-172.
[12] Du B, Cai S H, Wu C, et al. Object tracking in satellite videos based on a multiframe optical flow tracker[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(8):3043-3055.
[13] Shao J, Du B, Wu C, et al. VCF:velocity correlation filter, towards space-borne satellite video tracking[C]//2018 IEEE International Conference on Multimedia and Expo(ICME), San Diego CA,USA:IEEE Press, 2018:1-6.
[14] Barnich O, Van Droogenbroeck M. ViBE:a powerful random technique to estimate the background in video sequences[C]//2019 IEEE Internationale Conference on Acoustics, Speech and Signal Processing, Taiwan, China:IEEE Press, 2009:945-948.
[15] Henriques J F, Caseiro R, Martins P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//12th European Conference on Computer Vision, Florence, Italy:Springer, 2012, 7575(4):702-715.
[16] 张文雅, 徐华中, 罗杰. 基于ViBe的复杂背景下的运动目标检测[J]. 计算机科学, 2017, 44(9):304-307.
[17] 蒋晶晶, 安博文. 低空航拍视频中基于Vibe算法的船舶检测方法[J]. 微型机与应用, 2017, 36(10):44-47.
[18] Henriques J F, Caseivo R, Martins P, et al. Exploiting the circulant structure of tracking-by-detection with kernels[C]//European Conference on Computer Vision. Berlin, Germany:Springer, 2012:702-715.
[19] Zhang K H, Zhang L, Yang M H. Real-time compressive tracking[C]//12th European Conference on Computer Vision, Florence, Italy:Springer, 2012, 7574(3):864-877.
[20] Ross D A, Lim J, Lin R S, et al. Incremental learning for robust visual tracking[J]. International Journal of Computer Vision, 2008, 77:125-141.
[21] Sevilla-Lara L, Learned-Miller E. Distribution fields for tracking[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA:IEEE, 2012:1910-1917.
[22] Wu Y, Shen B, Ling H B. Online robust image alignment via iterative convex optimization[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA:IEEE, 2012:1808-1814.
[23] Jia X, Lu H C, Yang M H. Visual tracking via adaptive structural local sparse appearance model[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA:IEEE, 2012:1822-1829.
[24] Bao C L, Wu Y, Ling H B, et al. Real time robust L1 tracker using accelerated proximal gradient approach[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA:IEEE, 2012:1830-1837.
[25] Zhang T Z, Ghanem B, Liu S, et al. Robust visual tracking via multi-task sparse learning[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA:IEEE, 2012:2042-2049.
[26] Zhong W, Lu H C, Yang M H. Robust object tracking via sparsity-based collaborative model[C]//2012 IEEE Conference on Computer Vision and Pattern Recognition, Providence, RI, USA:IEEE, 2012:1838-1845.
[27] Oron S, Bar-Hillel A, Levi D, et al. Locally orderless tracking[J]. International Journal of Computer Vision, 2015, 111(2):213-228.

基于V-CSK视频遥感卫星运动目标检测跟踪方法

Moving target detection and tracking of satellite videos based on V-CSK algorithm

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 10

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	刘雨洁, 齐向阳. 基于长时间间隔序贯SAR图像的运动舰船跟踪方法[J]. 中国科学院大学学报, 2021, 38(5): 642-648.
[2]	矫腾章, 胡玉新, 吕鹏, 张凯, 台宪青. 一种在轨海上多运动舰船目标检测和跟踪方法[J]. 中国科学院大学学报, 2020, 37(3): 368-378.
[3]	王海军, 张圣燕. 基于协同表示的目标跟踪算法[J]. 中国科学院大学学报, 2016, 33(1): 135-143.
[4]	张乾, 叶新, 方伟. 太阳同步轨道卫星上太阳方位的计算及精度分析[J]. 中国科学院大学学报, 2011, 28(3): 310-314.
[5]	崔明路, 王治强, 刘薇. 一种星地量子密钥通信仿真平台[J]. 中国科学院大学学报, 2011, 28(2): 241-245.
[6]	刘伟, 罗铁坚, 陈肃. 一种监控网络程序的信息收集方法[J]. 中国科学院大学学报, 2009, 26(6): 850-854.
[7]	吴波, 王宏琦. 一种稳健的基于主颜色的多目标跟踪算法[J]. 中国科学院大学学报, 2008, 26(6): 816-823.
[8]	卢晓鹏殷学民邹谋炎. 基于核密度相关度量的视频目标跟踪[J]. 中国科学院大学学报, 2007, 24(4): 501-505.
[9]	屠海瑞, 叶顶峰. 带有身份公开委员会的群签名[J]. 中国科学院大学学报, 2005, 22(1): 94-99.
[10]	喻俊志, 陈尔奎, 王硕, 谭民. 基于颜色信息的多机器鱼并行视觉跟踪算法[J]. 中国科学院大学学报, 2003, 20(4): 433-440.