背景差分与帧间差分相融合的遥感卫星视频运动车辆检测方法

doi:10.7523/j.issn.2095-6134.2018.01.007

中国科学院大学学报 ›› 2018, Vol. 35 ›› Issue (1): 50-58.DOI: 10.7523/j.issn.2095-6134.2018.01.007

背景差分与帧间差分相融合的遥感卫星视频运动车辆检测方法

袁益琴^1,2, 何国金^1,3, 王桂周^1,3, 江威^1,2, 康金忠⁴

1. 中国科学院遥感与数字地球研究所, 北京 100094;
2. 中国科学院大学, 北京 100049;
3. 海南省地球观测重点实验室, 海南三亚 572000;
4. 吉林大学地球探测科学与技术学院, 长春 130012

收稿日期:2017-03-04 修回日期:2017-04-07 发布日期:2018-01-15
通讯作者: 何国金
基金资助:
国家重点研发计划全球变化及应对专项课题（2016YFA0600302），海南省重大科技计划项目（ZDKJ2016021，ZDKJ2016015-1）和中国科学院大学生创新实践训练计划（Y6Y01724KX）资助

A background subtraction and frame subtraction combined method for moving vehicle detection in satellite video data

YUAN Yiqin^1,2, HE Guojin^1,3, WANG Guizhou^1,3, JIANG Wei^1,2, KANG Jinzhong⁴

1. Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China;
3. Key Laboratory for Earth Observation of Hainan Province, Sanya 572000, Hainan, China;
4. College of Earth Exploration Science and Technology, Jilin University, Changchun 130012, China

Received:2017-03-04 Revised:2017-04-07 Published:2018-01-15

摘要/Abstract

摘要： 遥感视频卫星的出现为实时连续对地观测提供了新的契机，为遥感动态监测与目标跟踪提供了新数据源。在分析遥感卫星视频目标检测与传统监控视频目标检测的差异的基础上，阐述现有目标检测算法直接应用到遥感卫星视频上存在的不足，提出一种背景差分与帧间差分相融合的方法并将其应用于遥感卫星视频运动车辆的目标检测中。通过抽取UrtheCast遥感卫星视频的4帧实验图像，分别采用背景差分法、帧间差分法和本文提出的方法对运动车辆进行检测并分析。结果表明，本文提出的方法能够更有效抑制移动的背景边缘和残留噪声干扰，提高检测的正确度和质量，在遥感卫星视频运动目标检测中具有良好的应用潜力。

关键词: 视频卫星, 背景差分法, 帧间差分法, 目标检测

Abstract: Appearance of video satellite brings a new favorable opportunity for real-time observation of remote sensing and provides a kind of new data for dynamic monitoring and target tracking. Based on the differences in target detection between remote sensing satellite video and traditional surveillance video, this work indicates the problems about applying existing target detection algorithm directly to satellite video. A new approach which combines the background subtraction and frame subtraction technologies is proposed for better detection of the moving target in remote sensing satellite video. Moving vehicles in 4 frame images acquired from UrtheCast videos are detected by using the background subtraction method, the frame subtraction method, and the proposed method. The results indicate that the proposed method has a good ability in reducing the errors of mobile background edges and residual noises, improves the correctness and quality of detection, and has a promising application in moving target detection in satellite videos.

Key words: video satellite, background subtraction, frame subtraction, target detection

中图分类号:

TP75

袁益琴, 何国金, 王桂周, 江威, 康金忠. 背景差分与帧间差分相融合的遥感卫星视频运动车辆检测方法[J]. 中国科学院大学学报, 2018, 35(1): 50-58.

YUAN Yiqin, HE Guojin, WANG Guizhou, JIANG Wei, KANG Jinzhong. A background subtraction and frame subtraction combined method for moving vehicle detection in satellite video data[J]. , 2018, 35(1): 50-58.

参考文献

[1] Gómez C, White J C, Wulder M A. Optical remotely sensed time series data for land cover classification:a review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2016, 116:55-72.
[2] 李德仁, 王密, 沈欣,等. 从对地观测卫星到对地观测脑[J]. 武汉大学学报(信息科学版), 2017, 42(2):1-5.
[3] 刘韬. 国外视频卫星发展研究[J]. 国际太空, 2014, 9(2):50-56.
[4] 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(10):23-28.
[5] 潘益云, 李海超. 低轨视频卫星成像特性分析[J]. 航天器工程, 2015, 24(5):52-57.
[6] Yilmaz A, Javed O, Shah M, et al. Object tracking:a survey[J]. ACM Computing Surveys, 2006, 38(4):1-45.
[7] Mithun N C, Howlader T, Rahman S M, et al. Video-based tracking of vehicles using multipleztime-spatialzimages[J]. Expert Systems with Applications, 2016, 62:17-31.
[8] 张过. 卫星视频处理与应用进展[J]. 应用科学学报, 2016, 34(4):361-366.
[9] 付凯林, 杨芳, 黄敏,等. 低轨道视频卫星任务模式的研究与应用[C]//北京力学会学术年会, 2015:17-22.
[10] Amri S, Barhoumi W, Zagrouba E, et al. A robust framework for joint background/foreground segmentation of complex video scenes filmed with freely moving camera[J]. Multimedia Tools and Applications, 2010, 46(2):175-205.
[11] Sobral A, Vacavant A. A comprehensive review of background subtraction algorithms evaluated with synthetic and real videos[J]. Computer Vision and Image Understanding, 2014, 122(5):4-21.
[12] Appiah K, Hunter A, Dickinson P, et al. Accelerated hardware video object segmentation:from foreground detection to connected components labelling[J]. Computer Vision and Image Understanding, 2010, 114(11):1282-1291.
[13] Khare M, Srivastava R K, Khare A, et al. Single change detection-based moving object segmentation by using Daubechies complex wavelet transform[J]. Iet Image Processing, 2014, 8(6):334-344.
[14] Yin H, Chai Y, Yang S X, et al. Fast-moving target tracking based on mean shift and frame-difference methods[J]. Journal of Systems Engineering and Electronics, 2012, 22(4):587-592.
[15] Alani M, Hammouri A. Video compression algorithm based on frame difference approaches[J]. International Journal of Soft Computing, 2011, 2(4):67-79.
[16] Suganyadevi K, Malmurugan N. OFGM-SMED:an efficient and robust foreground object detection in compressed video sequences[J]. Engineering Applications of Artificial Intelligence, 2014, 28(1):210-217.
[17] Xin Y, Hou J, Dong L, et al. A self-adaptive optical flow method for the moving object detection in the video sequences[J]. Optik-International Journal for Light and Electron Optics, 2014, 125(19):5690-5694.
[18] Yalcin H, Hebert M, Collins R T, et al. A flow-based approach to vehicle detection and background mosaicking in airborne video[J]. Computer Vision and Pattern Recognition, 2005:1202-1202.
[19] George K, Konstantinos K. Vehicle detection and traffic density monitoring from very high resolution satellite video data[C]//2015 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 2015:1881-1884.
[20] Yang T, Wang X, Yao B, et al. Small moving vehicle detection in a satellite video of an urban area[J]. Sensors, 2016, 16(9):1528.
[21] Barnich O, Droogenbroeck M V. ViBe:a powerful random technique to estimate the background in video sequences[J]. IEEE International Conference on Acoustics, Speech and Signal Processing, 2009:945-948.
[22] Qiu G N, Quan H M. Moving object detection algorithm based on symmetrical-differencing and background subtraction[J]. Computer Engineering and Applications, 2014, 50:158-162.
[23] Bhattacharya S, Idrees H, Saleemi I, et al. Moving object detection and tracking in forward looking Infra-Red aerial imagery[J]. Machine Vision Beyond Visible Spectrum, 2011, 1:221-252.
[24] Cao Y T, Wang G, Yan D, et al. Two algorithms for the detection and tracking of moving vehicle targets in aerial Infrared image sequences[J]. Remote Sensing, 2015, 8(8):28-49.
[25] 谢红, 原博, 解武. LK光流法和三帧差分法的运动目标检测算法[J]. 应用科技, 2016, 43(3):23-28, 33.
[26] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 2007, 9(1):62-66.

背景差分与帧间差分相融合的遥感卫星视频运动车辆检测方法

A background subtraction and frame subtraction combined method for moving vehicle detection in satellite video data

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

访问统计

联系我们

[1]	席彦新, 计璐艳, 耿修瑞. 一种多时相遥感图像多目标检测算法[J]. 中国科学院大学学报, 2021, 38(4): 503-510.
[2]	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.
[3]	陈国炜, 刘磊, 郭嘉逸, 潘宗序, 胡文龙. 基于生成对抗网络的半监督遥感图像飞机检测[J]. 中国科学院大学学报, 2020, 37(4): 539-546.
[4]	卢凯旋, 李国清, 陈正超, 昝露洋, 李柏鹏, 高建威. 基于负样本多通道优化SSD网络的钢铁厂提取[J]. 中国科学院大学学报, 2020, 37(3): 352-359.
[5]	闫凯, 沈汀, 陈正超, 闫弘轩. 基于深度学习的SSD模型尾矿库自动提取[J]. 中国科学院大学学报, 2020, 37(3): 360-367.
[6]	王艳霞, 张毅. 机载单天线SAR动目标检测与参数估计[J]. 中国科学院大学学报, 2012, (2): 227-233.
[7]	宁忠磊, 王宏琦, 张正. 一种基于协方差矩阵的自动目标检测方法[J]. 中国科学院大学学报, 2010, 27(3): 370-375.