<-上一篇/Previous Article 下一篇/Next Article->

[1]王鑫,田甜,田金文.基于背景建模的VideoSAR动目标阴影检测方法[J].智能系统学报,2022,17(1):59-68.[doi:10.11992/tis.202107019]
　WANG Xin,TIAN Tian,TIAN Jinwen.Moving target shadow detection in VideoSAR based on background modeling[J].CAAI Transactions on Intelligent Systems,2022,17(1):59-68.[doi:10.11992/tis.202107019]

点击复制

基于背景建模的VideoSAR动目标阴影检测方法

PDF下载 HTML

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 17 期数: 2022年第1期页码: 59-68 栏目: 学术论文—机器学习出版日期: 2022-01-05

Title:: Moving target shadow detection in VideoSAR based on background modeling

作者:: 王鑫¹, 田甜^1,2, 田金文^1,2; 1. 华中科技大学人工智能与自动化学院，湖北武汉 430074;
2. 华中科技大学多谱信息处理技术国家级重点实验室，湖北武汉 430074

Author(s):: WANG Xin¹, TIAN Tian^1,2, TIAN Jinwen^1,2; 1. School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan 430074, China;
2. National Key Laboratory of Science and Technology on Multi-spectral Information Processing, Huangzhong University of Science and Technology, Wuhan 430074, China

关键词:: 视频合成孔径雷达; 动目标检测; 卷积神经网络; 乘性噪声; 去噪; 图像配准; 单高斯模型; 区域生长

Keywords:: VideoSAR; moving target detection; convolutional neural network; multiplicative noise; denoising; image registration; single Gaussian model; region growing

分类号:: TP391

DOI:: 10.11992/tis.202107019

摘要:: 针对视频合成孔径雷达(video synthetic aperture radar，VideoSAR)数据进行地面运动目标检测的问题，本文提出了一种基于单高斯背景模型的VideoSAR动目标阴影检测方法。该方法使用一个时间维度的滑窗对视频序列进行处理：首先使用RED20深度神经网络模型抑制VideoSAR图像的斑点噪声，随后使用帧间配准算法快速配准窗口内的图像序列，然后对序列进行建模和差分得到窗口末帧的二值化前景，最后通过连通区域筛选和区域生长剔除虚假目标。采用美国Sandia国家实验室公布的VideoSAR视频对本文算法进行了验证，实验表明，该算法能实现对动目标阴影的准确检测。

Abstract:: Aiming at the problem of ground moving target detection based on Video Synthetic Aperture Radar (VideoSAR) data, a VideoSAR moving target shadow detection method based on single Gaussian background model is proposed in this paper, which uses a time-dimensional sliding window to process the video sequence: The RED20 deep neural network model is first used to suppress the speckle noise of VideoSAR image, and then the interframe registration algorithm is applied to quickly register the image sequence of the window. After that, the binary foreground of the last frame of the window is obtained by sequence modeling and background subtraction. Finally, false targets are eliminated by connected region screening and region growing. The proposed approach is validated on the VideoSAR video published by Sandia National Laboratory, and experimental results show that the algorithm can accurately detect the shadow of moving targets.

参考文献/References:: [1] WELLS L, SORENSEN K, DOERRY A, et al. Developments in sar and ifsar systems and technologies at Sandia national laboratories[C]//2003 IEEE Aerospace Conference Proceedings. New York, USA: IEEE, 2003: 1085?1095.
[2] ZHAO Songtao, CHEN Jie, YANG Wei, et al. Image formation method for spaceborne video SAR[C]//2015 IEEE 5th Asia-Pacific Conference on Synthetic Aperture Radar. New York, USA: IEEE, 2015: 148?151.
[3] KIM C K, AZIM M T, SINGH A K, et al. Doppler shifting technique for generating multi-frames of video SAR via sub-aperture signal processing[J]. IEEE transactions on signal processing, 2020, 68: 3990–4001.
[4] MOSES R L, ASH J N. Recursive SAR imaging[J]. Proceedings of SPIE - The International Society for Optical Engineering, 2010, 6970: 69700P-1–69700P-12.
[5] MOSES R L, ASH J N. An autoregressive formulation for SAR backprojection imaging[J]. IEEE transactions on aerospace and electronic systems, 2011, 47(4): 2860–2873.
[6] HAWLEY R W, GARBER W L. Aperture weighting technique for video synthetic aperture radar[C]//Algorithms for synthetic aperture radar imagery XVIII. Orlando, USA: SPIE, 2011, 8051: 67?73.
[7] LINNEHAN R, MILLER J, BISHOP E, et al. An autofocus technique for video-SAR[C]//Algorithms for synthetic aperture radar imagery XX. Baltimore, USA: SPIE, 2013, 8746: 56?65.
[8] MILLER J, BISHOP E, DOERRY A. An application of backprojection for video SAR image formation exploiting a subaperature circular shift register[C]//Algorithms for synthetic aperture radar imagery XX. Baltimore, USA: SPIE, 2013, 8746: 66?79.
[9] BISHOP E, LINNEHAN R, DOERRY A. Video-SAR using higher order Taylor terms for differential range[C]//2016 IEEE Radar Conference. New York, USA: IEEE, 2016.
[10] SONG Xiaoshen, YU Weidong. Processing video-SAR data with the fast backprojection method[J]. IEEE transactions on aerospace and electronic systems, 2016, 52(6): 2838–2848.
[11] HU Ruizhi, MIN Rui, PI Yiming. Interpolation-free algorithm for persistent multi-frame imaging of video-SAR[J]. IET radar, sonar & navigation, 2017, 11(6): 978–986.
[12] GARREN D A. SAR focus theory of complicated range migration signatures due to moving targets[J]. IEEE geoscience and remote sensing letters, 2018, 15(4): 557–561.
[13] LIU Zhongkang, AN Daoxiang, HUANG Xiaotao. Moving target shadow detection and global background reconstruction for VideoSAR based on single-frame imagery[J]. IEEE access, 2019, 7: 42418–42425.
[14] 闫贺, 黄佳, 李睿安, 等. 基于改进快速区域卷积神经网络的视频SAR运动目标检测算法研究[J]. 电子与信息学报, 2021, 43(3): 615–622
YAN He, HUANG Jia, LI Ruian, et al. Research on video SAR moving target detection algorithm based on improved faster region-based CNN[J]. Journal of electronics & information technology, 2021, 43(3): 615–622
[15] 聊蕾, 左潇丽, 云涛, 等. 基于图像序列的VideoSAR动目标检测方法[J]. 雷达科学与技术, 2016, 14(6): 563–567,573
LIAO Lei, ZUO Xiaoli, YUN Tao, et al. An approach to detect moving target in VideoSAR imagery sequence[J]. Radar science and technology, 2016, 14(6): 563–567,573
[16] 张营, 朱岱寅, 俞翔, 等. 一种VideoSAR动目标阴影检测方法[J]. 电子与信息学报, 2017, 39(9): 2197–2202
ZHANG Ying, ZHU Daiyin, YU Xiang, et al. Approach to moving targets shadow detection for VideoSAR[J]. Journal of electronics & information technology, 2017, 39(9): 2197–2202
[17] TIAN Xiaoqing, LIU Jing, MALLICK M, et al. Simultaneous detection and tracking of moving-target shadows in ViSAR imagery[J]. IEEE transactions on geoscience and remote sensing, 2021, 59(2): 1182–1199.
[18] HUANG Xuejun, DING Jinshan, GUO Qinghua. Unsupervised image registration for video SAR[J]. IEEE journal of selected topics in applied earth observations and remote sensing, 2020, 14: 1075–1083.
[19] MAO Xiaojiao, SHEN Chunhua, YANG Yubin. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections[J]. Neural information processing systems, 2016, 29: 2810–2818.
[20] LI Zihan, DONG Zhen, YU Anxi, et al. A robust image sequence registration algorithm for VideoSAR combining surf with inter-frame processing[C]//2019 IEEE International Geoscience and Remote Sensing Symposium. New York, USA: IEEE, 2019: 2794?2797.
[21] ALVAREZ L, LIONS P L, MOREL J M. Image selective smoothing and edge detection by nonlinear diffusion. II[J]. SIAM journal on numerical analysis, 1992, 29(3): 845–866.
[22] WANG Hongshuo, ZHAO Baojun, YANG Xingsha. Moving target detection based on Circular Video SAR[C]//2019 IEEE International Conference on Signal, Information and Data Processing. New York, USA: IEEE, 2019.
[23] NASON G P, SILVERMAN B W. The stationary wavelet transform and some statistical applications[M]//Wavelets and Statistics. New York, USA: Springer New York, 1995: 103: 281?299.
[24] COIFMAN R R, DONOHO D L. Translation-invariant de-noising[M]//Wavelets and Statistics. New York, USA: Springer New York, 1995: 125?150.
[25] PESQUET J C, KRIM H, CARFANTAN H. Time-invariant orthonormal wavelet representations[J]. IEEE transactions on signal processing, 1996, 44(8): 1964–1970.

备注/Memo

收稿日期:2021-07-12。
基金项目:国家自然科学基金项目(42071339).
作者简介:王鑫，硕士研究生，主要研究方向为VideoSAR运动目标检测;田甜，副教授，博士，主要研究方向为遥感图像处理、计算机视觉、深度学习;田金文，教授，博士，主要研究方向为人工智能、计算机视觉。
通讯作者:田甜. E-mail: ttian@hust.edu.cn

更新日期/Last Update: 1900-01-01

基于背景建模的VideoSAR动目标阴影检测方法 PDF下载HTML

备注/Memo

基于背景建模的VideoSAR动目标阴影检测方法

PDF下载 HTML