车载前视GPSAR序列图像浅埋目标检测新方法

杨延光; 宋千; 周智敏; 金添; 张汉华

doi:10.3724/SP.J.1146.2008.00515

车载前视GPSAR序列图像浅埋目标检测新方法

doi: 10.3724/SP.J.1146.2008.00515

计量
- 文章访问数: 3403
- HTML全文浏览量: 72
- PDF下载量: 774
- 被引次数: 0
出版历程
- 收稿日期: 2008-04-28
- 修回日期: 2008-10-27
- 刊出日期: 2009-06-19

A Novel Detection Method of Shallow Buried Objects with Sequence Images of the Vehicle-Mounted Forward-Looking GPSAR

摘要

摘要: 由于浅埋小目标的雷达截面较小、埋设环境复杂，导致单帧检测结果中存在大量虚警，该文提出一种预筛选-交替后向跟踪-多帧确认目标检测方法。首先利用CFAR检测、形态滤波和聚类分析对图像进行预筛选；然后利用当前距离多视图像对应的聚类中心标记待跟踪的潜在目标，采用点跟踪搜索和块相关检测相结合的交替后向跟踪获得潜在目标轨迹；最后计算潜在目标轨迹的加权历史置信度，进行目标确认，剔除自然杂波。实测数据处理结果表明：该方法可快速、稳健地实现目标检测，明显减少虚警。
- 前视地表穿透雷达;地雷检测;交替后向跟踪;块相关检测;历史置信度
Abstract: Since the small Radar Cross Section (RCS) and complicated buried environments of shallow buried targets will lead to large numbers of false alarms in the detection results of single frame image, a novel detection method called as prescreening-alternately backward tracking-multiframe confirmation is proposed in this paper. Firstly, the prescreening of images is made by the Constant False Alarm Rate (CFAR) detector, then followed by a morphological filter and clustering analysis. Secondly, the clustering centers of the current frame range multi-look image are utilized to mark the potential targets for tracking, and a new alternately backward tracking method is used to obtain the potential object tracks. Finally, the tracks are employed to compute the weighted historical confidences, which are exploited to eliminate the natural clutters and confirm targets. Experimental results of the real data show that the proposed approach can acquire the regions of interest fast and robustly, reduce the false alarms obviously.

HTML全文

参考文献(1)

Schreiner K. Landmine detection research pushes forward,despite challenges. IEEE Intelligent Systems, 2002, 17(2):4-7.[2]Kositsky J, Cosgrove R B, and Amazeen C, et al.. Resultsfrom a forward-looking GPR mine detection system[J].Proceedings of SPIE.2002, 4742:206-217[3]Bradley M, Witten T, and Duncan M, et al.. Mine detectionwith a forward-looking ground-penetrating syntheticaperture radar[J].Proceedings of SPIE.2003, 5089:334-347[4]Sun Y and Li J. Time-frequency analysis for plastic landminedetection via forward-looking ground penetrating radar[J].IEEProc. Radar Sonar Navig.2003, 150(4):253-261[5]Sun Y and Li J. Adaptive learning approach to landminedetection[J].IEEE Trans. on Aerospace and Electronic Systems.2005, 41(3):973-985[6]Wang T, Keller J M, and Gader P D, et al.. Frequencysub-band processing and feature analysis of forward-lookingground-penetrating radar signals for landmine detection[J].IEEE Trans. on Geoscience and Remote Sensing.2007, 45(3):718-729[7]赵坤. 复杂环境下红外小目标检测与跟踪技术研究[D]. [博士论文], 哈尔滨工程大学, 2006.Zhao Kun. Research on Infrared Detection and TrackingTechnique of Small Target for Complex InterferenceEnvironment[D]. [Ph.D.dissertation], Harbin EngineeringUniversity, 2006.[8]杨磊. 复杂背景条件下的红外小目标检测与跟踪算法研究[D].[博士论文], 上海交通大学, 2006.Yang Lei. Study on Infrared Small Target Detection andTracking Algorithm under Complex Backgrounds[D]. [Ph.D.dissertation], Shanghai Jiao Tong University, 2006.[9]Qian Z, Liu X, and Li J. A real-time system for targetdetection and tracking in IR image. IEEE InternationalConference on Intelligent Processing Systems, Beijing, China,Oct. 28-31, 1997: 1005-1008.[10]Teknomo K, Takeyama Y, and Inamura H. Frame-basedtracing of multiple objects. Proceedings of IEEE Workshopon Multi-Object Tracking, Serdai, Japan,8 July, 2001: 11-18.[11]Parry H S, Marshall A D, and Markham K C. Trackingtargets in FLIR images by region template correlate[J].Proceedings of SPIE.1997, 3086:221-232[12]Bizup D F and Brown D E. Detect-track-confirm filter withminimal constraints[J].IEEE Trans. on Aerospace andElectronic Systems.2004, 40(1):336-345[13]Bal A and Alam M S. Automatic detection and tracking ofreappearing targets in forward looking infrared imagery[J].Proc.SPIE -IST Electronic Imaging.2006, 6064:1-6[14]Askar H, Li X, and Li Z. Performance analysis of dim movingpoint target detection algorithm. IEEE InternationalConference on Communications, Circuits and Systems andWest Sino Expositions, Chengdu, China, 29 June-1 July, 2002:977-981.[15]杨志国. 基于ROI 的UWB SAR 叶簇覆盖目标鉴别方法研究[D]. [博士论文], 国防科技大学, 2007.Yang Zhiguo. Foliage-concealed Target Discrimination ofUWB SAR Based on ROI[D]. [Ph.D.dissertation], NationalUniversity of Defense Technology, 2007.[16]Brown L G. A survey of image registration techniques. ACMComputing Surveys, 1992, 24(4): 326-376.[17]Cosgrove R B, Milanfar P, and Kositsky J. Trained detectionof buried mines in SAR images via the deflection-optimalcriterion[J].IEEE Trans. on Geoscience and Remote Sensing.2004, 42(11):2569-2575[18]Dawoud A, Alam M S, and Bal A, et al.. Decision fusionalgorithm for target tracking in forward-looking infraredimagery[J].Proceedings of SPIE.2004, 5434:156-162[19]Liang H and Ni G. The analysis of target detectionprobability in sequence image[J].Proceedings of. SPIE.2000,4130:791-799

施引文献

资源附件(0)

访问统计