高分辨率合成孔径雷达图像舰船目标几何特征提取方法
|
摘要
针对高分辨率合成孔径雷达图像设计了一种舰船目标几何特征提取算法.通过视觉注意机制检测目标区域的算法,通过频谱残差视觉显著计算模型求取显著图,完成显著区域的检测以实现舰船目标的初步定位,基于获得的视觉显著图采用最大熵算法完成阈值分割筛选出舰船区域.在提取的舰船切片的基础上,采用针对几何特征的提取算法,经图像预处理、方位角估计、旋转获取最佳表征舰船目标几何轮廓的外接矩形,相对有效准确地提取几何特征;最后,采用典型的TerraSAR-X数据进行仿真实验.结果表明,与传统方法相比,本文提出的频谱残差视觉模型完成合成孔径雷达图像舰船切片的区域分割能够有效降低虚警率,舰船目标的检测速度提高了25%~50%.该方法能够快速稳定地提取舰船目标的几何特征,也更加符合实际高分辨率图像舰船目标检测的应用需求.
A new method for geometric features extraction of ship target in high-resolution Synthetic Aperture Radar(SAR)image was proposed,After detecting and locating ship targets from highresolution SAR images.The algorithm continues to acquire target slices to construct the process of the ship target geometric feature extraction.Firstly,the algorithm obtained a saliency map,completed the detection and positioning of ship targets,and obtained the ship target slices.Secondly,the algorithm extracted the geometric features based on the resulting ship slices.The slices was estimated by the azimuth to obtain the exact minimum bounding rectangle,then effective and accurate extraction of geometric features can be completed.Finally,the algorithm appied to SAR image target detection,which is efficient proved by experimental results.The experiments on TerraSAR-X and a large number of satellite data demonstrate that the proposed algorithm can extract the geometric features with high accuracy and good stability.Unlike traditional methods,the use of improved spectral residual visual significant computational models to locate and segment ship targets can effectively reduce the false alarm rates,and the detection speed increased by 25% to 50%.And it is suitable for practical requirements of ship target detection in high-resolution images.
A new method for geometric features extraction of ship target in high-resolution Synthetic Aperture Radar(SAR)image was proposed,After detecting and locating ship targets from highresolution SAR images.The algorithm continues to acquire target slices to construct the process of the ship target geometric feature extraction.Firstly,the algorithm obtained a saliency map,completed the detection and positioning of ship targets,and obtained the ship target slices.Secondly,the algorithm extracted the geometric features based on the resulting ship slices.The slices was estimated by the azimuth to obtain the exact minimum bounding rectangle,then effective and accurate extraction of geometric features can be completed.Finally,the algorithm appied to SAR image target detection,which is efficient proved by experimental results.The experiments on TerraSAR-X and a large number of satellite data demonstrate that the proposed algorithm can extract the geometric features with high accuracy and good stability.Unlike traditional methods,the use of improved spectral residual visual significant computational models to locate and segment ship targets can effectively reduce the false alarm rates,and the detection speed increased by 25% to 50%.And it is suitable for practical requirements of ship target detection in high-resolution images.
引文
[1]MOREIRA A.A tutorial on synthetic aperture radar[J].IEEE Geoscience and Remote Sensing Magazine,2013,1(1):6-43.
[2]GU D,XU X.Multi-Feature extraction of ships from SAR images[C].2013 6th International Congress on Images and Signal Processing,2013:454-458.
[3]XING Xiang-wei,JI Ke-feng,KANG Li-hong,et al.Review of ship surveillance technologies based on high-resoluion wide-swath synthetic aperture radar imaging[J].Journal of Radar,2015,4(1):107-121.邢相薇,计科峰,康利鸿,等.HRWS SAR图像舰船目标监视技术研究综述[J].雷达学报,2015,4(1):107-121.
[4]HE You,GUAN Jian,PENG Ying-ning.Automatic radar detection and constant false alarm rate processing[M].Tsinghua University Press,1999.何友,关键,彭应宁.雷达自动检测与恒虚警处理[M].北京:清华大学出版社,1999.
[5]DENG Yun-kai,ZHAO Feng-jun.Development trend and application of spaceborne SAR Technology[J].Journal of Radar,2012,1(1):1-10.邓云凯,赵凤军.星载SAR技术的发展趋势及应用浅析[J].雷达学报,2012,1(1):1-10.
[6]JIAO Li-cheng,ZHANG Xiang-rong,HOU Biao,et al.Intelligent SAR image processing and interpretation[M].Science Press,2007.焦李成,张向荣,侯彪,等.智能SAR图像处理与解译[M].科学出版社,2007.
[7]FARROUKI A,BARKAT M.Automatic censoring CFAR detector based on ordered data variability for nonhomogeneous environments[J].IEEE Proceeding Radar,Sonar and Navigation,2005,152(1):43-51.
[8]HARM G.Developments in detection algorithms at JRC[C].The Third Meeting of the DECLIMS Project,Vancouver,BC,2004:1-7.
[9]ACHANTA R,ESTRADA F,WILS P,et al.Salient region detection and segmentation[C].Proceedings of the 6th International Conference on Computer Vision Systems(ICVS 2008),Santorini,Greece,2008,2507:66-75.
[10]ZHANG Zhi-long,YANG Wei-ping,ZHANG Yan Li,et al.Ship detection in infrared remote sensing images based on spectral residual transform[J].Journal of Electronics&Information Technology,2015,2(5):8-15.张志龙,杨卫平,张焱,等.基于频谱残留变换的红外遥感图像舰船目标检测方法[J].电子与信息学报,2015,2(5):8-15
[11]HOU X,ZHONG L.Saliency detection:a spectral residual approach[C].Proceedings of the 2007IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2007),Minneapolis,Minnesota,USA,2007:1-8.
[12]ITTI L.Models of bottom-up and top-down visual attention[D].California Institute of Technology,2000:13-19,32-34.
[13]CHEN Li-min,YANG Xue-zhi,ZHANG Xi,et al.The comparison and analysis of the ship detection algorithm in SARimages[J].Remote Sensing Information,2015,5(2):99-104.陈利民,杨学志,张晰,等.SAR舰船检测算法对比分析研究[J].遥感信息,2015,5(2):99-104.
[14]GAO Gui,HE Juan,KUANG Gang-yao,et al.A survey of target’s orientation estimation in SAR image[J].Signal Processing,2008,24(3):438-443.高贵,何娟,匡纲要,等.SAR图像方位角估计方法综述[J].信号处理,2008,24(3):438-443.
[15]GAO D,HAN S,VASCONCELOS N.Discriminant saliency,the detection of suspicious coincidences and applications to visual recognition[J].Pattern Analysis and Machine Intelligence,2009,31(6):989-1005.
[16]JI Ke-feng,KUANG Gang-yao,YU Weng-xian.A method of estimating target azimuth from SAR image based on linear regression[J].Modern Radar,2003,26(11):26-29.计科峰,匡纲要,郁文贤.基于线性回归的SAR目标方位角估计方法[J].现代雷达,2003,26(11):26-29.
[17]GUO Shao-jun,Lou Shu-li,LIU Feng.Multi-ship saliency detection via patch fusion by color clustering[J].Optics and Precision Engineering,2016,24(7):1807-1817.郭少军,娄树理,刘峰.应用颜色聚类图像块的多舰船显著性检测[J].光学精密工程,2016,24(7):1807-1817.
[18]WANG Xiao-hong.Moment Technique and its Applications in Image Processing and Recognition[D].Xi’an:Northwestern Polytechnic University,2001.王晓红.矩技术及其在图像处理与识别中的应用研究[D].西安:西北工业大学,2001.
[2]GU D,XU X.Multi-Feature extraction of ships from SAR images[C].2013 6th International Congress on Images and Signal Processing,2013:454-458.
[3]XING Xiang-wei,JI Ke-feng,KANG Li-hong,et al.Review of ship surveillance technologies based on high-resoluion wide-swath synthetic aperture radar imaging[J].Journal of Radar,2015,4(1):107-121.邢相薇,计科峰,康利鸿,等.HRWS SAR图像舰船目标监视技术研究综述[J].雷达学报,2015,4(1):107-121.
[4]HE You,GUAN Jian,PENG Ying-ning.Automatic radar detection and constant false alarm rate processing[M].Tsinghua University Press,1999.何友,关键,彭应宁.雷达自动检测与恒虚警处理[M].北京:清华大学出版社,1999.
[5]DENG Yun-kai,ZHAO Feng-jun.Development trend and application of spaceborne SAR Technology[J].Journal of Radar,2012,1(1):1-10.邓云凯,赵凤军.星载SAR技术的发展趋势及应用浅析[J].雷达学报,2012,1(1):1-10.
[6]JIAO Li-cheng,ZHANG Xiang-rong,HOU Biao,et al.Intelligent SAR image processing and interpretation[M].Science Press,2007.焦李成,张向荣,侯彪,等.智能SAR图像处理与解译[M].科学出版社,2007.
[7]FARROUKI A,BARKAT M.Automatic censoring CFAR detector based on ordered data variability for nonhomogeneous environments[J].IEEE Proceeding Radar,Sonar and Navigation,2005,152(1):43-51.
[8]HARM G.Developments in detection algorithms at JRC[C].The Third Meeting of the DECLIMS Project,Vancouver,BC,2004:1-7.
[9]ACHANTA R,ESTRADA F,WILS P,et al.Salient region detection and segmentation[C].Proceedings of the 6th International Conference on Computer Vision Systems(ICVS 2008),Santorini,Greece,2008,2507:66-75.
[10]ZHANG Zhi-long,YANG Wei-ping,ZHANG Yan Li,et al.Ship detection in infrared remote sensing images based on spectral residual transform[J].Journal of Electronics&Information Technology,2015,2(5):8-15.张志龙,杨卫平,张焱,等.基于频谱残留变换的红外遥感图像舰船目标检测方法[J].电子与信息学报,2015,2(5):8-15
[11]HOU X,ZHONG L.Saliency detection:a spectral residual approach[C].Proceedings of the 2007IEEE Conference on Computer Vision and Pattern Recognition(CVPR 2007),Minneapolis,Minnesota,USA,2007:1-8.
[12]ITTI L.Models of bottom-up and top-down visual attention[D].California Institute of Technology,2000:13-19,32-34.
[13]CHEN Li-min,YANG Xue-zhi,ZHANG Xi,et al.The comparison and analysis of the ship detection algorithm in SARimages[J].Remote Sensing Information,2015,5(2):99-104.陈利民,杨学志,张晰,等.SAR舰船检测算法对比分析研究[J].遥感信息,2015,5(2):99-104.
[14]GAO Gui,HE Juan,KUANG Gang-yao,et al.A survey of target’s orientation estimation in SAR image[J].Signal Processing,2008,24(3):438-443.高贵,何娟,匡纲要,等.SAR图像方位角估计方法综述[J].信号处理,2008,24(3):438-443.
[15]GAO D,HAN S,VASCONCELOS N.Discriminant saliency,the detection of suspicious coincidences and applications to visual recognition[J].Pattern Analysis and Machine Intelligence,2009,31(6):989-1005.
[16]JI Ke-feng,KUANG Gang-yao,YU Weng-xian.A method of estimating target azimuth from SAR image based on linear regression[J].Modern Radar,2003,26(11):26-29.计科峰,匡纲要,郁文贤.基于线性回归的SAR目标方位角估计方法[J].现代雷达,2003,26(11):26-29.
[17]GUO Shao-jun,Lou Shu-li,LIU Feng.Multi-ship saliency detection via patch fusion by color clustering[J].Optics and Precision Engineering,2016,24(7):1807-1817.郭少军,娄树理,刘峰.应用颜色聚类图像块的多舰船显著性检测[J].光学精密工程,2016,24(7):1807-1817.
[18]WANG Xiao-hong.Moment Technique and its Applications in Image Processing and Recognition[D].Xi’an:Northwestern Polytechnic University,2001.王晓红.矩技术及其在图像处理与识别中的应用研究[D].西安:西北工业大学,2001.