基于形态学重构的侧扫声呐图像目标分割方法
|
摘要
与光学图像相比,侧扫声呐图像具有强背景噪声、对比度低、边缘不清晰等特点,声呐图像的目标物分割处理更为困难,基于形态学提出一种针对声呐图像目标分割的有效处理方式。首先,利用形态学的顶帽重构对侧扫声呐图像进行背景与阴影的分割处理以更好得获得目标区域,即利用特定形态的结构元素与原图像进行运算,对侧扫声呐的背景与阴影进行抑制;其次,对所获得的图像目标区域进行边缘检测,得到目标物的边缘信息;再次,采用形态学方法对目标区域及目标边缘进行膨胀腐蚀操作,以去除孤立区域、填充孔洞,从而得到图像的掩模,根据掩模图像将目标物分割出来。
Compared with optical images,side-scan sonar images are characterized by strong background noise,low contrast and unclear edges.Therefore,the object segmentation of sonar image is more difficult.So,based on morphology,an effective processing method for sonar image segmentation is proposed.Firstly,the background and shadow segmentation of the side-scan sonar image is performed by using the morphological top hat reconstruction to obtain the target region better.That is to say,the structure elements of the specific morphology are used to perform the operation with the original image.The background and shadow of the side-scan sonar are suppressed.Secondly,the edge information of the object is obtained by edge detection of the target area of the image.Thirdly,the target area and the edge of the target are corroded by the morphological method.In order to remove the isolated region and fill the hole,the mask of the image is obtained,and the object is segmented according to the mask image.
Compared with optical images,side-scan sonar images are characterized by strong background noise,low contrast and unclear edges.Therefore,the object segmentation of sonar image is more difficult.So,based on morphology,an effective processing method for sonar image segmentation is proposed.Firstly,the background and shadow segmentation of the side-scan sonar image is performed by using the morphological top hat reconstruction to obtain the target region better.That is to say,the structure elements of the specific morphology are used to perform the operation with the original image.The background and shadow of the side-scan sonar are suppressed.Secondly,the edge information of the object is obtained by edge detection of the target area of the image.Thirdly,the target area and the edge of the target are corroded by the morphological method.In order to remove the isolated region and fill the hole,the mask of the image is obtained,and the object is segmented according to the mask image.
引文
[1]李勇航,牟泽霖,万芃.海洋侧扫声呐探测技术的现状及发展[J].通讯世界,2015(3):213-214.
[2]REED S,PETILLOT Y,BELL J.An automatic approach to the detection and extraction of mine features in sidescan sonar[J].IEEE Journal of Oceanic Engineering,2003,28(1):90-105.
[3]陈立强,刘忠,田晓东.基于边缘特征的水下目标分类识别算法[J].自动化技术与应用,2007(8):77-79.
[4]霍冠英,王敏,程晓轩,等.用于侧扫声纳图像边缘检测的改进Canny算子[J].应用科学学报,2011,29(6):613-618.
[5]李庆武,马国翠,霍冠英,等.基于NSCT域边缘检测的侧扫声呐图像分割新方法[J].仪器仪表学报,2013,34(8):1795-1801.
[6]郭海涛,徐雷,赵红叶,等.一种抑制声呐图像散斑噪声的形态学滤波器[J].仪器仪表学报,2015,36(3):654-660.
[7]VINCENT L.Morphological grayscale reconstruction in image analysis:Applications and efficient algorithms[C].IEEE Transactions on Image Processing,1993:176-201.
[8]BRAGANETO U M,GOUTSIAS J I.Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators[J].Journal of Electronic Imaging,2004,13(4):802-802.
[9]康牧,许庆功,王宝树.一种Roberts自适应边缘检测方法[J].西安交通大学学报,2008(10):1240-1244.
[10]袁春兰,熊宗龙,周雪花,等.基于Sobel算子的图像边缘检测研究[J].激光与红外,2009,39(1):85-87.
[11]谢昭莉,白颖杰.Prewitt图像边缘检测及边缘细化的FPGA实现[J].电子技术应用,2010,36(6):39-41,45.
[12]盛艳青.一种基于LOG算子提取显著封闭边缘的新方法[C].第十三届全国图象图形学学术会议,2006:4.
[13]许宏科,秦严严,陈会茹.一种基于改进Canny的边缘检测算法[J].红外技术,2014,36(3):210-214.
[14]ABDOU I E,PRATT W.Quantitative design and evaluation of enhancement/thresholding edge detectors[J].Proceedings of the IEEE,1979,67(5):753-763.
[15]韩丽蓉.掩模图像生成时阈值取值的合理性探讨[J].国土资源遥感,2017,29(2):22-28.
[2]REED S,PETILLOT Y,BELL J.An automatic approach to the detection and extraction of mine features in sidescan sonar[J].IEEE Journal of Oceanic Engineering,2003,28(1):90-105.
[3]陈立强,刘忠,田晓东.基于边缘特征的水下目标分类识别算法[J].自动化技术与应用,2007(8):77-79.
[4]霍冠英,王敏,程晓轩,等.用于侧扫声纳图像边缘检测的改进Canny算子[J].应用科学学报,2011,29(6):613-618.
[5]李庆武,马国翠,霍冠英,等.基于NSCT域边缘检测的侧扫声呐图像分割新方法[J].仪器仪表学报,2013,34(8):1795-1801.
[6]郭海涛,徐雷,赵红叶,等.一种抑制声呐图像散斑噪声的形态学滤波器[J].仪器仪表学报,2015,36(3):654-660.
[7]VINCENT L.Morphological grayscale reconstruction in image analysis:Applications and efficient algorithms[C].IEEE Transactions on Image Processing,1993:176-201.
[8]BRAGANETO U M,GOUTSIAS J I.Automatic target detection and tracking in forward-looking infrared image sequences using morphological connected operators[J].Journal of Electronic Imaging,2004,13(4):802-802.
[9]康牧,许庆功,王宝树.一种Roberts自适应边缘检测方法[J].西安交通大学学报,2008(10):1240-1244.
[10]袁春兰,熊宗龙,周雪花,等.基于Sobel算子的图像边缘检测研究[J].激光与红外,2009,39(1):85-87.
[11]谢昭莉,白颖杰.Prewitt图像边缘检测及边缘细化的FPGA实现[J].电子技术应用,2010,36(6):39-41,45.
[12]盛艳青.一种基于LOG算子提取显著封闭边缘的新方法[C].第十三届全国图象图形学学术会议,2006:4.
[13]许宏科,秦严严,陈会茹.一种基于改进Canny的边缘检测算法[J].红外技术,2014,36(3):210-214.
[14]ABDOU I E,PRATT W.Quantitative design and evaluation of enhancement/thresholding edge detectors[J].Proceedings of the IEEE,1979,67(5):753-763.
[15]韩丽蓉.掩模图像生成时阈值取值的合理性探讨[J].国土资源遥感,2017,29(2):22-28.