结合巴氏系数和灰度共生矩阵的遥感影像分割
|
摘要
针对遥感影像纹理信息丰富的特点,以及传统分水岭变换用于遥感影像分割容易出现过分割的问题,提出了一种基于巴氏系数和灰度共生矩阵的区域合并方法改进分水岭算法的分割结果。首先,利用数学形态学的方法提取原始影像的梯度图像,并且从梯度图像中获取标记;其次,在标记的梯度图像上进行分水岭变换,得到初始分割图像;最后,利用所提出的结合巴氏系数和灰度共生矩阵的区域合并方法对过分割区域进行合并,得到最终分割结果。实验结果表明,该算法既能得到连通,封闭的分割轮廓,还能有效解决分水岭分割算法的过分割问题,得到了较为准确的分割结果。
Aiming at the rich feature information of remote sensing image,and the over-segmentation problem of the traditional watershed transform for remote sensing image segmentation,a new region merging method based on Bhattacharyya coefficient(BC)and gray level co-occurrence matrix(GLCM),i.e.,BC-GLCM,is proposed to improve the results of watershed segmentation.Firstly,the gradient image of the original image is extracted by using mathematical morphology,resulting in obtaining marks of the gradient image.Secondly,the watershed transformation is applied on the gradient image with marks to obtain initial segmentations.Finally,the over-segmented regions are merged by using the proposed BC-GLCM method.The experimental results show that the proposed method can not only get connected,closed segmentation contours,but also effectively solve the problem of oversegmentation of watershed segmentation algorithm,and obtain more accurate segmentation results.
Aiming at the rich feature information of remote sensing image,and the over-segmentation problem of the traditional watershed transform for remote sensing image segmentation,a new region merging method based on Bhattacharyya coefficient(BC)and gray level co-occurrence matrix(GLCM),i.e.,BC-GLCM,is proposed to improve the results of watershed segmentation.Firstly,the gradient image of the original image is extracted by using mathematical morphology,resulting in obtaining marks of the gradient image.Secondly,the watershed transformation is applied on the gradient image with marks to obtain initial segmentations.Finally,the over-segmented regions are merged by using the proposed BC-GLCM method.The experimental results show that the proposed method can not only get connected,closed segmentation contours,but also effectively solve the problem of oversegmentation of watershed segmentation algorithm,and obtain more accurate segmentation results.
引文
[1]GAETANO R,MASI G,POGGI G,et al.Marker-controlled watershed-based segmentation of multiresolution remote sensing images[J].IEEE Transactions on Geoscience&Remote Sensing,2015,53(6):2987-3004.
[2]LI B,PAN M,WU Z.An improved segmentation of high spatial resolution remote sensing image using marker-based watershed algorithm[C]//IEEE International Conference on Geoinformatics.Hongkong:IEEE,2012:1-5.
[3]肖鹏峰,冯学智,王培法,等.高分辨率遥感图像分割与信息提取[M].北京:科学出版社,2012:1-3.
[4]鲁恒,付萧,刘超,等.基于无人机影像的快速分割方法[J].国土资源遥感,2016,28(2):72-78.
[5]许妙忠,丛铭,万丽娟,等.视觉感受与Markov随机场相结合的高分辨率遥感影像分割法[J].测绘学报,2015,44(2):198-205.
[6]王春艳,徐爱功,李玉,等.融入空间关系的二型模糊模型高分辨率遥感影像分割[J].遥感学报,2016,20(1):103-113.
[7]YANG J,HE Y,CASPERSEN J.A multi-band watershed segmentation method for individual tree crown delineation from high resolution multispectral aerial image[C]//IEEE Geoscience and Remote Sensing Symposium.Quebec City:IEEE,2014:1588-1591.
[8]高丽,杨树元,李海强,等.一种基于标记的分水岭图像分割新算法[J].中国图象图形学报,2007,12(6):1025-1032.
[9]邵龙,杨景辉,洪友堂.结合异质性及分水岭变换的遥感影像分割方法[J].测绘科学,2014,39(3):19-22.
[10]蔡彩,李培军,郭建聪.基于分水岭变换及分层区域合并的城市高分辨率影像分割[J].北京大学学报(自然科学版),2014,50(2):323-330.
[11]IJITONA T B,REN J,HWANGH P B.SAR sea ice image segmentation using watershed with intensity-based region merging[C]//IEEE International Conference on Computer and Information Technology.Xi’an:IEEE,2014:168-172.
[12]SAHIN K,ULUSOY I.Automatic multi-scale segmentation of high spatial resolution satellite images using watersheds[C]//IEEE Geoscience and Remote Sensing Symposium.Melbourne:IEEE,2014:2505-2508.
[13]张博,何彬彬.改进的分水岭变换算法在高分辨率遥感影像多尺度分割中的应用[J].地球信息科学学报,2014,16(1):142-150.
[14]张志禹,孟令辉,雷涛.自适应梯度重建分水岭分割算法[J].中国图象图形学报,2014,19(10):1430-1437.
[15]张海涛,李雅男.阈值标记的分水岭彩色图像分割[J].中国图象图形学报,2015,20(12):1602-1611.
[16]MEYER F.Topographic distance and watershed lines[J].Signal Processing,1994,38(1):113-125.
[17]CAO H,DENG J,GUO H,et al.An improved recommendation algorithm based on Bhattacharyya Coefficient[C]//IEEEInternational Conference on Knowledge Engineering and Applications.Singapore:IEEE,2017:241-244.
[18]MESHKINI K,GHASSEMIAN H.Texture classification using Shearlet transform and GLCM[C]//IEEE Iranian Conference on Electrical Engineering.Tehran:IEEE,2017:1845-1850.
[19]侯群群,王飞,严丽.基于灰度共生矩阵的彩色遥感图像纹理特征提取[J].国土资源遥感,2013,25(4):26-32.
[20]THAKARE V S,PATIL N N.Classification of texture using Gray level co-occurrence matrix and self-organizing map[C]//IEEE International Conference on Electronic Systems,Signal Processing and Computing Technologies.Nagpur:IEEE,2014:350-355.
[21]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4):622-635.
[2]LI B,PAN M,WU Z.An improved segmentation of high spatial resolution remote sensing image using marker-based watershed algorithm[C]//IEEE International Conference on Geoinformatics.Hongkong:IEEE,2012:1-5.
[3]肖鹏峰,冯学智,王培法,等.高分辨率遥感图像分割与信息提取[M].北京:科学出版社,2012:1-3.
[4]鲁恒,付萧,刘超,等.基于无人机影像的快速分割方法[J].国土资源遥感,2016,28(2):72-78.
[5]许妙忠,丛铭,万丽娟,等.视觉感受与Markov随机场相结合的高分辨率遥感影像分割法[J].测绘学报,2015,44(2):198-205.
[6]王春艳,徐爱功,李玉,等.融入空间关系的二型模糊模型高分辨率遥感影像分割[J].遥感学报,2016,20(1):103-113.
[7]YANG J,HE Y,CASPERSEN J.A multi-band watershed segmentation method for individual tree crown delineation from high resolution multispectral aerial image[C]//IEEE Geoscience and Remote Sensing Symposium.Quebec City:IEEE,2014:1588-1591.
[8]高丽,杨树元,李海强,等.一种基于标记的分水岭图像分割新算法[J].中国图象图形学报,2007,12(6):1025-1032.
[9]邵龙,杨景辉,洪友堂.结合异质性及分水岭变换的遥感影像分割方法[J].测绘科学,2014,39(3):19-22.
[10]蔡彩,李培军,郭建聪.基于分水岭变换及分层区域合并的城市高分辨率影像分割[J].北京大学学报(自然科学版),2014,50(2):323-330.
[11]IJITONA T B,REN J,HWANGH P B.SAR sea ice image segmentation using watershed with intensity-based region merging[C]//IEEE International Conference on Computer and Information Technology.Xi’an:IEEE,2014:168-172.
[12]SAHIN K,ULUSOY I.Automatic multi-scale segmentation of high spatial resolution satellite images using watersheds[C]//IEEE Geoscience and Remote Sensing Symposium.Melbourne:IEEE,2014:2505-2508.
[13]张博,何彬彬.改进的分水岭变换算法在高分辨率遥感影像多尺度分割中的应用[J].地球信息科学学报,2014,16(1):142-150.
[14]张志禹,孟令辉,雷涛.自适应梯度重建分水岭分割算法[J].中国图象图形学报,2014,19(10):1430-1437.
[15]张海涛,李雅男.阈值标记的分水岭彩色图像分割[J].中国图象图形学报,2015,20(12):1602-1611.
[16]MEYER F.Topographic distance and watershed lines[J].Signal Processing,1994,38(1):113-125.
[17]CAO H,DENG J,GUO H,et al.An improved recommendation algorithm based on Bhattacharyya Coefficient[C]//IEEEInternational Conference on Knowledge Engineering and Applications.Singapore:IEEE,2017:241-244.
[18]MESHKINI K,GHASSEMIAN H.Texture classification using Shearlet transform and GLCM[C]//IEEE Iranian Conference on Electrical Engineering.Tehran:IEEE,2017:1845-1850.
[19]侯群群,王飞,严丽.基于灰度共生矩阵的彩色遥感图像纹理特征提取[J].国土资源遥感,2013,25(4):26-32.
[20]THAKARE V S,PATIL N N.Classification of texture using Gray level co-occurrence matrix and self-organizing map[C]//IEEE International Conference on Electronic Systems,Signal Processing and Computing Technologies.Nagpur:IEEE,2014:350-355.
[21]刘丽,匡纲要.图像纹理特征提取方法综述[J].中国图象图形学报,2009,14(4):622-635.