在高分辨率遥感图像分割方法中,分形网络演化算法(fractal net evolution approach,FNEA)是一种经典的影像对象构造方法。但在计算影像对象之间的异质性时,使用根据经验选择的固定权值会导致该算法不能很好地适应不同属性的影像对象分割。针对这一问题,提出了一种改进的FNEA方法,根据不同影像对象的空间和光谱特征,自适应地计算空间判据权值和紧凑度判据权值,并将不同光谱分量对光谱判据的贡献引入到影像对象之间异质性的计算中。计算机仿真实验结果表明,该文提出的算法对不同属性的影像对象具有很好的适应性,与同类算法相比,图像分割结果得到了较好的改善。
In the methods for high-resolution remote sense image segmentation,the fractal net evolution approach (FNEA)is relatively mature among the object-oriented image segmentation algorithms.In calculating the heterogeneity of each pair of neighboring objects,the spatial criterion and weight of compactness are user-defined according to experience. In this paper,an improved method of adaptive FNEA algorithm was proposed by adaptively calculating the weights of spatial criterion and compactness according to the different properties of various kinds of objects. Moreover,the contributions of different spectroscopic components were introduced into calculating of the heterogeneity. Computer simulation demonstrates that the proposed algorithm has better adaptability to the image objects with different attributes. A comparison with some similar algorithms shows that the method proposed in this paper performs better for image segmentation.
[1] 王文杰,赵忠明,朱海青.面向对象特征融合的高分辨率遥感图像变化检测方法[J].计算机应用研究,2009,26(8):3149-3151. Wang W J,Zhao Z M,Zhu H Q.Object-oriented change detection method based on features fusion for high-resolution remote sensing image[J].Application Research of Computers,2009,26(8):3149-3151.[2] Rizvi I A,Mohan B K.Object-based image analysis of high-resolution satellite images using modified cloud basis function neural network and probabilistic relaxation labeling process[J].IEEE Transaction on Geoscience and Remote Sensing,2011,49(12):4815-4820.[3] 卢昭羿,左小清,黄亮,等.面向对象的投影互分割道路变化检测[J].国土资源遥感,2012,24(3): 60-64. Lu Z Y,Zuo X Q,Huang L,et al.Road change detection using object-oriented projective interactive partition[J].Remote Sensing for Land and Resources,2012,24(3):60-64.[4] 沈金祥,杨辽,陈曦,等.面向对象的山区湖泊信息自动提取方法[J].国土资源遥感,2012,24(3):84-91. Shen J X,Yang L,Chen X,et al.A method for object-oriented automatic extraction of lakes in the mountain area from remote sensing image[J].Remote Sensing for Land and Resources,2012,24(3):84-91.[5] 徐宏根,王建超,郑雄伟,等.面向对象的植被与建筑物重叠区域的点云分类方法[J].国土资源遥感,2012,24(2):23-27. Xu H G,Wang J C,Zheng X W,et al.Object-based point clouds classification of the vegetation and building overlapped area[J].Remote Sensing for Land and Resources,2012,24(2):23-27.[6] Baatz M,Schape A.Multiresolution segmentation:An optimization approach for high quality multiscale image segmentation[C]//Heidelberg:Angewandte Geographische Information Sverarbeitung XII.2000:12-23[7] 高伟,刘修国,彭攀,等.一种改进的高分辨率遥感影像分割方法[J].中国地质大学学报,2010,25(3):421-425. Gao W,Liu X G,Peng P,et al.An improved method of high resolution remote sensing image segmentation[J].Earth Science—Journal of China University of Geosciences,2010,25(3):421-425.[8] Tang Y Q,Zhang L P,Huang X.Object-oriented change detection based on the Kolmogorov-Smirnov test using high-resolution multispectral imagery[J].International Journal of Remote Sensing,2011,32(20):5719-5740.[9] 王慕华,张继贤,李海涛,等.基于区域特征的高分辨率遥感影像变化检测研究[J].测绘科学,2009,34(1):92-94. Wang M H,Zhang J X,LI H T,et al.High resolution image change detection based on region feature[J].Science of Surveying and Mapping,2009,34(1):92-94.