基于区域合并的高分辨率遥感图像多尺度分割

南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (5): 1030–1038.

基于区域合并的高分辨率遥感图像多尺度分割

张学良1,2,3，冯学智1,2,3 ，肖鹏峰1,2,3

出版日期:2015-09-08 发布日期:2015-09-08
作者简介:（1. 江苏省地理信息技术重点实验室，南京大学，南京，210023；
2. 卫星测绘技术与应用国家测绘地理信息局重点实验室，南京大学，南京，210023；
3. 南京大学地理信息科学系，南京，210023）
基金资助:
?国家高分辨率对地观测系统重大专项项目（95-Y40B02-9001-13/15-04），江苏高校“青蓝工程”项目（201423）

Multiscale segmentation of high-resolution remote sensing images based on region merging

Zhang Xueliang1, Feng Xuezhi1,2,3*, Xiao Pengfeng1,2,3

Online:2015-09-08 Published:2015-09-08
About author:(1. Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology, Nanjing University, Nanjing, 210023, China;
2. Key Laboratory for Satellite Mapping Technology and Applications of State Administration of Surveying, Mapping and Geoinformation of China, Nanjing University, Nanjing, 210023, China;
3. Department of Geographic Information Science, Nanjing University, Nanjing, 210023, China)

摘要/Abstract

摘要： 图像分割是高分辨率遥感图像处理和分析的关键环节。本文探讨了将区域合并方法应用于高分辨率遥感图像多尺度分割的技术要点，旨在提升分割的精度和效率，获得地物对象的多尺度表达。主要研究内容包含如下五个方面：（1）图模型的构建，包括区域邻接图和最近邻图，以提高分割效率；（2）合并准则的确定，选择能有效表征区域同质性、形状和边界的图像特征并加以组合，提升分割精度；（3）合并策略的选择，针对寻优范围不同列出面向全局、面向局部以及混合区域合并等三种合并策略，并分析各自的特点；（4）尺度参数的设置，针对面向局部的区域合并策略提出递增的尺度参数序列控制方法，生成边界一致的多尺度分割结果；（5）分割树的设计，利用树中不同层级的节点表达不同尺度的分割区域，可快速输出多尺度分割结果。研究成果可应用于高分辨率遥感图像面向对象分析、地物目标识别和信息提取。

Abstract: Image segmentation is the critical step in object-based analysis of high-resolution remote sensing images. In this study, we examined the key steps of region merging method for remote sensing image segmentation. The following five aspects are involved. (1) We construct a graph model, including the region adjacency graph and the nearest neighbor graph, to improve segmentation efficiency. (2) The features of region homogeneity, shape, and edges are integrated in the merging criterion to improve segmentation accuracy. (3) We present and compare three different region merging strategies, including the global-oriented, local-oriented and hybrid region merging. (4) A step-wise scale parameter strategy is proposed to set scale parameters, aiming at producing nested multiscale segmentations by local-oriented region merging methods. (5) We present a segment tree model to represent multiscale segments, which can be used to produce segmentations at different scale extremely fast without repeating the region merging procedure. The proposed methods are applicable for object-based image analysis, geographic object recognition, and information extraction from high spatial resolution remote sensing images.

张学良1,2,3，冯学智1,2,3 ，肖鹏峰1,2,3
. 基于区域合并的高分辨率遥感图像多尺度分割[J]. 南京大学学报(自然科学版), 2015, 51(5): 1030–1038.

Zhang Xueliang1, Feng Xuezhi1,2,3*, Xiao Pengfeng1,2,3
. Multiscale segmentation of high-resolution remote sensing images based on region merging[J]. Journal of Nanjing University(Natural Sciences), 2015, 51(5): 1030–1038.

参考文献

[1] 李德仁, 童庆禧, 李荣兴等. 高分辨率对地观测的若干前沿科学问题. 中国科学: 地球科学, 2012, 42(6): 805–813.
[2] Benediktsson J A, Chanussot J, Moon W M. Very High-Resolution Remote Sensing: Challenges and Opportunities. Proceedings of the IEEE, 2012, 100(6): 1907–1910.
[3] Blaschke T. Object based image analysis for remote sensing. ISPRS Journal of Photogrammetry and Remote Sensing, 2010, 65(1): 2–16.
[4] Blaschke T, Hay G J, Kelly M, et al. Geographic Object-Based Image Analysis–Towards a new paradigm. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 87: 180–191.
[5] Benz U C, Hofmann P, Willhauck G, et al. Multi-resolution, object-oriented fuzzy analysis of remote sensing data for GIS-ready information. ISPRS Journal of Photogrammetry & Remote Sensing, 2004 58(3-4): 239–258.
[6] Borenstein E, Ullman S. Combined top-down/bottom-up segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008, 30(12): 2109–2125.
[7] Schiewe J, Tufte L, Ehlers M. Potential and problems of multi-scale segmentation methods in remote sensing. GIS - Zeitschrift für Geoinformations systeme, 2001, 6: 34–39.
[8] Carleer A P, Debeir O, Wolff E. Assessment of very high spatial resolution satellite image segmentations. Photogrammetric Engineering and Remote Sensing, 2005, 71(11): 1285–1294
[9] Dey V, Zhang Y, Zhong M. A review on image segmentation techniques with remote sensing perspective. In Wagner W. and Székely B. (eds.): ISPRS TC VII Symposium – 100 Years ISPRS. Vienna, Austria: ISPRS, 2010, XXXVIII (7A): 31–42.
[10] Haris K, Efstradiadis S, Maglaveras N, et al. Hybrid image segmentation using watershed and fast region merging. IEEE Transactions on Image Processing, 1998, 7(12): 1684–1699.
[11] Zhang X, Xiao P, Feng X. Fast hierarchical segmentation of high-resolution remote sensing image with adaptive edge penalty. Photogrammetric Engineering & Remote Sensing, 2014, 80(1): 71–80.
[12] Zhang X, Xiao P, Song X, et al. Boundary-constrained multi-scale segmentation method for remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 78: 15–25.
[13] Comaniciu D, Meer P. Mean shift: A robust approach toward feature space analysis. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603–619.
[14] Vincent L, Soille P. Watershed in digital spaces: an efficient algorithm based on immersion simulations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1991, 13(6): 583–598.
[15] Beaulieu J M, Goldberg M. Hierarchy in picture segmentation: a stepwise optimization approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(2): 150–163.
[16] Baatz M, Sch?pe A. Multiresolution segmentation—an optimization approach for high quality multi-scale image segmentation. In Strobl, J., Blaschke, T., Griesebner, G. (Eds.), Angewandte Geographische Informations-Verarbeitung XII. Wichmann Verlag, Karlsruhe, 2000, 12–23.
[17] Zhang X, Xiao P, Feng X, et al. Hybrid region merging method for segmentation of high-resolution remote sensing images. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 98: 19–28.
[18] Cardoso J S, Corte-Real L. Toward a generic evaluation of image segmentation. IEEE Transactions on Image Processing, 2005, 14(11): 1773–1782.
[19] Hubert L, Arabie P. Comparing Partitions. Journal of Classification, 1985, 2(1): 193–218.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed