基于协同分割的高分辨率遥感图像变化检测

南京大学学报(自然科学版) ›› 2015, Vol. 51 ›› Issue (5): 1039–1048.

基于协同分割的高分辨率遥感图像变化检测

袁敏1,2,3，肖鹏峰1,2,3*，冯学智1,2,3，张学良1,2,3，胡永月1,2,3

出版日期:2015-09-09 发布日期:2015-09-09
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:
江苏高校"青蓝工程"（201423）,浙江省科技计划项目（2014F50022）

Change detection from high-resolution remotely sensed images based on cosegmentation

Yuan Min1,2,3, Xiao Pengfeng1,2,3*, Feng Xuezhi1,2,3, Zhang Xueliang1,2,3, Hu Yongyue1,2,3

Online:2015-09-09 Published:2015-09-09
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： 针对面向对象变化检测存在的多时相对象边界不一致的难题，基于计算机视觉领域的多视图像协同分割思想，提出一种面向多时相高分辨率遥感图像变化检测的协同分割方法。首先对多时相遥感图像进行协同处理，利用多时相信息发现变化特征，以光谱变化为指标，获得变化强度图，进而在变化强度图的引导下，结合各时相的图像自身特征进行分割，通过能量函数的构建和优化，直接生成边界准确、空间对应的多时相变化对象。利用两个时相的高分辨率航空图像进行实验表明，该方法可以较完整准确地分割出变化对象，通过建立其空间对应关系，能清晰地表达对象的变化过程，为高分辨率遥感图像面向对象变化检测提供了新思路。

Abstract: Due to the inconsistency of multi-temporal objects’ boundaries for object-based change detection, this paper proposes a new change detection approach from multi-temporal high-resolution remotely sensed images based on the concept of cosegmentation in the filed of computer vision. First, multi-temporal remotely sensed images are co-processed to discover the change feature and a map of change intensity is obtained using the magnitude of spectral change between images. Then cosegmentation is performed under the guidance of the change intensity map, combined with each image features. Multi-temporal change objects with accurate boundaries and spatial correspondence are directly generated by energy function minimization finally. Experimental results obtained on multi-temporal aerial images show that multi-temporal change objects are preferably segmented and the change process can also be clearly acquired through establishing a correspondence between multi-temporal change objects. This novel method can provide a workable way for object-based change detection from high-resolution remotely sensed images

袁敏1,2,3，肖鹏峰1,2,3*，冯学智1,2,3，张学良1,2,3，胡永月1,2,3. 基于协同分割的高分辨率遥感图像变化检测[J]. 南京大学学报(自然科学版), 2015, 51(5): 1039–1048.

Yuan Min1,2,3, Xiao Pengfeng1,2,3*, Feng Xuezhi1,2,3, Zhang Xueliang1,2,3, Hu Yongyue1,2,3. Change detection from high-resolution remotely sensed images based on cosegmentation[J]. Journal of Nanjing University(Natural Sciences), 2015, 51(5): 1039–1048.

参考文献

[1].Singh A. Review article digital change detection techniques using remotely-sensed data. International Journal of Remote Sensing, 1989, 10(6): 989–1003.
[2].[2] Desclée B, Bogaert P, Defourny P. Forest change detection by statistical object-based method. Remote Sensing of Environment, 2006, 102(1): 1–11.
[3].[3] Niemeyer I, Marpu P R, Nussbaum S. Change detection using object features. In: Blaschke T, Lang S, Hay G J. Object-Based Image Analysis: Spatial Concepts for Knowledge-Driven Remote Sensing Applications. Berlin Heidelberg: Springer, 2008: 185–201.
[4].[4] Im J, Jensen J R, Tullis J A. Object-based change detection using correlation image analysis and image segmentation. International Journal of Remote Sensing, 2008, 29(2): 399–423.
[5].[5] Conchedda G, Durieux L, Mayaux P. An object-based method for mapping and change analysis in mangrove ecosystems. ISPRS Journal of Photogrammetry and Remote Sensing, 2008, 63(5): 578–589.
[6].[6] Lefebvre A, Corpetti T, Hubert-Moy L. Object-oriented approach and texture analysis for change detection in very high resolution images. In: 2008 IEEE International Geoscience and Remote Sensing Symposium(IGARSS). 2008, 4: 663–666.
[7].[7] Listner C, Niemeyer I. Recent advances in object-based change detection. In: 2011 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 2011: 110–113.
[8].[8] Chen J, Mao Z, Philpot B, et al. Detecting changes in high-resolution satellite coastal imagery using an image object detection approach. International Journal of Remote Sensing, 2013, 34(7): 2454–2469.
[9].[9] Hussain M, Chen D, Cheng A, et al. Change detection from remotely sensed images: From pixel-based to object-based approaches. ISPRS Journal of Photogrammetry and Remote Sensing, 2013, 80: 91–106.
[10].[10] Rother C, Kolmogorov V, Minka T, et al. Cosegmentation of image pairs by histogram matching-incorporating a global constraint into MRFs. In: 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2006, 1: 993–1000.
[11].[11] Mukherjee L, Singh V, Dyer C R. Half-integrality based algorithms for cosegmentation of images. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition. 2009: 2028–2035.
[12].[12] Hochbaum D S, Singh V. An efficient algorithm for co-segmentation. In: The 12th IEEE International Conference on Computer Vision. 2009: 269–276.
[13].[13] Vicente S, Kolmogorov V, Rother C. Cosegmentation revisited: Models and optimization. In: Daniilidis K, Maragos P, Paragios N. Proceedings of the 11th European Conference on Computer Vision, Part Ⅱ. Berlin Heidelberg: Springer, 2010: 465–479.
[14].[14] Mukherjee L, Singh V, Peng J. Scale invariant cosegmentation for image groups. In: 2011 IEEE Conference on Computer Vision and Pattern Recognition. 2011: 1881–1888.
[15].[15] Mu Y, Zhou B. Co-segmentation of image pairs with quadratic global constraint in MRFs. In: Yagi Y, Kang S B, Kweon I S, et al. Proceedings of the 8th Asian Conference on Computer Vision, Part Ⅱ. Berlin Heidelberg: Springer, 2007: 837–846.
[16].[16] Huang X, Zhang L, Zhu T. Building change detection from multitemporal high-resolution remotely sensed images based on a morphological building index. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(1): 105–115.
[17].[17] Boykov Y, Jolly M P. Interactive graph cuts for optimal boundary & region segmentation of objects in N-D images. In: Proceedings of the 8th IEEE International Conference on Computer Vision. 2001, 1: 105–112.
[18].[18] Chu W S, Chen C P, Chen C S. MOMI-cosegmentation: Simultaneous segmentation of multiple objects among multiple images. In: Kimmel R, Klette R, Sugimoto A. The 11th Asian Conference on Computer Vision, Part Ⅰ. Berlin Heidelberg: Springer, 2011: 355–368.
[19].[19] Haralick R M, Shanmugam K, Dinstein I H. Textural features for image classification. IEEE Transactions on Systems, Man and Cybernetics, 1973, 3(6): 610–621.
[20].[20] Ford L, Fulkerson D. Flows in networks. Princeton: Princeton University Press, 1962, 208.
[21].[21] Boykov Y, Veksler O. Graph cuts in vision and graphics: Theories and applications. In: Paragios N, Chen Y, Faugeras O. Handbook of mathematical models in computer vision. New York: Springer, 2006: 79–96.
[22].[22] Goldberg A V, Tarjan R E. A new approach to the maximum-flow problem. Journal of the Association for Computing Machinery (JACM), 1988, 35(4): 921–940.
[23].[23] Boykov Y, Kolmogorov V. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2004, 26(9): 1124–1137.
[24].[24] Schott J R, Salvaggio C, Volchok W J. Radiometric scene normalization using pseudoinvariant features. Remote Sensing of Environment, 1988, 26(1): 1–16.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed