Remote Sensing Image Segmentation Based on Human Visual System Region-Split and Graph Cut

Abstract:

Aiming at the problem of poor real-time ability of Normalized Cut (NC), this paper suggests a remote sensing image segmentation algorithm based on region-split and graph cut within human visual system (HVS). According to the features of HVS, the algorithm uses region-split method to segment the remote sensing image into a large number of small regions. By integrating gray feature and spatial location of each region, NC is used to segment the image among regions from global view, by which the final segmented image can be generated. Experimental results show that comparing with the traditional NC, operating speed is significantly improved as getting close segmentation quality, and this is a kind of effective method of image segmentation.

• Periodical: Applied Mechanics and Materials (Volumes 55-57)
• Pages: 115-118
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.55-57.115
• Online since: May 2011
• Authors: Hua Jiang, Jing Wen
• Keywords: Graph Cut, Normalized Cut, Region- Split, Remote Sensing Image Segmentation

References

[1] LIU JIANHUA, MAO ZHENGYUAN, Summary of researches on high-resolution remote sensing image segmentation algorithm [J], Remote sensing information, 2009, 6: 95-101.

[2] LI XIAO-BIN, TIAN ZHENG. Optimum cut-based clustering [J], Signal Processing, 2007, 87(11): 2491-2502.

DOI: 10.1016/j.sigpro.2007.03.017

[3] WU Z Y, LEAHY R. An optimal graph theoretic approach to data clustering: Theory and its application to image segmentation [J]. IEEE Transactions on Pattern Analysis Machine Intelligence. 1993, 15(11): 1101-1113.

DOI: 10.1109/34.244673

[4] SHI J, MALIK J. Normalized cuts and image segmentation [J]. IEEE Transaction on Pattern Analysis Machine Intelligence. 2000, 22(8): 888-905.

DOI: 10.1109/34.868688

[5] PAVAN M, PELILLO M．A new graph-theoretic ap-proach to clustering and segmentation[C]．Proceedings of 2003 IEEE Computer Society Conference on CVPR，2003，1：145-152.

DOI: 10.1109/cvpr.2003.1211348

[6] MARTINEZ A M ．On combining graph-partitioning with non-parametric clustering for image segmentation[J]．Computer Vision and Image Understanding， 2004， 95 (1)：72—85.

DOI: 10.1016/j.cviu.2004.01.003

[7] CEVAHIR CIGLA, A. AYDIN ALATAN, Region-based image segmentation via graph cuts [J], IEEE Communication and Applications Conference, 2008, 16: 1-4.

DOI: 10.1109/siu.2008.4632542

[8] TAO WEN-BING, JIN HAI, ZHANG YI-MIN. Color image segmentation based on mean shift and Normalized Cut[J], IEEE Transaction on Systems, Man, and Cybernetics, 2007, 37(5): 1382-1389.

DOI: 10.1109/tsmcb.2007.902249

[9] ANJIN PARK, JUNGWHAN KIM, Graph Cut-based automatic color image segmentation using mean shift analysis [J], Computing: Techniques and Applications, 2008, 56: 564 - 571.

[10] WANG ZHENLIANG, WANG JICHENG, Multi-resolution image segmentation based on Normalized Cut [J], Computer Application, 2008, 28(9): 2309-231.

DOI: 10.3724/sp.j.1087.2008.02309