Remote Sensing Image Segmentation Based on a Multiresolution Region Granularity Analysis Method
ZHENG Chen1, SUN Ding-qian3, CHEN Xiao-hui2*
1. School of Mathematics and Information Sciences, Henan University, Kaifeng 475000, China 2. Library, Henan University, Kaifeng 475000, China 3. Mathematics Department, Southeast University, Nanjing 211189, China
Abstract：Remote sensing image has abundant granularity information. In order to utilize this information, a multiresolution region granularity analysis method is proposed in the present paper for image segmentation. The proposed method firstly uses the mean shift to obtain the initial over-segmented regions at each resolution of the image, and then extracts the granularity information based on the region size and the region context, the Markov random field is employed to provide the final segmentation result by modeling the spectrum information and the granularity information. The SPOT5 remote sensing images of Pingshuo and the aerial image of Taizhou were tested to evaluate the proposed method. Compared with other spectrum-based methods, our method shows a better performance and results improved the segmentation accuracy.
Key words：Image segmentation;Granularity information;Markov random field
[1] Zhang Lei, Ji Qiang. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2010, 32(8): 1406. [2] Yu Qiyao, Clausi David A. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2008, 30(12): 2126. [3] Peter Yu, Qin A K, Clausi David A. IEEE Transaction on Geoscience and Remote Sensing, 2012, 50(4): 1302. [4] Wang Xiaofeng, Zhang X P. 2009 IEEE International Conference on Multimedia & Expo., 2009. 642. [5] Xia Guisong, Chu He, Sun H. Proceedings of 2006 CIE International Conference on Radar, 2006. 1. [6] Gkhan Akay H, Selim Aksoy. IEEE Transaction on Geoscience and Remote Sensing, 2008, 46(7): 2097. [7] Stanz L. Markov Random Field Modeling in Image Analysis. 3rd ed. UK: Springer Press, 2009. 21. [8] Comaniciu D, Meer P. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2002, 24(5): 603. [9] Besag J. Journal of the Royal Statistical Society, 1986，Series B 48: 259. [10] Boykov Y, Veksler O, Zabih R. IEEE Transaction on Pattern Analysis and Machine Intelligence, 2001, 23(11): 1222. [11] Sarkar A, Biswas M K, Sharma K M S. IEEE Transactions on Image Processing, 2000, 9(5): 801. [12] Noda H, Shirazi M N, Kawaguchi E. Pattern Recognition, 2002, 35(4): 771. [13] ZHAO Ying-shi(赵英时). Theory and Methods of Remote Sensing Applications(遥感应用分析原理与方法). Beijing：Science Press(北京：科学出版社), 2003. 207. [14] Unnikrishnan R, Hebert M. Seventh IEEE Workshops on Application of Computer Vision, 2005, 1: 394.
