A Novel Level Set Method for Remote Sensing Image

Abstract:

Due to the characteristic of remote sensing image, we propose a novel method based on K-means algorithm also with the improved multi-phrase level set model. Comparing with the classical multi-phase C-V model, the improved model considers the region area information, gradient information and edge detection .Proper use of gradient information can overcome the inaccurate edge localization defects in image segmentation. The edge detection is used for keeping the boundary information better in the evolution process .For the reason of picking up the contour’s convergent speed and enable the avoidance of trap .Four stages are constructed. Firstly, a median filtering is applied to smooth the original image and reduce parts of noise. Secondly, the usage of K-means algorithm gains more obvious differences of characteristics. Next, the reconstruction of gradient is obtained by using Sobel operator. Finally, segmentation result is achieved by using an improved method of multi-phase level set image segmentation. Experimental results show that the proposed approach has advantages in rapid and efficient application of remote sensing image segmentation.

• Periodical: Applied Mechanics and Materials (Volume 610)
• Pages: 457-463
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.610.457
• Online since: August 2014
• Authors: Er Jing Xu, Zhen Hong Jia*, Lie Jun Wang, Ying Jie Hu, Jie Yang
• Keywords: K-Means Algorithm, Level Set Model, Remote Sensing Image Segmentation

References

[1] ChanT, VeseL. Active contours without edages. IEEE Transactions on Image Processing, 2001, 10( 2): 266- 277.

[2] Mumford D, Shah J. Optimal approximation by piecewise smooth functions and associated variational problems. Communications on Pure and Applied Mathematics, 1989, 42( 6 ): 577 - 685.

DOI: 10.1002/cpa.3160420503

[3] Pin Zhang, Rong Li, Jun Li. Segmentation of holographic images using the level set Method. Optik 123(2012) 132-136.

DOI: 10.1016/j.ijleo.2011.02.023

[4] Changlei Dongye, Yongguo Zheng, Bin Zhang. A fast segmentation of MRI image based on Chan-Vese model. Automatic control and artificial intelligence(ACAI 2012)E-ISBN: 978-1-84919-537-9, pages: 62-65.

DOI: 10.1049/cp.2012.0920

[5] Ahmed Dirami, Kamal Hammouche, Moussa Diaf, Patrick Siarry. Fast multilevel thresholding for image segmentation through a multiphase level set method. Signal processing. 2013, 93(1): 139-153.

DOI: 10.1016/j.sigpro.2012.07.010

[6] Parvin Ahmadi, Saeed Sadri, Rassoul Amirfattahi, Niloofar Gheissari. Automatic aerial image segmentation based on a modified Chan-Vese algorithm. Image and signalprocessing. Oct. 2012, ISBN: 978-1-4673-0965-3, pages: 643-647.

DOI: 10.1109/cisp.2012.6469766

[7] Yun Qian, Yingjie Zhang. Level set image segmentation method Summary. Chinese Journal of image and graphics, 13（1）：7-14.

[8] Bmanthey, Hroglin. Improved smoothed analysis of the k-means method. Siamsymp on discrete algorithms. 2009, 31(2): 461–470.

[9] Zhenkuan Pan, Hua Li, Weibo Wei and Zhenbo Guo A Variational Level Set Method for Multiphase Image Segmentation. IEEE Transactions on Image Processing2008, 525-530.

DOI: 10.1109/icalip.2008.4590001

[10] Bo Wang, Chunping Liu, Yong Sun, Zhaohui Wang, Shengrong Gong . A fusion-based approach to image segmentation using ROI and multi-phase level set model. 2010 3rd International Congress on Image and Signal Processing：1263-1267.

DOI: 10.1109/cisp.2010.5647435

[11] L. Vese, T. Chan. A multiphase level set framework for image segmentation using the Mumford and Shah model. Int. J. Comput Vis. 50, 271–293 (2002).

[12] Wu Hualing, Xu Xiaobo. Research on automatic segmentation of remote sensing image. IEEE Transactions on Image Processing, 2010 , 111-115.

DOI: 10.1109/gcis.2010.128

[13] Bin Wang, Jie Li, Xinbo Gao. A novel priori level set segmentation method based on edge and area. Journal of Computers, 2012, 35（5）: 1067-1073.