J4 ›› 2015, Vol. 42 ›› Issue (5): 48-54.doi: 10.3969/j.issn.1001-2400.2015.05.009

• Original Articles • Previous Articles     Next Articles

SAR images segmentation algorithm using chain coding grid in G0 distribution

ZHANG Zejun;SHUI Penglang   

  1. (National Key Lab. of Radar Signal Processing, Xidian Univ., Xi'an  710071, China)
  • Received:2014-05-31 Online:2015-10-20 Published:2015-12-03
  • Contact: ZHANG Zejun E-mail:zjzhang_xd@163.com

Abstract:

An adaptive weighted synthetic aperture radar(SAR) images segmentation model is proposed based on the minimum description length(MDL) principle to alleviate the influence of complexity of the SAR images' scene on segmentation results. In the model, G0 distribution is used for describing SAR image data, and the 4-neighborhood chain coding grid is utilized for coding boundaries of regions in the SAR image. An adaptive estimation method for the weight of the segmentation model is proposed using the SAR image data. The segmentation model is fast minimized by using region merging technology. Experimental results show that, compared with two methods of the same kind, the proposed method effectively alleviates the degree of over-segmentation in texture fields.

Key words: synthetic aperture radar(SAR) image segmentation, G0 distribution, chain coding grid, region merging technique

CLC Number: 

  • TP751.1