Acta Geodaetica et Cartographica Sinica ›› 2015, Vol. 44 ›› Issue (7): 791-796.doi: 10.11947/j.AGCS.2015.20140060

Previous Articles     Next Articles

An Improved Algorithm Based on Minimum Spanning Tree for Multi-scale Segmentation of Remote Sensing Imagery

LI Hui, TANG Yunwei, LIU Qingjie, DING Haifeng, JING Linhai   

  1. Key Laboratory of Digital Earth Science, Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China
  • Received:2014-01-26 Revised:2015-01-22 Published:2015-07-28
  • Supported by:

    One Hundred Person Project of the Chinese Academy of Sciences (Nos.Y34005101A;Y2ZZ03101B);Project of the China Geological Survey (No.12120113089200);The International S&T Cooperation Program of China (No.2013DFG21640)

Abstract:

As the basis of object-oriented information extraction from remote sensing imagery,image segmentation using multiple image features,exploiting spatial context information, and by a multi-scale approach are currently the research focuses. Using an optimization approach of the graph theory, an improved multi-scale image segmentation method is proposed. In this method, the image is applied with a coherent enhancement anisotropic diffusion filter followed by a minimum spanning tree segmentation approach, and the resulting segments are merged with reference to a minimum heterogeneity criterion.The heterogeneity criterion is defined as a function of the spectral characteristics and shape parameters of segments. The purpose of the merging step is to realize the multi-scale image segmentation. Tested on two images, the proposed method was visually and quantitatively compared with the segmentation method employed in the eCognition software. The results show that the proposed method is effective and outperforms the latter on areas with subtle spectral differences.

Key words: multi-scale segmentation, minimum spanning tree, minimum heterogeneity criterion, remotely sensed imagery

CLC Number: