A Multi-Feature Fusion-Based Change Detection Method for Remote Sensing Images

Liping Cai, Wenzhong Shi, Ming Hao, Hua Zhang, Lipeng Gao

Research output: Journal article publicationJournal articleAcademic researchpeer-review

9 Citations (Scopus)


An object-oriented change detection method for remote sensing images based on multiple features using a novel weighted fuzzy c-means (WFCM) method is presented. First, Gabor and Markov random field textures are extracted and added to the original images. Second, objects are obtained by using a watershed segmentation algorithm to segment the images. Third, simple threshold technology is applied to produce the initial change detection results. Finally, refining is conducted using WFCM with different feature weights identified by the Relief algorithm. Two satellite images are used to validate the proposed method. Experimental results show that the proposed method can reduce uncertainties involved in using a single feature or using equally weighted features, resulting in higher accuracy.

Original languageEnglish
Pages (from-to)2015-2022
Number of pages8
JournalJournal of the Indian Society of Remote Sensing
Issue number12
Publication statusPublished - 1 Dec 2018


  • Feature weight
  • Fuzzy c-means
  • Multi-feature fusion
  • Object-oriented change detection

ASJC Scopus subject areas

  • Geography, Planning and Development
  • Earth and Planetary Sciences (miscellaneous)


Dive into the research topics of 'A Multi-Feature Fusion-Based Change Detection Method for Remote Sensing Images'. Together they form a unique fingerprint.

Cite this