A Multi-Feature Fusion-Based Change Detection Method for Remote Sensing Images
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.
KeywordsMulti-feature fusion Feature weight Fuzzy c-means Object-oriented change detection
This work was supported partly by the National Natural Science Foundation of China (41331175), a Project of Shandong Province Higher Educational Science and Technology Program (J17KA064), and the Open Fund of Key Laboratory of Coastal Zone Exploitation and Protection, Ministry of Land and Resource (2017CZEPK02).
- Kennedy, R. E., Townsend, P. A., Gross, J. E., Cohen, W. B., Bolstad, P., Wang, Y. Q., et al. (2009). Remote sensing change detection tools for natural resource managers: Understanding concepts and tradeoffs in the design of landscape monitoring projects. Remote Sensing of Environment, 113(7), 1382–1396.CrossRefGoogle Scholar
- Liu, X., Shang, Y., Lei, Z., & Yu, Q. (2012). Change detection by local illumination compensation using local binary pattern. Optical Engineering, 51(9), 1487–1489.Google Scholar