The land-use change detection method using object-based feature consistency analysis

The land use change detection methods using remote sensing data have been studied for a long term. All of these methods can be divided into three levels: pixel-level, feature-level and knowledge-level. In this paper, the advantages and disadvantages of these methods are analyzed, and a novel approach is proposed to detect the land use changes using the object-based feature consistency analysis. The image objects are generated by the fusion of the remote sensing images and geographic information vector data. According to the priori knowledge in the vector data, the changed objects are detected by comparing with the consistency of the objects´ features in T1 and T2 periods. An experiment is conducted to validate the proposed approach. Comparing with the non-auxiliary data change detection and change detection based on the correlation analysis, the result indicates that the proposed approach is valid for improving the accuracy of the land use change detection.