The study of land use change detection based on object-oriented analysis

Conventional map-to-map comparison method is used frequently to land use change detection from remote sensing data. However, only the spectral information is used in the process of classification. The accuracy is very low. This paper applies object-oriented image analysis to the change detection and can overcome the limitation stated above. It classifies through selecting samples, using multi-scale image segmentation techniques, allowing the integration of a broad spectrum of different object features, such as spectral values, shape, texture and thematic information. In the study, it detects the land use change information of the test area during ten years through the method based on object-oriented analysis. The result is satisfying and can provide the foundation for sustaining development of land resource.