An Object-based Change Detection Approach by Integrating Intensity and Texture Differences

With the development of remote sensing technology, using remote sensing images to do change detection is becoming a hotspot. This paper introduces the research status of pixel-based and object-based change detection technology as well as comments on several change detection methods. A technique for pixel-based change detection by integrating the intensity and texture differences between two frames is studied. An object based change detection method based on this technique is proposed. Experimental results show that the integrated measure is robust with respect to the illumination changes and noise, the performance of which is outstanding especially when applied to object-based change detection because of pixels' consistency in an object and sharp contrast between objects.