论文部分内容阅读
Object-based change detection has been the hotspot in remote sensing image processing.A new approach toward object-based change detection is proposed.The two different temporal images are unitedly segmented using the mean shift procedure to obtain corresponding objects.Then change detection is implemented based on the integration of corresponding objects’ intensity and texture differences.Experiments are conducted on both panchromatic images and multispectral images and the results show that the integrated measure is robust with respect to illumination changes and noise.Supplementary color detection is conducted to determine whether the color of the unchanged objects changes or not when dealing with multispectral images.Some verification work is carried out to show the accuracy of the proposed approach.
Object-based change detection has been the hotspot in remote sensing image processing. A new approach toward object-based change detection is proposed. The two different temporal images are unitedly segmented using the mean shift procedure to obtain corresponding objects. based on the integration of corresponding objects’ intensity and texture differences.Experiments are conducted on both panchromatic images and multispectral images and the results show that the integrated measure is robust with respect to illumination changes and noise. Supplementary color detection is conducted to determine whether the the color of the unchanged objects changes or not when dealing with multispectral images. Home verification work is carried out to show the accuracy of the proposed approach.