Abstract
An object-based method is proposed in this paper for change detection in urban areas with multi-sensor multispectral (MS) images. The co-registered bi-temporal images are resampled to match each other. By mapping the segmentation of one image to the other, a change map is generated by characterizing the change probability of image objects based on the proposed change feature analysis. The map is then used to separate the changes from unchanged areas by two threshold selection methods and k-means clustering (k = 2). In order to consider the multi-scale characteristics of ground objects, multi-scale fusion is implemented. The experimental results obtained with QuickBird and IKONOS images show the superiority of the proposed method in detecting urban changes in multi-sensor MS images.
Highlights
Instead of comparing the objects’ spectral bands in the bi-temporal images, we summarize the possible distribution between any image object and its relevant changed areas, and we analyze the statistical feature variation of the change-related objects and define a change feature to represent the change probability of the image objects in the bi-temporal MS images
It can be seen that the proposed method is better able to detect the changes in an urban area with multi-sensor proposed method is better able to detect the changes in an urban area with multi-sensor MS images
A novel object-based change detection method has been proposed for multi-sensor
Summary
Change detection involves identifying the changed ground objects between a given pair of multi-temporal (so-called bi-temporal) images observing the same scene at different times [1,2]. Object-based theory regards some of the spatially-neighboring and spectrally-similar pixels as a union (a so-called object) to detect whether they are changed It makes use of the spatial information in the high-resolution image, together with the spectrum, and reduces the salt-and-pepper effect. Robust change vector analysis (RCVA) was proposed for multi-sensor change detection with very-high-resolution optical satellite data, and this approach improves the robustness of CVA to different viewing geometries or registration noise [37]. These methods do not consider the incompatibility between different band widths in bi-temporal multispectral (MS) images (Table 1).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
