Sliver Removal in Object-Based Change Detection from VHR Satellite Images

This paper presents a novel strategy for object-based change detection using very high spatial resolution (VHR) satellite images captured under variable off-nadir view angles. The variable off-nadir angle, along with weak absolute orientation, generates spurious slivers during the multitemporal comparison of classification results. The proposed solution for accurate object-to-object comparison is based on an intermediate registration of object-based classification results with a piecewise affine transformation followed by robust, geometry-based techniques for sliver removal. Although different remote sensing applications require different strategies and methods for object-based change detection, the approach developed in this paper can overcome the overall limitation introduced by the slivers generated by weak geo-localization, variable off-nadir angles, and image segmentation.