Co-segmentation of aircrafts from high-resolution satellite images

Abstract

Purely bottom-up, unsupervised target segmentation is one of the most challenging problems in satellite image interpretation within the computer vision community. In this paper, we focus on the problem of automatically segmenting aircrafts from high-resolution satellite images based on the idea of co-segmentation. First, we selectively segment out the regions of interest (ROIs) from the satellite images. Then, we apply a region based shadow detection and removal approach to remove shadows. Finally, the anisotropic heat diffusion model is employed to fulfill our co-segmentation task. Experimental results on a given dataset have demonstrated the effectiveness of our method.