Flying spacecraft detection with the earth as the background based on superpixels clustering

On orbit flying spacecraft detection in near range is of great significance to space based surveillance and the final stage of rendezvous & docking. In this paper, we propose an effective flying spacecraft detection algorithm with the earth as the cluttered dynamic background based on superpixels clustering. Labeled point trajectories are used as the motion cue, and both color and texture features are extracted from generated superpixels for clustering. Experimental results show that our proposed method performs well on real world videos recorded by cameras onboard the International Space Station.