Jornal de Sensoriamento Remoto e GIS

Abstrato

Motion Detection in Satellite Video

Aigong Xu, Jiaqi Wu, Guo Zhang, Shenlin Pan, Taoyang Wang, Yonghua Jang and Xin Shen

In view of the problem of satellite video motion detection, a background subtraction method of combining global motion compensation and local dynamic updating is proposed. In the first instance, the improved ViBE model method is used to establish the background model in the middle frame. The background model has one more dynamic update factor. Secondly, the motion model of global scene between frames is estimated by using uniform blocked forward-back LK optical flow, and the global motion compensation is performed. Last but not least, comparison between compensated frame and model, and connected domain analysis are employed to detect and segment the motion objects. Even more, we can correct the update factor of model according to the “pseudo motion” judgment. And then, the model would be updated locally and adaptively. “Target-wise” evaluation recall rate method is proposed which statistic the object entirety but not pixels. We do four experiments using Skysat and JL1H video. The results show that the proposed method perform a favorable effect on “Target-wise” recall rate and the error detection rate is low. The “Target-wise” recall rate is better than 80%. The error detection rate is reduced by at least 10 times, and even more than 160 times, compared with the classical method. The method could be suitable for advanced application and motion analysis in satellite video