People re-identification across multiple non-overlapping cameras

The research addressed in this paper consists in developing an automatic system for detecting/reidentifying moving people in different sites with non-overlapping views. Firstly, we propose an automatic process for silhouette extraction. Then, a new colour descriptor is proposed for characterizing the silhouettes of the detected people. Once all the appearance information of each passage is extracted, a graph-based algorithm is used to realize the comparison of passages of people in front of cameras and to make the final decision of reidentification. The global system is tested on two real and difficult data sets recorded in very different environments. The experimental results show that our proposed system leads to very satisfactory results.