People re-identification by spectral classification of silhouettes

The problem described in this paper consists in re-identifying moving people in different sites which are completely covered with non-overlapping cameras. Our proposed framework relies on the spectral classification of the appearance-based signatures extracted from the detected person in each sequence. We first propose a new feature called “color-position” histogram combined with several illumination invariant methods in order to characterize the silhouettes in static images. Then, we develop an algorithm based on spectral analysis and support vector machines (SVM) for the re-identification of people. The performance of our system is evaluated on real datasets collected on INRETS premises. The experimental results show that our approach provides promising results for security applications.