Tracking individuals within a wide area camera network is a tough problem. Obtaining information across uncovered areas is an open issue that person re-identification methods deal with. A novel appearance-based method for person re-identification is proposed. The approach computes a novel discriminative signature by exploiting multiple local features. A novel signature distance measure is given by exploiting a body part division approach. The method has been compared to state-of-the-art methods using a re-identification benchmark dataset. A new dataset acquired from non-overlapping cameras has been built to validate the method against a real wide area camera network scenario. The method has proven to be robust against low resolution images, viewpoint and illumination changes, occlusions and pose variations. Results show that the proposed approach outperforms state-of-the-art methods used for comparison
