Discriminative feature and dictionary learning with part-aware model for vehicle re-identification

Abstract

With the development of smart cities, urban surveillance video analysis plays a further significant role in intelligent transportation systems. Vehicle re-identification (re-ID) aims at identifying the same target vehicle in large datasets from non-overlapping cameras, which has grown into a hot topic in promoting intelligent transportation systems. However, due to the similar appearances, vehicle re-ID has become a challenging task. In this paper, we tackle this challenge by proposing Triplet Center Loss based Part-aware Model (TCPM) that leverages the discriminative features in part details of vehicles to refine the accuracy of vehicle re-ID. TCPM mainly partitions the vehicle from horizontal and vertical directions to strengthen the details of the vehicle and reinforce the internal consistency of the parts. In addition, to eliminate intra-class differences in local regions of the vehicle, we utilize the external memory modules to emphasize the consistency of each part to learn the discriminating features, which form a global dictionary over all categories in the dataset. Moreover, in TCPM, triplet-center loss is introduced to ensure that each part of vehicle features has intra-class consistency and inter-class separability. Experimental results show that our proposed TCPM has competitive results over the existing state-of-the-art methods on benchmark datasets VehicleID and VeRi-776.