Two Stream Pose Guided Network for Vehicle Re-identification

Vehicle Re-Identifcation is the task of fnding images of the same vehicle with di?erent views across a surveillance camera network, which is a very benefcial yet challenging task. Huge intra-class di?erences and small inter-class di?erence makes this task hard to tackle. Appearance-based information is utilized in this paper to cope with vehicle re-identifcation problem; we have proposed a deep learning technique by incorporating poses of vehicles generated by pose estimation network and visual information. When query image is given, the two-stream network generates a feature embedding by concatenating pose feature from pose network. Extensive experiments are done on two of the benchmark datasets of vehicle re-identifcation VeRi-776 and VehicleID. Experimental results are supporting the competitiveness of the proposed method with recent state-of-the-art methods.