Urban Area Vehicle Re-Identification With Self-Attention Stair Feature Fusion and Temporal Bayesian Re-Ranking

Vehicle re-identification (Re-ID) plays a key role in many smart traffic management systems. Re-identifying a vehicle can be very challenging because the differences in visual appearances between pairs of vehicles are sometimes extremely subtle if they have the same colour and the same model. Given an image of a vehicle, most existing techniques adopt a global feature representation where details may be ignored. In this paper, we propose an Self-Attention Stair Feature Fusion model to learn the discriminative features for vehicle Re-ID. The model is designed to extract multi-level features in order to capture as much small details as possible. We also propose a Temporal Bayesian Re-Ranking method to exploit the spatial-temporal information in the vehicles’ travel patterns. Our algorithm has been tested against state-of-the-art techniques on popular benchmarks. The results show that our algorithm outperforms other state-of-the-art techniques by a large margin.