Vehicle Re-Identification with Location and Time Stamps

Kai Lv, Heming Du, Yunzhong Hou, Weijian Deng, Hao Sheng, Jianbin Jiao, Liang Zheng; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2019, pp. 399-406

This paper focuses on the problem of vehicle re-identification (Re-ID). In our attempt, we propose a re-identification framework by exploiting vehicle location and time stamps. The location and time information have the potential to cover the shortage of appearance-based feature representations. First, we introduce an ensemble technique to combine the informative cues of multiple Re-ID models effectively. To further improve the accuracy, we then build up a system to acquire the vehicle location and time stamps. Specifically, we utilize the detected results to obtain the needed information. With the help of the proposed system, we can remove irrelevant images from a given ranking list. Our system finished 3rd place in the 2019 AI-City challenge for city-scale multi-camera vehicle re-identification.