City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones
Abstract
Multi-Target Multi-Camera Tracking has a wide range of applications and is the basis for many advanced inferences and predictions. This paper describes our solution to the Track 3 multi-camera vehicle tracking task in 2021 AI City Challenge (AICITY21). This paper proposes a multi-target multi-camera vehicle tracking framework guided by the crossroad zones. The framework includes: (1) Use mature detection and vehicle re-identification models to extract targets and appearance features. (2) Use modified JDE-Tracker (without detection module) to track single-camera vehicles and generate single-camera tracklets. (3) According to the characteristics of the crossroad, the Tracklet Filter Strategy and the Direction Based Temporal Mask are proposed. (4) Propose Sub-clustering in Adjacent Cameras for multi-camera tracklets matching. Through the above techniques, our method obtained an IDF1 score of 0.8095, ranking first on the leaderboard1. The code will be released later.
Cite
Text
Liu et al. "City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00466Markdown
[Liu et al. "City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/liu2021cvprw-cityscale/) doi:10.1109/CVPRW53098.2021.00466BibTeX
@inproceedings{liu2021cvprw-cityscale,
title = {{City-Scale Multi-Camera Vehicle Tracking Guided by Crossroad Zones}},
author = {Liu, Chong and Zhang, Yuqi and Luo, Hao and Tang, Jiasheng and Chen, Weihua and Xu, Xianzhe and Wang, Fan and Li, Hao and Shen, Yi-Dong},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2021},
pages = {4129-4137},
doi = {10.1109/CVPRW53098.2021.00466},
url = {https://mlanthology.org/cvprw/2021/liu2021cvprw-cityscale/}
}