Vehicle Re-Identifiation and Multi-Camera Tracking in Challenging City-Scale Environment

Abstract

In our submission to the NVIDIA AI City Challenge, we address vehicle re-identification and vehicle multi-camera tracking. Our approach to vehicle re-identification is based on the extraction of visual features and aggregation of these features in the temporal domain to obtain a single feature descriptor for the whole observed track. For multi-camera tracking, we proposed a method for matching vehicles by the position of trajectory points in real-world space (linear coordinate system). Furthermore, we use CNN for vehicle re-identification task to filter out false matches generated by proposed positional matching method for better results.

Cite

Text

Spanhel et al. "Vehicle Re-Identifiation and Multi-Camera Tracking in Challenging City-Scale Environment." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.

Markdown

[Spanhel et al. "Vehicle Re-Identifiation and Multi-Camera Tracking in Challenging City-Scale Environment." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019.](https://mlanthology.org/cvprw/2019/spanhel2019cvprw-vehicle/)

BibTeX

@inproceedings{spanhel2019cvprw-vehicle,
  title     = {{Vehicle Re-Identifiation and Multi-Camera Tracking in Challenging City-Scale Environment}},
  author    = {Spanhel, Jakub and Bartl, Vojtech and Juránek, Roman and Herout, Adam},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2019},
  pages     = {150-158},
  url       = {https://mlanthology.org/cvprw/2019/spanhel2019cvprw-vehicle/}
}