A Vision-Based System for Traffic Anomaly Detection Using Deep Learning and Decision Trees

CVPRW 2021 pp. 4207-4212

doi:10.1109/CVPRW53098.2021.00475 /cvprw/2021/aboah2021cvprw-visionbased/

Abstract

Any intelligent traffic monitoring system must be able to detect anomalies such as traffic accidents in real time. In this paper, we propose a Decision-Tree enabled approach powered by deep learning for extracting anomalies from traffic cameras while accurately estimating the start and end times of the anomalous event. Our approach included creating a detection model, followed by anomaly detection and analysis. YOLOv5 served as the foundation for our detection model. The anomaly detection and analysis step entail traffic scene background estimation, road mask extraction, and adaptive thresholding. Candidate anomalies were passed through a decision tree to detect and analyze final anomalies. The proposed approach yielded an F1 score of 0.8571, and an S4 score of 0.5686, per the experimental validation.

PDF CVPRW Semantic Scholar

Cite

Text

Aboah. "A Vision-Based System for Traffic Anomaly Detection Using Deep Learning and Decision Trees." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021. doi:10.1109/CVPRW53098.2021.00475

Markdown

[Aboah. "A Vision-Based System for Traffic Anomaly Detection Using Deep Learning and Decision Trees." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2021.](https://mlanthology.org/cvprw/2021/aboah2021cvprw-visionbased/) doi:10.1109/CVPRW53098.2021.00475

BibTeX

@inproceedings{aboah2021cvprw-visionbased,
  title     = {{A Vision-Based System for Traffic Anomaly Detection Using Deep Learning and Decision Trees}},
  author    = {Aboah, Armstrong},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2021},
  pages     = {4207-4212},
  doi       = {10.1109/CVPRW53098.2021.00475},
  url       = {https://mlanthology.org/cvprw/2021/aboah2021cvprw-visionbased/}
}