Evaluating State-of-the-Art Object Detector on Challenging Traffic Light Data
Abstract
Traffic light detection (TLD) is a vital part of both intel- ligent vehicles and driving assistance systems (DAS). Gen- eral for most TLDs is that they are evaluated on small and private datasets making it hard to determine the exact per- formance of a given method. In this paper we apply the state-of-the-art, real-time object detection system You Only Look Once, (YOLO) on the public LISA Traffic Light dataset available through the VIVA-challenge, which contain a high number of annotated traffic lights, captured in varying light and weather conditions.<br/>The YOLO object detector achieves an AUC of impres- sively 90.49 % for daysequence1, which is an improvement of 50.32 % compared to the latest ACF entry in the VIVA- challenge. Using the exact same training configuration as the ACF detector, the YOLO detector reaches an AUC of 58.3 %, which is in an increase of 18.13 %.
Cite
Text
Jensen et al. "Evaluating State-of-the-Art Object Detector on Challenging Traffic Light Data." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.122Markdown
[Jensen et al. "Evaluating State-of-the-Art Object Detector on Challenging Traffic Light Data." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/jensen2017cvprw-evaluating/) doi:10.1109/CVPRW.2017.122BibTeX
@inproceedings{jensen2017cvprw-evaluating,
title = {{Evaluating State-of-the-Art Object Detector on Challenging Traffic Light Data}},
author = {Jensen, Morten B. and Nasrollahi, Kamal and Moeslund, Thomas B.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2017},
pages = {882-888},
doi = {10.1109/CVPRW.2017.122},
url = {https://mlanthology.org/cvprw/2017/jensen2017cvprw-evaluating/}
}