A Cost-Effective Framework for Automated Vehicle-Pedestrian Near-Miss Detection Through Onboard Monocular Vision
Abstract
Onboard monocular cameras have been widely deployed in both public transit and personal vehicles. Obtaining vehicle-pedestrian near-miss event data from onboard monocular vision systems may be cost-effective compared with onboard multiple-sensor systems or traffic surveillance videos. But extracting near-misses from onboard monocular vision is challenging and little work has been published. This paper fills the gap by developing a framework to automatically detect vehicle-pedestrian near-misses through onboard monocular vision. The proposed framework can estimate depth and real-world motion information through monocular vision with a moving video background. The experimental results based on processing over 30-hours video data demonstrate the ability of the system to capture near-misses by comparison with the events logged by the Rosco/MobilEye Shield+ system which includes four cameras working cooperatively. The detection overlap rate reaches over 90% with the thresholds properly set.
Cite
Text
Ke et al. "A Cost-Effective Framework for Automated Vehicle-Pedestrian Near-Miss Detection Through Onboard Monocular Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.124Markdown
[Ke et al. "A Cost-Effective Framework for Automated Vehicle-Pedestrian Near-Miss Detection Through Onboard Monocular Vision." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/ke2017cvprw-costeffective/) doi:10.1109/CVPRW.2017.124BibTeX
@inproceedings{ke2017cvprw-costeffective,
title = {{A Cost-Effective Framework for Automated Vehicle-Pedestrian Near-Miss Detection Through Onboard Monocular Vision}},
author = {Ke, Ruimin and Lutin, Jerome and Spears, Jerry and Wang, Yinhai},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2017},
pages = {898-905},
doi = {10.1109/CVPRW.2017.124},
url = {https://mlanthology.org/cvprw/2017/ke2017cvprw-costeffective/}
}