Embedded Computing Framework for Vision-Based Real-Time Surround Threat Analysis and Driver Assistance
Abstract
In this paper, we present a distributed embedded vision system that enables surround scene analysis and vehicle threat estimation. The proposed system analyzes the surroundings of the ego-vehicle using four cameras, each connected to a separate embedded processor. Each processor runs a set of optimized vision-based techniques to detect surrounding vehicles, so that the entire system operates at real-time speeds. This setup has been demonstrated on multiple vehicle testbeds with high levels of robustness under real-world driving conditions and is scalable to additional cameras. Finally, we present a detailed evaluation which shows over 95% accuracy and operation at nearly 15 frames per second.
Cite
Text
Lu et al. "Embedded Computing Framework for Vision-Based Real-Time Surround Threat Analysis and Driver Assistance." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016. doi:10.1109/CVPRW.2016.117Markdown
[Lu et al. "Embedded Computing Framework for Vision-Based Real-Time Surround Threat Analysis and Driver Assistance." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2016.](https://mlanthology.org/cvprw/2016/lu2016cvprw-embedded/) doi:10.1109/CVPRW.2016.117BibTeX
@inproceedings{lu2016cvprw-embedded,
title = {{Embedded Computing Framework for Vision-Based Real-Time Surround Threat Analysis and Driver Assistance}},
author = {Lu, Frankie and Lee, Sean and Satzoda, Ravi Kumar and Trivedi, Mohan M.},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2016},
pages = {901-909},
doi = {10.1109/CVPRW.2016.117},
url = {https://mlanthology.org/cvprw/2016/lu2016cvprw-embedded/}
}