DeepCrashTest: Turning Dashcam Videos into Virtual Crash Tests for Automated Driving Systems
Lists
Only you see this
Abstract
The goal of this paper is to generate simulations with real-world collision scenarios for training and testing autonomous vehicles. We use numerous dashcam crash videos uploaded on the internet to extract valuable collision data and recreate the crash scenarios in a simulator. We tackle the problem of extracting 3D vehicle trajectories from videos recorded by an unknown and uncalibrated monocular camera source using a modular approach. A working architecture and demonstration videos along with the open-source implementation are provided with the paper.
BibTeX
@inproceedings{bashetty2020deepcrashtest,
author = {Sai Krishna Bashetty and Heni Ben Amor and Georgios Fainekos},
title = {{DeepCrashTest: Turning Dashcam Videos into Virtual Crash Tests for Automated Driving Systems}},
booktitle = {IEEE International Conference on Robotics and Automation},
year = {2020},
url = {https://openreview.net/forum?id=0lX5jQcozX},
}Loading related content...