Understanding complex scenarios from in-vehicle cameras is essential for safely operating autonomous driving systems in densely populated areas . Intersection areas are one of the most critical as they concentrate aconsiderable number of traffic accidents and fatalities . Detecting and understanding the scene configuration of these usually crowded areas is then ofextreme importance for both autonomous vehicles and modern ADAS aimed at preventing road crashes and increasing the safety of vulnerable road users . An extensiveexperimental activity aimed at identifying the best input configuration andevaluating different network parameters on both the well-known KITTI dataset and the new KITTi-360 sequences shows that our method outperforms current state-of-the-art approaches on a per-frame basis .

Author(s) : Augusto Luis Ballardini, Álvaro Hernández, Miguel Ángel Sotelo

Links : PDF - Abstract

Code :

https://github.com/oktantod/RoboND-DeepLearning-Project


Coursera

Keywords : road - areas - aimed - configuration - intersection -

Leave a Reply

Your email address will not be published. Required fields are marked *