Title:	Deep Learning for Autonomous Vehicle Vision AdamGeorgJoakim
DNr:	Berzelius-2022-129
Project Type:	LiU Berzelius
Principal Investigator:	Joakim Johnander <joakim.johnander@liu.se>
Affiliation:	Linköpings universitet
Duration:	2022-07-01 – 2023-01-01
Classification:	10207
Keywords:

Abstract

Deep learning has become a cornerstone in surround sensing systems in autonomous vehicles. In this project, several novel types of neural networks are to be tried for different tasks in such surround sensing systems. The primary research questions revolve around processing videos in order to capture the dynamics of the scene or to improve performance for tasks typically tackled with single images. The project is a collaboration between three members at different universities: Lund, Linköping, and Chalmers. Each member is part of another project with GPU-hours, namely Berzelius-2021-100, Berzelius-2022-109, and Berzelius-2022-117.