3D perception of vehicle surroundings

Paper Title:

A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective

Published on:

8 May 2024

Primary Category:

Computer Vision and Pattern Recognition

Paper Authors:

Huaiyuan Xu,

Junliang Chen,

Shiyu Meng,

Yi Wang,

Lap-Pui Chau

Bullets

Key Details

•

3D occupancy perception is an emerging trend for autonomous vehicle perception systems

•

It fuses multi-source input data to capture 3D environments

•

Key methodologies involve 2D-to-3D transformations, multi-view and multi-frame fusion

•

It shows promise for precise scene understanding to enable autonomous driving tasks

Explore the topics in this paper

3d occupancy

autonomous vehicles

deep learning

scene understanding

sensor fusion

AI generated summary

3D perception of vehicle surroundings

This paper surveys recent research on 3D occupancy perception, which seeks to capture detailed 3D structures around vehicles to enable autonomous driving systems to precisely understand complex environments. It highlights that occupancy perception combines inputs from multiple sensors and fuses information across data sources. Key challenges include converting 2D images to 3D representations, integrating multi-camera and multi-frame observations, and training networks. The paper analyzes performance on datasets and discusses future opportunities like robust perception, generalized understanding via language models, and planning applications.