Surround-view Fisheye Camera Perception for Automated Driving: Overview, Survey and Challenges

TL;DR

This paper reviews surround-view fisheye camera perception in automated driving, highlighting unique challenges, existing methods, and future research directions for near-field perception tasks.

Contribution

It provides a comprehensive overview, taxonomy, and discussion of perception tasks, challenges, and future directions specific to fisheye cameras in automotive applications.

Findings

Limited datasets for near-field perception tasks.

High precision detection of 10cm is required.

Fisheye distortion complicates standard perception algorithms.

Abstract

Surround-view fisheye cameras are commonly used for near-field sensing in automated driving. Four fisheye cameras on four sides of the vehicle are sufficient to cover 360{\deg} around the vehicle capturing the entire near-field region. Some primary use cases are automated parking, traffic jam assist, and urban driving. There are limited datasets and very little work on near-field perception tasks as the focus in automotive perception is on far-field perception. In contrast to far-field, surround-view perception poses additional challenges due to high precision object detection requirements of 10cm and partial visibility of objects. Due to the large radial distortion of fisheye cameras, standard algorithms cannot be extended easily to the surround-view use case. Thus, we are motivated to provide a self-contained reference for automotive fisheye camera perception for researchers and practitioners. Firstly, we provide a unified and taxonomic treatment of commonly used fisheye camera models. Secondly, we discuss various perception tasks and existing literature. Finally, we discuss the challenges and future direction.