Optical Flow for Autonomous Driving: Applications, Challenges and Improvements

TL;DR

This paper reviews optical flow estimation for autonomous driving, highlighting challenges like fisheye lens distortion and low light, and proposes novel training strategies and semi-supervised frameworks to improve accuracy in these conditions.

Contribution

It introduces new training strategies for fisheye optical flow and a semi-supervised approach to enhance performance in low-light scenarios, addressing gaps in current methods.

Findings

Model generalizes well from synthetic to real fisheye data.

Semi-supervised framework improves optical flow accuracy in low light.

First approach explicitly targeting low-light optical flow estimation.

Abstract

Optical flow estimation is a well-studied topic for automated driving applications. Many outstanding optical flow estimation methods have been proposed, but they become erroneous when tested in challenging scenarios that are commonly encountered. Despite the increasing use of fisheye cameras for near-field sensing in automated driving, there is very limited literature on optical flow estimation with strong lens distortion. Thus we propose and evaluate training strategies to improve a learning-based optical flow algorithm by leveraging the only existing fisheye dataset with optical flow ground truth. While trained with synthetic data, the model demonstrates strong capabilities to generalize to real world fisheye data. The other challenge neglected by existing state-of-the-art algorithms is low light. We propose a novel, generic semi-supervised framework that significantly boosts performances of existing methods in such conditions. To the best of our knowledge, this is the first approach that explicitly handles optical flow estimation in low light.