CVApr 10, 2021

Preprocessing Methods of Lane Detection and Tracking for Autonomous Driving

arXiv:2104.04755v19 citations
Originality Synthesis-oriented
AI Analysis

This is an incremental survey focused on improving vision-based systems for autonomous driving applications.

The paper surveys preprocessing methods for lane detection and tracking in autonomous driving, addressing challenges like noise and lighting variations to enhance real-time performance for tasks such as lane keeping assistance.

In the past few years, researches on advanced driver assistance systems (ADASs) have been carried out and deployed in intelligent vehicles. Systems that have been developed can perform different tasks, such as lane keeping assistance (LKA), lane departure warning (LDW), lane change warning (LCW) and adaptive cruise control (ACC). Real time lane detection and tracking (LDT) is one of the most consequential parts to performing the above tasks. Images which are extracted from the video, contain noise and other unwanted factors such as variation in lightening, shadow from nearby objects and etc. that requires robust preprocessing methods for lane marking detection and tracking. Preprocessing is critical for the subsequent steps and real time performance because its main function is to remove the irrelevant image parts and enhance the feature of interest. In this paper, we survey preprocessing methods for detecting lane marking as well as tracking lane boundaries in real time focusing on vision-based system.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes