Skip to main navigation Skip to search Skip to main content

Application of Lane Detection Based on Point Instance Network in Autonomous Driving

  • Jialin Liu
  • , Quanqing Yu*
  • , Pengyu Zhu
  • *Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Lane detection is the core problem of autonomous driving. After completing lane recognition, the autonomous driving system can realize the active safety and control function of vehicle lateral movement. However, the existing methods cannot adapt well to various environments and generate many unnecessary points, resulting in low detection accuracy. In this paper, Point Instance Network (PINet) based on key points estimation and instance segmentation is used, which is composed of several stacked hourglass networks that are trained at the same time. Compared with existing algorithms, PINet achieves ideal accuracy and false positive rate on CULane, especially in night and dazzle light.

Original languageEnglish
Title of host publicationThe Proceedings of the 5th International Conference on Energy Storage and Intelligent Vehicles, ICEIV 2022
EditorsFengchun Sun, Qingxin Yang, Erik Dahlquist, Rui Xiong
PublisherSpringer Science and Business Media Deutschland GmbH
Pages1014-1022
Number of pages9
ISBN (Print)9789819910267
DOIs
StatePublished - 2023
Externally publishedYes
Event5th International Conference on Energy Storage and Intelligent Vehicles, ICEIV 2022 - Virtual, Online
Duration: 3 Dec 20224 Dec 2022

Publication series

NameLecture Notes in Electrical Engineering
Volume1016 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference5th International Conference on Energy Storage and Intelligent Vehicles, ICEIV 2022
CityVirtual, Online
Period3/12/224/12/22

Keywords

  • Autonomous driving
  • Lane detection
  • Point Instance Network

Fingerprint

Dive into the research topics of 'Application of Lane Detection Based on Point Instance Network in Autonomous Driving'. Together they form a unique fingerprint.

Cite this