A Method of Lane Departure Identification Based on Roadside Multi-Sensor Fusion

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

Abstract

In order to reduce the lane departure accident caused by driver's negligence, lane departure warning systems (LDWS) have become increasingly prevalent and important. Most proposed approaches mainly focus on how to detect lane markings by single-vehicle systems. However, due to limited detection range and processing ability, the robustness of single-vehicle systems is poor in complex traffic scenarios. Therefore, this paper proposes a method of lane departure identification based on roadside multi-sensor fusion. The time to lane crossing (TLC) is used to identify the lane departure. Compared with a single-vehicle system, the roadside equipment has stronger robustness in special scenarios. This approach also avoids the calculation resource consumption of single-vehicle systems caused by lane detection. The experiment verified that the vehicle detection rate of various scenes exceeded 98%, and the lane departure identification rate was 100%.

Original languageEnglish
Title of host publicationCICTP 2020
Subtitle of host publicationAdvanced Transportation Technologies and Development-Enhancing Connections - Proceedings of the 20th COTA International Conference of Transportation Professionals
EditorsHaizhong Wang, Heng Wei, Lei Zhang, Yisheng An
PublisherAmerican Society of Civil Engineers (ASCE)
Pages190-201
Number of pages12
ISBN (Electronic)9780784482933
DOIs
StatePublished - 2020
Event20th COTA International Conference of Transportation Professionals: Advanced Transportation Technologies and Development-Enhancing Connections, CICTP 2020 - Xi'an, China
Duration: 14 Aug 202016 Aug 2020

Publication series

NameCICTP 2020: Advanced Transportation Technologies and Development-Enhancing Connections - Proceedings of the 20th COTA International Conference of Transportation Professionals

Conference

Conference20th COTA International Conference of Transportation Professionals: Advanced Transportation Technologies and Development-Enhancing Connections, CICTP 2020
Country/TerritoryChina
CityXi'an
Period14/08/2016/08/20

Keywords

  • Lane departure
  • Multi-sensor fusion
  • RSU

Fingerprint

Dive into the research topics of 'A Method of Lane Departure Identification Based on Roadside Multi-Sensor Fusion'. Together they form a unique fingerprint.

Cite this