Bionic vision inspired on-road obstacle detection and tracking using radar and visual information

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

43 Scopus citations

Abstract

Inspired by the cooperation between the cone cell and the rod cell in human vision system, this paper presents a novel method for fusing millimeter wave (MMW) radar and monocular vision sensor information for on-road obstacle detection. The MMW radar performs similarly as the cone cell to indicate potential target region in the view, while the camera plays the same role as that of the rod cell to obtain precise target contour and to allow tracking over frames. Using real-world data collected from on-road vehicles, experimental evaluations have shown that, our proposed system could detect on-road obstacles with high detection rate and low false-alarm rate, yet the overall image processing time is significantly reduced compared to conventional approaches. In addition, the system has been applied on our unmanned vehicle for the past two years' 'Future Challenge' autonomous vehicles competition.

Original languageEnglish
Title of host publication2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages39-44
Number of pages6
ISBN (Electronic)9781479960781
DOIs
StatePublished - 14 Nov 2014
Event2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014 - Qingdao, China
Duration: 8 Oct 201411 Oct 2014

Publication series

Name2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014

Conference

Conference2014 17th IEEE International Conference on Intelligent Transportation Systems, ITSC 2014
Country/TerritoryChina
CityQingdao
Period8/10/1411/10/14

Fingerprint

Dive into the research topics of 'Bionic vision inspired on-road obstacle detection and tracking using radar and visual information'. Together they form a unique fingerprint.

Cite this