Vision-based vehicle event detection through visual rhythm analysis

Chia Hung Yeh*, Jia Chi Bai, Sun Chen Wang, Po Yi Sung, Ruey Nan Yeh, Maverick Shih

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

In this paper, a simple and reliable on-road vehicle event detection algorithm is proposed to identify events for vehicle. A virtual line at the same position of a frame is employed to extract visual rhythm. The visual rhythm is a compact representation of a video that captures the temporal information of vehicle status of a coarsely spatially sampled video sequence. By analyzing statistical characteristics of the visual rhythm, the events such as safe distance, passing and lane changing can be effectively detected. The proposed techniques can prevent accidents and improve traffic safety by monitoring the alertness of drivers, augmenting vision fields to prevent collision. The proposed system is efficient both in terms of computational complexity and memory requirements. Experimental results show the efficiency and effectiveness of the proposed system for intelligent transport system.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings
Pages309-312
Number of pages4
DOIs
Publication statusPublished - 2008
Externally publishedYes
Event2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Hannover, Germany
Duration: 2008 Jun 232008 Jun 26

Publication series

Name2008 IEEE International Conference on Multimedia and Expo, ICME 2008 - Proceedings

Other

Other2008 IEEE International Conference on Multimedia and Expo, ICME 2008
Country/TerritoryGermany
CityHannover
Period2008/06/232008/06/26

Keywords

  • Intelligent transport system
  • Vehicle event detection
  • Visual rhythm

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Vision-based vehicle event detection through visual rhythm analysis'. Together they form a unique fingerprint.

Cite this