Vehicle detection and counting by using headlight information in the dark environment

Thou Ho Chen, Jun Liang Chen, Chin-Hsing Chen, Chao Ming Chang

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

13 Citations (Scopus)

Abstract

This paper is dedicated to detecting and counting vehicles in dark (nighttime) environment by using headlight information. The basic idea is to use variation ratio in color space to detect the ground-illumination resulted from the head-lighting of vehicle. Then, headlight classification provides the headlight information for determining the moving-object region and compensating pixels, which are wrongly classified as ground-illumination, back to the object mask. Besides, shadow is possibly detected by prediction rules and then excluded for deriving better results of vehicle segmentation and counting. Experimental results show that the proposed algorithm can detect vehicles and reduce both effects of ground-illumination and shadow. In the normal condition (non-crowding), the average accuracy can be raised near to 90%.

Original languageEnglish
Title of host publicationProceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.
Pages519-522
Number of pages4
DOIs
Publication statusPublished - 2007 Dec 1
Event3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007 - Kaohsiung, Taiwan
Duration: 2007 Nov 262007 Nov 28

Publication series

NameProceedings - 3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007.
Volume2

Other

Other3rd International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIHMSP 2007
CountryTaiwan
CityKaohsiung
Period07-11-2607-11-28

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing
  • Information Systems and Management

Fingerprint Dive into the research topics of 'Vehicle detection and counting by using headlight information in the dark environment'. Together they form a unique fingerprint.

Cite this