Vision-based vehicle detector in various traffic conditions with reducing shadow effects

Bing-Fei Wu, Jhy Hong Juang*

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

Abstract

Multiple-vehicle detection and tracking systems are becoming increasingly important in visual-based ITS applications. This paper proposes methods for solving problems of vehicle detection in various traffic conditions with reducing shadow effects that frequently appears in the real traffic conditions. It is always a tough task for a vision-based vehicle detector working well in various traffic conditions. These various conditions include traffic jams, night conditions, shadow conditions and various weather conditions. In this paper, first, the effects of weather and light impacts are removed. Second, vehicle detection with proper merging and splitting procedures is utilized to detect the vehicle candidates. Finally, useful traffic parameters are built based on a tracking procedure with reducing shadow effects. Experimental results show that the proposed methods are robust, accurate, and powerful to overcome complex weather conditions and shadow effects.

Original languageEnglish
Pages (from-to)334-342
Number of pages9
JournalJournal of Convergence Information Technology
Volume6
Issue number11
DOIs
StatePublished - 1 Nov 2011

Keywords

  • Shadow
  • Tracking
  • Traffic Jam
  • Traffic Parameter
  • Vehicle Detection

Fingerprint Dive into the research topics of 'Vision-based vehicle detector in various traffic conditions with reducing shadow effects'. Together they form a unique fingerprint.

Cite this