The obstacle detection method using optical flow estimation at the edge image

Takayuki Naito, Toshio Ito, Yukio Kaneda

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

21 Citations (Scopus)

Abstract

The purpose of this study is to develop an algorithm for the detection of the obstacle ahead of a host vehicle by image processing using a monocular onboard camera, and to show that this algorithm is able to apply the prevention of the collision accident. It can be supposed that there is some important information on the edge of the image. In this paper we show an obstacle detection method by extracting optical flow along the edge of the image, and estimated result of the three dimensional (3D) information in the world coordinate system from the optical flow.

Original languageEnglish
Title of host publicationProceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007
Pages817-822
Number of pages6
Publication statusPublished - 2007 Dec 1
Externally publishedYes
Event2007 IEEE Intelligent Vehicles Symposium, IV 2007 - Istanbul, Turkey
Duration: 2007 Jun 132007 Jun 15

Publication series

NameIEEE Intelligent Vehicles Symposium, Proceedings

Conference

Conference2007 IEEE Intelligent Vehicles Symposium, IV 2007
CountryTurkey
CityIstanbul
Period07/6/1307/6/15

ASJC Scopus subject areas

  • Modelling and Simulation
  • Automotive Engineering
  • Computer Science Applications

Fingerprint Dive into the research topics of 'The obstacle detection method using optical flow estimation at the edge image'. Together they form a unique fingerprint.

  • Cite this

    Naito, T., Ito, T., & Kaneda, Y. (2007). The obstacle detection method using optical flow estimation at the edge image. In Proceedings of the 2007 IEEE Intelligent Vehicles Symposium, IV 2007 (pp. 817-822). [4290217] (IEEE Intelligent Vehicles Symposium, Proceedings).