Title :
The Obstacle Detection Method using Optical Flow Estimation at the Edge Image
Author :
Naito, Takayuki ; Ito, Toshio ; Kaneda, Yukio
Author_Institution :
Kwansei Gakuin Univ., Nishinomiya
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.
Keywords :
collision avoidance; image processing; traffic engineering computing; cars; collision accident; edge image; image processing; obstacle detection method; optical flow estimation; traffic accidents; Cameras; Data mining; Equations; Gradient methods; Image edge detection; Image motion analysis; Intelligent vehicles; Optical detectors; Vehicle detection; Vehicle safety;
Conference_Titel :
Intelligent Vehicles Symposium, 2007 IEEE
Conference_Location :
Istanbul
Print_ISBN :
1-4244-1067-3
Electronic_ISBN :
1931-0587
DOI :
10.1109/IVS.2007.4290217
