Overtaking vehicle detection using implicit optical flow

Author

Batavia, Parag H. ; Pomerleau, Dean A. ; Thorpe, Charles E.

Author_Institution

Robotics Inst., Carnegie Mellon Univ., Pittsburgh, PA, USA

fYear

1997

fDate

9-12 Nov 1997

Firstpage

729

Lastpage

734

Abstract

We describe an optical flow based obstacle detection system for use in detecting vehicles approaching the blind spot of a car on highways and city streets. The system runs at near frame rate (8-15 frames/second) on PC hardware. We will discuss the prediction of a camera image given an implicit optical flow field and comparison with the actual camera image. The advantage to this approach is that we never explicitly calculate optical flow. We will also present results on digitized highway images, and video taken from Navlab 5 while driving on a Pittsburgh highway

Keywords

automated highways; automotive electronics; computer vision; image sequences; microcomputer applications; object detection; 8 to 15 Hz; Navlab 5; PC hardware; Pennsylvania; Pittsburgh highway; USA; blind spot; camera image prediction; implicit optical flow; obstacle detection system; overtaking vehicle detection; Automated highways; Cameras; Cities and towns; Hardware; Image motion analysis; Laser radar; Optical sensors; Radar detection; Road vehicles; Vehicle detection;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation System, 1997. ITSC '97., IEEE Conference on

Conference_Location

Boston, MA

Print_ISBN

0-7803-4269-0

Type

conf

DOI

10.1109/ITSC.1997.660564

Filename

660564