01520141

Component

The paper outlines a new idea of abandoned object detection based on three-dimensional image information to prevent traffic accidents for traffic surveillance systems. It is proposed a new BIRR (Binocular Information Reconstruction and Recognition) algorithm to implement the new idea. As initial detection, suspected-abandoned objects are detected by proposed dual-background difference algorithm based on surveillance video from monocular camera. After detection of suspected-abandoned object, 3D (three-dimensional) information of suspected-abandoned object is reconstructed by proposed theory about 3D object information reconstruction with images from binocular camera. To determine whether the detected object is hazardous to normal road traffic, road plane equation and height of suspected-abandoned object are calculated based on three-dimensional information. Experiments results show that the algorithm implements real time detection of abandoned objects and has detection accuracy of 93%. This algorithm can be used for road traffic monitoring and public area surveillance.

This paper was sponsored by TRB committee ABJ50 Information Systems and Technology.

01503729

14-0447

English

18p

2014

Transportation Research Board 93rd Annual Meeting

Digital/other

Figures; References; Tables

Algorithms; Detection and identification systems; Surveillance; Traffic crashes; Video cameras

Data and Information Technology; Highways; I72: Traffic and Transport Planning

Transportation Research Board Annual Meeting 2014 Paper #14-0447

TRIS, TRB, ATRI

Jan 27 2014 2:14PM