Automatic incident detection using computer vision techniques.

Author(s)
Blosseville, J.M. Sellam, S. Guillen, S. Motika, V. & Bessaguet, F.
Year
Abstract

The main objective of the DRIVE project INVAID (V 1026) is to develop an Automatic Incident Detection System for both, motorway and urban network application, using computer vision techniques. Computer vision involves the automatic digitizing, processing and interpretation of the pictures from roadside CCTV cameras. INVAID is therefore primarily concerned with the interpretation of camera information and the preparation of information to be sent to operators. The INVAID system comprises three main modules: There are two data/image processing modules, each using different camera arrangements, image processing and algorithms. The third module, the Central System, takes its input from the data/image processing modules and additional information from the RTI (Road Transport Informatics) systems in order to provide output, through a man-machine interface, suitable for use by traffic controller. In this paper one of the data/image processing modules (Type A) for both motorway and urban junction application and the Central System are described. The other data/image module is presented in a separate paper.

Request publication

8 + 7 =
Solve this simple math problem and enter the result. E.g. for 1+3, enter 4.

Publication

Library number
C 412 (In: C 367 a) /72 / IRRD 848058
Source

In: Advanced Telematics in Road Transport : proceedings of the DRIVE Conference, Brussels, February 4-6, 1991, Volume I, p. 714-739, 11 ref.

Our collection

This publication is one of our other publications, and part of our extensive collection of road safety literature, that also includes the SWOV publications.