Application of the image analysis technique to detect left-turning vehicles at intersections.

Author(s)
Lu, Y.-J. Hsu, Y.-H. & Tan, G.C.
Year
Abstract

This study applies the image analysis technique to detect left-turning vehicles at intersections. The problems existing in the current method of left-turn data collection are discussed. An optical image device system including a CCD video camera, an interface board, an image monitor, and an ibm pc/at was used. An algorithm with linear time complexity was developed for detecting left-turning movements at intersections. Microcomputer software was derived for the algorithm. This computer system is a real time system. The accuracy of the algorithm is about 80% for detecting the left-turning vehicles whose signal lights are on. This study so far has had only limited success. The difficulties of attaining greater accuracy as well as the possibilities of improving the developed image analysis system are also discussed.

Request publication

1 + 0 =
Solve this simple math problem and enter the result. E.g. for 1+3, enter 4.

Publication

Library number
C 15556 (In: C 15543 S) /71 / IRRD 828102
Source

In: Traffic flow theory and highway capacity : a peer-reviewed publication of the Transportation Research Board TRB, Transportation Research Record TRR No. 1194, p. 120-128, 17 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.