Moving Vehicle Detection and Tracking in Traffic Images Based on Horizontal Edges

Abstract

This paper presents a moving vehicle detection and tracking system, which comprising of Horizontal Edges method and Local AutoCorrelation. Horizontal Edges characteristic can be strengthened and the influence of weather condition is reduced by using Local AutoCorrelation, so the detection rate of extracting and tracking moving vehicles with horizontal edge can be raised. Local AutoCorrelation images are generated for vehicle detection and based on Horizontal Edges method. The distance of the gravity center of Horizontal Edges is used to track vehicles in traffic video. We verify the system using a variety of weather (in fog, car shadow existence, morning and evening) traffic video. Experimental results have shown that the high detection rate of moving vehicles be obtained by using the proposed method. DOI: http://dx.doi.org/10.11591/telkomnika.v11i11.3485