NEW VEHICLE DETECTION ALGORITHM USING SYMMETRY SEARCH AND GA-BASED SVM

Abstract

In this paper, we present a two-stage vision-based approach to detect front and rear vehicle views in road scene images. The first stage is hypothesis generation (HG), in which potential vehicles are hypothesized. During the HG step, we use a vertical, horizontal edge map, and different colors between road background and the lower part of vehicle to determine the bottom position of the vehicle. Next, we apply vertical symmetry axis detection into contour edge images to build the potential regions where vehicles may be presented. The second stage is hypothesis verification (HV). In this stage, all hypotheses are verified by Decision Tree (DT) training combined with a modified Genetic Algorithm (GA) to find the best features subset based on Haar-like feature extraction and an appropriate parameters set of Support Vector Machine for classification, which is robust for front and rear views of vehicle detection and recognition problems.