2DPCA for Vehicle Detection from CCTV Captured Image

Abstract

This paper has proposed an application of 2D principal component analysis (2DPCA) and genetic algorithm (GA) for vehicle detection from CCTV captured image. The system deploys a 2DPCA algorithm for feature extraction of vehicle within gray scale images. These vehicle feature matrices of size 50x20 are trained and then classified by using genetic algorithm. This system can detect different vehicle sizes from different proportional image area. Bilinear interpolation is used to resize each proportional image area to vehicle feature matrix. The proposed system can detect various type of vehicles at the maximum accuracy of 95 percents.