On-road precise vehicle detection system using ROI estimation

Abstract

In this paper, the authors propose a new on-road vehicle detection system. Appearance of vehicles in image has various ratios because of its many kinds of models such as sedan, SUV and truck. For this reason, using ROI with fixed ratio can cause the degradation for detecting vehicles of various models. To solve this problem, the authors propose a new vehicle detection system using estimating ratio of vehicles. The proposed method estimates the ratio of vehicle ROI and extracted feature based evaluated ratio. It shows robust detection performance for various vehicle models because it extracts the feature from compact ROI with exact vehicle size. In these experiments, histogram of oriented histogram (HOG) feature and support vector machine (SVM) are used for the vehicle detection system. In order to evaluate the detection performance, the Pittsburgh dataset including various vehicle models such as sedan, SUV, truck and bus is used. In this dataset, it is shown that the proposed method is more robust than previous works to detect various vehicle models.