Vehicle and Pedestrian Detection Using Support Vector Machine and Histogram of Oriented Gradients Features

Abstract

Vehicle and Pedestrian Detection is a key problem in computer vision, with several applications including robotics, surveillance and automotive safety. Much of the progress of the past few years has been driven by the availability of challenging public datasets. In this paper, we build up a vehicle and pedestrian detection system by combing Histogram of Oriented Gradients (HoG) feature and support vector machine (SVM). HoG feature provides a reasonable and feature invariant object representation, while SVM framework gives us a robust classifier that can control both the training set error and the classifier's complexity. A detailed system architecture design is presented and the testing experiments show that high performance in both accuracy and speed can be achieved by the developed system.