Quantcast

Development of Nighttime Vehicle Detection System using 5-stage Cascade Classifier

Research paper by Ranganathan Venkatasubramanian, Elangovan M

Indexed on: 23 Dec '18Published on: 19 Dec '18Published in: International Journal of Engineering & Technology



Abstract

There is one death in every four minutes due to road accidents in India. This paper is a contribution towards the development of Advanced Driver Assistance Systems such as overtaking assistance system, Adaptive cruise control system, etc., which in turn could reduce the number of road accidents. This paper proposes a three-step method to detect the vehicles in front during nighttime in one-way road. In the first step, the classifier is trained with negative samples and Region of Interest (ROI) marked positive samples. In the second step, input images are acquired and enhanced. In the third step, the enhanced input images are fed into the trained 5-stage cascade classifier, where the vehicles in front are detected and visually presented. This method can detect the vehicles in front during nighttime in one-way road with 65.6% accuracy.