Nighttime Vehicle Tail Light Detection with Rule Based Image Processing

Abstract

In this paper, an algorithm is presented for nighttime vehicle tail lights detection which is a combination of Haar cascade classifier and rule based image processing. Haar, which is frequently used for vehicle detection in literature and tail lights or rear vision of vehicles are used for detection. However, these algorithms are mostly for daytime vehicle detection. In this paper, we present an algorithm and experimental results for, Haar cascade classifier and rule based image processing combination for nighttime vehicle tail light detection. Experimental results show that the proposed method detects with high accuracy than most of vehicle tail light detection algorithms that using a single classifier.