Vehicle Brake Light Detection Using Hybrid Color Model

Autor: Mohd Chachuli, Siti Amaniah, Ishak, Khairul Anuar, Yusop, Norbayah
Zdroj: Applied Mechanics and Materials; November 2014, Vol. 695 Issue: 1 p828-831, 4p
Abstrakt: This paper presents a method based on hybrid color model (HCM) to detect vehicle brake light during daytime. Five weathers during daytime have been considered in this work which are morning, noon, cloudy, rainy and evening. The hybrid color model (HCM) is developed by combination of red color from RGB color model and saturation and intensity values from HSI color model. Otsu method and HCM method have been applied in this work to find the adaptive threshold. Erosion and dilation techniques have been applied in morphology operations to enhance the detection results. The results have been verified by using Matlab software. From the analyses that have been carried out, this method able to detect vehicle brake light about 90.63% in 0.92 seconds. Comparison of HCM method with CBS method shows that detection by using HCM method produced better detections in a short time. This method also shows that HCM method can be applied on various weathers and situations on the road.
Databáze: Supplemental Index