Vehicle Brake Light Detection Using Hybrid Color Model

Abstract:

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.

• Periodical: Applied Mechanics and Materials (Volume 695)
• Pages: 828-831
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.695.828
• Online since: November 2014
• Authors: Siti Amaniah Mohd Chachuli*, Khairul Anuar Ishak, Norbayah Yusop
• Keywords: Brake, HSI, Hybrid, Otsu Method

References

[1] Almagambetov, A., Casares, M., Velipasalar, S., Autonomous Tracking of Vehicle Rear Lights and Detection of Brakes and Turn Signals, IEEE Symposium on Computational Intelligence for Security and Defence Applications (CISDA), pp.1-7, (2012).

DOI: 10.1109/cisda.2012.6291543

[2] E. Cuevas, D. Zaldivar, and R. Rojas. Kalman filter for vision tracking. Technical Report B 05-12, Freie Universitat Berlin, Inst. Informatik, Berlin, Germany, (2005).

[3] D. Koller, J. Weber, and M. J. Robust multiple car tracking with occlusion reasoning. Springer-Verlag, Germany, (2006).

[4] Y. -M. Chan, S. -S. Huang, L. -C. Fu, and P. -Y. Hsiao, Vehicle detection under various lighting conditions by incorporating particle filter. IEEE Intelligent Transportation Systems Conf. ITSC 2007, p.534–539, (2007).

DOI: 10.1109/itsc.2007.4357745

[5] R. O'Malley, E. Jones, and M. Glavin, Rear-lamp vehicle detection and tracking in low-exposure color video for night conditions, IEEE Transactions on Intelligent Transportation Systems, 11(2): 453–462, (2010).

DOI: 10.1109/tits.2010.2045375

[6] Q. Ming and K. -H. Jo, Vehicle detection using tail light segmentation, 6th Int Strategic Technology (IFOST) Forum, vol. 2, p.729–732, (2011).

DOI: 10.1109/ifost.2011.6021126

[7] P. Thammakaroon and P. Tangamchit, Predictive brake warning at night using taillight characteristic, IEEE Int. Symp. Industrial Electronics, p.217–221, (2009).

DOI: 10.1109/isie.2009.5218254

[8] S. Nagumo, H. Hasegawa, and N. Okamoto, Extraction of forward vehicles by front-mounted camera using brightness information, Canadian Conf. Electrical and Computer Engineering IEEE CCECE 2003, vol. 2, p.1243–1246, (2003).

DOI: 10.1109/ccece.2003.1226124

[9] M. -Y. Chern and P. -C. Hou, The lane recognition and vehicle detection at night for a camera-assisted car on highway, IEEE Int. Conf. Robotics and Automation ICRA '03, vol. 2, p.2110–2115, (2003).

DOI: 10.1109/robot.2003.1241905