Role Of Artificial Intelligence In Automatic Traffic Light Detection System

Artificial intelligence, Driver assistance system, Traffic Light detection system, visually color deficient, Computer vision, Image processing, Segmentation & classification.

ABSTRACT

In the era of high-end cutting edge technology, Artificial Intelligence (AI) serves as the backbone of intelligent & self-adaptive devices. AI has spread its root in almost every field by providing ease in the development of powerful, robust, and expeditious devices. These AI-based systems serve as a helping tool for Driver Assistance system (DAS) and Traffic Light Detection Systems (TLDS). These systems can be of great help to a visually deficient or a Colorblind person by generating alert messages and helping collision avoidance and saving the driver from any mishap. TLDS may also strengthen the mobility of visually challenged and old-aged. The TLDS stages can be categorized into four steps, preprocessing for noise removal, segmentation for region of interests (ROI) generation, feature extraction actual color, and shape detection. The Application areas for AI in computer vision and image processing are lane detection, trajectory planning, motion detection, geo-location localization, traffic lights, and signs detection, etc. This study concentrates on AI-based TLDS tools/apps and videos. As a result of AI-based TLDS, the roads will be more mobile, energy-efficient, less collided thus saving human lives.

REFERENCES

[1]. E. Koukoumidis, M. Martonosi, and L. S. Peh, “Leveraging smartphone cameras for collaborative road advisories,” IEEE Trans. Mob. Comput., vol. 11, no. 5, pp. 707–723, 2012.
[2]. Shebeeb, O. (2016). Helping Autonomous Vehicles at Signalized Intersections. In TAC 2016: Efficient Transportation-Managing the Demand-2016 Conference and Exhibition of the Transportation Association of Canada.
[3]. M. Fareed, M. A. Anwar, and M. Afzal, “Prevalence and gene frequency of color vision impairments among children of six populations from North Indian region,” Genes Dis., vol. 2, no. 2, pp. 211–218, Jun. 2015.
[4]. J. Kim, H. Cho, M. Hwangbo, J. Choi, J. Canny, and Y. P. Kwon, “Deep Traffic Light Detection for Self-Driving Cars from a Large-scale Dataset.”
[5]. Jensen, M. B., Philipsen, M. P., Møgelmose, A., Moeslund, T. B., & Trivedi, M. M. (2016). Vision for looking at traffic lights: Issues, survey, and perspectives. IEEE Transactions on Intelligent Transportation Systems, 17(7), 1800-1815.
[6]. Buch, N., Velastin, S. A., & Orwell, J. (2011). A review of computer vision techniques for the analysis of urban traffic. IEEE Transactions on Intelligent Transportation Systems, 12(3), 920-939.
[7]. Tubaishat, M., Shang, Y., & Shi, H. (2007, January). Adaptive traffic light control with wireless sensor networks. In 2007 4th IEEE Consumer Communications and Networking Conference (pp. 187-191). IEEE.
[8]. Y. Shen, U. Ozguner, K. Redmill, and J. Liu, “A robust video based traffic light detection algorithm for intelligent vehicles,” IEEE Intell. Veh. Symp. Proc., pp. 521–526, 2009.
[9]. M. Diaz-Cabrera, P. Cerri, and J. Sanchez-Medina, “Suspended traffic lights detection and distance estimation using color features,” IEEE Conf. Intell. Transp. Syst. Proceedings, ITSC, pp. 1315–1320, 2012.
[10]. https://play.google.com/store/apps/details?id=com.js.aitldnr
[11]. https://play.google.com/store/apps/details?id=com.TASAG.MyTrafficLightFree
[12]. https://play.google.com/store/apps/details?id=com.forforest.ringo
[13]. https://play.google.com/store/apps/details?id=com.happyconz.blackbox
[14]. https://play.google.com/store/apps/details?id=com.thefrenchsoftware.driverassistancesystem