• Manasi Adsul
• Isha Chhawchharia
• Nidhi Chauhan
• Kumud Wasnik

With advanced technology coming into play so frequently, there is a prominent need to develop a solution to reduce traffic congestion by high volumes of vehicles, especially on urban roads. The time delay of the signal lights and the go-time is hard-coded on the signal and does not depend on the actual traffic at a given time. The development of an Intelligent Traffic Signal Control (ITSC) system is needed. The objective of the paper is to create an Automated Traffic Signal Control (ATSC) and automate the process of video surveillance in real-time. This study aims to develop a solution to control traffic congestion using computer vision and deep learning. The signal timing of each lane decided on the density of the vehicles is found using deep CNN called You Only Look Once (YOLO). Vehicles are classified using the ReLU activation function in the Alexnet model as Emergency or Non-Emergency. Based on this classification, emergency vehicles get the highest priority.

Intelligent Traffic Signal Control, ATSC, Video-surveillance, Computer vision, Deep learning, YOLO, Deep CNN, Alexnet CNN, ReLU.

"Real Time Automated Traffic Signal Controller", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 6, page no.c71-c76, June-2021, Available :http://www.jetir.org/papers/JETIR2106279.pdf

"Real Time Automated Traffic Signal Controller", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 6, page no. ppc71-c76, June-2021, Available at : http://www.jetir.org/papers/JETIR2106279.pdf