• Sunil Jaybhaye
• Neha Bhalke
• Pankaj Chavan
• Prof. Mrs Nutan Patil

The idea is to create a traffic light system that varies depending on the number of people present. The signal time adjusts automatically when there is a lot of traffic at an intersection. Many large cities across the world have heavy traffic, making it difficult to travel to work on a daily basis. Traditional traffic signal systems work on the assumption that each side of an intersection has a certain amount of time. They can't be altered to accommodate increased traffic. The times of the intersections that have been put up for them cannot be changed. There may be more traffic at one intersection, making the regular green time more difficult to terminate. Following the processing and . A threshold is defined and a contour is drawn to illustrate how many automobiles are in the region after translating the traffic signal object recognition into a simulator. We can figure out which side has the most cars based on the signals given to each side and the number of cars

CNN, Machine Learning, preprocessing, classification, self-driving, traffic signals, deep learning, detection

"Problems with Traffic Signal Scheduling in Heterogeneous Traffic Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.e34-e37, May-2022, Available :http://www.jetir.org/papers/JETIR2205504.pdf

"Problems with Traffic Signal Scheduling in Heterogeneous Traffic Networks", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppe34-e37, May-2022, Available at : http://www.jetir.org/papers/JETIR2205504.pdf