The venture is intended to foster a thickness based unique traffic light framework. The sign timing changes consequently on detecting the traffic thickness at the intersection. Gridlock is an extreme issue in many significant urban communities across the world and it has turned into a bad dream for the workers in these urban areas. Traditional traffic signal framework depends on fixed time idea allocated to each side of the intersection which can't be changed according to fluctuating traffic thickness. Intersection timings apportioned are fixed. Some of the time higher traffic thickness at one side of the intersection requests longer green time when contrasted with standard allocated time. The item identification in the traffic light is handled and changed over into test system then, at that point, its limit is determined in view of which the shape has been attracted request to ascertain the quantity of vehicles present nearby. In the wake of working out the quantity of vehicles we will came to realize in which side the thickness is high in light of which signs will be distributed for a specific side. On account of its high recognition rate, CNN can be used to realize various computer vision tasks. Tensor Flow is used to implement CNN. In the German data sets, we are able to identify the circular symbol with more than 98.2% accuracy.