These days traffic congestion is becoming a
serious problem. Roads and streets are getting over
crowded, mainly in large cities leading to long vehicle
queue, long hour of traffic on daily basis. This can
evoke the day-to-day travellers to violate or break the
traffic rules which can sometimes lead to accidents.
Controlling and managing traffic system is the most
demanding work in present days and the tradition
traffic system cannot manage it efficiently. Nowadays
worldwide in many big cities Intelligent system is been
used for traffic surveillance and controlling. Therefore,
we proposed a traffic control and management system
which will detect the movement of vehicles, identify,
track and count the numbers of vehicles in the lane by
analysing a real-time live video feed form the camera
with the help of computer vision and after detecting,
classifying and counting the numbers of vehicle on a
specific lane it will control traffic light according to the
set threshold value, threshold value will be based on two
criteria one is the density count of the lane and other is
priority of that lane. This is done by using OpenCV and
(YOLOV3) You Only Look Once real-time object
detection algorithm based on CNN (Convolutional
Neural Network).
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.