This paper is published in Volume-7, Issue-1, 2021
Area
Computer Vision
Author
Sahil Shaikh, Swapnil Patil, Niranjan Patil, Purushottam Kulkarni, J. K. Kamble
Org/Univ
SCTR'S Pune Institute of Computer Technology, Pune, Maharashtra, India
Pub. Date
15 February, 2021
Paper ID
V7I1-1236
Publisher
Keywords
Yolov4, OCR, Computer Vision

Citationsacebook

IEEE
Sahil Shaikh, Swapnil Patil, Niranjan Patil, Purushottam Kulkarni, J. K. Kamble. Smart traffic manager: Computer vision and deep learning-based approach, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Sahil Shaikh, Swapnil Patil, Niranjan Patil, Purushottam Kulkarni, J. K. Kamble (2021). Smart traffic manager: Computer vision and deep learning-based approach. International Journal of Advance Research, Ideas and Innovations in Technology, 7(1) www.IJARIIT.com.

MLA
Sahil Shaikh, Swapnil Patil, Niranjan Patil, Purushottam Kulkarni, J. K. Kamble. "Smart traffic manager: Computer vision and deep learning-based approach." International Journal of Advance Research, Ideas and Innovations in Technology 7.1 (2021). www.IJARIIT.com.

Abstract

In the last couple of decades, the number of vehicles has been on the road increased drastically. Hence it has become very difficult to keep track of every vehicle for traffic management and law enforcement. With the increasing number of vehicles on roads, it is getting difficult to manually enforce laws and traffic rules for smooth traffic flow. Traffic Management systems are installed on traffic signals to check for vehicles breaking the traffic rules. To automate all these processes a system is required to easily identify a vehicle. The main aim to design this system is to reduce the mishaps which occur due to reckless driving and violations of the traffic rules. The important question here is how to identify a particular vehicle, The obvious answer to this question is by using the vehicle’s registered license plate as every vehicle has a unique number through which it is easily differentiated from all the other vehicles. Vehicles in each country have a unique license number, which is written on their registered number plate. This number distinguishes one vehicle from the other, which is useful especially when both are of the same make and model. So, the basic idea will be identifying whether the two-wheeler rider is wearing a helmet or not, over speeding vehicles, zebra crossing violators, etc. Most of the tasks in this will require machine learning/deep learning models for image processing tasks. In the end, this system would be very effective to automate the hectic task of the traffic police and can be very efficient in terms to reduce the workload and manage the different tasks autonomously.
Paper PDF