Automated Traffic Rule Violation Detection System
By — Avinash Koshal, Parush Gupta and Rohit Sharma
Abstract: The number of vehicles has increased drastically in the last few decades making it difficult to monitor each and every vehicle for traffic management and law enforcement purposes.
Every now and then we hear about road accidents. The most common cause of these accidents is Over-speeding. So we proposed a computer vision based solution using deep learning that automatically detects traffic violators.The main objective is to detect vehicles that do not follow the rules of traffic, such as over-speeding, overloading, not wearing helmet and running on the wrong side of the road. We use Yolov3 for object detection and DeepSort for tracking the vehicles and pedestrians. The system detects the type of violation along with the vehicle information, maintains a log of violations, provides a detailed dashboard and provides alerts to the traffic police personnel. The logs can also be used for forensic purposes.
INTRODUCTION
What is Computer Vision: Computer Vision, often abbreviated as CV, is defined as a field of study that seeks to develop techniques to help computers “see” and understand the content of digital images such as photographs and videos.
Object detection is a computer vision technique for locating instances of objects in images or videos. Object detection algorithms typically leverage machine learning or deep learning to produce meaningful results. When humans look at images or video, we can recognize and locate objects of interest within a matter of moments. The goal of object detection is to replicate this intelligence using a computer.
Object tracking is the process of locating a moving object (or multiple objects) over time using a camera. It has a variety of uses, some of which are: human-computer interaction, security and surveillance, video communication and compression, augmented reality, traffic control, medical imaging and video editing.
Problem Description
As pedestrians taking the dog for a walk, escorting our kids to school, or marching to our workplace in the morning, we’ve all experienced unsafe, fast-moving vehicles operated by inattentive drivers that nearly mow us down.Many of us live in apartment complexes or housing neighborhoods where ignorant drivers disregard safety and zoom by, going way too fast.We feel almost powerless. These drivers disregard speed limits, crosswalk areas, school zones, and “children at play” signs altogether. When there is a speed bump, they speed up almost as if they are trying to catch some air! Apart from this they also don’t follow other traffic rules such as Wearing a helmet, driving in the right lane or do not overload.
Is there anything we can do?
But what if we could catch these reckless neighborhood miscreants in action and provide video evidence of the vehicle, speed, and time of day to local authorities?
So we proposed a computer vision based solution using deep learning that automatically detects traffic violators.The main objective is to detect vehicles that do not follow the rules of traffic, such as over-speeding, overloading, not wearing helmet and running on the wrong side of the road. We use Yolov3 for object detection and DeepSort for tracking the vehicles and pedestrians. The system detects the type of violation along with the vehicle information, maintains a log of violations, provides a detailed dashboard and provides alerts to the traffic police personnel. The logs can also be used for forensic purposes.
Innovation and Impact :
Innovation
* Automated monitoring of traffic
in real time
* Helmet detection
* Overloading detection
* Wrong-way detection
Impact
* Traffic monitoring without human intervention
* Less Traffic Violations
* Reduced road accidents
* Support for forensics
Functional Workflow
Interaction Model
Language(s) | API(s) | Technology Stack
Dashboard
We have used Bootstrap to design the front end. The dashboard contains “Nav-bar”, “Cards”, “Graphs” and “Video feed from IP Camera”. The Charts are built using High Charts. Database is created using phpmyadmin.
Conclusion
With the help of this system our main goal is to reduce the road accidents thereby indirectly trying to save lives and law enforcement.
This system will be used for Traffic monitoring and identify those who violate traffic laws.
Key Words: Computer Vision ,YOLOV3, Object Detection and Tracking, Deep Learning , Artificial Intelligence
References
https://pjreddie.com/
www. wikipedia.org
www.learnopencv.com
www.iopscience.iop.org
www.researchgate.net
