Harnessing AI for Traffic Regulation

Published 16 Dec, 2023

Vehant Technologies announced a significant achievement through its partnership with the Delhi Police the previous year. The esteemed law enforcement agency has chosen our smart security and surveillance solutions, opting for installing 535 Automatic Number Plate Recognition (ANPR) software at key locations throughout the city.

The AI-powered ANPR system integrates with police station control rooms, enhancing traffic surveillance by efficiently analyzing video streams to recognize and capture vehicle number plates. Over 2,000 lanes have been covered with number plate reading cameras by us to track vehicle movement in the city, particularly concerning stolen or missing vehicles.

Worldwide, computer vision algorithms are becoming indispensable tools for law enforcement agencies. These algorithms analyze real-time video feeds, identify and track people and vehicles, and help law enforcement agencies enhance public safety, investigate incidents, and respond promptly to potential security threats.

AI-based VIDS for traffic enforcement

Vehant’s technology is also being utilized by the Gurugram police, who have deployed approximately 300 state-of-the-art cameras in the city for traffic enforcement. The models detect violations such as speeding, no helmet, and tripling, among others.

The company leverages image classification, object detection, object tracking, and image retrieval algorithms to improve the accuracy in the search and retrieval of objects of reference and expedite its clients’ decision-making capabilities. 

The models generally available are trained on generic datasets. The ones we use are application-oriented, and we customize them by training them for specific problem-solving. The models run on edge devices. Ideas are taken from the literature and developed in-house solutions with performance at par.

Our enforcement camera system are spread across 250 different lanes in Gurugram. The system detects violations, for example, someone riding without a helmet. It captures a snapshot, reads the number plate, and provides an image of the number plate. This information is bundled into a challan form and presented to the user for real-time analysis with the help of AI. However, manual intervention is involved, as law enforcement agencies are mandated by law to manually verify if the challans are accurate and whether they should be subject to a fine. Once verified, it gets integrated with the NIC database of Sarthi and Vahaan, where the information is fed, and an auto-challan is generated. So, this is a completely integrated seamless traffic enforcement solutions.

Currently, around 2,000 challans are validated on a daily basis. However, the number of challans generated by AI is way higher. Our number plate scanning technology is also deployed in 50 Smart Cities across India, and the system manages close to 1 billion transactions a year.

Source:- Analytics India Mag.