Delhi govt plans to install AI-powered cameras to detect traffic violations

Delhi government is planning to install artificial intelligence (AI) powered cameras across the national capital to detect traffic rule violations and increase road safety, PTI has reported. The report claims that with this strategy, the AI-powered cameras will be able to detect traffic violations like triple riding on motorcycles, using cellphones while driving, vehicles plying in the city without a valid PUCC etc.

The Delhi government's transport department is reportedly planning to spend ₹20 crore to install Automatic Number Plate Recognition (ANPR) based traffic rule violation detection cameras across the national capital. The Delhi government has reportedly floated a tender to procure such cameras and supportive technology as well.

The report further stated that to improve road safety on the streets of the city, the Delhi government has taken the initiative to deploy an Integrated Traffic Enforcement Management System (ITMS) across Delhi. This system is claimed to help reduce the number of accidents and related fatalities with the help of advanced AI-based video analytics technology-based solutions. "The objective of the ITMS is to reduce the number of drivers who violate traffic rules, penalise the offenders, and run road safety awareness initiatives across the junctions thereby making the roads of Delhi safer for both pedestrians and motorists," a government official has reportedly explained, while also stating that the ANPR technology is a key aspect of the ITMS.

This system will reportedly allow the operator to set traffic rules such as no heavy vehicles during certain times of the day for selected traffic junctions. This will enable the system to identify heavy vehicles and generate an alert in case the vehicle is violating the rule within the configured time and area. The system is also capable of keeping track of the violation history for each vehicle and generating reports as required.

Major traffic violations in Delhi

The Delhi government's transport department has identified speed violations, riding without a helmet, triple riding, driving without a seat belt, driving while on phone calls, uncovered good carriage, and overloading in the case of commercial vehicles as major traffic rule violations, while driving in the wrong lane, buses not moving in designated lanes, private vehicles parked on roads are among the other issues.

Besides that, de-registered end-of-life vehicles being parked in public spaces or being driven on roads or vehicles without a valid PUCC being driven on roads are among traffic violations registered in the city. Apart from that, traffic rule violations are recorded when the Odd-Even program or GRAP restrictions are in place. The new AI-based system is claimed to tackle these issues using them as use cases and its deep learning technology.

How ITMS will work

The new system claims to provide insights for traffic planners using innovative dashboards for various parameters such as violations, traffic count, vehicle classification, present and historical trends, and comparison of roads or junctions. The ITMS claims to serve the transport department as a decision support system and provide actionable intelligence to help make the roads safer and less congested for both motorists and pedestrians.

The ANPR software system claims to capture the licence plates of vehicles across different categories such as cars, heavy commercial vehicles, three-wheelers, two-wheelers, and buses. The system will store the licence plate and vehicle category information for each transaction in its database. The ITMS will categorise licence plates into 'good' (readable), 'bad/dilapidated' (partial or fully non-readable), and ‘broken’ (licence plates without numbers). It will use image processing algorithms to identify licence plates and convert them into a text string for four-wheelers and other vehicles with a minimum detection accuracy of 95 per cent and a minimum conversion accuracy of 90 per cent, claims the report.

Also, the ITMS will have an automated traffic rule violation detection and ticket generation process based on the ANPR conversion and violation detection confidence level.