Facial recognition enabled cameras, automatic vehicle number plate identification, and an entire city inundated with surveillance cameras — these are just a few ways in which Noida is planning to surveil its traffic, and commuters. The city administration — the Noida Authority — earlier this month, floated a tender to upgrade its traffic management system, which proposes to install close to 1,000 cameras across the city, which includes CCTV cameras, and separate number plate recognition cameras. The tender document — more than 400 pages long — mentions the word privacy just once.

Alarmingly, the system will also communicate with large scale databases like driver license and vehicle registration databases maintained by the Road Transport Ministry, and the centrally maintained criminal database Crime and Criminal Tracking Networks and Systems (CCTNS).

The surveillance infrastructure will come in at a huge cost — the advertised cost of setting it up is in the upwards of ₹88 crore. It will be implemented across 84 busy intersections in the city, including Rajnigandha Chowk, Electronic City, Botanical Garden Metro area, and Kalindi Kunj bridge, among others.

The city administration’s argument is that this will help in making the city’s traffic situation better. The implementation of the online system will ensure “efficient traffic management”, the Noida Authority said. Continuous surveillance will result in a reduction in the number of criminal and unlawful activities, number of traffic rule violations, illegal parking, and encroachments, among other things, it claimed.

This development is in line with an increasing trend among Indian government bodies: from organisations that track crime statistics such as the NCRB, to  an education board like the CBSE, a number of government institutions are deploying facial recognition systems — all while India lacks a data protection law.

How the surveillance infrastructure will work

As part of the project, the city administration is planning a complete overhaul of its traffic management system — by increasing surveillance manifold, and by digitising a number of components. This includes installation of facial recognition-enabled surveillance cameras, round the clock speed detection cameras, e-challan generation systems, and vehicle number plate recognition cameras, among other things. Some of the components of this system include:

  • Adaptive traffic control system (ATCS): This will serve as an automated traffic-light control system that switches traffic lights depending on the density of traffic in a road. It also includes sensor and video-based vehicle detectors.
  • Traffic surveillance cameras: The cameras should be placed so that they can cover the junctions, its connecting roads, non-parking areas, side view of metro stations, and even market areas to increase the amount of space that can be monitored, the Noida Authority said.
  • Automatic number plate recognition system (ANPR): This will include setting up cameras that can capture and process images of vehicle number plates with the “highest possible accuracy”. It should also be able to identify stolen or suspected vehicles by cross checking the registration numbers with the vehicle database (Vahan). These cameras should have a minimum accuracy of 90%, per the tender document.
  • Red light violation detection system (RLVD): This solution will have an overview camera to capture the zoomed-out picture of an entire area when there has been a red-light violation. Light sensors will be placed to detect the change in traffic light. Once the traffic light has turned red, the sensors will activate the camera for capturing images of the vehicles which have jumped the traffic light. The ANPR will read the number plate of the offending vehicle and store it in the database.
  • e-challan system: Currently, the city uses an e-challan system developed by the National Informatics Centre (NIC). However, the selected company’s e-challan system should be compatible with at least three other cities in the country, in order to fulfil the “one nation one challan” requirement.
  • Environmental sensors: On the upside however, the surveillance architecture will also house environmental sensors, that can monitor air quality.

How the entire infrastructure will look | Source: Tender document

A command and control centre is at the ‘heart’ of this project

The command and control centre is at the “heart of this project”, where the overall monitoring and control of major functions of the data and communication network will reside. The information gathered at the control centre will can rapidly be shared various across agency lines, Noida Authority claimed.

The control centre should be able to store 10 TB worth of video footage to begin with, but that should be expandable upto 100 TB, and live video feeds of two days should always be readily available at the control centre.

The city currently already has a central command centre, but under this project, a new command centre will be set up, and integrated with the old one. The current command centre — set up in 2015 — is based on a highway traffic management system (HTMS), which monitors traffic between Mahamaya and Pari Chowk on the Gautam Buddha Expressway. The system was developed by Gurgaon-based EFKON Limited.

“The traffic violations observed on this stretch [Mahamaya to Pari Chowk] is manually entered by the NOIDA Traffic Cell in the e-Challan system and then the challan is generated and sent to the violators,” the Noida Authority said. Also, on this stretch, there are currently 92 surveillance cameras, and 24 number plate recognition cameras.

For managing backend functions, the chosen company will also have to provide edge devices, and network connectivity, among other things. Data of the surveillance architecture will be hosted on the cloud, and the successful bidder will have to make all arrangements to ensure that the data remains safe and secure.

Everyone’s deploying a facial recognition tool

From several departments of the Indian government itself to several state governments and their respective police departments, the use of facial recognition technology is proliferating across the country. Recently, CBSE rolled out a facial recognition system — sans a privacy policy — for students to download their academic documents. The National Crime Records Bureau is currently working towards building a national level facial recognition system, and only very recently revealed that it wants to test the system on mask-wearing faces, and for it to generate “comprehensive biometric reports”.

Several airports have added facial recognition systems as an additional way for passengers to board flights. Local police departments are purchasing, or piloting facial recognition algorithms — for instance, the Vadodara city police piloted Clearview AI’s controversial facial recognition system. States like Telangana have piloted the tech in civic elections, and are mulling introducing the tool for obtaining ration at fair price shops.

Indian Railways’ central division is also considering setting up similar facial recognition systems at some of its premises in Parel, we had earlier reported. Bengaluru’s railway station is gearing up to be surveilled by CCTV cameras capable of carrying out facial recognition, at a cost of over ₹4.5 crore.

Read more from our coverage related to facial recognition: