Learn everything about Analytics

Home » IIT Hyderabad Researchers are using Machine Learning to Identify Bike Drivers without Helmets

IIT Hyderabad Researchers are using Machine Learning to Identify Bike Drivers without Helmets


  • Researchers from IIT Hyderabad have designed a system that can detect bike drivers without helmets
  • A convolutional neural network is at the core of the system
  • It is expected to go live in Hyderabad soon and has the potential of significantly reducing road accidents



Getting drivers of two-wheeler vehicles to wear helmets in India has been an eternal struggle. Despite the law being made official, and the number of road accidents increasing, the adoption of helmets by these riders has sadly been a no-show. How does the police enforce this rule?

According to a report by the Economic Times, researchers from IIT Hyderabad may have the answer. They have designed a machine learning algorithm that uses computer vision techniques to detect motorcyclists without helmets, using CCTV cameras. They have already filed to get this technology patented and this could soon be put into action on the Hyderabad roads.

The algorithm will be installed in the CCTV cameras, which will be connected to the servers that will be monitored by the police. It will also be conncted to the existing RTO website so that appropriate fines and penalties can be handed out. Additionally, the violaters will be notified of their error through a SMS.

As with almost all advanced research being done around the world in machine learning, the technique at the core of this system is a convolutional neural network. The current idea is to deploy these cameras at various intersections in the city, like toll bridges, checkpoints, traffic lights, etc.

Along with this, the researchers have also developed a framework for detecting snatch thieves in the city.


Our take on this

A great initiative and it feels wonderful to see this coming from India. This framework can also be applied to other road related incidents – traffic light violations, detection of tripling on two-wheelers, overspeeding, among other things.

I hope this sees the light of day sooner rather than later because it has the potential to reduce the number of accidents by quite a margin. And of course, it will be another shining example of machine learning being put to use for the welfare of society.


Subscribe to AVBytes here to get regular data science, machine learning and AI updates in your inbox!


You can also read this article on our Mobile APP Get it on Google Play
This article is quite old and you might not get a prompt response from the author. We request you to post this comment on Analytics Vidhya's Discussion portal to get your queries resolved

One Comment