Hyderabad: IIIT-H scientists are using artificial intelligence (AI) to spot potholes and alert drivers, as also to spot distracted drivers, traffic rule-breakers, and erratic two-wheelers. The scientists are working with a suite of low-cost, real-world AI tools developed for Indian roads.
At the recent TechForward seminar, Prof. C.V. Jawahar showcased how the Centre for Visual Information Technology (CVIT) at IIITH was building AI not just to detect, but anticipate road risks. “Most global models are trained on neat, rule-following traffic. That doesn’t help much in India,” Prof Jawahar explained. “Our goal is to build systems that work amid uncertainty, and on a phone, not just in a lab.”
Among their most recent tools is Dashgaze, which estimates driver attention using a regular dashcam or mobile phone camera. Unlike expensive eye-tracking hardware, Dashgaze collects naturalistic driving data, nearly one million frames, from real-world conditions. “Distraction is a major cause of road accidents, but the tech to measure it has been out of reach, we’re trying to change said,” Jawahar said.
The team is also focused on predicting driver and rider behaviour through datasets like DAAD (Driving Action Anticipation Dataset) and two-wheeler intention models submitted to international competitions. “If a rider is about to make a sharp turn without warning, the AI should catch the cues before the manoeuvre begins,” said a researcher from the project team. “These few seconds can be the difference between a near miss and a crash.”
IIITH has also applied AI to tasks like pothole detection, tree cover mapping, and traffic violation monitoring, all using mobile cameras mounted on public vehicles. The aim is to replace bulky or visible surveillance with ambient, real-time monitoring. “People behave differently when they know a CCTV is watching. But roads need safer behaviour all the time,” Prof. Jawahar said.
These tools are fuelled by the India Driving Dataset (IDD), a publicly available dataset of road footage developed with Intel. “We wanted start-ups and researchers to stop building on foreign data,” Prof. Jawahar said. “The idea was, here’s how Indian roads actually look.”
Some of this work is now feeding into real-world projects like iRASTE, being piloted in Telangana and Nagpur, where AI systems help identify accident blackspots, analyse mobility risks, and support driver alerts. “Road safety can’t wait for autonomous cars to arrive. We need AI that helps today’s vehicles and today’s drivers make better decisions, especially on our kind of roads,” Prof. Jawahar added
Disclaimer : This story is auto aggregated by a computer programme and has not been created or edited by DOWNTHENEWS. Publisher: deccanchronicle.com
