IIIT-Hyderabad tracking system to help IAF radar systems
Hyderabad: The target scopes of the Indian Air Force and its ground-based radars are all set to get sharper and identify enemy and friendly aircraft more accurately, thanks to an algorithm developed by the International Institute for Information Technology, Hyderabad for Bharat Electronics Ltd. The algorithm and software, which has been transitioned to BEL and […]
Hyderabad: The target scopes of the Indian Air Force and its ground-based radars are all set to get sharper and identify enemy and friendly aircraft more accurately, thanks to an algorithm developed by the International Institute for Information Technology, Hyderabad for Bharat Electronics Ltd.
The algorithm and software, which has been transitioned to BEL and is currently being tested out in their simulation environment, when integrated with the existing Air Force tracking system during research, was found to be improving accuracy in object identification by radars up to 96 per cent from the existing 91 per cent.
Flying objects in the Indian airspace are detected and tracked by ground-based radars produced by BEL. The current tracking system used by the Indian Air Force relies on a Multi-Sensor Tracking mechanism via radars that are located at different parts of the country. Information such as location and velocity coordinates captured by each radar is collated to provide what is known as the Air Situation Picture (ASP), a detailed listing of all aircraft in the airspace along with their corresponding flight numbers and flight plans.
However, with overlapping radars sensing sometimes the same aircraft, and delay in communication between sensors, two common errors emerge – the ‘merging’ error, where multiple aircraft in close proximity are incorrectly identified as one; and ‘splitting’, where a single aircraft is sensed as multiple and erroneously flagged as a threat. Thus, the ASP generated is not always accurate.
To address these issues, a team from BEL Ghaziabad approached IIITH and has been involved in multiple discussions for development of an automated solution.
The IIITH research team led by Prof. Praveen Paruchuri of the Machine Learning Lab, IIITH with Masters student Anoop Dasika trained a machine learning model with 11 days of anonymised and labelled data collected from 17 million data points captured by various radars.
While the original tracking mechanism was 91 per cent accurate, an AI-assisted tracker created by the IIITH team has demonstrated a five percent improvement. The plus point, according to the team, is that it also helps in detailed radar analysis.
The research findings have been published in a paper titled ‘CB NN Ensemble to Improve Tracking Accuracy in Air Surveillance’ and will be presented at the 34th Annual Conference on Innovative Applications of Artificial Intelligence later this month.
Now you can get handpicked stories from Telangana Today on Telegram everyday. Click the link to subscribe.
Click to follow Telangana Today Facebook page and Twitter .
