VIVAERO

ISRO develops AI model for aircraft tracking and surveillance

The Indian Space Research Organisation (ISRO) has successfully tested an AI model capable of automated airport monitoring and aircraft tracking. The model was tested in airports in Mumbai, Pune, and Ahmedabad.

Researchers from the Space Applications Centre (SAC) at the Indian Space Research Organisation (ISRO) have developed an AI model that offers a comprehensive airport monitoring and aircraft tracking feature set along with surveillance. 

The Times of India reports that the model was developed in collaboration with an institute and tested at airports in Ahmedabad, Mumbai, and Pune. The model utilizes the CosmiQ Works RarePlanes dataset, an open-source machine-learning dataset from CosmiQ and AI Reverie, that incorporates real-world and synthetically generated satellite imagery.

Besides the RarePlanes dataset, the model was trained on the Airbus Aircraft detection dataset and Indian remote sensing satellite imagery. 

"The deep learning data models were called YOLOv5 and YOLOv7, which belong to the You Only Look Once (YOLO) family, widely used in various applications, including aircraft detection in satellite imagery," a senior official told The Times of India. 

The model reportedly had an accuracy level of 94% for larger aircraft and 88% for smaller ones. YOLOv7 was the superior performer in these tests. The research team is now working to expand the model's capabilities and include Synthetic Aperture Radar (SAR) satellite data, which can help with aircraft detection during extreme weather conditions.