Campus Beat Hyderabad

IIIT-H student bags first prize at Indian Navy hackathon

Listen to Story
IIIT-H student bags first prize at Indian Navy hackathon

Hyderabad: A student of IIIT-Hyderabad has secured first place and won a cash award of Rs 3 lakh at an Indian Navy event which tackles navigation and tracking challenges. Rishabh Bhattacharya, a third-year student at the premier institute created this algorithm which improves navigation and real-time tracking of flying objects, including drones.

The Indian Navy’s Innovation and Indigenisation Seminar ‘Swavalamban 2024’ was held in October. During the event, nation-wide competition was announced, aimed at addressing real world operational challenges with innovative technological solutions.

Participants were presented with a number of problem statements to choose from ranging from drone swarm coordination and maritime situational awareness to to navigation and real-time tracking of flying objects.

Inspired by his own work that was presented at the IEEE International Conference on Robotics and Automation (ICRA) 2023, Bhattacharya opted to challenge himself by developing an optical flow tracking algorithm capable of sub-pixel accuracy to enhance navigation and real-time tracking of flying objects.

“One of the criteria laid out was for the solution to demonstrate resilience to varying lighting conditions, rapid movements, and complex textures while maintaining efficiency on platforms like drones or embedded systems,” he said.

Rishabh said, the goal of achieving high precision at a sub-pixel level is challenging but nevertheless vital for fine-grained motion estimation and tracking. He said achieving this level of precision was challenging due to the unpredictable movements of flying objects.

“Additionally, tracking flying objects introduces complexities due to their rapid and unpredictable movements, necessitating advanced detection and tracking mechanisms that can operate seamlessly in real-time,” he added.

To address the lack of comprehensive datasets that encompass a wide variety of flying objects, including planes, helicopters and UAVs, Rishabh integrated the Flying Objects dataset from Sekilab, which includes planes, helicopters and birds, with the UAV dataset available on Kaggle. This resulted in a diverse and extensive dataset tailored to the specific needs of the project.

He further informed that the combined dataset, totalling 7.7 gigabytes, is slated for public release to benefit the broader research community.

Rishabh utilised the framework that he had initially proposed in his research paper to enhance the robustness of the object detection component of the optical flow tracker. The framework introduces a domain-agnostic network architecture that can be integrated into existing object detection models such as YOLOv8, to improve performance under challenging environmental conditions like fog, and low lighting.

“The enhanced YOLOv8 model, augmented with the GDIP framework, was trained using the combined dataset over 50 epochs,” Rishabh said and added that that the model was fine-tuned to process each frame of a GIF or incoming video stream in approximately 2 milliseconds.

Recalling his meeting with Navy admirals and commanders at the hackathon, Rishabh said the Navy officials expressed interest in integrating his solution into operational frameworks.

“The various things that I worked on in the Machine Learning Lab under the guidance of Dr Naresh Manwani gave me exposure to different ideas, some of which I used in the hackathon,” he added.