Year: 2025
Type: conference-paper
Abstract: Accurate, real-time collision detection is essential for ensuring player safety and effective refereeing in high-contact sports such as rugby, particularly given the severe risks associated with traumatic brain injuries (TBI). Traditional collision-monitoring methods employing fixed cameras or wearable sensors face limitations in visibility, coverage, and responsiveness. Previously, we introduced a framework using unmanned aerial vehicles (UAVs) for monitoring and real time kinematics extraction from videos of collision events. In this paper, we show that the strategies operating on the objective of ensuring at least one UAV captures every incident on the pitch have an emergent property of fulfilling a stronger key condition for successful kinematics extraction. Namely, they ensure that almost all collisions are captured by multiple drones, establishing multi-view fidelity and redundancy, while not requiring any drone-to-drone communication.
Authors: Yu Cheng, Harun Šiljak
Institution: Trinity College Dublin
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Award: G1243903716
OpenAlex ID: W4415709583