One-Shot Badminton Shuttle Detection for Mobile Robots
It addresses the lack of egocentric shuttlecock detection for mobile robots, enabling downstream tasks like tracking and trajectory estimation, but is incremental as it adapts existing methods to a new application.
This paper tackles the problem of detecting badminton shuttlecocks from the dynamic viewpoints of mobile robots by introducing a dataset of 20,510 annotated frames and fine-tuning a YOLOv8 network, achieving an F1-score of 0.86 in similar environments and 0.70 in unseen ones.
This paper presents a robust one-shot badminton shuttlecock detection framework for non-stationary robots. To address the lack of egocentric shuttlecock detection datasets, we introduce a dataset of 20,510 semi-automatically annotated frames captured across 11 distinct backgrounds in diverse indoor and outdoor environments, and categorize each frame into one of three difficulty levels. For labeling, we present a novel semi-automatic annotation pipeline, that enables efficient labeling from stationary camera footage. We propose a metric suited to our downstream use case and fine-tune a YOLOv8 network optimized for real-time shuttlecock detection, achieving an F1-score of 0.86 under our metric in test environments similar to training, and 0.70 in entirely unseen environments. Our analysis reveals that detection performance is critically dependent on shuttlecock size and background texture complexity. Qualitative experiments confirm their applicability to robots with moving cameras. Unlike prior work with stationary camera setups, our detector is specifically designed for the egocentric, dynamic viewpoints of mobile robots, providing a foundational building block for downstream tasks, including tracking, trajectory estimation, and system (re)-initialization.