Spin Detection Using Racket Bounce Sounds in Table Tennis

2024-09-18

arXiv.org

AI Summary

To address the challenge of accurately inferring ball spin states in table tennis solely from auditory cues, this paper proposes an end-to-end audio-based spin recognition method leveraging racket–ball impact sounds. We introduce the first multi-source acoustic dataset covering 10 distinct racket configurations and diverse spin combinations, enabling millisecond-level bounce event localization and binary spin detection (spin vs. no-spin). Our approach jointly optimizes acoustic event detection and spin classification within a supervised learning framework, integrating high-frequency peak detection, time–frequency representation, and a convolutional neural network classifier. Experimental results demonstrate high-accuracy racket-type identification (10 classes) and reliable discrimination between spin and no-spin strokes. This work establishes a novel auditory-driven paradigm for intelligent table tennis training and assistive officiating, providing foundational technical support for real-time, sound-based sports analytics.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Knowledge Representation and Reasoning: Knowledge Acquisition

Application Category

• Web Mining and Content Analysis: Robustness and generalizability of Web mining methods
• Responsible Web: Social and technical mechanisms of refusal for web technologies and applications
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

While table tennis players primarily rely on visual cues, sound provides valuable information. The sound generated when the ball strikes the racket can assist in predicting the ball's trajectory, especially in determining the spin. While professional players can distinguish spin through these auditory cues, they often go unnoticed by untrained players. In this paper, we demonstrate that different rackets produce distinct sounds, which can be used to identify the racket type. In addition, we show that the sound generated by the racket can indicate whether spin was applied to the ball, or not. To achieve this, we created a comprehensive dataset featuring bounce sounds from 10 racket configurations, each applying various spins to the ball. To achieve millisecond level temporal accuracy, we first detect high frequency peaks that may correspond to table tennis ball bounces. We then refine these results using a CNN based classifier that accurately predicts both the type of racket used and whether spin was applied.

Problem

• Detecting table tennis bounces with millisecond accuracy
• Classifying bounce surface from racket-ball impact sounds
• Identifying spin application using audio-based analysis

Innovation

• Energy-based peak detection for bounce identification
• Convolutional neural networks for audio classification
• Real-time pipeline processing 3,396 bounce samples