Silent Impact: Tracking Tennis Shots from the Passive Arm

2025-07-30

AI Summary

Existing tennis motion analysis typically relies on sensors mounted on the racket or dominant arm, which can impede natural movement. This work introduces a novel, unobtrusive paradigm for stroke sensing using an inertial measurement unit (IMU) worn on the non-dominant arm—demonstrating, for the first time, its viability as an effective sensing location. We propose an end-to-end neural network model that jointly performs stroke event detection and six-class stroke classification, integrated into a smartwatch–smartphone prototype application. Evaluated on data from 20 amateur players, our approach achieves 88.2% classification accuracy and an F1-score of 86.0% for stroke detection. A user study confirms that this non-dominant-arm IMU placement significantly reduces both physical and cognitive load, while maintaining high accuracy and seamless wearability. Our solution advances sports analytics by enabling natural, user-centric motion sensing without compromising performance.

Technology Category

• Humans and AI: Brain-Sensing and Analysis
• Computer Vision: Motion & Tracking
• Intelligent Robots: Manipulation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Security and Privacy: Large-scale security measurements

Abstract

Wearable technology has transformed sports analytics, offering new dimensions in enhancing player experience. Yet, many solutions involve cumbersome setups that inhibit natural motion. In tennis, existing products require sensors on the racket or dominant arm, causing distractions and discomfort. We propose Silent Impact, a novel and user-friendly system that analyzes tennis shots using a sensor placed on the passive arm. Collecting Inertial Measurement Unit sensor data from 20 recreational tennis players, we developed neural networks that exclusively utilize passive arm data to detect and classify six shots, achieving a classification accuracy of 88.2% and a detection F1 score of 86.0%, comparable to the dominant arm. These models were then incorporated into an end-to-end prototype, which records passive arm motion through a smartwatch and displays a summary of shots on a mobile app. User study (N=10) showed that participants felt less burdened physically and mentally using Silent Impact on the passive arm. Overall, our research establishes the passive arm as an effective, comfortable alternative for tennis shot analysis, advancing user-friendly sports analytics.

Problem

• Analyzing tennis shots without disrupting natural motion
• Replacing dominant-arm sensors with passive-arm wearable tech
• Achieving accurate shot classification using minimal sensor data

Innovation

• Uses passive arm sensor for shot analysis
• Neural networks classify shots with 88.2% accuracy
• End-to-end smartwatch and mobile app system