BadminSense: Enabling Fine-Grained Badminton Stroke Evaluation on a Single Smartwatch

2026-03-23

AI Summary

This work addresses the lack of fine-grained, expert-level assessment of stroke mechanics among amateur badminton players. The authors propose a multitask learning approach that relies solely on vibration signals from a single commercial smartwatch to simultaneously recognize stroke types, estimate stroke quality scores, and infer racket-ball impact locations. By integrating wearable sensing, signal segmentation, and joint classification and regression modeling, the method achieves three granular performance evaluation tasks on a single wearable device for the first time. Evaluated on a dataset collected from 12 amateur players, the approach demonstrates strong effectiveness and substantially lowers the barrier to professional-grade motion analysis in real-world settings.

Technology Category

• Computer Vision: Motion & Tracking
• Intelligent Robots: Manipulation
• Machine Learning: Evaluation and Analysis

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Evaluating badminton performance often requires expert coaching, which is rarely accessible for amateur players. We present adminSense, a smartwatch-based system for fine-grained badminton performance analysis using wearable sensing. Through interviews with experienced badminton players, we identified four system design requirements with three implementation insights that guide the development of BadminSense. We then collected a badminton strokes dataset on 12 experienced badminton amateurs and annotated it with fine-grained labels, including stroke type, expert-assessed stroke rating, and shuttle impact location. Built on this dataset, BadminSense segments and classifies strokes, predicts stroke quality, and estimates shuttle impact location using vibration signal from an off-the-shelf smartwatch. Our evaluations show that

Problem

• badminton stroke evaluation
• fine-grained performance analysis
• amateur players
• wearable sensing
• smartwatch

Innovation

• smartwatch sensing
• badminton stroke analysis
• fine-grained performance evaluation
• vibration signal processing
• wearable computing