MoCap-Impute: A Comprehensive Benchmark and Comparative Analysis of Imputation Methods for IMU-based Motion Capture Data

2025-07-14

AI Summary

IMU-based motion capture data often suffer from missing values, hindering applications in sports science; however, existing imputation methods lack systematic evaluation. This paper introduces the first publicly available benchmark dataset for IMU motion capture imputation—comprising data from 53 karate practitioners—and designs three realistic missingness patterns: Missing Completely at Random (MCAR), block-wise missingness, and signal-transition-dependent missingness. We systematically evaluate statistical, machine learning, and deep learning methods—including multivariate time-series models, GAIN, and iterative imputers—across three evaluation scenarios: univariate, cross-subject, and multivariate imputation. Results show that multivariate approaches significantly outperform univariate ones, reducing MAE by up to 50% (10.8 → 5.8) under complex missingness. GAIN and iterative imputation models achieve the best overall performance. This work establishes a standardized evaluation framework and empirical benchmark for IMU data imputation.

Technology Category

• Computer Vision: Motion & Tracking
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Mining multimedia, multimodal, multilingual, cross-lingual Web data

Abstract

Motion capture (MoCap) data from wearable Inertial Measurement Units (IMUs) is vital for applications in sports science, but its utility is often compromised by missing data. Despite numerous imputation techniques, a systematic performance evaluation for IMU-derived MoCap time-series data is lacking. We address this gap by conducting a comprehensive comparative analysis of statistical, machine learning, and deep learning imputation methods. Our evaluation considers three distinct contexts: univariate time-series, multivariate across subjects, and multivariate across kinematic angles. To facilitate this benchmark, we introduce the first publicly available MoCap dataset designed specifically for imputation, featuring data from 53 karate practitioners. We simulate three controlled missingness mechanisms: missing completely at random (MCAR), block missingness, and a novel value-dependent pattern at signal transition points. Our experiments, conducted on 39 kinematic variables across all subjects, reveal that multivariate imputation frameworks consistently outperform univariate approaches, particularly for complex missingness. For instance, multivariate methods achieve up to a 50% mean absolute error reduction (MAE from 10.8 to 5.8) compared to univariate techniques for transition point missingness. Advanced models like Generative Adversarial Imputation Networks (GAIN) and Iterative Imputers demonstrate the highest accuracy in these challenging scenarios. This work provides a critical baseline for future research and offers practical recommendations for improving the integrity and robustness of Mo-Cap data analysis.

Problem

• Evaluates imputation methods for missing IMU-based MoCap data
• Compares statistical, machine learning, and deep learning techniques
• Introduces a public MoCap dataset for imputation benchmarking

Innovation

• Multivariate imputation frameworks outperform univariate approaches
• GAIN and Iterative Imputers show highest accuracy
• Public MoCap dataset introduced for imputation benchmarking