Skip to content
Open access

An Adaptive IMU–Visual Multimodal Fusion System for Real-Time Exercise Recognition and Movement Quality Assessment

Sep 2026 · Italian National Conference on Sensors · Vol 26 · 0 citations · 59 references
Medicine

TL;DR

A dual-stream prototype that combines a nine-axis inertial measurement unit (IMU) with vision-based pose estimation and establishes feasibility within the studied cohort and exercises; broader generalization and feedback effectiveness require larger, independently controlled evaluations.

Abstract

Exercise recognition and movement quality assessment remain challenging in supervised exercise training, particularly under viewpoint changes and self-occlusion. Vision-based methods provide spatial posture information but are susceptible to keypoint loss, whereas inertial sensing is less affected by occlusion but provides limited information about global posture geometry. This study presents a dual-stream prototype that combines a nine-axis inertial measurement unit (IMU) with vision-based pose estimation. A 1DCNN-LSTM branch models inertial dynamics, a custom keypoint temporal branch models normalized pose sequences, and a confidence-gated rule adjusts their contributions according to visual keypoint reliability. Owing to the absence of a public synchronized multi-view IMU–vision exercise dataset with the required protocol, we constructed IMV-Exercise, comprising 10 participants, three exercises, and 900 repetition-level samples with side-, front-, and posterior-view recordings. The system achieved 96.0% exercise recognition accuracy under leave-one-subject-out cross-validation. In a separate viewpoint-specific evaluation, the fused output achieved 91.2% action-window accuracy under posterior viewing. Across 50 online trials, the reported recognition accuracy was 96.0%, the mean end-to-end latency was 195 ms, and the recorded maximum was below 210 ms. These results establish feasibility within the studied cohort and exercises; broader generalization and feedback effectiveness require larger, independently controlled evaluations.

Read PDF

Similar papers

Open access Sep 2026

Evolution of a Real-Time Markerless Kinematic Posture-Assessment System: From Multi-Participant Monitoring to Depth-Aware Angular Assessment

The technological evolution from KUMITRON to COLLVIT is presented, the rationale behind the patent-based design decisions, the implementation of the current prototype, and directions for its future development and validation.

Jon Echeverria, Olga C. Santos · 0 citations
Conference Sep 2026

Precise feedback system for motion posture based on computer vision

Against the backdrop of national fitness programs, the standardization of motion posture in daily public exercise directly affects training effectiveness and sports safety. Traditional offline coaching has disadvantages such as high cost and significant spatiotemporal constraints, while standardized online courses fail...

Rui-Bo Li · 0 citations
Conference Sep 2026

Deep pose estimation-based action recognition and performance analysis for intelligent motion understanding

Pose-ARPA is proposed, a unified framework that combines deep pose estimation with spatiotemporal representation learning for comprehensive action recognition and performance analysis and achieves superior recognition accuracy, robust generalization under noisy or occluded conditions, and real-time inference capability...

Qi Yang, Long-Hui Wen · 0 citations
Open access Sep 2026

Vision-based human pose estimation for intelligent sports training and teaching assistance

GSANet substantially reduces model parameters and computational complexity relative to the reported HRNet-W32 configuration without ImageNet pre-training, although its absolute pose-estimation accuracy is lower.

Pu-Ling Li, Lei Lu, Tao Zheng et al. · 1 citation
#computer vision Preprint Oct 2026

Robust Real-Time Monocular Human Pose Estimation with Insole-Based Sensor Fusion

Real-time monocular human pose estimation is an important sensing component for human-centered intelligent systems. While recent camera-based methods have achieved impressive accuracy, fundamental challenges persist, particularly when visual observations are incomplete, such as during lower-body occlusion or short out-...

Liang Yu, Tao Zhu, Xiang-Qing Lu et al. · 0 citations
Open access Sep 2026

IMU-weighted multimodal fusion for robust gesture recognition across arm positions

This study addresses the cross-position sensitivity of ultrasound-based HMIs by fusing ultrasound data with sEMG and inertial measurement unit (IMU) data using an IMU-weighted multimodal fusion framework, providing a practical route toward robust gesture recognition based on A-mode ultrasound across varying arm positio...

Shang Shi, Jian-Jun Meng, Zong-Tian Yin et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.