Creative Commons source reading · Movement biomechanics and kinetics
Validation of video-based event detection against laboratory-standard biomechanical measures: a synchronized multimodal study
Zhenping Xiao; Zaitian Huang; Henrui Zhang; Daiyuan Tang; Jingyu Li; Yangjie Li; Chengkai He; Li Tan; Fei He
Originally published in Front Bioeng Biotechnol · 2026-10-26
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
IntroductionBiomechanical event detection is fundamental to human movement analysis in clinical, rehabilitation, and sports settings, yet conventional laboratory systems remain costly and inaccessible in many contexts. This study validated a markerless, video-primary event detection system against laboratory-reference biomechanical measurements using synchronized multimodal data.MethodsEight healthy adults performed standardized upper-limb dumbbell lifting tasks in a controlled laboratory while video, Vicon motion-capture, and surface electromyography (EMG) data were recorded (76 valid trials; 304 event labels). A hybrid pipeline combining threshold-based peak detection with Long Short-Term Memory (LSTM) networks identified four events: action start, peak of rising, end of holding, and start of returning. Kinematic features were…
Summary of major results
The summary of results in Table 12 shows that the video-based event detection system exhibits high consistency with the laboratory standard system, low temporal error, low bias, and high classification levels. Taken together, the findings support the conclusion that the proposed multimodal setup is a viable and valid alternative for detecting events during controlled upper-limb biomechanical examination.
Interpretation of key findings
The purpose of the research problem was to compare the validity of a video-based event detection system with that achieved by laboratory-quality biomechanical measures using synchronized multimodal data. The results indicate that the proposed system closely tracked the laboratory (Vicon) reference motion capture system, with excellent intraclass correlation coefficients and low temporal error values. The consistency of event recognition across successive trials indicates that a combination of threshold-based event detection and LSTM modeling for upper-limb motion was highly efficient at detecting critical time features of the motion. These findings are also consistent with the latest advances in computer vision, in which markerless systems have been employed to obtain laboratory-ready measurements under controlled conditions (Colyer…
Editorial reading guide
- How was movement measured, and what error or calibration information is reported?
- Can the finding transfer from the tested task and population to the intended sport setting?
