Journal DOI 10.68956/journal.human-performance-futures

Creative Commons source reading · Wearable and smart-textile sensing

Deep Learning for Sensor-Based Sport Performance and Health Monitoring: A Review of Wearable, Vision-Based, and Multimodal Sensing Approaches

Liu L; Hu X; Wei H; Yang Z; Sun T

Originally published in Sensors (Basel) · 2026-07-10

From the article

Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.

Abstract

AbstractRecent advances in wearable, vision-based, trajectory, physiological, and multimodal sensing technologies, together with deep learning, have enabled continuous, objective, and individualized assessment of sport performance and athlete health. Unlike prior reviews that primarily focus on a single sensing modality, sport, or algorithmic series, this review integrates wearable, vision-based, trajectory, physiological, and multimodal sensing streams with deep learning models across both performance analysis and athlete health monitoring, thereby clarifying modality-task-model relationships and translational limitations. This review synthesizes recent progress in sensor-based sports intelligence, focusing on how heterogeneous data streams are transformed into performance- and health-related decision support. The reviewed…

7. Conclusions

This review examined recent progress in sensor-driven sport performance analysis and athlete health monitoring. Multisource sensing provides the data foundation for sports intelligence, while deep learning converts heterogeneous data into information for perception, movement understanding, tactical interpretation, load assessment, injury-risk prediction, and rehabilitation support. This field is moving from manual observation and post-event statistics toward continuous sensing, data-driven modeling, and real-time feedback. Taken together, the review shows that sensor-based sports intelligence should be interpreted through a unified chain from sensor choice to data representation, model design, application endpoint, and deployment constraint. In sport performance analysis, deep learning models extract action features, interaction…

Editorial reading guide

  • Which population, sport, device and reference measure were studied?
  • Does the evidence support monitoring, prediction or a clinical decision, and under what conditions?