AI Posture Estimation for Remote Exercise Therapy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
There is a need for a method and system to provide online-based exercise therapy for musculoskeletal diseases, capable of analyzing a patient's exercise motion from an exercise image using artificial intelligence models.
Innovation Solution
The system receives prescription information from a doctor terminal, allocates an exercise plan to a patient's account, and analyzes the patient's exercise motion by extracting keypoints from an exercise image using an artificial intelligence posture estimation model and motion analysis model.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If online-based exercise therapy is provided using AI models, then accessibility and compliance are improved, but measurement precision and reliability of exercise analysis may deteriorate without proper keypoint extraction and motion analysis
Solution Approach 1:
The patent replaces manual exercise therapy monitoring with an automated AI-based system that uses posture estimation models and motion analysis models to automatically extract keypoints and analyze exercise motions from images, eliminating the need for physical presence of healthcare providers while maintaining analysis accuracy
Solution Approach 2:
The system enables patients to perform exercise therapy independently at home by providing real-time automated feedback through AI analysis of their posture and motion, allowing self-monitored rehabilitation without requiring continuous professional supervision
2Measurement precision
If AI posture estimation and motion analysis models are used, then exercise motion analysis accuracy is improved, but device complexity increases
Solution Approach 1:
The patent divides the complex AI analysis system into distinct functional modules: a posture estimation model that extracts keypoints from images, and a motion analysis model that analyzes the extracted keypoints to determine exercise performance, making the overall system more manageable and interpretable
Solution Approach 2:
The system introduces keypoint extraction as an intermediary step between image capture and motion analysis, where the posture estimation model identifies specific anatomical landmarks that serve as intermediate data for the subsequent motion analysis process
Data Source
AI summary
A method of providing exercise therapy using an artificial intelligence motion analysis model comprises: receiving, from a doctor terminal, prescription information related to exercise for a patient; allocating, to an account of the patient, based on the prescription information, an exercise plan including at least one prescribed exercise; receiving, from a patient terminal, an exercise image in which an exercise according to the prescribed exercise is photographed; extracting, from the exercise image including a subject of the patient, a keypoint corresponding to each of a plurality of preset joint points, using an artificial intelligence posture estimation model trained based on a training data set; and analyzing, using an artificial intelligence motion analysis model, a relative positional relationship between the keypoints, and analyzing, based on the analysis of the positional relationship, an exercise motion of the patient for the prescribed exercise.