Video-Based Exercise Assistance Without Wearable Sensors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current exercise assisting devices and applications lack real-time analysis and adjustment capabilities, failing to provide effective training suggestions and modifications without wearable sensors, leading to reduced training efficiency and potential injuries due to incorrect exercise execution.
Innovation Solution
An exercise assisting device and method that utilizes a processor connected to a storage and transceiver interface to analyze video streams of users, determine motion recognition results, and input these results into an expert suggestion model to generate follow-up motion suggestions and demonstration videos, allowing for real-time adjustments without the need for wearable sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If wearable sensors are used to collect limb motion data for real-time analysis, then measurement precision is improved, but device complexity and ease of operation deteriorate due to sensor replacement requirements
Solution Approach 1:
The patent extracts the motion data collection function from wearable sensors and relocates it to the image capturing device. The processor analyzes video streams to generate motion recognition results, eliminating the need for wearable sensors while maintaining measurement precision for exercise form analysis.
Solution Approach 2:
The image capturing device is赋予 multiple functions: it not only captures video for exercise demonstration but also collects motion data for real-time analysis. This multi-functional approach replaces the specialized wearable sensors, improving ease of operation while maintaining analysis accuracy.
2Device complexity
If standardized fixed courses are provided without real-time analysis, then device complexity is reduced, but training efficiency deteriorates due to inability to provide real-time adjustments
Solution Approach 1:
The patent implements real-time feedback by analyzing motion recognition results during exercise execution. When the processor detects that a motion target value is not achieved, it generates follow-up motion suggestions and adjusts the exercise course dynamically, maintaining training efficiency while keeping the course structure relatively simple.
Solution Approach 2:
The exercise course transitions from a fixed standardized structure to a dynamic adaptive structure. The processor continuously adjusts the exercise course based on real-time motion analysis, allowing the training program to adapt to user performance while maintaining operational simplicity through automated adjustments.
3Device complexity
If user self-judgment of exercise conditions is relied upon, then device complexity is minimized, but reliability deteriorates due to lack of professional knowledge
Solution Approach 1:
The system performs self-service by automatically analyzing motion recognition results and generating follow-up motion suggestions without requiring user expertise. The processor acts as an automated professional coach, evaluating exercise conditions and providing reliable guidance while keeping the system structure simple.
Solution Approach 2:
The processor serves as an intermediary between the user and professional exercise guidance. It translates raw motion recognition data into professional assessments and actionable suggestions, bridging the gap between simple self-monitoring and expert-level training advice, thereby improving reliability without complicating the system.
Data Source
AI summary
An exercise assisting device and exercise assisting method are provided. The device performs the following operations: transmitting a first control signal, the first control signal is related to a motion demonstration video corresponding to an exercise course data; receiving a video stream of a user; analyzing the video stream to generate a motion recognition result corresponding to the exercise course data of the user, and determining whether a motion target value is achieved according to the motion recognition result and the exercise course data; and when the motion target value is not achieved, the motion recognition result and the motion target value are input into an expert suggestion model to generate a follow-up motion suggestion and to determine a follow-up motion demonstration video corresponding to the follow-up motion suggestion.