Repetitive Motion Tracking on Mobile Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for real-time analysis of repetitive motions in fitness and training activities require multiple high-definition cameras and significant computational resources, making them inefficient and impractical for use on mobile devices.
Innovation Solution
A method and system for analyzing and classifying repetitive motions using a single mobile device, which involves landmark detection, principle component analysis, and machine learning algorithms to determine repetitive motions with minimal delay and data transfer overhead, allowing for real-time tracking and classification on smartphones or tablets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple high-definition cameras and high-end desktop/server-grade hardware are used for real-time tracking, then measurement precision and reliability are improved, but device complexity and use of energy increase significantly
Solution Approach 1:
The patent uses a single mobile device camera to capture images, replacing the need for multiple high-definition cameras. The image processing algorithms extract sufficient tracking information from standard-definition images, creating a functional copy of the multi-camera system's capability using simpler hardware
Solution Approach 2:
The patent extracts only the essential tracking information (landmark positions, motion patterns) from video frames rather than processing complete high-definition video streams. This extraction approach maintains measurement precision while dramatically reducing computational requirements and eliminating the need for complex multi-camera systems
2Measurement precision
If multiple high-definition cameras and massive processing power are used, then measurement precision is improved, but use of energy increases significantly
Solution Approach 1:
The system processes standard-definition images from a single mobile camera instead of high-definition video from multiple cameras. This copying approach captures sufficient motion information while consuming far less energy, enabling real-time tracking on battery-powered devices
Solution Approach 2:
The patent extracts only critical landmark positions and motion patterns from each frame rather than analyzing complete high-definition video. This selective extraction maintains tracking precision while minimizing computational load and energy consumption on mobile devices
3Measurement precision
If multiple cameras and high-end hardware are deployed, then measurement precision and reliability are improved, but ease of operation deteriorates due to calibration requirements
Solution Approach 1:
The patent extracts tracking information from a single camera's video stream, eliminating the need for multi-camera calibration. The system processes images directly from the mobile device camera without requiring complex calibration procedures, making the system immediately operational
Solution Approach 2:
The system performs automatic landmark detection and motion pattern recognition without requiring manual calibration or configuration. The algorithms automatically adapt to the camera's field of view and lighting conditions, enabling the system to serve itself and eliminating calibration steps
4Productivity
If real-time analysis is performed on multiple camera streams, then productivity is improved, but use of energy and computational resources increases
Solution Approach 1:
The patent extracts essential motion information from a single camera stream, processing only landmark positions and basic motion patterns. This extraction maintains real-time analysis capability while reducing computational energy requirements by avoiding processing of complete high-definition video streams from multiple cameras
Data Source
AI summary
Methods and systems for determining and classifying a number of repetitive motions in a video are described, and include the steps of first determining a plurality of images from a video, where the images are segmented from at least one video frame of the video. Next, performing a pose detection process on a feature of the images to generate one or more landmarks. Next, determining one or more principle component axes on points associated with a given landmark. Finally, determining at least one repetitive motion based on a pattern associated with a projection of the points onto the one or more principle components. In some embodiments, the disclosed methods can classify the repetitive motions to respective types. The present invention can be implemented for convenient use on a mobile computing device, such as a smartphone, for tracking exercises and similar repetitive motions.