Football Event Classification Using Wearable Motion Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle with managing and synchronizing large amounts of data from various sources like video footage and motion sensors to accurately identify and classify athletes' activities during training and matches, requiring significant manual effort to derive performance insights.
Innovation Solution
A machine learning model is applied to analyze motion data from wearable monitors to classify athlete activities, automatically identifying events such as warm-ups, training, and matches, and synchronize this data with video footage without human oversight.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual sorting and collation of motion data and video footage is used, then data accuracy and synchronization can be achieved, but significant time and human resources are required
Solution Approach 1:
The patent replaces the manual mechanical process of sorting and collating data with an automated machine learning system. The ML model automatically classifies motion data and synchronizes it with video footage, eliminating the need for human analysts to manually process the data while maintaining high accuracy in activity classification.
Solution Approach 2:
The system enables self-service by allowing the data to classify itself through automated machine learning algorithms. The ML model independently processes motion data, determines activity types, and synchronizes with video footage without requiring human intervention, thus resolving the contradiction between accuracy and time consumption.
2Adaptability or versatility
If data from multiple sources (video footage and motion sensors) are collected, then comprehensive performance analysis is enabled, but data synchronization and management complexity increases
Solution Approach 1:
The machine learning model serves multiple functions: it classifies motion data, synchronizes with video footage, and provides activity recognition. This multi-functional approach allows the system to handle diverse data sources (motion sensors and video) through a single unified processing framework, reducing management complexity while maintaining comprehensive analysis capability.
Solution Approach 2:
The ML model acts as an intermediary between raw motion data and video footage, automatically aligning and integrating these diverse data sources. This intermediary processing layer simplifies the complexity of managing multiple data streams by providing a unified interface for performance analysis.
3Productivity
If automated machine learning classification is implemented, then analysis time is reduced, but system complexity increases
Solution Approach 1:
The system performs preliminary classification of motion data using the ML model before detailed analysis is needed. By pre-processing and categorizing data automatically, the system reduces the time required for subsequent analysis while the complexity is contained within the initial automated classification stage.
Data Source
AI summary
A method of determining an event participated in by an athlete includes receiving, at a computing device, a plurality of motion determinations generated by a monitor from motion data captured from the athlete's motions during a monitoring window. The motion determinations include actions performed by the athlete, performance metrics of the athlete, or both. The method also includes classifying, by use of a machine learning model stored on the computing device, which event among a plurality of predetermined events the athlete participated in during the monitoring window based at least in part on the plurality of motion determinations.