Sensor-Video Fusion for Motion Event Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current motion capture systems lack integration of sensor and video data, leading to inaccurate and inefficient analysis of motion events, with limitations in synchronization, object identification, and data processing, resulting in excessive storage and bandwidth requirements, and inability to detect rotational accelerations and concussions.

Innovation Solution

An integrated sensor and video motion analysis method that synchronizes and transfers concise event videos with motion data from sensors, using sensor fusion to create integrated motion metrics, and enables intelligent selection of videos, alteration of camera parameters, and generation of highlight reels, while allowing analysis and comparison of movement data across users and equipment.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If sensor data and video data are collected continuously for motion analysis, then complete motion data is captured, but storage requirements and bandwidth usage increase significantly

Engineering Contradiction:
Improvecompleteness of motion dataVSAvoidstorage requirements
Core Design Contradiction:
ReliabilityVSQuantity of substance

Solution Approach 1:

The system extracts only the relevant portions of video data that correspond to detected motion events. When a motion event is detected by sensors, the system retrieves only the specific video segment associated with that event rather than storing or transmitting entire video files, thereby reducing storage and bandwidth requirements while maintaining data completeness for analysis purposes

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system performs preliminary motion detection using sensors before processing or storing video data. By detecting motion events in advance through sensor data analysis, the system can selectively capture and store only the video portions corresponding to actual motion events, avoiding the need to store continuous video streams and significantly reducing storage requirements

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If sensor data and video data are synchronized for integrated analysis, then motion analysis accuracy improves, but system complexity increases

Engineering Contradiction:
Improvemotion analysis accuracyVSAvoidsystem integration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system uses timestamps as an intermediary mechanism to synchronize sensor data and video data. Both data streams are tagged with temporal information that allows them to be correlated and integrated without requiring complex real-time synchronization protocols, thereby reducing system complexity while maintaining motion analysis accuracy

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system merges sensor data and video data into a unified motion analysis framework by correlating them through temporal tags and event identifiers. This integration allows the system to leverage the complementary strengths of both data sources - the temporal precision of sensors and the visual information from video - to achieve accurate motion analysis without requiring overly complex separate processing systems

Inventive Principle:
Principle #5Merging (Combining)

3Measurement precision

If video frame rate is increased for better motion precision, then motion detection precision improves, but data processing requirements and storage increase

Engineering Contradiction:
Improvemotion detection precisionVSAvoidvideo data volume
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The system applies different video quality and frame rate settings to different temporal segments based on motion activity. During periods with detected motion events, the system uses higher frame rates to capture precise motion details, while during static periods, it reduces or suspends video capture, thereby maintaining motion detection precision when needed while minimizing overall video data volume

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP3323240B1Integrated sensor and video motion analysis method
Publication Date: 2021.04.28 BLAST MOTION INC
  • EP3323240B1 patent drawingFigure 1
  • EP3323240B1 patent drawingFigure 1A
  • EP3323240B1 patent drawingFigure 1B

AI summary

A method that integrates sensor data and video analysis to analyze object motion. Motion capture elements generate motion sensor data for objects of interest, and cameras generate video of these objects. Sensor data and video data are synchronized in time and aligned in space on a common coordinate system. Sensor fusion is used to generate motion metrics from the combined and integrated sensor data and video data. Integration of sensor data and video data supports robust detection of events, generation of video highlight reels or epic fail reels augmented with metrics that show interesting activity, and calculation of metrics that exceed the individual capabilities of either sensors or video analysis alone.