Computer Vision Ergonomic Risk Assessment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current worker risk assessment systems are limited by the need for wearable sensors, which can alter movement patterns, are uncomfortable for workers, and are costly, while also failing to accurately assess multiple joints simultaneously, leading to incomplete and inaccurate safety management.

Innovation Solution

A non-intrusive computer vision system using deep machine learning analyzes video data from surveillance cameras to assess kinematic variables of multiple joints without sensors, providing real-time ergonomic assessments and risk evaluations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If wearable sensors are used to assess worker risk, then movement data can be collected, but the sensors alter movement patterns and provide false data

Engineering Contradiction:

Improvemovement data accuracyVSAvoidsensor interference with natural movement

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent replaces the mechanical/wearable sensor system with a computer vision system using cameras and machine learning algorithms. The system captures images of workers performing tasks and automatically analyzes joint angles, postures, and movements through image processing, eliminating the need for physical sensors on workers while maintaining measurement accuracy.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system creates a digital representation (copy) of the worker's movements and postures through computer vision. By capturing images and generating virtual models of joint positions and movements, the system analyzes risk factors without physically contacting or interfering with the worker's natural movements.

Inventive Principle:

Principle #26Copying

2Measurement precision

If wearable sensors are used for risk assessment, then worker data can be collected, but workers find them uncomfortable

Engineering Contradiction:

Improveworker data collectionVSAvoidworker comfort

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent eliminates wearable sensors entirely by substituting them with a remote computer vision system. Cameras positioned in the workspace capture worker movements, and machine learning algorithms analyze the images to determine joint angles, postures, and ergonomic risk factors, removing all physical discomfort associated with wearing sensors.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces an intermediary (computer vision system with cameras and processing algorithms) that collects worker movement data remotely without requiring direct contact with the worker. This intermediary captures and analyzes movements through images, eliminating the need for workers to wear uncomfortable sensors.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Measurement precision

If wearable sensors are used to assess risk, then individual worker data can be obtained, but the system becomes expensive

Engineering Contradiction:

Improveindividual worker assessmentVSAvoidsystem cost

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces expensive wearable sensors with a more cost-effective computer vision system using standard cameras and processing software. The system analyzes worker movements and postures through image processing algorithms, eliminating the need for costly sensor hardware while maintaining the ability to assess individual workers.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

4Measurement precision

If single-joint assessment systems are used, then focus can be maintained on one area, but multiple joints cannot be monitored simultaneously

Engineering Contradiction:

Improvesingle joint measurement accuracyVSAvoidassessment coverage

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The computer vision system is designed to simultaneously analyze multiple joints and body regions through a single imaging system. By capturing complete body or regional images and processing them to identify joint angles and postures across multiple locations, the system provides comprehensive multi-joint assessment without requiring separate measurement systems for each joint.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11775902B2System and method to predict, prevent, and mitigate workplace injuries

Publication Date: 2023.10.03 THE UNIVERSITY OF IOWA RESEARCH

AI summary

A prevention and safety management system utilizes a non-intrusive imaging sensor (e.g. surveillance cameras, smartphone cameras) and a computer vision system to record videos of workers not wearing sensors. The videos are analyzed using a deep machine learning algorithm to detect kinematic activities (set of predetermined body joint positions and angles) of the workers and recognizing various physical activities (walk/posture, lift, push, pull, reach, force, repetition, duration etc.). The measured kinematic variables are then parsed into metrics relevant to workplace ergonomics, such as number of repetitions, total distance travelled, range of motion, and the proportion of time in different posture categories. The information gathered by this system is fed into an ergonomic assessment system and is used to automatically populate exposure assessment tools and create risk assessments.