Hand Washing Pose Analysis for Technique Compliance Monitoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing hand washing monitoring systems fail to comprehensively analyze hand washing techniques, often missing critical areas like the tips of fingers and thumbs, and do not ensure that all steps of the hand washing process are completed effectively.
Innovation Solution
A hand washing monitoring system utilizing a camera and processor that analyzes hand motion and image data to determine if desired poses are executed and for the correct durations, generating a quality indication by extracting feature vectors and using classifiers to assess hand washing compliance, independent of the order of motion poses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If simple motion detection is used to monitor hand washing, then the system is easier to implement, but the monitoring precision and comprehensiveness of hand washing technique analysis deteriorates
Solution Approach 1:
The hand washing process is segmented into multiple distinct phases (wet hands, apply soap, rub palms, rub back of hands, interlace fingers, wash thumbs, rub finger tips, rinse, dry). Each phase is detected and monitored separately through image analysis, allowing comprehensive technique assessment while maintaining systematic implementation simplicity.
Solution Approach 2:
The system transitions from simple motion detection to analyzing multiple dimensions of hand washing including pose configuration, motion duration, phase sequence, and specific hand regions (fingertips, thumbs). This multi-dimensional analysis achieves comprehensive monitoring precision through computer vision and image processing techniques.
2Measurement precision
If comprehensive image analysis is performed to assess all hand washing steps, then the monitoring precision improves, but the processing time and computational complexity increases
Solution Approach 1:
The system performs preliminary detection of hand presence and skin tone identification before detailed phase analysis. This preliminary action filters out non-relevant frames and prepares data structures in advance, reducing processing time for comprehensive analysis while maintaining monitoring precision.
Solution Approach 2:
The system continuously analyzes video frames throughout the hand washing process, maintaining constant monitoring without interruption. This continuous analysis ensures all phases are captured precisely while optimizing processing throughput to minimize overall processing time.
3Measurement precision
If the system monitors specific hand regions (fingertips, thumbs) in detail, then the measurement precision of technique compliance improves, but the device complexity increases
Solution Approach 1:
The system applies local quality analysis by focusing detailed image processing specifically on critical hand regions (fingertips, thumbs) where pathogen transfer risk is highest. These regions receive enhanced analysis for proper rubbing coverage while other areas use standard monitoring, achieving high precision where needed without proportionally increasing overall system complexity.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
A hand washing monitoring system (1) comprising a camera (2), a processor (4), the processor being adapted to receive from the camera images of hand washing activity. The processor analyses mutual motion of hands to determine if the hands mutually move in desired poses, and if so, the durations of the patterns; and generates a hand washing quality indication according to the analysis. The processor extracts information features from the images and generates feature vectors based on the features, including bimanual hand and arm shape vectors, and executes a classifier with the vectors to determine the poses. The processor uses edge segmentation and pixel spatio-temporal measurements to form at least some of the feature vectors.