Remote Photoplethysmography Activity Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for automated surveillance and behavior analysis in public spaces fail to accurately obtain and synchronize physiological parameters like heart rate and pupil dilation with video footage, leading to ambiguous classification of human activities.
Innovation Solution
A method that uses remote photoplethysmography and vision-based analysis to classify human activities by obtaining spatiotemporal coefficients from digital images, determining physiological parameters like heart rate through pixel data analysis, and selectively illuminating subjects to avoid shadows and distinguish between similar actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If separate sensors are used to obtain physiological parameters, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent combines multiple functions (video capture, physiological parameter measurement, illumination) into a single integrated system. The camera records both visual information and photoplethysmographic signals, while the light source serves both illumination and photoplethysmography excitation purposes, eliminating the need for separate sensors and reducing system complexity
Solution Approach 2:
The camera is used for multiple purposes: standard video recording and photoplethysmographic signal acquisition. The light source also serves dual functions: illumination and photoplethysmography excitation. This multi-functionality reduces the number of components needed while maintaining measurement precision
2Reliability
If separate sensors and synchronization mechanisms are added, then reliability of physiological data is improved, but ease of operation deteriorates
Solution Approach 1:
The patent merges the acquisition of video data and physiological data into a single unified process using the same camera and light source. This eliminates the need for separate sensors and synchronization mechanisms, maintaining data reliability while significantly improving ease of operation
3Ease of operation
If standard vision-based analysis is used alone, then ease of operation is maintained, but measurement precision of activity classification deteriorates
Solution Approach 1:
The patent merges vision-based analysis with photoplethysmographic analysis to classify human activities. The combination of visual information and physiological signals (heart rate, blood perfusion) improves classification accuracy while maintaining ease of operation through automated processing
Solution Approach 2:
The patent uses photoplethysmographic signals as an intermediary to disambiguate activities with similar visual appearances. For example, physiological signals help distinguish between running and jogging by detecting heart rate differences, while the visual system provides the basic motion framework
4Device complexity
If ambient light is used for photoplethysmography, then device complexity is reduced, but measurement precision deteriorates due to shadows and insufficient illumination
Solution Approach 1:
The patent segments the illumination function from ambient light and provides dedicated controlled illumination for photoplethysmography. This separation allows optimization of lighting conditions for physiological signal acquisition without adding complex multi-function illumination systems
Solution Approach 2:
The patent changes the illumination parameters by introducing a controlled light source with specific characteristics (wavelength, intensity, direction) optimized for photoplethysmography. This improves signal quality by eliminating shadows and ensuring sufficient illumination, while the illumination system remains relatively simple
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach allows for efficient, contactless, and unobtrusive classification of human activities with high accuracy, distinguishing between actions like running and jogging without requiring separate sensors, and can be scaled for multiple subjects, providing a strong signal for physiological parameter determination.
Implementation Method 1
obtaining a sequence of digital images of a scene comprising at least a living being, using a camera
Implementation Method 2
controlling a directable light source to illuminate at least the part of the selected living being with the exposed skin surface
Implementation Method 3
determining at least one value of a physiological parameter, by remote photoplethysmography, of a living being represented in at least some of the sequence of images through analysis of pixel data
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A method of image analysis, includes: obtaining a sequence (37;51) of images, each represented by pixel data; performing a vision-based analysis on at least one of the sequence (37;51) of images to obtain data for classifying a state of a subject represented in the images; - determining at least one value of a physiological parameter of a living being represented in at least some of the sequence (37;51) of images; and classifying a state of the subject using the data obtained with the vision-based analysis and the at least one value of the physiological parameter. The at least one value of the physiological parameter is determined through analysis of image data from the same sequence (37;51) of images from which the at least one image on which the vision-based analysis is performed is taken. A method of enabling remote photoplethysmographic analysis includes: obtaining a sequence (37;51) of images from at least one camera (3), each represented by pixel data representative of reflected ambient light in at least a limited range of wavelengths; and, for at least one measurement zone (41), providing a signal representative of at least variations in a time-varying value of a combination of pixel values at at least a number of image points in the measurement zone (41) for use in determining at least one value of a physiological parameter. At least part of a selected subject represented in the sequence (37;51) of images is tracked, and a directable light source (4) illuminating at least part of the selected subject is controlled.