Remote PPG Signal Extraction via 3D Surface Mesh Motion Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Motion stabilization in endoscopic imaging is challenging due to deformation and movement of internal organs, making it difficult to compensate for perspective changes and relative motion between the camera and the region of interest.
Innovation Solution
A processor and system for processing 3D images to derive remote photoplethysmography (PPG) signals by constructing a surface representation from 3D images, matching these representations using transformations for motion compensation, and extracting PPG signals from matched locations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If motion stabilization is applied to endoscopic images, then PPG signal extraction becomes possible, but the complexity of processing increases due to organ deformation and perspective changes
Solution Approach 1:
The patent transforms 2D endoscopic images into 3D surface representations, adding a dimensional aspect to the data. This allows motion compensation to be performed in 3D space, accounting for organ deformation and perspective changes more effectively than traditional 2D stabilization methods, thereby improving PPG signal extraction reliability while managing processing complexity through intelligent 3D reconstruction
Solution Approach 2:
The patent introduces an intermediate 3D surface representation as a mediator between the raw endoscopic images and the final PPG signal extraction. This intermediate representation captures the geometric transformations and organ deformations, serving as a bridge that enables accurate motion compensation without requiring direct complex processing of the original images, thus improving reliability while controlling complexity
2Measurement precision
If 3D surface representation is constructed from endoscopic images, then motion compensation accuracy improves, but computational requirements increase
Solution Approach 1:
The patent segments the endoscopic image processing into distinct stages: 3D surface reconstruction, motion compensation, and PPG signal extraction. By dividing the computational task into manageable segments, the system achieves high motion compensation accuracy through 3D geometric transformations while controlling computational energy consumption by processing only relevant portions of the data at each stage
Solution Approach 2:
The patent performs preliminary 3D surface reconstruction and motion compensation before PPG signal extraction. By pre-processing the images to establish accurate 3D geometric relationships and compensate for motion in advance, the system achieves high measurement precision while reducing the computational burden during the actual signal extraction phase, thereby managing energy consumption more efficiently
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 enables reliable extraction of PPG signals and perfusion maps from internal body areas, providing improved motion compensation and deformation handling, especially in endoscopic imaging scenarios.
Implementation Method 1
PPG imaging utilizes an off-the-shelf camera and a light source to remotely detect the dynamic changes in blood volume beneath the skin
Data Source
AI summary
A PPG imaging system and method is provided for processing 3D images to derive remote PPG signals. A surface mesh of a region of interest is created from each of a set of the 3D images. The surface meshes are matched to each other using mesh transformations thereby providing motion compensation. A remote PPG signal is then obtained from each of a set of mesh locations of the matched surface meshes, thereby to derive a set of PPG signals. A perfusion map and/or a PPG delay map may be obtained from the set of PPG signals.