Vital Sign Detection via Image Sub-region Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing detection devices struggle to accurately identify and track a region of interest for vital sign measurement when the subject is not facing the camera, or in conditions with inadequate lighting, leading to failed vital sign measurements.
Innovation Solution
A detection device comprising an image processing module, a calculation module, and an identification module that divides frames into sub-regions, generates feature signals based on vital-sign features, and determines valid image signals to identify and track the region of interest, even in varying lighting conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a video camera is used to extract vital sign signals, then the measurement is convenient, comfortable, and safe, but the system fails to identify appropriate ROI when the subject is not facing the camera or in inadequate lighting conditions
Solution Approach 1:
The image frame is divided into multiple sub-regions, and vital sign features are extracted independently from each sub-region. This segmentation allows the system to identify at least one valid ROI even when the overall image quality is poor, as long as some sub-regions contain detectable vital sign signals.
Solution Approach 2:
Instead of requiring uniform image quality across the entire frame, the system evaluates vital sign features locally in each sub-region. This enables the system to identify ROIs in regions with adequate signal quality while ignoring regions with poor lighting or incorrect orientation.
2Ease of operation
If the subject's face or chest is not properly positioned in the camera view, then non-contact measurement is maintained, but the ROI cannot be identified and vital sign measurement fails
Solution Approach 1:
By segmenting the image into sub-regions and independently analyzing vital sign features in each, the system can identify valid ROIs even when the subject is not properly positioned. At least one sub-region will contain detectable vital sign signals from the subject's skin or chest.
Solution Approach 2:
The system automatically identifies valid ROIs by analyzing vital sign features in each sub-region without requiring manual intervention or proper subject positioning. The subject's own vital sign signals serve as the indicator for ROI identification.
3Ease of operation
If the lighting conditions are too light or too dark, then non-contact measurement is maintained, but the video camera cannot identify an appropriate ROI for accurate measurement
Solution Approach 1:
Dividing the image into sub-regions allows the system to find at least one region with adequate lighting conditions for vital sign detection, even when overall lighting is poor. Some sub-regions may contain skin or chest areas with sufficient signal quality.
Solution Approach 2:
The system evaluates lighting conditions and signal quality locally in each sub-region rather than requiring uniform conditions across the entire frame. This enables ROI identification in regions with acceptable lighting while excluding regions with inadequate signal quality.
Data Source
AI summary
A detection method and a detection device for detection of at least one region of interest (ROI) using the same are provided. A plurality of successive frames is captured by an image sensor. A first frame among the plurality of successive frames is divided into a plurality of sub regions. A first vital-sign feature of a first sub region among the plurality of sub regions is obtained. A first feature signal is generated according to the first vital-sign feature. Whether the first feature signal is a first valid image signal is determined. When it is determined that the first feature signal is a first valid image signal, the first sub region is identified as a first ROI. In the frames occurring after the first frame, the first ROI is tracked.