Video-image-based method and system for detecting non-contact vital sign
A technology for vital signs and detection methods, applied in medical images, medical imaging, pulse rate/heart rate measurement, etc., can solve problems such as increased error in detection results, limited denoising and anti-noise capabilities, and inability to complete detection, achieving increased Resistance, fast measurement, wide range of effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0068] Using the non-contact vital sign detection method based on video images of the present invention, a single person is used as a detection target for detection, and the process is as follows:
[0069] Get the video image of the target to be tested
[0070] Such as image 3 As shown, the video image of the target to be tested is continuously collected by the video image acquisition module 1 at a fixed frame rate.
[0071] In this example, if Figure 4 As shown, the Logitech webcam (model C250) can be used to capture 24-bit RGB true-color images with a frame rate of 15fps and an image resolution of 640×480. In the present invention, the higher the acquisition frame rate and the image resolution, the better, but these two items are also restricted by the execution speed, so they should be analyzed and determined according to specific conditions in practical application. Theoretically, for a heart rate test, a frame rate of 7fps can test a heartbeat of up to 200bpm; for ...
Embodiment 2
[0113] Simultaneous detection with two people as the detection target, the only difference from a single person is:
[0114] The automatic detection module performs automatic upper body contour recognition through edge contour detection, and firstly determines the number of targets to be measured as two by the number of upper body contours.
[0115] For each test target within the range of its upper body contour, determine the chest position as the breathing detection ROI area; determine the heart rate detection ROI area through skin color detection. Then each test target is processed separately, and the processing method is the same as the single-person detection. For the original time series signals of R, G, and B channels of heart rate detection, see Figure 17 , the normalized time series signal of heart rate detection see Figure 18 , the ICA independent component of heart rate detection see Figure 19 , the ICA independent components of heart rate detection after flat...
Embodiment 3
[0118] The animal pig is used as the detection target for detection. Other experimental procedures are similar to Example 1, and will not be repeated. Wherein, the difference is that the pig's heart rate and respiration ROI area can be taken as the pig's abdomen at the same time. The automatic detection of pig belly is realized by edge contour detection. The details are as follows: recognize the pig’s contour through edge contour detection, and perform ellipse fitting on the pig’s body. The center position of the fitted ellipse is the center of the abdomen. Take 40% of the long and short axes of the fitted ellipse to obtain the belly area of the pig. as the ROI area. Subsequent processing is the same as single-person detection. For the original time series signals of R, G, and B channels of heart rate detection, see Figure 23 , the normalized time series signal of heart rate detection see Figure 24 , the ICA independent component of heart rate detection see Figu...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com