Removing environment factors from signals generated from video images captured for biomedical measurements
US-9185353-B2 · Nov 10, 2015 · US
US9364157B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9364157-B2 |
| Application number | US-201414243110-A |
| Country | US |
| Kind code | B2 |
| Filing date | Apr 2, 2014 |
| Priority date | Nov 14, 2013 |
| Publication date | Jun 14, 2016 |
| Grant date | Jun 14, 2016 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
An apparatus and method based on image for detecting heart rate activity is provided. The method includes: obtaining a plurality of color images; based on a complexion target condition, defining a target region; performing color composition analysis on the target region to obtain red channel signal, green channel signal and blue channel signal, respectively; performing independent component analysis on separate red, green and blue channel signals to obtain separate first independent component signal, second independent component signal and third independent component signal; performing frequency domain transform, signal energy computation and signal optimization processes on separate first, second and third independent component signals to obtain a filter signal, comparing filter signal based on a pre-set condition to determine if target region belonging to a human, and performing a physiological information analysis.
Opening claim text (preview).
What is claimed is: 1. An image-based apparatus for detecting heart rate activity, comprising: a detecting unit, configured to obtain a plurality of color images of a monitored target; a memory unit, coupled to the detecting unit, configured to store the color images obtained by the detecting unit; and a processor, coupled to the memory unit, wherein the processor further comprising: a target area defining module, configured to execute a target area detection process targeting the color images, wherein the target area detection process performing computation analysis on the color images to define a target area in the monitored target in the color image according to a predefined skin color target condition; a color image composition analysis module, configured to perform a color image composition analysis on the target area, wherein the color image composition analysis performing statistic computation for a red channel, a green channel and a blue channel of the target area to obtain a red channel signal, a green channel signal and a blue channel signal; an independent component analysis module, based on an independent component analysis method, configured to perform computation on the red channel signal, the green channel signal and the blue channel signal to obtain a first independent component signal, a second independent component signal, and a third independent component signal; a signal processing module, configured to perform a frequency domain transform process, a signal energy computation process and a signal fitness process for the first independent component signal, the second independent component signal, and the third independent component signal to obtain a filtered signal; a comparison module, configured to compare the filtered signal with at least a pre-defined condition to confirm the monitored target as a real human and provide an analysis instruction accordingly; and a physiological information analysis module, based on the analysis instruction, configured to execute a physiological information analysis process, wherein the signal energy computation process comprises the Euclidean norm. 2. The image-based apparatus for detecting heart rate activity as claimed in claim 1 , wherein the physiological analysis process is to analyze the heart rate activity of the monitored target. 3. The image-based apparatus for detecting heart rate activity as claimed in claim 1 , wherein the frequency domain transform process is a Fourier Transform process. 4. The image-based apparatus for detecting heart rate activity as claimed in claim 1 , wherein the signal fitness process further comprises a smoothing processing method. 5. The image-based apparatus for detecting heart rate activity as claimed in claim 4 , wherein the processor is able to obtain a regularity parameter according to the filtered signal. 6. The image-based apparatus for detecting heart rate activity as claimed in claim 5 , wherein the pre-defined condition further comprises a regularity default value. 7. The image-based apparatus for detecting heart rate activity as claimed in claim 6 , wherein the monitored target is determined as a real human when the regularity parameter is greater than the regularity default value. 8. An image-based apparatus for detecting heart rate activity, comprising: a detecting unit, configured to obtain a plurality of color images of a plurality of monitored targets; a memory unit, coupled to the detecting unit, configured to store the color images obtained by the detecting unit; and a processor, coupled to the memory unit, wherein the processor further comprising: a target area defining module, configured to execute a target area detection process targeting the color images, wherein the target area detection process performing computation analysis on the color images to define a plurality of target areas in the monitored target in the color image according to a predefined skin color target condition; a color image composition analysis module, configured to perform a color image composition analysis on each of the plurality of target areas, wherein the color image composition analysis performing statistic computation for a red channel, a green channel and a blue channel of each of the target areas to obtain a red channel signal, a green channel signal and a blue channel signal; an independent component analysis module, based on an independent component analysis method, configured to perform computation on the red channel signal, the green channel signal and the blue channel signal of each of the target areas to obtain a first independent component signal, a second independent component signal, and a third independent component signal; a signal processing module, configured to perform a frequency domain transform process, a signal energy computation process and a signal fitness process for the first independent component signal, the second independent component signal, and the third independent component signal of each of the target areas to obtain a filtered signal; a comparison module, configured to compare the filtered signal of each of the target areas with a first pre-defined condition to confirm the filtered signal of each of target areas as a real human signal; a relevance analysis module, configured to compare each filtered signal of each of the target areas with a second pre-defined condition to identify relevance among each of the target areas to confirm whether each of the target areas belonging to a real human and provide an analysis instruction accordingly; and a physiological information analysis module, based on the analysis instruction, configured to execute a physiological information analysis process, wherein the signal energy computation process comprises the Euclidean norm. 9. The image-based apparatus for detecting heart rate activity as claimed in claim 8 , wherein the physiological analysis process is to analyze the heart rate activity of the plurality of monitored targets. 10. The image-based apparatus for detecting heart rate activity as claimed in claim 8 , wherein the frequency domain transform process is a Fourier Transform process. 11. The image-based apparatus for detecting heart rate activity as claimed in claim 8 , wherein the signal fitness process further comprises a smoothing processing method. 12. The image-based apparatus for detecting heart rate activity as claimed in claim 11 , wherein the first pre-defined condition is a regularity default value. 13. The image-based apparatus for detecting heart rate activity as claimed in claim 12 , wherein the processor is able to obtain a regularity parameter according to each filtered signal of each target area. 14. The image-based apparatus for detecting heart rate activity as claimed in claim 13 , wherein the filtered signal is determined as a real human signal when the regularity parameter of the target area is greater than the regularity default value. 15. The image-based apparatus for detecting heart rate activity as claimed in claim 14 , wherein the second pre-defined condition is a waveform difference default value. 16. The image-based apparatus for detecting heart rate activity as claimed in claim 15 , wherein the processor obtains a peak interval parameter according to computation on the filtered signal of each of the plurality of target areas. 17. The image-based apparatus for detecting heart rate activity as claimed in claim 16 , wherein the processor compares the peak interval parameter of each target area and computes difference between any two peak interval parameters of the targe
Physics · mapped topic
Color image · CPC title
adapted for image acquisition of a particular organ or body part (A61B5/0082 takes precedence; arrangements for optical scanning A61B5/0062) · CPC title
Measuring pulse rate or heart rate · CPC title
Heart; Cardiac · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.