Processing images of at least one living being

• US 8,805,019 B2
• Filed: 09/23/2013
• Issued: 08/12/2014
• Est. Priority Date: 03/06/2009
• Status: Active Grant

• Current Assignee: Koninklijke Philips N.V.
• Original Assignee: Koninklijke Philips N.V.
• Inventors: Jeanne, Vincent, Vlutters, Ruud, Cennini, Giovanni, Chestakov, Dmitri, de Bruijn, Frederik J.
• Primary Examiner(s): Mehta, Bhavesh
• Assistant Examiner(s): Harandi, Siamak
• Application Number:
  US14/033,696
• Publication Number:
  US 20140023236A1
• Time in Patent Office: 323 Days
• Field of Search: None
• US Class Current: 382/103
• CPC Class Codes: A61B 2562/0233 Special features of optical sensors or probes classified in A61B5/00
• CPC Class Codes: A61B 2562/046 in a matrix array
• CPC Class Codes: A61B 5/0064 Body surface scanning
• CPC Class Codes: A61B 5/0255 Recording instruments specially adapted therefor
• CPC Class Codes: A61B 5/0816 Measuring devices for examining respiratory frequency measuring frequency of electric signals G01R23/00
• CPC Class Codes: A61B 5/7285 for synchronising or triggering a physiological measurement or image acquisition with a physiological event or waveform, e.g. an ECG signal A61B6/5205, A61B6/541, A61B8/5207, A61B8/543 take precedence
• CPC Class Codes: A61B 6/541 involving acquisition triggered by a physiological signal
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/30076 Plethysmography
• CPC Class Codes: G06T 2207/30201 Face
• CPC Class Codes: G06T 7/20 Analysis of motion motion estimation for coding, decoding, compressing or decompressing digital video signals H04N19/43, H04N19/51
• CPC Class Codes: G06T 7/90 Determination of colour characteristics

Abstract

A method of processing images of at least one living being, includes obtaining a sequence (19) of digital images taken at consecutive points in time. At least one measurement zone (26) comprising a plurality of image points is selected. For each measurement zone (26), a signal (28,30) representative of at least variations in a time-varying value of a combination of pixel values at at least a number of the image points for use in determining at least one of a presence and a frequency value of at least one peak in a spectrum of the signal (28,30) corresponding to a frequency of a periodic physiological phenomenon is obtained. The step (25) of selecting at least one measurement zone (26) includes analyzing information based on pixel data of a plurality of image parts in at least one of the images (19), each image part including at least one image point, and selecting each measurement zone (26) from contiguous parts determined to have similar characteristics.

Claims

1. A method of image processing of a scene with respect to at least one living being having at least one body part, comprising:

receiving a sequence of digital images representing the scene at successive points in time, each said digital image including a plurality of image parts, each image part including at least one image point, each image point having at least one pixel value;

analyzing a plurality of image parts of at least one of the digital images so as to determine a set of contiguous image parts having similar characteristics;

responsive to analyzing so as to determine a set of contiguous image parts, automatically selecting at least one measurement zone, the at least one measurement zone including one or more image points of at least one of said contiguous image parts;

for at least one measurement zone, generating a signal representative of a time-varying average of the at least one pixel value of selected image points of the measurement zone; and

determining at least one of a presence and a frequency value of at least one peak in a spectrum of the signal corresponding to a frequency of a periodic physiological phenomenon of a living being.

2. A method according to claim 1, further comprising:

performing image segmentation on at least one of the digital images so as to determine at least one image segment; and

determining a measurement zone as to each so-determined image segment.

3. A method according to claim 2, wherein performing image segmentation includes using an algorithm for recognizing one or more image segments corresponding to at least one body part of at least one living being.

4. A method according to claim 2, further comprising:

tracking at least one of the image segments and such image segment'"'"'s measurement zone in each of a plurality of the digital images in the sequence of images; and

determining the position of such measurement zone relative to such image segment in each of the plurality of the digital images.

5. A method according to claim 1, wherein analyzing a plurality of image parts of at least one of the digital images comprises conducting a spatial analysis of the at least one pixel value of one or more image points of a plurality of image parts.

6. A method according to claim 1, wherein analyzing a plurality of image parts of at least one of the digital images comprises detecting image parts associated with minimal gradiant variations.

7. A method according to claim 6, wherein automatically selecting at least one measurement zone comprises forming the measurement zone from the image parts associated with the minimal gradient variations.

8. A method according to claim 1, wherein generating a signal comprises using a pixel value corresponding to brightness, whereby the so-generated signal is representative of the time-varying average brightness of the image points of the measurement zone.

9. A method according to claim 8, further comprising:

in generating a signal, discarding pixel values of selected image points, whereby the so-generated signal is representative of the time-varying average brightness of the fewer than all image points of the measurement zone.

10. A method according to claim 8, further comprising:

in generating a signal, selecting one or more color components and selectively combining the selected color components.

11. A method according to claim 10, wherein selectively combining includes obtaining a weighted sum among selected color components.

12. A method according to claim 8, further comprising centering the signal on its mean value so as to yield a further signal.

13. A method according to claim 1, further comprising centering the signal on its mean value so as to yield a further signal.

14. A method according to claim 13, further comprising:

determining a correction signal corresponding to time-variations associated with at least one pixel value of at least a number of image points in an image part other than the measurement zone; and

decorrelating the further signal with the correction signal.

15. A method according to claim 1, further comprising filtering the signal so as to yield a further signal.

16. A method according to claim 1, further comprising causing the sequence of digital images to be captured by a camera upon completion of an initialization phase, the initialization phase including measuring periodic intensity fluctuations in at least parts of images acquired by the camera while camera settings are varied, and selecting values of the camera settings at which measured periodic intensity fluctuations in at least a range of frequencies are determined to be minimal.

17. A method according to claim 1, further comprising:

determining a correction signal corresponding to a time-varying value of a combination of pixel values of at least a number of image points in an image part other than the measurement zone; and

decorrelating the signal from the correction signal.

18. A method according to claim 1, wherein determining at least one of a presence and a frequency value of at least one peak comprises comparing the spectrum or peaks of the spectrum, in at least a limited range, with a pre-determined reference range corresponding to a frequency of a periodic physiological phenomenon of a living being.

19. A method according to claim 18, wherein so determining comprises comparing to a reference range corresponding to one or both of typical human heart rates or respiration rates.

20. A method according to claim 18, further comprising:

responsive to determining presence of at least one peak in the spectrum corresponding to a frequency of a periodic physiological phenomenon, performing a function conditional on detecting a presence of at least one human being.