IP Library › Granted Patent US 12,300,021
Granted Patent B2
US 12,300,021 · App. 17/951,954 · Granted May 13, 2025

Video processing apparatus, control method therefor, and non-transitory computer-readable storage medium

Inventor: Kimimaru Kato (Tokyo, JP)
Assignee: Canon Kabushiki Kaisha
G06V40/15G06V10/56G06V20/40G06V40/166
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,300,021
App. No.
17/951,954
Granted
May 13, 2025
Kind
B2
Abstract

This disclosure provides a video processing apparatus that detects biometric information of an object from a video of the object composed of a plurality of time-series images, wherein the apparatus comprises an acquiring unit which receives the video input thereto, and acquires a skin area of an object; a determining unit which determines correction coefficients based on a color of the skin area and a color indicating a target hue, the correction coefficients being for approximating a hue of pixels in the skin area to the target hue; a correcting unit which corrects, with use of the correction coefficients, the pixels in the skin area in each of the frames composing the video; and a detecting unit which detects biometric information of the object based on time-series images of the skin area after the correction by the correcting unit.

Claims (29)

1. A video processing apparatus that detects biometric information of an object from a video of the object composed of a plurality of time-series images, the apparatus comprising:

an acquiring unit configured to receive the video input thereto, and acquire a skin area of an object;

a determining unit configured to determine correction coefficients based on a color of the skin area acquired by the acquiring unit and a color indicating a target hue, the correction coefficients being for approximating a hue of pixels in the skin area acquired by the acquiring unit to the target hue;

a correcting unit configured to correct, with use of the correction coefficients, at least the pixels in the skin area in each of the frames composing the video; and

a detecting unit configured to detect biometric information of the object based on time-series images of the skin area after the correction by the correcting unit.

2. The apparatus according to claim 1 , wherein the determining unit

determines, as the color of the skin area, a color indicated by an average value of values of respective color components of all pixels within the skin area in a representative frame which is included in the video and which has been set in advance, and

determines ratios between values of respective color components indicating the color of the skin area and values of respective color components indicating the color of the target hue as the correction coefficients, and

the correcting unit performs the correction by multiplying values of respective color component of the pixels in the skin area by corresponding correction coefficients, respectively.

3. The apparatus according to claim 1 , wherein provided that a direction of R components, a direction of G components, and a direction of B components are 0°, 120°, and 240°, respectively, the target hue indicates a direction of 50° or 230°.

4. The apparatus according to claim 1 , wherein (amplitude) scores are calculated by converting the pixels in the skin area obtained from the plurality of frames into candidate hues of a plurality of patterns, and the target hue is the candidate hue that corresponds to the highest (amplitude) score.

5. The apparatus according to claim 1 , wherein the determining unit determines N sets of correction coefficients based on the color of the skin area acquired by the acquiring unit and colors indicating N target hues that have been set in advance (where N≥2), the N sets of correction coefficients being for approximating the hue of the pixels in the skin area acquired by the acquiring unit to each of the N target hues,

wherein the correcting unit generates N pieces of time-series image data of the skin area by correcting at least pixels in the skin area in accordance with the N sets of correction coefficients in each of the frames composing the video, and

wherein the detecting unit determines biometric information of the object to be output by detecting N pieces of biometric information of the object based on the N pieces of time-series image data of the skin area acquired by the correcting unit and evaluating the N pieces of biometric information of the object.

6. The apparatus according to claim 5 , wherein provided that a direction of R components, a direction of G components, and a direction of B components are 0°, 120°, and 240°, respectively, the N target hues are N hues which are centered at 50° or 230° and which neighbor one another at an interval of a preset angle.

7. The apparatus according to claim 1 , wherein the biometric information includes at least one of a pulse rate, blood pressure, a stress index, and biometric determination information.

8. The apparatus according to claim 1 , wherein the video is a video that has been captured by a visible light camera.

9. The apparatus according to claim 1 , wherein based on the time-series images of the skin area after the correction by the correcting unit, the detecting unit detects the biometric information indicating a pulse estimated from an amplitude that has occurred in a first predetermined time period.

10. The apparatus according to claim 1 , wherein based on the time-series images of the skin area after the correction by the correcting unit, the biometric information indicating presence or absence of a heartbeat estimated from an amplitude that has occurred in a second predetermined time period is detected.

11. A method of controlling a video processing apparatus that detects biometric information of an object from a video of the object composed of a plurality of time-series images, the method comprising:

(a) receiving the video input thereto, and acquiring a skin area of an object;

(b) determining correction coefficients based on a color of the skin area acquired in the step (a) and a color indicating a target hue, the correction coefficients being for approximating a hue of pixels in the skin area acquired in the acquiring step to the target hue;

(c) correcting, with use of the correction coefficients, at least the pixels in the skin area in each of the frames composing the video; and

(d) detecting biometric information of the object based on time-series images of the skin area after the correction in the step (c).

12. A non-transitory computer-readable storage medium storing a program which, when read and executed by a computer, caused the computer to execute the steps of a method of controlling a video processing apparatus that detects biometric information of an object from a video of the object composed of a plurality of time-series images, the method comprising:

(a) receiving the video input thereto, and acquiring a skin area of an object;

(b) determining correction coefficients based on a color of the skin area acquired in the step (a) and a color indicating a target hue, the correction coefficients being for approximating a hue of pixels in the skin area acquired in the acquiring step to the target hue;

(c) correcting, with use of the correction coefficients, at least the pixels in the skin area in each of the frames composing the video; and

(d) detecting biometric information of the object based on time-series images of the skin area after the correction in the step (c).

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 28, 2022
From: KATO, KIMIMARU
To: CANON KABUSHIKI KAISHA
Reel/Frame 061573/0270 →
Priority Claims (1)
JP 2021-164293 · Oct 5, 2021 · national
Continuity (1)
Related Publication 20230108023A1 · Apr 6, 2023
References Cited (11)
US 10595732B2 · Jones et al. · 2020 [cited by applicant]
US 20190125197A1 · Fukuda · 2019 [cited by examiner]
US 20200260956A1 · Lee et al. · 2020 [cited by applicant]
US 20210030285A1 · Fukuda et al. · 2021 [cited by applicant]
US 20210089786A1 · Kon · 2021 [cited by examiner]
JP 2021023490 · 2021 [cited by applicant]
JP 6911609B2 · 2021 [cited by applicant]
Cho Dongrae et al: “Non-contact robust heart rate estimation using HSV color model and matrix-based IIR filter in the face video imaging”, 2016 38th Annual International Conference of the IEEE Engineering in Medicine an… [cited by applicant]
Gill R. Tsouri et al: “On the benefits of alternative color spaces for noncontact heart rate measurements using standard red-green-blue cameras”, Journal Of Biomedical Optics, vol. 20, No. 4, Apr. 15, 2015 (Apr. 15, 201… [cited by applicant]
Cardani Darrin: “Adventures in HSV Space”, Dec. 31, 2001 (Dec. 31, 2001), pp. 1-10, XP93019423, Retrieved from the Internet: URL:http://robotlab.itk.ppke.hu/˜rakadam/hsvspace.pdf. [cited by applicant]
Extended European Search Report dated Feb. 8, 2023 in counterpart EP Application No. 22196516.3. [cited by applicant]