Automatic pan-tilt-zoom adjustment to improve vital sign acquisition

Patent metadata

Field	Value
Publication number	US-11100635-B2
Application number	US-201716343827-A
Country	US
Kind code	B2
Filing date	Oct 31, 2017
Priority date	Nov 3, 2016
Publication date	Aug 24, 2021
Grant date	Aug 24, 2021

Abstract

Techniques disclosed herein relate to automatic pan-tilt-zoom adjustment to improve vital sign acquisition. In various embodiments, a vital sign acquisition camera (176) operable to pan, tilt, and zoom (“PTZ”) may capture (402) an image of a patient (100). The image may be analyzed (404) to detect a depicted position of the patient within an image coordinate space of the image. A desired position of the patient within the image coordinate space of the image may determined (406), and a difference in the image coordinate space between the depicted position and the desired position may be calculated (408). The difference may then be mapped (410) from the image coordinate space to a PTZ space. One or more PTZ parameters of the vital sign acquisition camera may be altered (412) based on the mapping. After altering the one or more PTZ parameters, the vital sign acquisition camera may acquire (414) one or more vital signs from the patient.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
capturing, by a vital sign acquisition camera, an image of a patient, wherein the vital sign acquisition camera is operable to pan, tilt, and zoom (“PTZ”);
analyzing the image to detect a depicted position and size of the patient within an image coordinate space of the image, a detected width of the patient's face within the imagine coordinate space of the image, and a detected length of the patient's face within the image coordinate space of the image;
determining a desired position and size of the patient within the image coordinate space of the image, determining the desired position and size including:
determining a desired width of the patient's face within the image coordinate space of the image as a first predetermined percentage of a width of the image coordinate space of the image, wherein the first predetermined percentage is not 100 percent;
determining a desired zoom scale as the desired width of the patient's face within the image coordinate space of the image times a detected zoom scale of the image of the patient divided by the detected width of the patient's face within the image coordinate space of the image;
determining a desired length of the patient's face within the image coordinate space of the image as the desired zoom scale times the detected length of the patient's face within the image coordinate space of the image divided by the detected zoom scale of the image of the patient; and
determining a desired offset of the patient's face from a top of the image coordinate space of the image as a second predetermined percentage of the desired length of the patient's face within the image coordinate space of the image, wherein the second predetermined percentage is not 0 percent,
wherein the desired position and size of the patient within the image coordinate space of the image is based on the desired width of the patient's face, the desired length of the patient's face, and the desired offset of the patient's face from the top of the image coordinate space of the image;

calculating a difference in the image coordinate space between the depicted position and size and the desired position and size;
mapping the difference from the image coordinate space to a PTZ space;
altering one or more PTZ parameters of the vital sign acquisition camera based on the mapping; and
after altering the one or more PTZ parameters, acquiring, by the vital sign acquisition camera, one or more vital signs from the patient.

2. The computer-implemented method of claim 1 , wherein the analyzing includes detecting one or more sizes of one or more depicted portions of the patient within the image coordinate space of the image.

3. The computer-implemented method of claim 2 , further comprising:
determining one or more desired sizes of the one or more depicted portions of the patient within the image coordinate space of the image;
wherein the difference in the image coordinate space includes one or more scale differences between the detected one or more sizes of the one or more depicted portions of the patient and the one or more desired sizes.

4. The computer-implemented method of claim 1 , wherein the mapping is based on prior calibration of the vital sign acquisition camera.

5. The computer-implemented method of claim 4 , wherein the prior calibration includes estimating a focal length at each of a plurality of zoom levels of the vital sign acquisition camera.

6. A system comprising one or more processors and memory operably coupled with the one or more processors, wherein the memory stores instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to:
capture, by a vital sign acquisition camera, an image of a patient, wherein the vital sign acquisition camera is operable to pan, tilt, and zoom (“PTZ”);
analyze the image to detect a depicted position and size of the patient within an image coordinate space of the image, a detected width of the patient's face within the image coordinate space of the image, and a detected length of the patient's face within the image coordinate space of the image;
determine a desired width of the patient's face within the image coordinate space of the image as a first predetermined percentage of a width of the image coordinate space of the image, wherein the first predetermined percentage is not 100 percent;
determine a desired zoom scale as the desired width of the patient's face within the image coordinate space of the image times a detected zoom scale of the image of the patient divided by the detected width of the patient's face within the image coordinate space of the image;
determine a desired length of the patient's face within the image coordinate space of the image as the desired zoom scale times the detected length of the patient's face within the image coordinate space of the image divided by the detected zoom scale of the image of the patient; and
determine a desired offset of the patient's face from a top of the image coordinate space of the image as a second predetermined percentage of the desired length of the patient's face within the image coordinate space of the image, wherein the second predetermined percentage is not 0 percent,
wherein the desired position and size of the patient within the image coordinate space of the image is based on the desired width of the patient's face, the desired length of the patient's face, and the desired offset of the patient's face from the top of the image coordinate space of the image;

calculate a difference in the image coordinate space between the depicted position and size and the desired position and size;
map the difference from the image coordinate space to a PTZ space;
alter one or more PTZ parameters of the vital sign acquisition camera based on the mapping; and
after altering the one or more PTZ parameters, acquire, by the vital sign acquisition camera, one or more vital signs from the patient.

7. The system of claim 6 , further comprising instructions to detect one or more sizes of one or more depicted portions of the patient within the image coordinate space of the image.

8. The system of claim 7 , further comprising instructions to:
determine one or more desired sizes of the one or more depicted portions of the patient within the image coordinate space of the image;
wherein the difference in the image coordinate space includes one or more scale differences between the detected one or more sizes of the one or more depicted portions of the patient and the one or more desired sizes.

9. The system of claim 6 , wherein the mapping is based on prior calibration of the vital sign acquisition camera.

10. The system of claim 9 , wherein the prior calibration includes estimating a focal length at each of a plurality of zoom levels of the vital sign acquisition camera.

11. At least one non-transitory computer-readable medium comprising instructions that, in response to execution of the instructions by one or more processors, cause the one or more processors to perform the following operations
capturing, by a vital sign acquisition camera, an image of a patient, wherein the vital sign acquisition camera is operable to pan, tilt, and zoom (“PTZ”);
analyzing the image to detect a depicted position and size of the patient within an image coordinate space of the image, a detected width of the patient's face within the image coordinate space of the image, and detected length of the patient's face within the image coordinate space of the image;
determining a desired position and size of the patient within the image coordinate space of the image, determining the desired

Assignees

• Koninklijke Philips Nv

Inventors

• Wang Haibo
• Van Zon Cornelis Conradus Adrianus Maria

Classifications

• H04N23/695

  Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects · CPC title

• H04N23/69

  Control of means for changing angle of the field of view, e.g. optical zoom objectives or electronic zooming · CPC title

• G16H30/20 Primary

  for handling medical images, e.g. DICOM, HL7 or PACS · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title