Discriminating visual recognition program for digital cameras

• US 9,497,376 B2
• Filed: 04/07/2016
• Issued: 11/15/2016
• Est. Priority Date: 01/26/2015
• Status: Expired due to Fees

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bostick, James E., Cunico, Hernan A., Ganci, John M. Jr., Keen, Martin G.
• Primary Examiner(s): PRABHAKHER, PRITHAM DAVID
• Application Number:
  US15/093,182
• Publication Number:
  US 20160219214A1
• Time in Patent Office: 222 Days
• Field of Search: 348/222.1
• US Class Current: 1/1
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06F 3/0304 Detection arrangements using opto-electronic means constructional details of pointing devices not related to the detection arrangement using opto-electronic means G06F3/033; optical digitisers G06F3/042
• CPC Class Codes: G06K 7/1413 1D bar codes
• CPC Class Codes: G06K 7/1417 2D bar codes
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/13 Edge detection
• CPC Class Codes: G06V 40/20 Movements or behaviour, e.g. gesture recognition recognition of facial expressions G06V40/16
• CPC Class Codes: H04N 23/611 where the recognised objects include parts of the human body
• CPC Class Codes: H04N 23/62 Control of parameters via user interfaces
• CPC Class Codes: H04N 23/66 Remote control of cameras or camera parts, e.g. by remote control devices

Abstract

Control of a camera is provided. Data describing a visual key is generated. The data describing the visual key is transmitted. The visual key is identified. A person who is in possession of the visual key is identified. The person is associated with the visual key, wherein the person is authorized to control the camera using gestures. A gesture of the person is recognized. The gesture causes a program to execute a command that corresponds to the gesture, wherein the command cause the camera to perform a function.

Claims

1. A method comprising:

generating, by one or more computer processors, data describing a visual key;

transmitting, by one or more computer processors, the data describing the visual key;

capturing, by one or more computer processors, a first image that includes the visual key;

identifying, by one or more computer processors, the visual key in the first image;

determining, by one or more computer processors, an outline of a person in the first image based, at least in part, on at least one of edge detection code and edge matching code;

determining, by one or more computer processors, that a percentage on an area of the visual key that overlaps with an area defined by the outline of the person exceeds a threshold percentage, and in response, associating, by one or more computer processors, the visual key with the person, wherein an association with the visual key authorizes the person to control a camera;

capturing, by one or more computer processors, a second image that includes a gesture of the person, wherein the first image does not include the gesture; and

responsive to recognizing, by one or more computer processors, the gesture of the person in the second image, executing, by one or more computer processors, a command that corresponds to the gesture, wherein the command causes the camera to perform a function.

2. The method of claim 1, wherein identifying, by one or more computer processors, the visual key in the first image comprises:

dividing, by one or more computer processors, the first image into a plurality of regions;

for a region or the plurality of regions, determining, by one or more computer processors, a score based, at least in part, on how well the region matches the visual key; and

determining, by one or more computer processors, that the score exceeds a first threshold score, and in response, capturing, by one or more computer processors, a third image, wherein the third image is captured at a higher magnification than the first image.

3. The method of claim 2, wherein identifying, by one or more computer processors, the visual key in the first image further comprises:

in response to determining, by one or more computer processors, that a score of the region does not exceed a second threshold score, based, at least in part, on how well the third image matches the visual key, capturing, by one or more computer processors, a fourth image, wherein the fourth image is captured at a higher magnification than the third image and includes the region, and wherein the second threshold score is higher than the first threshold score.

4. The method of claim 2, wherein identifying, by one or more computer processors, the visual key in the first image further comprises:

in response to determining, by one or more computer processors, that a score of the region exceeds a second threshold score, based, at least in part, on how well the third image matches the visual key, identifying, by one or more computer processors, the region as the visual key, wherein the second threshold score is higher than the first threshold score.

5. The method of claim 4, wherein the visual key is a machine-readable pattern of geometric shapes.

6. The method of claim 5, wherein the machine-readable pattern of geometric shapes is a universal product code.

7. The method of claim 5, wherein the machine-readable pattern of geometric shapes is a quick response code.

8. The method of claim 7, wherein the score of the region is based, at least in part, on a model of the visual key that accounts for an orientation of the visual key in at least one of yaw, pitch, and roll.

9. A computer program product for controlling a camera, the computer program product comprising:

a computer readable storage device and program instructions stored on the computer readable storage device, the program instructions comprising;

program instructions to generate data describing a visual key;

program instructions to transmit the data describing the visual key;

program instructions to capture a first image that includes the visual key;

program instructions to identify the visual key in the first image;

program instructions to determine an outline of a person in the first image based, at least in part, on at least one of edge detection code and edge matching code;

program instructions to determine that a percentage on an area of the visual key that overlaps with an area defined by the outline of the person exceeds a threshold percentage, and in response, execute program instructions to associate the visual key with the person, wherein an association with the visual key authorizes the person to control a camera;

program instructions to capture a second image that includes a gesture of the person, wherein the first image does not include the gesture; and

program instructions to, responsive to recognizing the gesture of the person in the second image, execute-a command that corresponds to the gesture, wherein the command causes the camera to perform a function.

10. The computer program product of claim 9, wherein the program instructions to identify the visual key in the first image comprise:

program instructions to divide the first image into a plurality of regions;

program instructions to determine, for a region or the plurality of regions, a score based, at least in part, on how well the region matches the visual key; and

program instructions to determine that the score exceeds a first threshold score, and in response, execute program instructions to capture a third image, wherein the third image is captured at a higher magnification than the first image.

11. The computer program product of claim 10, wherein the program instructions to identify the visual key in the first image further comprise:

program instructions to, in response to determining that a score of the region does not exceed a second threshold score, based, at least in part, on how well the third image matches the visual key, capture a fourth image, wherein the fourth image is captured at a higher magnification than the third image and includes the region, and wherein the second threshold score is higher than the first threshold score; and

program instructions to, in response to determining that a score of the region exceeds a second threshold score, based, at least in part, on how well the third image matches the visual key, identify the region as the visual key, wherein the second threshold score is higher than the first threshold score.

12. The computer program product of claim 11, wherein the visual key is a machine-readable pattern of geometric shapes.

13. The computer program product of claim 12, wherein the machine-readable pattern of geometric shapes is a quick response code.

14. The computer program product of claim 13, wherein the score of the region is based, at least in part, on a model of the visual key that accounts for an orientation of the visual key in at least one of yaw, pitch, and roll.

15. A computer system for controlling a camera, the computer system comprising:

one or more computer processors;

one or more computer readable storage devices;

program instructions stored on the one or more computer readable storage devices for execution by at least one of the one or more processors, the program instructions comprising;

program instructions to generate data describing a visual key;

program instructions to transmit the data describing the visual key;

program instructions to capture a first image that includes the visual key;

program instructions to identify the visual key in the first image;

program instructions to determine an outline of a person in the first image based, at least in part, on at least one of edge detection code and edge matching code;

program instructions to determine that a percentage on an area of the visual key that overlaps with an area defined by the outline of the person exceeds a threshold percentage, and in response, execute program instructions to associate the visual key with the person, wherein an association with the visual key authorizes the person to control a camera;

program instructions to capture a second image that includes a gesture of the person, wherein the first image does not include the gesture; and

program instructions to, responsive to recognizing the gesture of the person in the second image, execute a command that corresponds to the gesture, wherein the command causes the camera to perform a function.

16. The computer system of claim 15, wherein the program instructions to identify the visual key in the first image comprise:

program instructions to divide the first image into a plurality of regions;

program instructions to determine, for a region or the plurality of regions, a score based, at least in part, on how well the region matches the visual key; and

program instructions to determine that the score exceeds a first threshold score, and in response, execute program instructions to capture a third image, wherein the third image is captured at a higher magnification than the first image.

17. The computer system of claim 16, wherein the program instructions to identify the visual key in the first image further comprise:

program instructions to, in response to determining that a score of the region does not exceed a second threshold score, based, at least in part, on how well the third image matches the visual key, capture a fourth image, wherein the fourth image is captured at a higher magnification than the third image and includes the region, and wherein the second threshold score is higher than the first threshold score; and

program instructions to, in response to determining that a score of the region exceeds a second threshold score, based, at least in part, on how well the third image matches the visual key, identify the region as the visual key, wherein the second threshold score is higher than the first threshold score.

18. The computer system of claim 17, wherein the visual key is a machine-readable pattern of geometric shapes.

19. The computer system of claim 18, wherein the machine-readable pattern of geometric shapes is a quick response code.

20. The computer system of claim 19, wherein the score of the region is based, at least in part, on a model of the visual key that accounts for an orientation of the visual key in at least one of yaw, pitch, and roll.