Automatic depth camera aiming

• US 9,008,355 B2
• Filed: 06/04/2010
• Issued: 04/14/2015
• Est. Priority Date: 06/04/2010
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: Markovic, Relja, Latta, Stephen, Lee, Kyungsuk David, Santos, Oscar Omar Garza, Geisner, Kevin
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): YANG, WEI WEN
• Application Number:
  US12/794,388
• Publication Number:
  US 20110299728A1
• Time in Patent Office: 1,775 Days
• Field of Search: 382/103, 382106-107, 382/172, 382/189
• US Class Current: 382/103
• CPC Class Codes: A63F 2300/1087 comprising photodetecting means, e.g. a camera
• CPC Class Codes: A63F 2300/8029 Fighting without shooting
• CPC Class Codes: G01S 3/786 the desired condition being maintained automatically
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: H04N 13/271 wherein the generated image signals comprise depth maps or disparity maps

Abstract

Automatic depth camera aiming is provided by a method which includes receiving from the depth camera one or more observed depth images of a scene. The method further includes, if a point of interest of a target is found within the scene, determining if the point of interest is within a far range relative to the depth camera. The method further includes, if the point of interest of the target is within the far range, operating the depth camera with a far logic, or if the point of interest of the target is not within the far range, operating the depth camera with a near logic.

Claims

1. A computing system, comprising:

a depth camera configured to capture depth information for targets in a field of view of the depth camera;

an aiming assembly configured to dynamically and repeatedly change the field of view of the depth camera by physically changing one or both of a pitch and a yaw of the depth camera to change an aiming vector of the depth camera while the depth camera images a scene;

a logic subsystem in operative communication with the depth camera and the aiming assembly; and

a data-holding subsystem holding instructions executable by the logic subsystem to;

receive from the depth camera one or more observed depth images including a plurality of pixels, each such pixel including a depth value indicating a distance to a surface in the scene imaged by that pixel;

instruct the aiming assembly to automatically change the field of view of the depth camera by physically changing one or both of the pitch and the yaw of the depth camera while the depth camera images the scene so that the aiming vector points with a first predetermined pitch to a predetermined default far focus if a target is within a far range; and

instruct the aiming assembly to automatically change the field of view of the depth camera by physically changing one or both of the pitch and the yaw of the depth camera while the depth camera images the scene so that the aiming vector points with a second predetermined pitch, different than the first predetermined pitch, to a predetermined default near focus, relatively closer to the depth camera than the predetermined default far focus, if the target is within a near range, relatively closer to the depth camera than the far range.

2. The computing system of claim 1, wherein the data-holding subsystem further holds instructions executable by the logic subsystem to instruct the aiming assembly to hold the depth camera so that the aiming vector does not move if a point of interest of the target is within the scene.

3. The computing system of claim 1, wherein the instructions instruct the aiming assembly to aim the depth camera so that the aiming vector points to the default far focus if the target is within the far range and a point of interest of the target is not within the scene at a current aiming vector, and wherein the instructions instruct the aiming assembly to hold the depth camera so that the aiming vector does not move if the point of interest of the target is within the scene at the current aiming vector.

4. The computing system of claim 1, wherein the instructions instruct the aiming assembly to aim the depth camera so that the aiming vector points to the predetermined default near focus if the target is within the near range and a point of interest of the target is not within the scene at a current aiming vector, and wherein the instructions instruct the aiming assembly to hold the depth camera so that the aiming vector does not move if the point of interest of the target is within the scene at the current aiming vector.

5. The computing system of claim 1, wherein the data-holding subsystem further holds instructions executable by the logic subsystem to instruct the aiming assembly to aim the depth camera so that the aiming vector points towards detected motion in the scene if a point of interest of the target is not within the scene.

6. The computing system of claim 1, wherein the data-holding subsystem further holds instructions executable by the logic subsystem to output a user message requesting the target to move from the near range to the far range if the target is within the near range.

7. The computing system of claim 1, wherein the data-holding subsystem further holds instructions executable by the logic subsystem to initialize a position of the depth camera.

8. The computing system of claim 7, wherein the position of the depth camera is initialized by finding a floor surface within the scene and calculating a height of the depth camera above the floor surface.

9. The computing system of claim 8, wherein the data-holding subsystem further holds instructions executable by the logic subsystem to calculate a position of the predetermined default far focus to be a predetermined distance above the floor surface at a predetermined distance away from the depth camera.

10. The computing system of claim 8, wherein the data-holding subsystem further holds instructions executable by the logic subsystem to calculate a position of the predetermined default near focus to be a predetermined distance above the floor surface at a predetermined distance away from the depth camera.

11. A method of automatically aiming a field of view of a depth camera at a point of interest, the method comprising:

receiving from the depth camera one or more observed depth images of a scene including a plurality of pixels, each such pixel including a depth value indicating a distance to a surface in the scene imaged by that pixel;

if a point of interest of a target is found within the scene while the depth camera images the scene with a first predetermined pitch having an aiming vector that points to a predetermined default far focus, determining if the point of interest is within a far range relative to a distance from the depth camera; and

if the point of interest of the target is within the far range, operating the depth camera with a far logic; and

if the point of interest of the target is not within the far range, automatically and dynamically adjusting the field of view of the depth camera relative to the scene by physically changing a pitch of the depth camera to a second predetermined pitch so that the aiming vector changes from pointing to the predetermined default far focus to pointing to a predetermined default near focus to image targets closer to the depth camera; and

operating the depth camera with a near logic.

12. The method of claim 11, wherein operating the depth camera with the far logic includes aiming the depth camera so that an aiming vector of the depth camera points to a default far focus if the point of interest of the target is not within the scene at a current aiming vector, and holding the depth camera so that the aiming vector does not move if the point of interest of the target is within the scene at the current aiming vector.

13. The method of claim 11, wherein operating the depth camera with the near logic includes aiming the depth camera so that an aiming vector of the depth camera points to a default near focus if the point of interest of the target is not within the scene at a current aiming vector, and holding the depth camera so that the aiming vector does not move if the point of interest of the target is within the scene at the current aiming vector.

14. The method of claim 11, wherein operating the depth camera with the far logic includes aiming the depth camera so that an aiming vector of the depth camera points towards detected motion in the scene if the point of interest of the target is not within the scene at a current aiming vector, and holding the depth camera so that the aiming vector does not move if the point of interest of the target is within the scene at the current aiming vector.

15. The method of claim 11, wherein operating the depth camera with the near logic includes aiming the depth camera so that an aiming vector of the depth camera points towards detected motion in the scene if the point of interest of the target is not within the scene at a current aiming vector, and holding the depth camera so that the aiming vector does not move if the point of interest of the target is within the scene at the current aiming vector.

16. The method of claim 11, further comprising initializing a position of the depth camera.

17. The method of claim 16, wherein initializing the position of the depth camera includes finding a floor surface within the scene and calculating a height of the depth camera above the floor surface.

18. The method of claim 17, further comprising calculating a position of a default far focus to be a predetermined distance above the floor surface at a predetermined distance away from the depth camera.

19. The method of claim 17, further comprising calculating a position of a default near focus to be a predetermined distance above the floor surface at a predetermined distance away from the depth camera.