3D SILHOUETTE SENSING SYSTEM

• US 20170285763A1
• Filed: 06/14/2017
• Published: 10/05/2017
• Est. Priority Date: 01/14/2014
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Inventors: KIM, David, IZADI, Shahram, PRADEEP, Vivek, BATHICHE, Steven, LARGE, Timothy Andrew, POWELL, Karlton David
• Granted Patent: US 10,001,845 B2
• Time in Patent Office: Days
• CPC Class Codes: G01B 11/24 for measuring contours or curvatures
• 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 3/0325 using a plurality of light emitters or reflectors or a plurality of detectors forming a reference frame from which to derive the orientation of the object, e.g. by triangulation or on the basis of reference deformation in the picked up image
• CPC Class Codes: G06F 3/0416 Control or interface arrangements specially adapted for digitisers
• CPC Class Codes: G06F 3/0421 by interrupting or reflecting a light beam, e.g. optical touch-screen
• CPC Class Codes: G06F 3/0425 using a single imaging device like a video camera for tracking the absolute position of a single or a plurality of objects with respect to an imaged reference surface, e.g. video camera imaging a display or a projection screen, a table or a wall surface, on which a computer generated image is displayed or projected tracking a projected light spot to determine a position on a display surface G06F3/0386
• CPC Class Codes: G06V 10/145 Illumination specially adapted for pattern recognition, e.g. using gratings
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• CPC Class Codes: G06V 40/10 Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
• CPC Class Codes: G06V 40/28 Recognition of hand or arm movements, e.g. recognition of deaf sign language static hand signs G06V40/113
• CPC Class Codes: H04N 13/204 using stereoscopic image cameras stereoscopic photography G03B35/00
• CPC Class Codes: H04N 5/33 Transforming infrared radiation cameras or camera modules for generating image signals from infrared radiation H04N23/20; circuitry of SSIS for transforming infrared radiation into image signals H04N25/20

Abstract

A 3D silhouette sensing system is described which comprises a stereo camera and a light source. In an embodiment, a 3D sensing module triggers the capture of pairs of images by the stereo camera at the same time that the light source illuminates the scene. A series of pairs of images may be captured at a predefined frame rate. Each pair of images is then analyzed to track both a retroreflector in the scene, which can be moved relative to the stereo camera, and an object which is between the retroreflector and the stereo camera and therefore partially occludes the retroreflector. In processing the image pairs, silhouettes are extracted for each of the retroreflector and the object and these are used to generate a 3D contour for each of the retroreflector and object.

Claims

1. A 3D sensing system comprising:

a stereo camera comprising a single RGB camera and an optical arrangement, wherein the RGB camera is arranged to capture two images at different wavelengths of visible light via the optical arrangement and store a combination of the two captured images as a single RGB image;

a light source; and

a 3D sensing module arranged to track a retroreflector during a time that an object partially occluding the retroreflector is tracked by the 3D sensing module using the two captured images, and to detect a touch event or determine a pressure value based at least in part on a depression of the retroreflector.

2. The system of claim 1, wherein the retroreflector is movable relative to the stereo camera.

3. The system of claim 2, wherein the retroreflector is transparent at visible wavelengths of light.

4. The system of claim 2, wherein the retroreflector comprises a user interface layout formed on an upper surface of the retroreflector, wherein the user interface layout is transparent at a wavelength range over which the retroreflector retroreflects.

5. The system of claim 1, wherein the light source comprises one or more light emitting diodes (LEDs).

6. The system of claim 1, wherein the 3D sensing module is at least partially implemented using hardware logic selected from any one or more of:

a field-programmable gate array, a program-specific integrated circuit, a program-specific standard product, a system-on-a-chip, a complex programmable logic device.

7. A method of 3D sensing comprising:

capturing, from a single RBG camera, a stereo camera to capture a pair of images of a scene at different wavelengths of visible light during a time that the scene is illuminated by a light source;

storing a combination of the two captured images as a single RGB image;

tracking a retroreflector during a time that an object partially occluding the retroreflector is tracked using the two captured images; and

detecting a touch event based at least in part on a depression of the retroreflector.

8. A method according to claim 7, further comprising repeating the method to capture pairs of images at a pre-defined frame rate and wherein the tracking is performed on a frame by frame basis in real time.

9. The method according to claim 7, wherein the retroreflector is transparent at visible wavelengths of light.

10. The method according to claim 7, further comprising:

computing a 3D depth contour for the retroreflector; and

computing a 3D depth contour for the object.

11. The method according to claim 10, further comprising classifying at least one of the retroreflector and the object by applying machine learning techniques to the 3D depth contour.

12. The method according to claim 11, further comprising generating an input signal for a software program based on a classification of at least the retroreflector.

13. The method according to claim 12, wherein the input signal is generated based on a classification of at least the retroreflector and a relative position of the retroreflector and the object.

14. The method according to claim 7, further comprising:

removing distortion from each image in the image pair;

rectifying each image in the image pair; and

identifying parts of each image to not consider parts of the scene not contained in the other image in the image pair in the tracking.

15. One or more computer-readable storage media comprising computer-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

capturing, from a single RBG camera, a stereo camera to capture a pair of images of a scene at different wavelengths of visible light during a time that the scene is illuminated by a light source;

storing a combination of the two captured images as a single RGB image;

tracking a retroreflector during a time that an object partially occluding the retroreflector is tracked using the two captured images; and

detecting a touch event based at least in part on a depression of the retroreflector.

16. The one or more computer-readable storage media of claim 15, wherein the computer-executable instructions further cause the one or more processors to repeat the operations to capture pairs of images at a pre-defined frame rate and wherein the tracking is performed on a frame by frame basis in real time.

17. The one or more computer-readable storage media of claim 15, wherein the retroreflector is transparent at visible wavelengths of light.

18. The one or more computer-readable storage media of claim 15, wherein the computer-executable instructions further cause the one or more processors to perform operations comprising:

computing a 3D depth contour for the retroreflector;

computing a 3D depth contour for the object; and

classifying at least one of the retroreflector and the object by applying machine learning techniques to the 3D depth contour.

19. The one or more computer-readable storage media of claim 18, wherein the computer-executable instructions further cause the one or more processors to perform operations comprising generating an input signal for a software program based on a classification of at least the retroreflector.

20. The one or more computer-readable storage media of claim 19, wherein the input signal is generated based on a classification of at least the retroreflector and a relative position of the retroreflector and the object.