Systems and methods of constructing three-dimensional (3D) model of an object using image cross-sections

• US 9,436,998 B2
• Filed: 05/12/2015
• Issued: 09/06/2016
• Est. Priority Date: 01/17/2012
• Status: Active Grant

• Current Assignee: Lmi Liquidating Co., LLC
• Original Assignee: Leap Motion Incorporated (Ultraleap Limited)
• Inventors: Holz, David S.
• Primary Examiner(s): Fitzpatrick, Atiba O
• Application Number:
  US14/710,512
• Publication Number:
  US 20150243039A1
• Time in Patent Office: 483 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G02B 2027/0138 comprising image capture systems, e.g. camera
• CPC Class Codes: G02B 2027/0141 characterised by the informative content of the display
• CPC Class Codes: G02B 2027/0187 slaved to motion of at least a part of the body of the user, e.g. head, eye
• CPC Class Codes: G02B 27/0172 characterised by optical features
• CPC Class Codes: G06F 3/005 Input arrangements through a video camera
• CPC Class Codes: G06F 3/011 Arrangements for interaction with the human body, e.g. for user immersion in virtual reality blind teaching G09B21/00
• 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 3/0346 with detection of the device orientation or free movement in a 3D space, e.g. 3D mice, 6-DOF [six degrees of freedom] pointers using gyroscopes, accelerometers or tilt-sensors
• CPC Class Codes: G06T 15/04 Texture mapping
• CPC Class Codes: G06T 15/205 Image-based rendering
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 19/006 Mixed reality object pose determination, tracking or camera calibration for mixed reality G06T7/00
• CPC Class Codes: G06T 2200/04 involving 3D image data
• CPC Class Codes: G06T 2200/08 involving all processing steps from image acquisition to 3D model generation
• CPC Class Codes: G06T 2207/10012 Stereo images
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 7/292 Multi-camera tracking
• CPC Class Codes: G06T 7/344 involving models
• CPC Class Codes: G06T 7/586 from multiple light sources, e.g. photometric stereo
• CPC Class Codes: G06T 7/593 : from stereo images
• CPC Class Codes: G06T 7/60 : Analysis of geometric attributes
• CPC Class Codes: G06T 7/70 : Determining position or orientation of objects or cameras camera calibration G06T7/80
• CPC Class Codes: G06T 7/75 : involving models
• CPC Class Codes: G06V 10/25 : Determination of region of interest [ROI] or a volume of interest [VOI]
• CPC Class Codes: G06V 20/64 : Three-dimensional objects
• CPC Class Codes: G06V 40/107 : Static hand or arm
• CPC Class Codes: G06V 40/11 : Hand-related biometrics; Hand pose recognition
• CPC Class Codes: G06V 40/117 : Biometrics derived from 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 13/207 : using a single 2D image sensor
• CPC Class Codes: H04N 7/183 : for receiving images from a single remote source

Abstract

Methods and systems for capturing motion and/or determining the shapes and positions of one or more objects in 3D space utilize cross-sections thereof. In various embodiments, images of the cross-sections are captured using a camera based on edge points thereof.

Claims

1. A method of identifying a position and shape of at least a portion of an object or object portion in three-dimensional (3D) space, the method comprising:

capturing, with a plurality of cameras, each camera having a particular vantage point, two or more images generated by casting an output from at least one source onto a portion of an object;

analyzing the two or more images captured by the cameras from the particular vantage points to computationally represent the object portion, as captured, as one or more mathematically represented three-dimensional (3D) surfaces, each 3D surface corresponding to a cross-section of the object portion, based at least in part on a plurality of edge points of the object portion in the image, tangent lines extending from the cameras to at least two of the plurality of edge points and a centerline corresponding to the tangent lines; and

reconstructing the position of and a shape fitting at least a portion of the object portion in 3D space based at least in part on the plurality of edge points and the centerline.

2. The method of claim 1, further comprising analyzing the one or more surfaces to produce a 3D model.

3. The method of claim 1, further comprising refining a 3D model by correlating a cross-section of an object portion represented by a first surface with a cross-section of at least one different object portion represented by at least one different 3D surface.

4. The method of claim 1, further comprising refining a 3D model based on at least one of an object type of an object comprising the object portion and characteristics of the object type.

5. The method of claim 1, further comprising refining a 3D model by informing results of the analyzing with results of such analyzing as conducted on images obtained at a different time and correspondingly modifying the model.

6. The method of claim 1, further comprising refining a position of an object portion based upon informing results of the analyzing with results of such analyzing as conducted on images obtained at a different time.

7. The method of claim 1, further comprising determining constraints on at least one of a number and position of one or more object portions according an object type.

8. The method of claim 1, further comprising resolving an at least partially occluded object portion by conducting spatial correlations across surfaces.

9. The method of claim 1, further comprising capturing one or more additional image sets of two or more images;

and resolving an at least partially occluded object portion by conducting temporal correlations across image sets.

10. The method of claim 1, further comprising resolving an at least partially occluded object portion by applying physical constraints of an object type.

11. The method of claim 1, further comprising refining a 3D model formed by the reconstructing.

12. The method of claim 11, wherein the model represents a generic hand, the refining further comprising texture mapping details from image capture onto a generic hand model.

13. The method of claim 11, further comprising morphing the model according to detected object orientation and motion.

14. The method of claim 11, wherein the refining includes refining a 3D model based at least in part upon one of continuity in motion and continuity in deformation.

15. The method of claim 1, further comprising refining a 3D model formed by the reconstructing by comparing a reconstructed model of the object portion to object types in a library of object types and characteristic parameters for objects in one or more possible poses;

and assigning matching object types to the model when a match based on characteristic parameters is found.

16. The method of claim 15, wherein the object type includes a hand, the pose includes fingers extended and palm facing the cameras, and the characteristic parameters include five fingers.

17. The method of claim 15, wherein refining the model further comprises applying a constraint to the model based on characteristics of the object type.

18. The method of claim 17, wherein the object type includes a hand, and the constraint includes positions and angles of fingers relative to each other and to a palm portion of a hand.

19. A head mounted device, comprising:

an optical assembly to display a displayed environment including at least one of a surrounding environment and a virtual environment, the surrounding environment including at least a portion of an object or object portion; and

a motion-capture system facilitating interactive control of the displayed environment, the system including;

a plurality of cameras, each camera having a particular vantage point, to capture two or more images of the object portion;

at least one source to direct illumination onto the object portion; and

an image analyzer coupled to the cameras and the at least one source and configured to;

analyze the two or more images captured by the cameras from the particular vantage points to computationally represent the object portion, as captured, as one or more mathematically represented 3 dimensional (3D) surfaces, each 3D surface corresponding to a cross-section of the object portion, based at least in part on a plurality of edge points of the object portion in the image, tangent lines extending from the cameras to at least two of the plurality of edge points and a centerline corresponding to the tangent lines; and

reconstruct a position of and a shape fitting at least a portion of the object portion in 3D space based at least in part on the plurality of edge points and the centerline.

20. The head mounted device of claim 19, wherein the motion-capture system further comprises a time-of-flight camera, and wherein a plurality of points on at least one object surface are determined from time-of-flight data.

21. The head mounted device of claim 20, wherein the motion-capture system further combines time-of-flight data with tangent-line information to provide a more detailed model of an object'"'"'s shape.

22. The head mounted device of claim 19, wherein the virtual environment comprises one or more virtual objects manipulable using hand gestures tracked by the motion-capture system.

23. The head mounted device of claim 19, wherein the object portion comprises at least a portion of a hand;

and wherein the motion-capture system detects a position and shape of the hand.

24. The head mounted device of claim 23, wherein the optical assembly projects gestures made by the hand into the displayed environment enabling interactive control of objects in the displayed environment.

25. The head mounted device of claim 24, wherein the displayed environment comprises at least one selected from a gaming application and an internet browsing application.