Method and apparatus for producing an enhanced 3D model of an environment or an object

• US 8,031,933 B2
• Filed: 12/18/2009
• Issued: 10/04/2011
• Est. Priority Date: 02/11/2005
• Status: Active Grant

• Current Assignee: Macdonald Dettwiler and Associates Limited
• Original Assignee: Macdonald Dettwiler and Associates Limited
• Inventors: Jakola, Roy Henry, Se, Shuen Yan Stephen, Jasiobedzki, Piotr, Parry, David Owen
• Primary Examiner(s): Tucker; Wesley
• Assistant Examiner(s): WOLDEMARIAM, AKILILU K
• Application Number:
  US12/654,452
• Publication Number:
  US 20100098328A1
• Time in Patent Office: 655 Days
• Field of Search: 382/254, 382/260, 382/266, 382/284, 382/294
• US Class Current: 382/154
• CPC Class Codes: A61B 5/113 occurring during breathing
• CPC Class Codes: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G06T 17/00 Three dimensional [3D] modelling, e.g. data description of 3D objects
• CPC Class Codes: G06T 2200/08 involving all processing steps from image acquisition to 3D model generation
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 7/285 using a sequence of stereo image pairs
• CPC Class Codes: G06T 7/33 using feature-based methods
• CPC Class Codes: G06T 7/579 from motion
• CPC Class Codes: G06T 7/593 from stereo images

Abstract

The present invention provides a system (method and apparatus) for creating photorealistic 3D models of environments and/or objects from a plurality of stereo images obtained from a mobile stereo camera and optional monocular cameras. The cameras may be handheld, mounted on a mobile platform, manipulator or a positioning device. The system automatically detects and tracks features in image sequences and self-references the stereo camera in 6 degrees of freedom by matching the features to a database to track the camera motion, while building the database simultaneously. A motion estimate may be also provided from external sensors and fused with the motion computed from the images. Individual stereo pairs are processed to compute dense 3D data representing the scene and are transformed, using the estimated camera motion, into a common reference and fused together. The resulting 3D data is represented as point clouds, surfaces, or volumes. The present invention also provides a system (method and apparatus) for enhancing 3D models of environments or objects by registering information from additional sensors to improve model fidelity or to augment it with supplementary information by using a light pattern projector. The present invention also provides a system (method and apparatus) for generating photo-realistic 3D models of underground environments such as tunnels, mines, voids and caves, including automatic registration of the 3D models with pre-existing underground maps.

Claims

1. A method of producing an enhanced three-dimensional (3D) model of an environment or an object, comprising the steps of:

a) acquiring 3D information of an environment or an object from at least one range sensing device;

b) producing a 3D model of the environment or object from the acquired 3D information suitable for visualization, analysis or post-processing;

c) projecting a light pattern onto a region of interest of the environment or object;

d) acquiring data from an additional sensing device trained on the region of interest of the environment or object onto which the light pattern is projected, the additional sensing device being positioned independently of the at least one range sensing device;

e) registering the acquired data from the additional sensing device within the region of interest with the 3D information from the at least one range sensing device by detecting said light pattern observed by the additional sensing device and establishing correspondence between the data from the additional sensing device and the data from the at least one range sensing device; and

f) combining the data from the additional sensing device with the 3D model to give an enhanced 3D model.

2. The method according to claim 1 wherein said least one range sensing device is a stereo camera integrated with said light pattern projection means.

3. The method according to claim 2 wherein said stereo camera includes at least two individual image capture means where there is an overlap between stereo images captured by said at least two individual image capture means, and wherein step b) of producing a 3D model of the environment or object from the acquired 3D information includes computing dense 3D data sets, representative of the environment, from stereo images captured by said at least two individual image capture means by matching image intensity or color distributions between the stereo images.

4. The method according to claim 2 wherein said additional sensing device trained on the region of interest is a camera.

5. The method according to claim 4 wherein the projected light pattern comprises identification features allowing establishing correspondence between images captured by the stereo camera and the camera.

6. The method according to claim 1 further comprising sampling areas of the region of interest using a contact sensor configured to make measurements of the region of interest, and including registering measurements from the contact sensor with the 3D information from the at least one range sensing device and combining the data from the contact sensor with the 3D model to give an enhanced 3D model.

7. The method according to claim 6 wherein said contact sensor is any one of a chemical, biological and radiological sensor for determining chemical, biological and radiological compositions of the region of interest.

8. The method according to claim 1 wherein said at least one range sensing device is at least one stereo camera mounted for movement with respect to the environment or an object, and wherein the steps of acquiring 3D information of the environment or object from the at least one range sensing device and producing a 3D model of the environment from the acquired 3D information suitable for visualization, analysis or post-processing includes:

a) acquiring a plurality of overlapping successive stereo images of the environment or an object from said at least one stereo camera, moving with respect to said environment or object, the at least one stereo camera having at least two individual image capture means where there is an overlap between images captured by said at least two individual image capture means;

b) for each successive stereo image detecting features in the stereo images and computing a 3D position and descriptor for each detected feature, and storing said 3D position and said descriptor as a 3D feature in a database;

c) for each successive stereo image computing relative motion of the at least one stereo camera with respect to the environment or object by matching the detected features in the stereo images with said 3D features stored in the database using descriptors of said 3D features;

d) for each successive stereo image computing dense 3D data sets, representative of the environment or object, from said at least one range sensing device;

e) for each successive stereo image transforming the computed dense 3D data from step d) into a selected coordinate frame of reference using the computed relative motion from step c) to give transformed dense 3D data in the selected coordinate frame of reference; and

f) storing the transformed dense 3D data for each successive stereo image and producing a 3D model of the environment or object from the stored transformed dense 3D data.

22. The method according to claim 6 wherein said contact sensor is any one of an X-ray fluorescence (XRF) sensor and a Laser Induced Breakdown Spectroscopy (LIBS) sensor.

23. The method according to claim 1 wherein said additional sensing device is anyone of a chemical, biological and radiological sensor for determining chemical, biological and radiological compositions of the region of interest.

24. The method according to claim 1 wherein said additional sensing device is a monocular camera.

25. The method according to claim 1 wherein said additional sensing device is a stereo camera.

26. The method according to claim 1 wherein said additional sensing device is a camera operating in a visible or beyond visible spectrum for detailed imaging of the region of interest of the environment or object.

9. An apparatus for producing an enhanced three-dimensional (3D) model of an environment or an object, comprising the steps of:

a) at least one range sensing device for acquiring 3D information of an environment or an object;

b) processing means for producing a 3D model of the environment or object from the acquired 3D information suitable for visualization, analysis or post-processing;

c) light pattern projection means for projecting a pattern of light onto a region of interest of the environment or object;

d) an additional sensing device trained on the region of interest for acquiring data from the region of interest onto which the light pattern is projected, said additional sensing device being positioned independent of said at least one range sensing device; and

e) processing means configured for registering the acquired data from the additional sensing device trained on the region of interest containing the projected light pattern with the 3D information from the range sensing device by detecting the light pattern observed by the additional sensing device and establishing correspondence between the data from the additional sensing device and the data from the at least one range sensing device, the processing means being configured for combining the data from the additional sensing device with the 3D model to give an enhanced 3D model.

10. The apparatus according to claim 9 wherein said at least one range sensing device is a stereo camera integrated with said light pattern projection means.

11. The apparatus according to claim 10 wherein said stereo camera integrated with said light pattern projection means are mounted on a pan and tilt unit.

12. The apparatus according to claim 11 wherein pan and tilt unit is mounted on any one of a stationary tripod and a mobile platform.

13. The apparatus according to claim 10 wherein said stereo camera integrated with said light pattern projection means are a hand-held device.

14. The apparatus according to claim 9 including further comprising a contact sensor configured to sample the region of interest of the environment or object, and wherein said processing means is configured to register measurements from the contact sensor with the 3D information from the at least one range sensing device and combining the data from the contact sensor with the 3D model to give an enhanced 3D model.

15. The apparatus according to claim 14 wherein said contact sensor is any one of a chemical, biological and radiological sensor for determining chemical, biological and radiological compositions of the region of interest.

16. The apparatus according to claim 9 wherein said processing means is configured for:

a) acquiring a plurality of overlapping successive stereo images of the environment or an object from said at least one stereo camera, moving with respect to said environment or an object, the at least one stereo camera having at least two individual image capture means where there is an overlap between images captured by said at least two individual image capture means;

b) for each successive stereo image detecting features in the stereo images and computing a 3D position and descriptor for each detected feature, and storing said 3D position and said descriptor as a 3D feature in a database;

c) for each successive stereo image computing relative motion of the at least one stereo camera with respect to the environment or object by matching the detected features in the stereo images with said 3D features stored in the database using descriptors of said 3D features;

d) for each successive stereo image computing dense 3D data sets, representative of the environment or object, from said at least one range sensing device;

e) for each successive stereo image transforming the computed dense 3D data from step d) into a selected coordinate frame of reference using the computed relative motion from step c) to give transformed dense 3D data in the selected coordinate frame of reference; and

f) storing the transformed dense 3D data for each successive stereo image and producing a 3D model of the environment or object from the stored transformed dense 3D data.

17. The apparatus according to claim 9 wherein said additional sensing device is a camera operating in a visible or beyond visible spectrum for detailed imaging of the region of interest of the environment or object.

18. The apparatus according to claim 9 wherein said additional sensing device is a monocular camera.

19. The apparatus according to claim 9 wherein said additional sensing device is a stereo camera.

20. The apparatus according to claim 14 wherein said contact sensor is any one of an X-ray fluorescence (XRF) sensor and a Laser Induced Breakdown Spectroscopy (LIBS) sensor.

21. The apparatus according to claim 9 wherein said additional sensing device is anyone of a chemical, biological and radiological sensor for determining chemical, biological and radiological compositions of the region of interest.