Computer vision collision avoidance in drilling operations

Patent metadata

Field	Value
Publication number	US-9396398-B2
Application number	US-201414284196-A
Country	US
Kind code	B2
Filing date	May 21, 2014
Priority date	May 21, 2013
Publication date	Jul 19, 2016
Grant date	Jul 19, 2016

Abstract

A system and method for automatically preventing a collision between objects is described. One or more images of a working space may be collected, and a first object may be identified based on the one or more images. Three-dimensional coordinates of the first object may be determined, and a virtual boundary enclosing the identified first object in a three-dimensional coordinate system may be generated based on the three-dimensional coordinates of the first object, wherein the virtual boundary specifies a volume in the working space that a second object in the working space should not occupy. The coordinates in the three-dimensional coordinate system corresponding to the generated virtual boundary may be transmitted to a second processor, and the second processor may control the second object to perform an operation in the working space that includes the first object without contacting the virtual boundary of the first object.

First claim

What is claimed is:

1. A method for automatically preventing a collision between objects, comprising:
(a) collecting, with one or more image capturing devices, one or more images of a working space;
(b) identifying, with a first processor, a first object based, at least in part, on the one or more images;
(c) determining, with the first processor, coordinates of the first object based, at least in part, on the one or more images, wherein determining comprises determining coordinates of the first object based on a two-dimensional coordinate system associated with the one or more images and transforming the coordinates of the first object from coordinates in a two-dimensional coordinate system associated with the one or more images to a three-dimensional coordinate system, wherein the step of transforming the coordinates is based at least in part on a projection matrix associated with the one or more image capturing devices and a calibration matrix associated with the one or more image capturing devices;
(d) generating, with the first processor, a virtual boundary enclosing the identified first object in the three-dimensional coordinate system based, at least in part, on the determined coordinates of the first object, wherein the virtual boundary specifies a volume in the working space that a second object in the working space should not occupy; and
(e) transmitting, with the first processor, to a second processor, coordinates in the three-dimensional coordinate system corresponding to the generated virtual boundary, wherein the second processor controls the second object to perform an operation in the working space that includes the first object without contacting the virtual boundary of the first object.

2. The method of claim 1 , wherein at least one of the first and second objects is a moving object in the working space and steps (a)-(e) are automatically repeated one or more times.

3. The method of claim 1 , wherein each of the first and second objects is one of a human and a tool.

4. The method of claim 1 , wherein an image capturing device comprises at least one of a still image capturing device and a video image capturing device.

5. The method of claim 1 , wherein the working space comprises a drill floor with a plurality of humans and/or tools located in the working space.

6. The method of claim 1 , wherein the first object is a human and the method further comprises identifying, with the first processor, a unique identity of the human based, at least in part, on the one or more images.

7. The method of claim 6 , wherein identifying the unique identity of the human comprises comparing, with the first processor, the one or more images of the identified human with a plurality of stored images of humans until features corresponding to the identified human match features of a human in one of the plurality of images of humans.

8. The method of claim 7 , further comprising determining, with the first processor, whether the human is authorized to be in the working space.

9. The method of claim 1 , wherein the first processor is also the second processor.

10. A system for automatically preventing a collision between objects, comprising: one or more image capturing devices configured to collect one or more images of a working space; and a first processor configured to receive the one or more images and to perform the steps of:
(a) identifying a first object based, at least in part, on the one or more images;
(b) determining coordinates of the first object based, at least in part, on the one or more images, wherein determining comprises determining coordinates of the first object based on a two-dimensional coordinate system associated with the one or more images and transforming the coordinates of the first object from coordinates in a two-dimensional coordinate system associated with the one or more images to a three-dimensional coordinate system, wherein the step of transforming the coordinates is based at least in part on a projection matrix associated with the one or more image capturing devices and a calibration matrix associated with the one or more image capturing devices;
(c) generating a virtual boundary enclosing the identified first object in the three-dimensional coordinate system based, at least in part, on the determined coordinates of the first object, wherein the virtual boundary specifies a volume in the working space that a second object in the working space should not occupy; and
(d) transmitting, to a second processor, coordinates in the three-dimensional coordinate system corresponding to the generated virtual boundary, wherein the second processor is configured to control the second object to perform an operation in the working space that includes the first object without contacting the virtual boundary of the first object.

11. The system of claim 10 , wherein at least one of the first and second objects is a moving object in the working space, the one or more image capturing devices are further configured to automatically repeat one or more times the collecting of one or more images, the first processor is further configured to automatically repeat steps (a)-(c) one or more times, and the second processor is further configured to automatically repeat step (d) one or more times.

12. The system of claim 10 , wherein each of the first and second objects is one of a human and a tool.

13. The system of claim 10 , wherein an image capturing device comprises at least one of a still image capturing device and a video image capturing device.

14. The system of claim 10 , wherein the working space comprises a drill floor with a plurality of humans and/or tools located in the working space.

15. The system of claim 10 , wherein the first object is a human and the first processor is further configured to perform the step of identifying a unique identity of the human based, at least in part, on the one or more images.

16. The system of claim 15 , wherein the first processor is further configured to perform the step of comparing the one or more images of the identified human with a plurality of stored images of humans until features corresponding to the identified human match features of a human in one of the plurality of images of humans.

17. The system of claim 16 , wherein the first processor is further configured to perform the step of determining whether the human is authorized to be in the working space.

18. The system of claim 10 , wherein the first processor is also the second processor.

Assignees

• Transocean Sedco Forex Ventures Ltd
• Transocean Secco Forex Ventures Ltd

Inventors

• Kozicz John
• Martin Trenton

Classifications

• G06V20/52

  Surveillance or monitoring of activities, e.g. for recognising suspicious objects (recognising microscopic objects G06V20/69) · CPC title

• G06T19/00 Primary

  Manipulating three-dimensional [3D] models or images for computer graphics · CPC title

• F16P3/142

  using image capturing devices · CPC title

• E21B19/00

  Handling rods, casings, tubes or the like outside the borehole, e.g. in the derrick; Apparatus for feeding the rods or cables · CPC title

• G06T2210/21

  Collision detection, intersection · CPC title