INFORMATION PROCESSING APPARATUS, METHOD OF CONTROLLING INFORMATION PROCESSING APPARATUS, AND STORAGE MEDIUM

• US 20170256046A1
• Filed: 02/27/2017
• Published: 09/07/2017
• Est. Priority Date: 03/02/2016
• Status: Active Grant

• Current Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Original Assignee: Canon Kabushiki Kaisha (Canon Inc.)
• Inventors: Watanabe, Daisuke
• Granted Patent: US 10,252,417 B2
• Time in Patent Office: Days
• CPC Class Codes: B25J 9/1612 characterised by the hand, wrist, grip control
• CPC Class Codes: B25J 9/1687 Assembly, peg and hole, palletising, straight line, weaving pattern movement
• CPC Class Codes: G06F 18/22 Matching criteria, e.g. proximity measures
• CPC Class Codes: G06T 2207/30164 Workpiece; Machine component
• CPC Class Codes: G06T 7/75 involving models
• CPC Class Codes: G06V 10/42 Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
• CPC Class Codes: G06V 10/467 Encoded features or binary features, e.g. local binary patterns [LBP]
• CPC Class Codes: G06V 10/761 Proximity, similarity or dissimilarity measures

Abstract

An information processing apparatus, comprises an obtainment unit configured to obtain a relative position and orientation between a first object and a second object; an specifying unit configured to specify an occlusion region where the second object occludes the first object, from an image that includes the first object and the second object, based on the relative position and orientation, a first shape model that represents a shape of the first object, and a second shape model that represents a shape of the second object; and a generation unit configured to generate information for obtaining a position and orientation of the first object based on the occlusion region.

Claims

1. An information processing apparatus, comprising:

an obtainment unit configured to obtain a relative position and orientation between a first object and a second object;

an specifying unit configured to specify an occlusion region where the second object occludes the first object, from an image that includes the first object and the second object, based on the relative position and orientation, a first shape model that represents a shape of the first object, and a second shape model that represents a shape of the second object; and

a generation unit configured to generate information for obtaining a position and orientation of the first object based on the occlusion region.

2. The information processing apparatus according to claim 1, further comprising a model obtainment unit configured to obtain each of the first shape model and the second shape model.

3. The information processing apparatus according to claim 1, further comprising a position and orientation obtainment unit configured to obtain the position and orientation of the first object based on the information generated by the generation unit.

4. The information processing apparatus according to claim 1, wherein the generation unit generates the information by selecting from the first shape model a portion to use based on the occlusion region.

5. The information processing apparatus according to claim 4, further comprising a position and orientation obtainment unit configured to obtain the position and orientation of the first object based on the information generated by the generation unit, wherein

the generation unit generates, as the information, model features other than model features of the first shape model that correspond to the specified occlusion region in the image, and

the position and orientation obtainment unit obtains the position and orientation of the first object by associating the model features generated as the information with image features in the image.

6. The information processing apparatus according to claim 1, wherein the generation unit generates the information by selecting from the image a portion to use based on the occlusion region.

7. The information processing apparatus according to claim 6, further comprising a position and orientation obtainment unit configured to obtain the position and orientation of the first object based on the information generated by the generation unit, wherein

the generation unit generates, as the information, image features other than image features included in the specified occlusion region in the image, and

the position and orientation obtainment unit obtains the position and orientation of the first object by associating the image features generated as the information with the first shape model.

8. The information processing apparatus according to claim 1, wherein

the generation unit

calculates, with respect to the occlusion region, an occlusion degree that represents a degree at which the second object occludes the first object,

sets a level of contribution when obtaining the position and orientation of the first object, based on the occlusion degree, and

generates the information using the level of contribution.

9. The information processing apparatus according to claim 1, wherein information for obtaining the position and orientation of the first object is a geometric feature of the image.

10. The information processing apparatus according to claim 1, wherein the specifying unit specifies the occlusion region based on a first relative position and orientation between the first object and the second object that is stored in advance, and an approximate position and orientation of the first object.

11. The information processing apparatus according to claim 1, wherein the specifying unit specifies the occlusion region by generating an image indicating a region in the image occupied by the second object, based on an approximate position and orientation of the second object and the second shape model of the second object.

12. The information processing apparatus according to claim 10, wherein the specifying unit specifies the occlusion region based on a result of rendering model information of the first object based on the approximate position and orientation of the first object, and a result of rendering the second object based on an approximate position and orientation of the second object that is obtained based on the first relative position and orientation.

13. The information processing apparatus according to claim 1, further comprising a second position and orientation obtainment unit configured to obtain a position and orientation of the second object based on the occlusion region and model information of the second object.

14. The information processing apparatus according to claim 13, further comprising an estimation unit configured to estimate a first relative position and orientation between the first object and the second object, based on the position and orientation of the first object and the position and orientation of the second object, and

a determination unit configured to determine an assembly state based on the estimated first relative position and orientation.

15. The information processing apparatus according to claim 14, wherein the determination unit determines the assembly state based on a difference between the first relative position and orientation and a second relative position and orientation between the first object and the second object that is stored in advance.

16. A method of controlling an information processing apparatus, comprising:

obtaining a relative position and orientation between a first object and a second object;

specifying an occlusion region where the second object occludes the first object, from an image that includes the first object and the second object, based on the relative position and orientation, a first shape model that represents a shape of the first object, and a second shape model that represents a shape of the second object; and

generating information for obtaining a position and orientation of the first object based on the occlusion region.

17. A non-transitory computer-readable storage medium storing a computer program for causing a computer to execute:

obtaining a relative position and orientation between a first object and a second object;

specifying an occlusion region where the second object occludes the first object, from an image that includes the first object and the second object, based on the relative position and orientation, a first shape model that represents a shape of the first object, and a second shape model that represents a shape of the second object; and

generating information for obtaining a position and orientation of the first object based on the occlusion region.