Moving body position estimating device, moving body position estimating method, and non-transitory recording medium

• US 9,684,823 B2
• Filed: 09/14/2015
• Issued: 06/20/2017
• Est. Priority Date: 09/16/2014
• Status: Active Grant

• Current Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Original Assignee: Kabushiki Kaisha Toshiba (Toshiba Corporation)
• Inventors: Takatani, Tsuyoshi
• Primary Examiner(s): Bella, Matthew
• Assistant Examiner(s): SHIN, SOO JUNG
• Application Number:
  US14/853,159
• Publication Number:
  US 20160078288A1
• Time in Patent Office: 645 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/30196 Human being; Person
• CPC Class Codes: G06T 2207/30241 Trajectory
• CPC Class Codes: G06T 2207/30244 Camera pose
• CPC Class Codes: G06T 7/246 using feature-based methods, e.g. the tracking of corners or segments
• CPC Class Codes: G06T 7/73 using feature-based methods
• CPC Class Codes: G06V 2201/12 Acquisition of 3D measurements of objects
• CPC Class Codes: G06V 40/25 Recognition of walking or running movements, e.g. gait recognition

Abstract

A moving body position estimating device includes an acquisition unit and a processor. The acquisition unit acquires information including first data relating to a first image and second data relating to a second image including a difference between the first image and the second image accompanying a movement of a moving body. The processor implements estimating, based on the information, a direction of a rotation accompanying the movement; detecting, based on the direction of the rotation, first feature points inside a first region inside the first image and second feature points inside a second region inside the first image; and determining first corresponding points inside a third region inside the second image and estimating a change of a position of the moving body based on each of the first feature points and each of the first corresponding points.

Claims

1. A moving body position estimating device, comprising:

a memory; and

processing circuitry configured to;

acquire information including first data and second data, the first data relating to a first image, the second data relating to a second image, the second image including a difference from the first image accompanying a movement of a moving body, the first image including a first region and a second region;

estimate, based on the information, a direction of a rotation accompanying the movement; and

detect, based on the direction of the rotation, a plurality of first feature points inside the first region and a plurality of second feature points inside the second region, a first density of the first feature points inside the first region being higher than a second density of the second feature points inside the second region, wherein

the direction of the rotation is a first direction, and

a second direction from the second region toward the first region has a component in a reverse direction of the first direction.

2. The device according to claim 1, wherein

the processing circuitry is further configured to determine a plurality of first corresponding points inside a third region inside the second image and estimate a change of a position of the moving body based on each of the plurality of first feature points and each of the plurality of first corresponding points, and

each of the plurality of first corresponding points corresponds respectively to at least one of the plurality of first feature points.

3. The device according to claim 2, wherein a direction from the first region toward the third region is aligned with the second direction when the first image and the second image are overlaid.

4. The device according to claim 2, wherein

the second image further includes a fourth region corresponding to the second region, and

the estimating of the change of the position includes determining a plurality of second corresponding points inside the fourth region and estimating the change of the position of the moving body based on each of the plurality of second feature points and each of the plurality of second corresponding points, each of the plurality of second corresponding points corresponding respectively to at least one of the plurality of second feature points.

5. The device according to claim 1, wherein the first direction is one of a left direction and a right direction, and the second direction is the other of the left direction and the right direction.

6. The device according to claim 1, wherein the first direction is one of an upward direction and a downward direction, and the second direction is the other of the upward direction and the downward direction.

7. The device according to claim 1, wherein

the second region includes a center of the first image when an angle of the rotation is not more than a determined value;

and

the first region is provided around the second region inside the first image when the angle of the rotation is not more than the determined value.

8. The device according to claim 1, wherein the processing circuitry is further configured to, prior to the detecting, perform image subdivision processing to determine a position inside the first image of the first region and a position inside the first image of the second region.

9. The device according to claim 1, wherein the estimating of the direction of the rotation is based on the first image and the second image.

10. The device according to claim 1, wherein

the information further includes information relating to an angular velocity obtained by a sensor mounted to the moving body, and

the estimating of the direction of the rotation is based on the information relating to the angular velocity.

11. The device according to claim 1, wherein

the information further includes information relating to an angular acceleration output by a sensor mounted to the moving body, and

the estimating of the direction of rotation includes estimating the direction of the rotation based on the information relating to the angular acceleration.

12. The device according to claim 1, wherein the first image and the second image are imaged by an imaging unit mounted to the moving body.

13. A moving body position estimating device, comprising:

a memory; and

processing circuitry configured to;

acquire information including first data and second data, the first data relating to a first image, the second data relating to a second image, the second image including a difference from the first image accompanying a movement of a moving body;

estimate, based on the information, a direction of a change of a position of the moving body accompanying the movement; and

detect, based on the direction of the change of the position, a plurality of first feature points inside a first region inside the first image and a plurality of second feature points inside a second region inside the first image, a first density of the first feature points inside the first region being higher than a second density of the second feature points inside the second region.

14. The device according to claim 13, wherein

the direction of the change of the position is a frontward/rearward direction of the moving body,

the second region includes a center of the first image, and

the first region is provided around the second region inside the first image.

15. The device according to claim 14, wherein

the processing circuitry is further configured to determine a plurality of first corresponding points inside a third region inside the second image and estimate the change of the position of the moving body based on each of the plurality of first feature points and each of the plurality of first corresponding points,

each of the plurality of first corresponding points corresponds respectively to at least one of the plurality of first feature points, and

the first region and the third region overlap when the first image and the second image are overlaid.

16. The device according to claim 13, wherein the estimating of the direction of the change of the position is based on the first image and the second image.

17. The device according to claim 13, wherein

the information further includes information relating to a velocity obtained by a sensor mounted to the moving body, and

the estimating of the direction of the change of the position is based on the information relating to the velocity.

18. The device according to claim 13, wherein

the information further includes information relating to an acceleration obtained by a sensor mounted to the moving body, and

the estimating of the direction of the change of the position is based on the information relating to the acceleration.

19. A moving body position estimating method, comprising:

acquiring information including first data and second data, the first data relating to a first image, the second data relating to a second image, the second image including a difference from the first image accompanying a movement of a moving body;

estimating, based on the information, a direction of a rotation accompanying the movement; and

detecting, based on the direction of the rotation, a plurality of first feature points inside a first region inside the first image and a plurality of second feature points inside a second region inside the first image, a first density of the first feature points inside the first region being higher than a second density of the second feature points inside the second region.

20. A non-transitory recording medium storing a moving body position estimating program which, when executed, causes a computer to execute:

acquiring information including first data and second data, the first data relating to a first image, the second data relating to a second image, the second image including a difference from the first image accompanying a movement of a moving body;

estimating, based on the information, a direction of a rotation accompanying the movement; and

detecting, based on the direction of the rotation, a plurality of first feature points inside a first region inside the first image and a plurality of second feature points inside a second region inside the first image, a first density of the first feature points inside the first region being higher than a second density of the second feature points inside the second region.