Movement distance estimating device and movement distance estimating method

Patent metadata

Field	Value
Publication number	US-9311757-B2
Application number	US-201414186491-A
Country	US
Kind code	B2
Filing date	Feb 21, 2014
Priority date	Mar 28, 2013
Publication date	Apr 12, 2016
Grant date	Apr 12, 2016

Abstract

A movement distance estimating device includes: a memory; and a processor coupled to the memory and configured to: determine, based on a first image and a second image included in images captured by an image capture device mounted on a moving body, an amount of relative movement of the moving body between a first time point at which the first image is captured and a second time point at which the second image is captured, determine a scale for the amount of relative movement, based on a relation in a three-dimensional space between a road surface and a spatial point corresponding to a feature point in an area other than a road-surface area in at least one image of the captured images, and determine a movement distance of the moving body between the first and second time points, based on the amount of relative movement and the scale.

First claim

What is claimed is:

1. A movement distance estimating device comprising:
a memory; and
a processor coupled to the memory and configured to:
determine, based on a first image and a second image included in a plurality of images among images captured by an image capture device mounted on a moving body, an amount of relative movement of the moving body between a first time point at which the first image is captured and a second time point at which the second image is captured,
determine a plurality of scales for the amount of relative movement using the plurality of images, each of the plurality of scales being determined based on a relation in a three-dimensional space between a road surface and a spatial point corresponding to a feature point in an area other than a road-surface area in each of the plurality of images,
select a smallest scale among the plurality of scales, and
determine a movement distance of the moving body between the first time point and the second time point, based on the amount of relative movement and the smallest scale.

2. The movement distance estimating device according to claim 1 ,
wherein the processor is configured to determine the plurality of scales, based on a condition that the spatial point exists on the road surface in the three-dimensional space.

3. The movement distance estimating device according to claim 1 ,
wherein the processor is configured to determine the plurality of scales, based on a condition that the spatial point that is included in spatial points corresponding to feature points in the area other than the road-surface area and that is within a given distance from the road surface exists on the road surface.

4. The movement distance estimating device according to claim 1 , wherein the processor is configured to:
determine another scale for the amount of relative movement, based on a partial image in the road-surface area in at least one of the captured images,
determine the plurality of scales, when the another scale is not determined based on the partial image, and
determine the movement distance, based on the amount of relative movement and one of the smallest scale and the another scale.

5. The movement distance estimating device according to claim 4 , wherein the processor is configured to:
detect a first lane-dividing line from one of the captured images,
detect a second lane-dividing line from one of the captured images, and
determine the another scale, based on a difference between a first difference and a second difference, the first difference being a difference between the moving body and the first lane-dividing line, and the second difference being a difference between the moving body and the second lane-dividing line.

6. The movement distance estimating device according to claim 1 ,
wherein the processor is configured to determine a movement speed of the moving body, based on the movement distance and a movement time from the first time point to the second time point.

7. The movement distance estimating device according to claim 1 , further comprising:
a storage configured to store therein the captured images, wherein the processor is configured to refer to the storage.

8. A movement distance estimating method comprising:
determining, based on a first image and a second image included in a plurality of images among images captured by an image capture device mounted on a moving body, an amount of relative movement of the moving body between a first time point at which the first image is captured and a second time point at which the second image is captured;
determining a plurality of scales for the amount of relative movement using the plurality of images, each of the plurality of scales being determined based on a relation in a three-dimensional space between a road surface and a spatial point corresponding to a feature point in an area other than a road-surface area in each of the plurality of images;
selecting a smallest scale among the plurality of scales; and
determining, by a processor, a movement distance of the moving body between the first time point and the second time point, based on the amount of relative movement and the smallest scale.

9. The movement distance estimating method according to claim 8 , wherein the determining the plurality of scales includes determining the plurality of scales based on a condition that the spatial point exists on the road surface in the three-dimensional space.

10. The movement distance estimating method according to claim 8 , wherein the determining the plurality of scales includes determining the plurality of scales based on a condition that the spatial point that is included in spatial points corresponding to feature points in the area other than the road-surface area and that is within a given distance from the road surface exists on the road surface.

11. The movement distance estimating method according to claim 8 , further comprising:
determining another scale for the amount of relative movement, based on a partial image in the road-surface area in at least one of the captured images;
determining the plurality of scales, when the another scale is not determined based on the partial image; and
determining the movement distance, based on the amount of relative movement and one of the smallest scale and the another scale.

12. The movement distance estimating method according to claim 11 , further comprising:
detecting a first lane-dividing line from one of the captured images;
detecting a second lane-dividing line from one of the captured images; and
determining the another scale, based on a difference between a first difference and a second difference, the first difference being a difference between the moving body and the first lane-dividing line, and the second difference being a difference between the moving body and the second lane-dividing line.

13. The movement distance estimating method according to claim 8 , further comprising:
determining a movement speed of the moving body, based on the movement distance and a movement time from the first time point to the second time point.

14. The movement distance estimating method according to claim 8 , further comprising:
referring to a storage configured to store therein the captured images.

15. A non-transitory computer-readable recording medium storing a program that causes a computer to execute a procedure, the procedure comprising:
determining, based on a first image and a second image included in a plurality of images among images captured by an image capture device mounted on a moving body, an amount of relative movement of the moving body between a first time point at which the first image is captured and a second time point at which the second image is captured;
determining a plurality of scales for the amount of relative movement using the plurality of images, each of the plurality of scales being determined based on a relation in a three-dimensional space between a road surface and a spatial point corresponding to a feature point in an area other than a road-surface area in each of the plurality of images;
selecting a smallest scale among the plurality of scales; and
determining a movement distance of the moving body between the first time point and the second time point, based on the amount of relative movement and the smallest scale.

Assignees

• Fujitsu Ltd

Inventors

• Osamura Kazuki
• Kitaura Asako
• Nakayama Osafumi

Classifications

• G06V20/588 Primary

  Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road · CPC title

• G07C5/00 Primary

  Registering or indicating the working of vehicles · CPC title

• G06K9/00798

  Physics · mapped topic

• G06T7/204

  Physics · mapped topic

• G06T2207/30236

  Traffic on road, railway or crossing · CPC title