ROAD SURFACE SHAPE ESTIMATING DEVICE

• US 20140180497A1
• Filed: 12/17/2013
• Published: 06/26/2014
• Est. Priority Date: 12/20/2012
• Status: Active Grant

• Current Assignee: DENSO Corporation
• Original Assignee: DENSO Corporation
• Inventors: Kojima, Shinya
• Granted Patent: US 9,489,583 B2
• Time in Patent Office: Days
• US Class Current: 701/1
• CPC Class Codes: G06V 20/588 Recognition of the road, e.g. of lane markings; Recognition of the vehicle driving pattern in relation to the road

Abstract

A road surface shape estimating device includes a target detecting unit, a coordinate calculating unit and an estimating unit. The target detecting unit detects a known target from a captured image capturing an area ahead of a vehicle. The known target is a target of which a size and positional relationship to a road surface is known. The coordinate calculating unit determines three-dimensional coordinates for each known target from a size and position in the captured image of the known target detected by the target detecting unit. The estimating unit estimates a road surface shape using the three-dimensional coordinates calculated by the coordinate calculating unit.

Claims

1. A road surface shape estimating device, comprising:

a target detecting unit that detects a known target from a captured image capturing an area ahead of a vehicle, the known target being a target of which a size and positional relationship to a road surface is known;

a coordinate calculating unit that determines three-dimensional coordinates for each known target from a size and position in the captured image of the known target detected by the target detecting unit; and

an estimating unit that estimates a road surface shape using the three-dimensional coordinates calculated by the coordinate calculating unit.

2. The road surface shape estimating device according to claim 1, further comprising:

a deleting unit that deletes a known target from a detection result of the known target detected by the target detecting unit, the known target having a distance from a road surface which is obtained from an estimation result of the road surface shape estimated by the estimating unit exceeds a predetermined allowable distance.

3. The road surface shape estimating device according to claim 2, further comprising:

a search area setting unit that sets a search area which allows the target detecting unit to search the known target in the captured image based on an estimation result of the road surface shape estimated by the estimating unit.

4. The road surface shape estimating device according to claim 3, wherein

the estimating unit is configured to estimate the road surface shape when the number of known targets detected by the target detecting unit is greater than or equal to a predetermined lower limit.

5. The road surface shape estimating device according to claim 4, wherein

the estimating means is configured to estimate the road surface shape by using a method of linear regression or nonlinear regression.

6. The road surface shape estimating device according to claim 5, wherein

the estimating means is configured to estimate the road surface shape by using a method of an approximate estimation that excludes a cross slope of the road surface shape.

7. The road surface shape estimating device according to claim 6, wherein

the estimating unit is configured to estimate the road surface shape by assuming that a point at which a camera capturing an area ahead of the vehicle to produce the captured image is present is a point of origin of the three-dimensional coordinates, and a plane indicating the road surface shape passes through the point of origin.

8. The road surface shape estimating device according to claim 1, further comprising:

a search area setting unit that sets a search area which allows the target detecting unit to search the known target in the captured image based on an estimation result of the road surface shape estimated by the estimating unit.

9. The road surface shape estimating device according to claim 1, wherein

the estimating unit is configured to estimate the road surface shape when the number of known targets detected by the target detecting unit is greater than or equal to a predetermined lower limit.

10. The road surface shape estimating device according to claim 1, wherein

the estimating means is configured to estimate the road surface shape by using a method of linear regression or nonlinear regression.

11. The road surface shape estimating device according to claim 1, wherein

the estimating means is configured to estimate the road surface shape by using a method of an approximate estimation that excludes a cross slope of the road surface shape.

12. The road surface shape estimating device according to claim 1, wherein

the estimating unit is configured to estimate the road surface shape by assuming that a point at which a camera capturing an area ahead of the vehicle to produce the captured image is present is a point of origin of the three-dimensional coordinates, and a plane indicating the road surface shape passes through the point of origin.

13. A vehicle control system, comprising:

a camera that captures an area ahead of a vehicle to produce a captured image;

a target detecting section that detects a target from the captured image to produce target information related to the detected target; and

a vehicle control executing section that performs a vehicle control based on the target information,

the target detecting section including a road surface shape estimating device comprising;

a target detecting unit that detects a known target from the captured image, the known target being a target of which a size and positional relationship to a road surface is known;

a coordinate calculating unit that determines three-dimensional coordinates for each known target from a size and position in the captured image of the known target detected by the target detecting unit; and

an estimating unit that estimates a road surface shape using the three-dimensional coordinates calculated by the coordinate calculating unit.

14. A road surface shape estimating method, comprising:

detecting, using a target detecting unit, a known target from a captured image capturing an area ahead of a vehicle, the known target being a target of which a size and positional relationship to a road surface is known;

determining, at a coordinate calculating unit, three-dimensional coordinates for each known target from a size and position in the captured image of the known target detected by the target detecting unit; and

estimating, at an estimating unit, a road surface shape using the three-dimensional coordinates calculated by the coordinate calculating unit.