Road surface detection device and road surface detection system

• US 9,912,933 B2
• Filed: 04/12/2016
• Issued: 03/06/2018
• Est. Priority Date: 04/17/2015
• Status: Active Grant

• Current Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Original Assignee: Toyota Jidosha Kabushiki Kaisha (Toyota Motor Corporation)
• Inventors: Nishijima, Masakazu, Sugaya, Fumio
• Primary Examiner(s): Dunn, Alex C
• Application Number:
  US15/096,594
• Publication Number:
  US 20160305785A1
• Time in Patent Office: 693 Days
• CPC Class Codes: G01C 11/06 by comparison of two or more pictures of the same area
• CPC Class Codes: G01C 7/04 involving a vehicle which moves along the profile to be traced
• 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
• CPC Class Codes: H04N 13/204 using stereoscopic image cameras stereoscopic photography G03B35/00
• CPC Class Codes: H04N 13/239 using two 2D image sensors having a relative position equal to or related to the interocular distance H04N13/243 takes precedence

Abstract

A road surface detection device that detects a road surface region based on disparity information obtained from a captured image of an area around a vehicle that is captured by an onboard camera, includes a path estimating portion that estimates a travel path where the vehicle will travel, based on driving information of the vehicle; and a detecting portion that weights the disparity information, and detects a road surface region in the captured image based on the weighted disparity information, wherein when the detecting portion weights the disparity information, the detecting portion gives less weight to the disparity information positioned on a side away from the travel path in the captured image than to the disparity information positioned on a side near the travel path in the captured image.

Claims

1. A road surface detection device that detects a road surface region based on disparity information obtained from a captured image of an area around a vehicle, comprising:

an onboard camera that obtains the captured image of the area around the vehicle and is configured to generate a disparity image that includes disparity information;

a path estimating portion that estimates a travel path where the vehicle will travel, based on driving information of the vehicle; and

a detecting portion that weights the disparity information of the disparity image generated by the onboard camera, and detects a road surface region in the captured image based on the weighted disparity information, wherein

when the detecting portion weights the disparity information, the detecting portion gives less weight to the disparity information positioned on a side away from the travel path in the captured image than to the disparity information positioned on a side near the travel path in the captured image.

2. The road surface detection device according to claim 1, wherein

the path estimating portion estimates the travel path, and estimates a curvature of a traveling lane of the vehicle based on the travel path;

and

when an amount of change per unit time in the curvature estimated by the path estimating portion is greater than a preset reference amount of change, the detecting portion prohibits a process that gives the disparity information positioned on the side away from the travel path in the captured image less weight than the disparity information positioned on the side near the travel path in the captured image.

3. A road surface detection device that detects a road surface region based on disparity information obtained from a captured image of an area around a vehicle, comprising:

an onboard camera that obtains the captured image and is configured to generate a disparity image that includes disparity information;

a path estimating portion that estimates a travel path where the vehicle will travel, based on driving information of the vehicle; and

a detecting portion that weights the disparity information of the disparity image generated by the onboard camera, and detects a road surface region in the captured image based on the weighted disparity information, wherein

when the detecting portion weights the disparity information, the detecting portion gives less weight to the disparity information positioned outside a predetermined area that is determined in advance from the travel path in the captured image than to the disparity information positioned inside the predetermined area.

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

the path estimating portion estimates the travel path, and estimates a curvature of a traveling lane of the vehicle based on the travel path;

and

when an amount of change per unit time in the curvature estimated by the path estimating portion is greater than a preset reference amount of change, the detecting portion prohibits a process that gives the disparity information positioned outside the predetermined area that is determined in advance from the travel path in the captured image less weight than the disparity information positioned inside the predetermined area.

5. A road surface detection system comprising:

a stereo camera that is mounted to a vehicle and captures an image of an area around the vehicle and generates a disparity image that includes disparity information; and

an ECU that estimates a potential road surface point, based on the disparity information, that is a potential road surface in the image captured by the stereo camera, and detects a road surface region in the image based on the potential road surface point, and outputs information about the road surface region, wherein

the ECU estimates a travel path where the vehicle will travel, and links the travel path to pixels of the image captured by the stereo camera;

the ECU gives a weight to the potential road surface point such that the weight is greater when a distance between the travel path and the potential road surface point in the image is close than when the distance between the travel path and the potential surface point in the image is far; and

the ECU determines that the potential road surface point is the road surface region based on the weight given to the potential road surface point.