Apparatus and method for recognizing a lane

• US 9,280,712 B2
• Filed: 03/19/2013
• Issued: 03/08/2016
• Est. Priority Date: 03/19/2012
• Status: Expired due to Fees

• Current Assignee: DENSO Corporation, Nippon Soken, Inc. (DENSO Corporation)
• Original Assignee: DENSO Corporation, Nippon Soken, Inc. (DENSO Corporation)
• Inventors: Kawasaki, Naoki, Hasegawa, Junichi, Takafuji, Tetsuya, Suzuki, Shunsuke
• Primary Examiner(s): Chu, Randolph I
• Application Number:
  US14/386,291
• Publication Number:
  US 20150055831A1
• Time in Patent Office: 1,085 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• 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: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

An apparatus for recognizing a lane is provided. The apparatus performs a near-field white line recognition process and calculates road parameters (lane position, lane inclination, lane curvature and lane width) near the vehicle. The road parameters are calculated using the extended Kalman filter. In the calculation, the calculated lane curvature is used as a lane curvature to be included in predicted values. The apparatus outputs the calculated road parameters to a warning/vehicle-control apparatus.

Claims

1. An apparatus for recognizing a lane, comprising:

an edge point extracting means for processing an image acquired by an in-vehicle camera that acquires an image of a road surface around a vehicle to extract edge points of a lane;

a first calculating means for calculating one or more road parameters as near-field road parameters from among a position of the lane, an angle of the lane with respect to a traveling direction of the vehicle, a curvature of the lane, and an interval between a plurality of lane markers in the lane in a width direction, on the basis of near-field edge points corresponding to the lane within a predetermined distance from the vehicle among the edge points extracted by the edge point extracting means; and

a second calculating means for calculating distant road parameters as the road parameters on the basis of distant edge points corresponding to the lane that is positioned beyond a predetermined distance from the vehicle among the edge points extracted by the edge extracting means, and the near-field road parameters calculated by the first calculating means,

wherein the first calculating means is configured to calculate the near-field road parameters by converting the edge points extracted by the edge point extracting means into coordinates in terms of a planar road surface;

the second calculating means is configured to calculate the distant road parameters on the basis of predicted values and measured values;

the measured values are the road parameters calculated on the basis of the distant edge points extracted by the edge extracting means; and

the predicted values are the road parameters calculated on the basis of the near-field road parameters calculated by the first calculating means and the distant road parameters calculated in past times by the second calculating means.

2. The apparatus according to claim 1, wherein the second calculating means is configured to calculate the distant road parameters by selecting and using the distant edge points that correspond to positions at which a lane is present, the lane being predicted on the basis of the near-field road parameters calculated by the first calculating means, from among the distant edge points extracted by the edge point extracting means.

3. The apparatus according to claim 2, wherein the second calculating means is configured to determine whether or not the distant road parameters are anomalous values by using, as reference values, the near-field road parameters calculated by the first calculating means.

8. A program that is stored in a memory in a readable manner to have a computer function as individual means that configure the lane recognition apparatus recited in claim 1.

4. An apparatus for recognizing a lane, comprising:

an edge point extracting means for processing an image acquired by an in-vehicle camera that acquires an image of a road surface around a vehicle to extract edge points of a lane;

a first calculating means for calculating one or more road parameters as near-field road parameters from among a position of the lane, an angle of the lane with respect to a traveling direction of the vehicle, a curvature of the lane, and an interval between a plurality of lane markers in the lane in a width direction, on the basis of near-field edge points corresponding to the lane within a predetermined distance from the vehicle among the edge points extracted by the edge point extracting means; and

a second calculating means for calculating distant road parameters as the road parameters on the basis of distant edge points corresponding to the lane that is positioned beyond a predetermined distance from the vehicle among the edge points extracted by the edge extracting means, and the near-field road parameters calculated by the first calculating means,

wherein the second calculating means is configured to calculate the distant road parameters on the basis of predicted values and measured values;

the measured values are the road parameters calculated on the basis of the distant edge points extracted by the edge point extracting means; and

the predicted values are the road parameters calculated on the basis of the near-field road parameters calculated by the first calculating means and the distant road parameters calculated in past times by the second calculating means.

5. The apparatus according to claim 4, wherein the second calculating means is configured to calculate the distant road parameters by selecting and using the distant edge points that correspond to positions at which a lane is present, the lane positionally being predicted on the basis of the near-field road parameters calculated by the first calculating means, from among the distant edge points extracted by the edge point extracting means.

6. The apparatus according to claim 5, wherein the second calculating means is configured to determine whether or not the distant road parameters are anomalous values by using, as reference values, the near-field road parameters calculated by the first calculating means.

7. A method of recognizing a lane, characterized in that the method comprises:

extracting edge points of a lane by processing an image acquired by an in-vehicle camera that acquires an image of a road surface around a vehicle;

first calculating one or more road parameters as near-field road parameters from among a position of the lane, an inclination of the lane with respect to a traveling direction of the vehicle, a curvature of the lane, and an interval between a plurality of lane markers in the lane in a width direction, on the basis of near-field edge points corresponding to the lane in a predetermined distance from the vehicle among the extracted edge points; and

second calculating distant road parameters as the road parameters on the basis of distant edge points corresponding to the lane that is positioned beyond a predetermined distance from the vehicle among the extracted edge points, and the calculated near-field road parameters,

wherein

the second calculating step calculating the distant road parameters on the basis of predicted values and measured values;

the measured values are the road parameters calculated on the basis of the distant edge points extracted by the edge point extracting step; and

the predicted values are the road parameters calculated on the basis of the near-field road parameters calculated by the first calculating step and the distant road parameters calculated in past times by the second calculating step.