LANE DETECTION APPARATUS AND OPERATING METHOD FOR THE SAME

• US 20160055751A1
• Filed: 08/22/2015
• Published: 02/25/2016
• Est. Priority Date: 08/22/2014
• Status: Active Grant

• Current Assignee: Hyundai Mobis Co., Ltd.
• Original Assignee: Hyundai Mobis Co., Ltd.
• Inventors: PARK, Sang jun
• Granted Patent: US 9,704,404 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06V 10/44 Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
• 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

Disclosed are a lane detection apparatus and an operating method for the same, and the operating method for the lane detection apparatus includes: detecting a plurality of edges in a driving image of a vehicle expressed by Cartesian coordinates; detecting a pattern of the plurality of edges; estimating a horizontal location of the vehicle in a driving lane based on the detected pattern; setting two regions of interest in the driving image based on the horizontal location; generating two Hough spaces corresponding two regions of interest, respectively, including a plurality of counting regions, and expressed by polar coordinates; calculating a polar coordinate value of each pixel included in the edge shown in each of two regions of interest among the plurality of edges by using Hough transform that transforms the Cartesian coordinates into the polar coordinates; accumulating the count of the counting region to which the polar coordinate value belongs, with respect to two respective Hough spaces; selecting a counting region having the highest count number among the plurality of counting regions with respect to two respective Hough spaces; transforming the counting region having the highest count number into two straight lines expressed by the Cartesian coordinates, with respect to two respective Hough spaces; and detecting two transformed straight lines as a left lane and a right lane of the driving lane.

Claims

1. An operating method for a lane detection apparatus comprising:

detecting a plurality of edges in a driving image of a vehicle expressed by Cartesian coordinates;

detecting a pattern of the plurality of edges;

estimating a horizontal location of the vehicle in a driving lane based on the detected pattern;

setting two regions of interest in the driving image based on the horizontal location;

generating two Hough spaces corresponding to two regions of interest, respectively, including a plurality of counting regions, and expressed by polar coordinates;

calculating a polar coordinate value of each pixel included in the edge shown in each of two regions of interest among the plurality of edges by using Hough transform that transforms the Cartesian coordinates into the polar coordinates;

accumulating the count of the counting region to which the polar coordinate value belongs, with respect to two respective Hough spaces;

selecting a counting region having the highest count number is selected among the plurality of counting regions with respect to two respective Hough spaces;

transforming the counting region having the highest count number into two straight lines expressed by the Cartesian coordinates, with respect to two respective Hough spaces; and

detecting two transformed straight lines as a left lane and a right lane of the driving lane.

2. The method of claim 1, wherein the detecting of the plurality of edges in the driving image of the vehicle includes:

receiving the driving image from a camera of the vehicle;

transforming the driving image into a gray image; and

detecting the plurality of edges based on brightness values of pixels included in the gray image.

3. The method of claim 2, wherein in the detecting of the plurality of edges, pixels of a region in which a brightness change amount of a reference value or more in the gray image are connected to detect the plurality of edges.

4. The method of claim 1, wherein the horizontal location is estimated as any one of a first location corresponding to the center of the driving lane, a second location corresponding to a left side of the driving lane, and a third location corresponding to a right side of the driving lane.

5. The method of claim 1, wherein the region of interest includes a first region of interest positioned at a left side and a second region of interest positioned at a right side based on a central vertical axis of the driving image.

6. The method of claim 5, wherein in the generating of the Hough space, each of a first Hough space corresponding to the first region of interest and a second Hough space corresponding to the second region of interest is generated.

7. The method of claim 1, wherein in the setting of the region of interest in the driving image, the size or location of the region of interest is decided based on an installation angle and an image angle of the camera photographing the driving image.

8. The method of claim 1, wherein the transforming of the counting region having the highest count number into the straight lines expressed by the Cartesian coordinates is performed when the count number of the selected counting region is equal to or more than a predetermined reference value.

9. The method of claim 1, further comprising:

calculating a distance between the left lane and the right lane;

determining whether the distance between the left lane and the right lane is within a predetermined reference range; and

increasing the number of the counting regions included in two respective Hough spaces when it is determined that the distance between the left lane and the right lane deviates from the predetermined reference range.

10. The method of claim 1, further comprising:

outputting a warning message when the length of at least any one of the left lane and the right lane rapidly decreases by a predetermined change amount or more.