TRAFFIC LANE RECOGNIZING APPARATUS AND METHOD THEREOF

• US 20140226011A1
• Filed: 01/09/2012
• Published: 08/14/2014
• Est. Priority Date: 08/04/2011
• Status: Abandoned Application

• Current Assignee: LG Electronics, Inc. (LG Corporation)
• Original Assignee: LG Electronics, Inc. (LG Corporation)
• Inventors: Park, Youngkyung, Kim, Jonghun, Lee, Jeihun, Dhir, Chandra Shekhar, Lee, Joongjae, Kim, Hyunsoo, Park, Junoh, Park, Andreas
• Application Number:
  US14/236,099
• Publication Number:
  US 20140226011A1
• Time in Patent Office: Days
• US Class Current: 348/148
• CPC Class Codes: G06T 2207/10021 Stereoscopic video; Stereoscopic image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• 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

Disclosed is a traffic lane recognizing apparatus and a method thereof. The traffic lane recognizing apparatus includes: a camera module; a display unit displaying an image captured by the camera module; and a controller detecting candidate traffic lanes from an image captured by the camera module, detecting double lines from the detected candidate traffic lanes, selecting a first traffic lane adjacent to a vehicle from among the detected double lines, selecting a second traffic lane adjacent to the vehicle from among the candidate traffic lanes, excluding the double lines, and displaying the first traffic lane and the second traffic lane on the image.

Claims

1. A traffic lane recognizing apparatus comprising:

a camera module;

a display unit configured to display an image captured by the camera module; and

a controller configured to detect candidate traffic lanes from an image captured by the camera module, detect double lines from the detected candidate traffic lanes, select a first traffic lane adjacent to a vehicle from among the detected double lines, select a second traffic lane adjacent to the vehicle from among the candidate traffic lanes, exclude the double lines, and display the first traffic lane and the second traffic lane on the image,

wherein the controller determines traffic lanes whose interval therebetween is a pre-set interval or smaller, among the detected candidate traffic lanes, as the double lines, and an interval of the double lines is smaller than an interval of the first and second traffic lanes.

3. The traffic lane recognizing apparatus of claim 1, wherein the double lines are double lines of solid lines, double lines of dotted lines, or double lines of a solid line and a dotted line.

4. The traffic lane recognizing apparatus of claim 1, wherein the controller detects the traffic lanes by extracting traffic lane feature points from the image, converting the extracted traffic lane feature points into world coordinates, and tracking the traffic lane feature points which have been converted into the world coordinates.

5. The traffic lane recognizing apparatus of claim 1, wherein the controller detects the traffic lanes by extracting traffic lane feature points from the image based on pre-set guide lines, converting the extracted traffic lane feature points into world coordinates, detecting a plurality of points corresponding to a traffic lane based on a previously stored traffic lane equation from the feature points which have been converted into the world coordinates, and tracking the plurality of detected points.

6. The traffic lane recognizing apparatus of claim 5, wherein the controller displays the first and second traffic lanes on the image by converting the traffic lane feature points into coordinates on an image domain, and overlapping the traffic lane feature points which have been converted into the coordinates on the image domain with the image.

7. The traffic lane recognizing apparatus of claim 5, wherein the controller converts the extracted traffic lane feature points into the world coordinates based on a previously stored homographic matrix.

8. The traffic lane recognizing apparatus of claim 1, wherein the controller detects the double lines by setting a plurality of guide lines in a horizontal direction of the image, extracting traffic lane feature points from the plurality of guide lines, and tracking the traffic lane feature points.

9. The traffic lane recognizing apparatus of claim 1, wherein the interval between the plurality of guide lines is gradually narrowed in a vertical direction of the image.

2. (canceled)

10. A traffic lane recognizing method comprising:

receiving an image captured by a camera;

detecting candidate traffic lanes from the image;

detecting double lines from the detected candidate traffic lanes;

selecting a first traffic lane adjacent to a vehicle from among the detected double lines, and selecting a second traffic lane adjacent to the vehicle from among the candidate traffic lanes excluding the double lines; and

overlapping the first and second traffic lanes with the image to display the same on a display unit,.

wherein traffic lanes whose interval therebetween is a pre-set interval or smaller, among the detected candidate traffic lanes, are determined as the double lines, and an interval of the double lines is smaller than an interval of the first and second traffic lanes.

12. The method of claim 10, wherein the double lines are double lines of solid lines, double lines of dotted lines, or double lines of a solid line and a dotted line.

13. The method of claim 10, wherein the detecting of traffic lanes comprises:

extracting traffic lane feature points from the image;

converting the extracted traffic lane feature points into world coordinates; and

detecting the traffic lanes by tracking the traffic lane feature points which have been converted into the world coordinates.

14. The method of claim 10, wherein the detecting of traffic lanes comprises:

extracting traffic lane feature points from the image based on pre-set guide lines;

converting the extracted traffic lane feature points into world coordinates;

detecting a plurality of points corresponding to a curve from the feature points which have been converted into the world coordinates based on a previously stored curve equation; and

detecting the traffic lanes by tracking the plurality of detected points.

15. The method of claim 14, wherein the displaying of the first and second traffic lanes on the image comprises:

converting the traffic lane feature points into coordinates on an image domain; and

overlapping the traffic lane feature points which have been converted into coordinates on the image domain, respectively, with the image to display the first and second traffic lanes on the image.

16. The method of claim 14, wherein the extracted traffic lane feature points are converted into the world coordinates based on a previously stored homographic matrix.

17. The method of claim 10, wherein the detecting of the candidate traffic lanes comprises:

setting a plurality of guide lines in a horizontal direction of the image;

extracting traffic lane feature points from the plurality of guide lines; and

detecting the candidate traffic lanes by tracking the traffic lane feature points.

18. The method of claim 17, wherein the interval between the plurality of guide lines is gradually narrowed in a vertical direction of the image.

11. (canceled)