Method and apparatus for detecting a lane on a road

• US 5,991,427 A
• Filed: 07/31/1997
• Issued: 11/23/1999
• Est. Priority Date: 07/31/1996
• Status: Expired due to Term

• Current Assignee: Aisin Seiki Co., Ltd. (Aisin Corp.)
• Original Assignee: Aisin Seiki Co., Ltd. (Aisin Corp.)
• Inventors: Kakinami, Toshiaki, Inoue, Ryo, Kimura, Yoshikatsu
• Primary Examiner(s): Chang, Jon
• Assistant Examiner(s): Patel, Jayanti K.
• Application Number:
  US08/903,729
• Time in Patent Office: 845 Days
• Field of Search: 382/104, 382/100, 382/107, 382/108, 382/153, 382/241, 382/266, 382/269, 382/286, 382/288, 382/316, 382/199, 382/291, 382/256, 56/10.2 F, 340/901, 340/576, 340/903, 342/69, 348/118, 348/119, 701/28, 701/300, 701/301, 701/93
• US Class Current: 382/104
• 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

Abstract

The invention is directed to a method and apparatus for detecting a lane on a road, the latter of which includes an edge sensor (ED) for detecting edges indicative of boundaries of opposite sides of each lane, an edge memory (EM) for storing the edges to form a couple of continuous lines of edge groups indicative of the opposite boundaries of the lane, and an image processor (DP) for defining the opposite boundaries of the lane on a plane in a three-dimensional geometry. A center of curvature defining device (RC) defines a center of curvature to the opposite boundaries of the lane. An edge line extracting device (ES) divides the edge groups stored in the edge memory into a plurality of continuous regions each having a predetermined length along a concentric circle arc having the same center as the center of curvature, and extracts a pair of edge lines from each region. A tangent defining device (TL) defines a couple of tangents to the edge lines, and a normal defining device (NL) defines a normal to the tangents. Then, a segment setting device (SD) defines a couple of intersections of the normal with the tangents, and sets a line segment between the intersections as a segment of the lane. The image processor (DP) renews the opposite boundaries of the lane on the basis of the segment of the lane.

Claims

1. A method for detecting a lane on a road, comprising the steps of:

detecting edges indicative of boundaries of opposite sides of each lane on a road on the basis of a density of image information including the opposite sides of said lane;

storing said edges in an edge memory to form a couple of continuous lines of edge groups indicative of the opposite boundaries of said lane;

defining the opposite boundaries of said lane on a plane in a three-dimensional geometry, at least on the basis of said lines of said edge groups;

defining a center of curvature to the opposite boundaries of said lane defined on said plane;

dividing said edge groups stored in said edge memory into a plurality of continuous regions each having a predetermined length along a concentric circle arc having the same center as said center of curvature;

extracting a pair of each lines from each region;

defining a couple of tangents to said edge lines extracted from each region, respectively;

defining a couple of intersections of said normal with said tangents;

setting a line segment between said intersections as a segment of said lane; and

renewing the opposite boundaries of said lane on the basis of said segment of said lane,

wherein said tangents are a couple of tangents to said edge lines extracted from each region which are assumed to be parallel with each other, and a center of gravity of edges forming said edge lines is defined, and wherein said normal is a normal including said center of gravity.

2. The method as set forth in claim 1, wherein said edges stored in said edge memory to form said continuous lines of edge groups indicative of the opposite boundaries of said lane is divided into a plurality of continuous regions each having a predetermined length along a concentric circle arc having the same center as said center of curvature, with neighboring regions partially overlapped with each other, and extracting a pair of edge lines from each region.

3. An apparatus for detecting a lane on a road, comprising:

edge detection means for detecting edges indicative of boundaries of opposite sides of each lane on a road on the basis of a density of image information including the opposite sides of said lane;

edge memory means for storing said edges to form a couple of continuous lines of edge groups indicative of the opposite boundaries of said lane;

image processing means for defining the opposite boundaries of said lane on a plane in a three-dimensional geometry, at least on the basis of said lines of said edge groups;

center of curvature defining means for defining a center of curvature to the opposite boundaries of said lane defined by said image processing means;

edge line extracting means for dividing said edge groups stored in said edge memory means into a plurality of continuous regions each having a predetermined length along a concentric circle arc having the same center as said center of curvature, and extracting a pair of edge lines from each region;

tangent defining means for defining a couple of tangents to said edge lines extracted from each region, respectively by said edge line extracting means;

normal defining means for defining a normal to said tangents;

segment setting means for defining a couple of intersections of said normal with said tangents, and setting a line segment between said intersections as a segment of said lane to output said segment of said lane to said image processing means, said image processing means renewing the opposite boundaries of said lane on the basis of said segment of said lane,

center of gravity defining means for defining a center of gravity of edges forming said edge lines, wherein said tangent defining means is adapted to define said tangents to be extracted from each region which are assumed to be parallel with each other, and wherein said normal defining means is adapted to define said normal to include said center of gravity.

4. The apparatus as set forth in claim 3, wherein said edge line extracting means divides said edge groups stored in said edge memory means into a plurality of continuous regions each having a predetermined length along a concentric circle arc having the same center as said center of curvature, with neighboring regions partially overlapped with each other, and extracting a pair of edge lines from each region.