Method of determining the configuration of a path for motor vehicle

• US 5,341,437 A
• Filed: 02/09/1993
• Issued: 08/23/1994
• Est. Priority Date: 12/22/1989
• Status: Expired due to Term

• Current Assignee: Honda Giken Kogyo Kabushiki Kaisha (Honda Motor Company)
• Original Assignee: Honda Giken Kogyo Kabushiki Kaisha (Honda Motor Company)
• Inventors: Nakayama, Shigeto
• Primary Examiner(s): Moore, David K.
• Assistant Examiner(s): CAMMARATA, MICHAEL
• Application Number:
  US08/016,656
• Time in Patent Office: 560 Days
• Field of Search: 382/1, 382/16, 382/43, 382/49, 382/48, 901/47, 358/103, 364/424.02, 364/461
• US Class Current: 382/104
• CPC Class Codes: G06T 7/00 Image analysis
• CPC Class Codes: G06V 10/457 by analysing connectivity, e.g. edge linking, connected component analysis or slices
• 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

The configuration of a path for motor vehicles is recognized on the basis of image data produced by a television camera or the like. Feature points contained in original image data of the path are determined, and a group of straight lines approximating the array of the feature points are also determined. From the group of straight lines, there are extracted straight lines which are effective to determine boundaries of the path. The extracted straight lines divided into a plurality of line segments by points of intersection between the straight lines. The line segments are then checked against the feature points of the original image data to determine whether the line segments correspond to the boundaries of the path. The original image data may be divided into a plurality of areas, and the above process may be carried out with respect to the image data in each of the areas.

Claims

1. A method of determining the configuration of a path for motor vehicles on roadways in which extraneous clutter and noise is relatively minimal, comprising the steps of:

extracting straight lines from a group of straight lines which have been redetermined from original image data of the path based on an array of feature points included in said original image data, wherein the extracted straight lines determine boundaries of the path;

dividing the extracted straight lines into a plurality of line segments, each of said line segments being defined by points of intersection between the straight lines; and

comparing said line segments with the feature points of said original image data to determine whether the line segments correspond to the boundaries of the path.

2. A method according to claim 1, wherein said step of extracting straight lines comprises the steps of determining whether the X coordinate of the starting point of one straight line is larger than the X coordinate of the starting point of another straight line, and whether the x coordinate of the ending point of said one straight line is larger than the X coordinate of the ending point of said other straight line, and determining a straight line which interconnects the starting point of said one straight line and the ending point of said other straight line, to be an effective straight line if said X coordinate of the starting point of said one straight line is larger than said X coordinate of the starting point of said other straight line and said X coordinate of the ending point of said one straight line is larger than said X coordinate of the ending point of said other straight line.

3. A method according to claim 1, wherein said step of extracting straight lines comprises the steps of determining whether the Y coordinate of the starting point of one straight line is larger than the Y coordinate of the starting point of another straight line, and whether the Y coordinate of the ending point of said one straight line is larger than the Y coordinate of the ending point of said other straight line, and determining a straight line which interconnects the starting end of said one straight line and the ending point of said other straight line, to be an effective straight line if said Y coordinate of the starting point of said one straight line is larger than said Y coordinate of the starting point of said other straight line and said Y coordinate of the ending point of said one straight line is larger than said Y coordinate of the ending point of said other straight line.

4. A method according to claim 1, wherein said step of extracting straight lines comprises the steps of determining whether the Y coordinate of the starting point of one straight line is smaller than the Y coordinate of the starting point of another straight line, and whether the Y coordinate of the ending point of said one straight line is smaller than the Y coordinate of the ending point of said other straight line, and determining a straight line which interconnects the ending point of said one straight line and the starting point of said other straight line, to be an effective straight line if said Y coordinate of the starting point of said one straight line is smaller than said Y coordinate of the starting point of said other straight line and said Y coordinate of the ending point of said one straight line is smaller than said Y coordinate of the ending point of said other straight line.

5. A method according to claim 1, wherein said step of dividing the extracted straight lines comprises the steps of defining one straight line as a first line segment and another straight line as a second line segment, determining whether said first and second lien segments are parallel to each other, determining a point of intersection between said first and second line segments if the first and second line segments are not parallel to each other, determining whether the point of intersection is positioned between the starting and ending points of said first and second line segments, and dividing said first and second line segments by the point of intersection if the point of intersection is positioned between the starting and ending points of the first and second line segments.

6. A method according to claim 1, wherein said step of comparing said line segments comprises the steps of scanning an edge image over a predetermined width across a line segment, comparing the intensity of the edge point of each dot which is scanned, with a predetermined threshold, counting edge points whose intensity is higher than said predetermined threshold, calculating the ratio of the number of the counted edge points to the length of the line segment, and determining whether the line segment corresponds to a boundary of the path based on the calculated ratio.

7. A method of determining the configuration of a path for motor vehicles on roadways in which extraneous clutter and noise is relatively minimal, comprising the steps of:

extracting straight lines from a group of straight lines which have been predetermined from original image data of the path based on an array of feature points included in said original image data, the original image data is being divided into a plurality of image areas, wherein the extracted straight lines determine boundaries of the path in each of said areas;

uniting the extracted straight lines in each of said areas into a single combination of image data representing a single straight line;

dividing said single straight line into a plurality of line segments; and

comparing said line segments with the feature points of said original image data to determine whether the line segments correspond to the boundaries of the path.

8. A method according to claim 7, wherein said step of extracting straight lines comprises the steps of determining whether the X coordinate of the starting point of one straight line is larger than the X coordinate of the starting point of another straight line, and whether the X coordinate of the ending point of said one straight line is larger than the X coordinate of the ending point of said other straight line, and determining a straight line which interconnects the starting point of said one straight line and the ending point of said other straight line, to be an effective straight line if said X coordinate of the starting point of said one straight line is larger than said X coordinate of the starting point of said other straight line and said X coordinate of the ending point of said one straight line is larger than said X coordinate of the ending point of said other straight line.

9. A method according to claim 7, wherein said step of extracting straight lines comprises the steps of determining whether the Y coordinate of the starting point of one straight line is larger than the Y coordinate of the starting point of another straight line, and whether the Y coordinate of the ending point of said one straight line is larger than the Y coordinate of the ending point of said other straight line, and determining a straight line which interconnects the starting end of said one straight line and the ending point of said other straight line, to be an effective straight line if said Y coordinate of the starting point of said one straight line is larger than said Y coordinate of the starting point of said other straight line and said Y coordinate of the ending point of said one straight line is larger than said Y coordinate of the ending point of said other straight line.

10. A method according to claim 7, wherein said step of extracting straight lines comprises the steps of determining whether the Y coordinate of the starting point of one straight line is smaller than the Y coordinate of the starting point of another straight line, and whether the Y coordinate of the ending point of said one straight line is smaller than the Y coordinate of the ending point of said other straight line, and determining a straight line which interconnects the ending point of said one straight line and the starting point of said other straight line, to be an effective straight line if said Y coordinate of the starting point of said one straight line is smaller than said Y coordinate of the starting point of said other straight line and said Y coordinate of the ending point of said one straight line is smaller than said Y coordinate of the ending point of said other straight line.

11. A method according to claim 7, wherein said step of dividing said single straight line comprises the steps of defining one straight line as a first line segment and another straight line as a second line segment, determining whether said first and second line segments are parallel to each other, determining a point of intersection between said first and second line segments if the first and second line segments are not parallel to each other, determining whether the point of intersection is positioned between the stating and ending points of said first and second line segments, and dividing said first and second line segments by the point of intersection if the point of intersection is positioned between the starting and ending points of the first and second line segments.

12. A method according to claim 7, wherein said step of comparing said line segments comprises the steps of scanning an edge image over a predetermined width across a line segment, comparing the intensity of the edge point of each dot which is scanned, with a predetermined threshold, counting edge points whose intensity is higher than said predetermined threshold, calculating the ratio of the number of the counted edge points to the length of the line segment, and determining whether the line segment corresponds to a boundary of the path based on the calculated ratio.