Boundary line recognition apparatus and branch road determination apparatus

• US 10,002,433 B2
• Filed: 12/26/2013
• Issued: 06/19/2018
• Est. Priority Date: 12/26/2012
• Status: Active Grant

• Current Assignee: DENSO Corporation, Nippon Soken, Inc.
• Original Assignee: DENSO Corporation, Nippon Soken, Inc.
• Inventors: Kumano, Syunya, Kawasaki, Naoki, Suzuki, Shunsuke, Takafuji, Tetsuya, Hashimoto, Kazuma
• Primary Examiner(s): HU, FRED H.
• Application Number:
  US14/655,698
• Publication Number:
  US 20150348275A1
• Time in Patent Office: 1,636 Days
• Field of Search: None
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10152 Varying illumination
• CPC Class Codes: G06T 2207/20061 Hough transform
• CPC Class Codes: G06T 2207/20076 Probabilistic image processing
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/13 Edge detection
• 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

In a boundary line recognition apparatus, based on luminance levels of an image captured by a camera, candidate edge points of a boundary line sectioning a travel road are extracted, and a candidate line of the boundary line is extracted. An apparent width of the candidate line on an image is calculated, from a width of the candidate line in a horizontal direction of the image and an angle of the candidate line relative to a vertical direction of the image. A probability of a candidate line being a boundary line is calculated to be higher, as a degree of the candidate line having characteristics as a boundary line is higher. The calculated probabilities are integrated in respect of a plurality of characteristics to recognize a boundary line. The characteristics include a ratio of the calculated apparent width to an image blur degree is larger than a predetermined value.

Claims

1. A boundary line recognition apparatus comprising:

a camera that is installed in a vehicle to capture an image of a travel road;

a boundary line candidate extraction section that extracts candidate edge points of a boundary line sectioning the travel road, on the basis of a luminance of an image captured by the camera, and extracts a candidate line of the boundary line from a series of the extracted candidate edge points;

a width calculation section that calculates, in the candidate line of the boundary line extracted by the boundary line candidate extraction section, an apparent thickness of the candidate line on the image, which is an apparent perpendicular distance from one side edge of the candidate line to the other side edge of the candidate line, from a width of the candidate line in a horizontal direction of the image and an angle of the candidate line relative to a vertical direction of the image;

a boundary line characteristics calculation unit that calculates a probability of the candidate line as being the boundary line to be higher, as the candidate line has a large degree of having characteristics as a boundary line; and

a boundary line recognition unit that integrates the probabilities calculated by the boundary line characteristics calculation section, in respect of a plurality of the characteristics to recognize the boundary line,

wherein the plurality of the characteristics of the boundary line include that a ratio of the apparent thickness calculated by the width calculation section, to a blur degree of the image is larger than a predetermined value, and

wherein the boundary line characteristics calculation unit calculates the probability to be lower, as the ratio of the apparent thickness to the blur degree of the image is smaller.

2. The boundary line recognition apparatus according to claim 1, wherein the boundary line characteristics calculation unit calculates the probability to be a predetermined minimum probability, when the ratio of the apparent thickness to the blur degree of the image is smaller than the predetermined value.

3. The boundary line recognition apparatus according to claim 1, wherein the boundary line characteristics calculation section calculates the probability to be a predetermined maximum probability, when the ratio of the apparent thickness to the blur degree of the image is larger than a predetermined maximum value that is set to be larger than the predetermined value.

4. The boundary recognition apparatus according to claim 1, wherein a blur degree of the image is a predetermined width of a primary differential distribution calculated by first-differentiating a luminance of surroundings that include the candidate edge points in a horizontal direction of the image.

5. The boundary line recognition apparatus according to claim 1, wherein a blur degree of the image is a width where luminance of from a first predetermined value to a second predetermined value that is larger than the first predetermined value is distributed in a luminance distribution of surroundings that include the candidate edge points distributed in a horizontal direction of the image.

6. The boundary line recognition apparatus according to claim 1, wherein a blur degree of the image is a conversion value obtained by converting a specification value of an amount of blurring of a lens possessed by the camera into a length on the image.

7. The boundary line recognition apparatus according to claim 6, wherein:

the vehicle includes a rain detecting means and a fog detecting means; and

when rain or fog is detected by the rain detecting means and the fog detecting means, the conversion value of a specification value of the amount of blurring is corrected to be a larger value then when the rain or the fog is not detected.

8. The boundary line recognition apparatus according to claim 1, wherein the boundary line characteristics calculation unit calculates the probability to be a predetermined minimum probability, when the ratio of the apparent thickness to the blur degree of the image is smaller than the predetermined value.

9. The boundary line recognition apparatus according to claim 1, wherein the boundary line characteristics calculation section calculates the probability to be a predetermined maximum probability, when the ratio of the apparent thickness to the blur degree of the image is larger than a predetermined maximum value that is set to be larger than the predetermined value.

10. The boundary line recognition apparatus according to claim 1, further comprising:

a vote calculation section configured to minimize the probability of the candidate line as being a boundary line if the number of votes through Hough transform is smaller than a predetermined number;

an edge intensity calculation section configured to minimize the probability of the candidate line as being a boundary line if the candidate line has, as signal intensities, an edge intensity smaller than a predetermined value; and

a branch road determination section configured to minimize the probability of the candidate line as being a boundary line if the branch road determination section determines the travel road to be a branch road.