Vehicle-Use Image Processing System, Vehicle-Use Image Processing Method, Vehicle-Use Image Processing Program, Vehicle, and Method of Formulating Vehicle-Use Image Processing System

• US 20080317282A1
• Filed: 03/16/2006
• Published: 12/25/2008
• Est. Priority Date: 03/22/2005
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Unoura, Kiyozumi
• Granted Patent: US 7,920,721 B2
• Time in Patent Office: Days
• US Class Current: 382/103
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• 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

Abstract

A system or the like capable of detecting lane marks more accurately by preventing false lane marks from being erroneously detected as true lane marks. A vehicle-use image processing system (100) allows a “road surface cluster” to be extracted from the “histogram” of luminance of each pixel in a “reference area” in a road surface image. Among “primary lane mark candidates,” those that overlap the “reference area” are detected as “secondary lane mark candidates.” Among the “secondary lane mark candidates,” those that have “luminance parameter” values falling within the luminance range of the “road surface cluster” are not detected as true lane marks. Thereby, lane marks are prevented from being erroneously detected (erroneous detection). This allows only lane marks to be detected more accurately.

Claims

1. A vehicle-use image processing system which performs image processing on the basis of a road surface image captured by an imaging device mounted on a vehicle, comprising:

a reference area setting unit which sets a reference area corresponding to a road surface portion other than a lane mark in the road surface image captured by the imaging device;

a histogram preparing unit which prepares a histogram by measuring the frequency of luminance of each pixel of the road surface image in the reference area set by the reference area setting unit;

a road surface cluster extracting unit which extracts a cluster of portions, which are equal to or higher than a threshold value in width, height, or area, as a road surface cluster from the histogram prepared by the histogram preparing unit;

a lane mark candidate detecting unit which detects a lane mark candidate on the basis of the road surface image captured by the imaging device;

a luminance parameter calculating unit which calculates luminance parameters based on the luminance of the lane mark candidate detected by the lane mark candidate detecting unit; and

a lane mark detecting unit which detects a lane mark candidate whose luminance parameters calculated by the luminance parameter calculating unit fall within the luminance range of the road surface cluster extracted by the road surface cluster extracting unit as a false lane mark, while detecting a lane mark candidate whose luminance parameters calculated by the luminance parameter calculating unit fall off the luminance range of the road surface cluster extracted by the road surface cluster extracting unit as a true lane mark.

2. A vehicle-use image processing system according to claim 1, wherein the reference area setting unit sets an area whose left and right are defined by a pair of offset lines, which are offset closer to the center of the lane than a pair of true lane marks detected by the lane mark detecting unit, as the reference area.

3. A vehicle-use image processing system according to claim 1, wherein the reference area setting unit sets the reference area whose top and bottom are defined by lines offset from the upper edge and lower edge of the road surface image, respectively.

4. A vehicle-use image processing system according to claim 1, wherein the road surface cluster extracting unit extracts a cluster having a shape whose middle part is higher than both ends as a primary road surface cluster candidate from the histogram prepared by the histogram preparing unit and extracts a primary road surface cluster candidate which is equal to or higher than the threshold value in area as the road surface cluster.

5. A vehicle-use image processing system according to claim 4, wherein, if both ends of a plurality of the primary road surface cluster candidates overlap each other and a valley portion generated in the overlap region is shallow in view of the noise components included in the histogram, the road surface cluster extracting unit integrates and extracts the plurality of primary road surface cluster candidates as one secondary road surface cluster candidate and then extracts a secondary road surface cluster candidate which is equal to or higher than a threshold value in area as the road surface cluster.

6. A vehicle-use image processing system according to claim 1, wherein:

the lane mark candidate detecting unit is composed of a primary lane mark candidate detecting unit which detects all lane mark candidates as primary lane mark candidates and a secondary lane mark candidate detecting unit which detects primary lane mark candidates whose distance from a point on the center line of a vehicle traffic lane is equal to or lower than a threshold value out of the primary lane mark candidates detected by the primary lane mark candidate detecting unit as secondary lane mark candidates; and

the luminance parameter calculating unit calculates luminance parameters based on the luminance of the secondary lane mark candidates detected by the secondary lane mark candidate detecting unit.

7. A vehicle-use image processing system according to claim 2, wherein:

the lane mark candidate detecting unit is composed of a primary lane mark candidate detecting unit which detects all lane mark candidates as primary lane mark candidates and a secondary lane mark candidate detecting unit which detects primary lane mark candidates which overlap the reference area set by the reference area setting unit out of the primary lane mark candidates detected by the primary lane mark candidate detecting unit as secondary lane mark candidates; and

the luminance parameter calculating unit calculates luminance parameters based on the luminance of the secondary lane mark candidates detected by the secondary lane mark candidate detecting unit.

8. A vehicle-use image processing system according to claim 7, wherein the luminance parameter calculating unit calculates the luminance parameters based on the luminance of the portions overlapping the reference area set by the reference area setting unit out of the secondary lane mark candidates detected by the secondary lane mark candidate detecting unit.

9. A vehicle-use image processing system according to claim 1, wherein, if the lane mark candidate detecting unit detects no lane mark candidate, the lane mark detecting unit detects the lane marks detected earlier as true lane marks.

10. A vehicle-use image processing system according to claim 1, wherein the lane mark candidate detecting unit detects edges or edge points of the lane marks closer to the center of the lane as lane mark candidates.

13. A method of downloading a part or all of the vehicle-use image processing program according to claim 12 to an in-vehicle computer in order to set up the vehicle-use image processing system according to claim 1.

14. A vehicle in which a vehicle-use image processing system according to one of claims 1 to 10.

11. A vehicle-use image processing method of performing image processing on the basis of a road surface image captured by an imaging device mounted on a vehicle, comprising:

a reference area setting step of setting a reference area corresponding to a road surface portion other than a lane mark in the road surface image captured by the imaging device;

a histogram preparing step of preparing a histogram by measuring the frequency of luminance of each pixel of the road surface image in the reference area set in the reference area setting step;

a road surface cluster extracting step of extracting a cluster of portions, which are equal to or higher than a threshold value in width, height, or area, as a road surface cluster from the histogram prepared in the histogram preparing step;

a lane mark candidate detecting step of detecting a lane mark candidate on the basis of the road surface image captured by the imaging device;

a luminance parameter calculating step of calculating luminance parameters based on the luminance of the lane mark candidate detected in the lane mark candidate detecting step; and

a lane mark detecting step of detecting a lane mark candidate whose luminance parameters calculated in the luminance parameter calculating step fall within the luminance range of the road surface cluster extracted in the road surface cluster extracting step as a false lane mark, while detecting a lane mark candidate whose luminance parameters calculated in the luminance parameter calculating step fall off the luminance range of the road surface cluster extracted in the road surface cluster extracting step as a true lane mark.

12. A vehicle-use image processing program for giving functions of performing image processing on the basis of a road surface image captured by an imaging device mounted on a vehicle, wherein the program gives the computer:

a reference area setting function of setting a reference area corresponding to a road surface portion other than a lane mark in the road surface image captured by the imaging device;

a histogram preparing function of preparing a histogram by measuring the frequency of luminance of each pixel of the road surface image in the reference area set by the reference area setting function;

a road surface cluster extracting function of extracting a cluster of portions, which are equal to or higher than a threshold value in width, height, or area, as a road surface cluster from the histogram prepared by the histogram preparing function;

a lane mark candidate detecting function of detecting a lane mark candidate on the basis of the road surface image captured by the imaging device;

a luminance parameter calculating function of calculating luminance parameters based on the luminance of the lane mark candidate detected by the lane mark candidate detecting function; and

a lane mark detecting function of detecting a lane mark candidate whose luminance parameters calculated by the luminance parameter calculating function fall within the luminance range of the road surface cluster extracted by the road surface cluster extracting function as a false lane mark, while detecting a lane mark candidate whose luminance parameters calculated by the luminance parameter calculating function fall off the luminance range of the road surface cluster extracted by the road surface cluster extracting function as a true lane mark.