Vehicle and lane mark recognition apparatus

• US 7,965,870 B2
• Filed: 06/23/2006
• Issued: 06/21/2011
• Est. Priority Date: 07/06/2005
• Status: Expired due to Fees

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Mori, Naoki, Kobayashi, Sachio, Aoki, Tomoyoshi, Nakamori, Takuma
• Primary Examiner(s): Lu; Tom Y
• Assistant Examiner(s): Conway; Thomas A
• Application Number:
  US11/994,940
• Publication Number:
  US 20090123065A1
• Time in Patent Office: 1,824 Days
• Field of Search: None
• US Class Current: 382/104
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: G06V 10/28 Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
• 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
• CPC Class Codes: G08G 1/167 Driving aids for lane monitoring, lane changing, e.g. blind spot detection

Abstract

A lane mark recognition apparatus includes an image capturing means (30) which captures a color image (IM_—0) of a road via a color video camera (10), a specific-color-extracted image generating means (31) which generates a luminance-extracted image (IM_—1) obtained by extracting white-color data from the color image (IM_—0) and a yellow-color-extracted image (IM_—2) obtained by extracting yellow-color data from the color image (IM_—0), and a lane mark detection means (50a) which detects a white line and a yellow line from a composite image (IM_C) formed from the luminance-extracted image (IM_—1) and the yellow-color-extracted image (IM_—2) and outputs position data (Pd1) of the white line and position data (Pd2) of the yellow line.

Claims

1. A vehicle comprising:

an imaging means;

an image capturing means which captures a color image of a road via the imaging means;

a specific-color-extracted image generating means which generates a plurality of specific-color-extracted images by performing a process of generating a specific-color-extracted image, which is obtained by extracting pixels of a specific color corresponding to the color of a lane mark in the road from the color image, with respect to a plurality of specific colors; and

a lane mark detection means which detects the lane marks of the specific colors from a composite image based on the plurality of specific-color-extracted images generated by the specific-color-extracted image generating means.

2. The vehicle according to claim 1, wherein the lane mark detection means generates the composite image by performing a process of adding data of a level equal to or higher than a threshold value for determining whether the specific color is a first specific color in a first specific-color-extracted image, in the case where a corresponding pixel in a specific-color-extracted image other than the first specific-color-extracted image has a specific color, for data of each pixel in the first specific-color-extracted image;

the first specific-color-extracted image, which is obtained by extracting pixels of the first specific color, among the plurality of specific-color-extracted images generated by the specific-color-extracted image generating means.

3. The vehicle according to claim 1, wherein the lane mark detection means generates the composite image by performing a process of comparing data levels of corresponding pixels between the first specific-color-extracted image, which is obtained by extracting the first specific-color data, among the plurality of specific-color-extracted images generated by the specific-color-extracted image generating means and a level-matched image;

the level-matched image, which is obtained by matching the data level of the pixel of the specific color in the specific-color-extracted image other than the first specific-color-extracted image to the data level of the pixel of the first specific color in the first specific-color-extracted image, and considering data of the highest level as data of the corresponding pixel in the composite image.

4. A lane mark recognition apparatus, comprising:

an image capturing means which captures a color image of a road via an imaging means;

a specific-color-extracted image generating means which generates a plurality of specific-color-extracted images by performing a process of generating a specific-color-extracted image, which is obtained by extracting pixels of a specific color corresponding to the color of a lane mark in the road from the color image, with respect to a plurality of specific colors; and

a lane mark detection means which detects the lane marks of the specific colors from a composite image based on the plurality of specific-color-extracted images generated by the specific-color-extracted image generating means.

5. The lane mark recognition apparatus according to claim 4, wherein the lane mark detection means generates the composite image by performing a process of adding data of a level equal to or higher than a threshold value for determining whether the specific color is a first specific color in a first specific-color-extracted image, in the case where a corresponding pixel in a specific-color-extracted image other than the first specific-color-extracted image has a specific color, for data of each pixel in the first specific-color-extracted image;

the first specific-color-extracted image, which is obtained by extracting pixels of the first specific color, among the plurality of specific-color-extracted images generated by the specific-color-extracted image generating means.

6. The lane mark recognition apparatus according to claim 4, wherein the lane mark detection means generates the composite image by performing a process of comparing data levels of corresponding pixels between the first specific-color-extracted image, which is obtained by extracting the first specific-color data, among the plurality of specific-color-extracted images generated by the specific-color-extracted image generating means and a level-matched image;

the level-matched image, which is obtained by matching the data level of the pixel of the specific color in the specific-color-extracted image other than the first specific-color-extracted image to the data level of the pixel of the first specific color in the first specific-color-extracted image, and considering data of the highest level as data of the corresponding pixel in the composite image.