Vehicular image processing device and vehicular image processing program

• US 8,681,221 B2
• Filed: 03/24/2009
• Issued: 03/25/2014
• Est. Priority Date: 03/26/2008
• Status: Active Grant

• Current Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Original Assignee: Honda Motor Co., Ltd. (Honda Motor Company)
• Inventors: Sakamoto, Yosuke
• Primary Examiner(s): Patel, Jay Au
• Assistant Examiner(s): Aghevli, Reza
• Application Number:
  US12/922,475
• Publication Number:
  US 20110019000A1
• Time in Patent Office: 1,827 Days
• US Class Current: 348/148
• CPC Class Codes: G06F 18/00 Pattern recognition
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/30256 Lane; Road marking
• CPC Class Codes: G06T 5/00 Image enhancement or restoration
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/60 Analysis of geometric attributes
• 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 vehicular image processing device is provided with a kernel setting unit which sets a plurality of smoothing kernels which have a width supposed to be between the width of the lane mark and that of the road to the image acquired from a photographing unit, a smoothing unit which smoothes the acquired image by filtering using the set smoothing kernels, a variation degree calculating unit which calculates the variation degree of the pixel value of each pixel in the acquired image with respect to the smoothed image, and a pixel value replacing unit which replaces the pixel value of a pixel which is of the acquired image and has the variation degree not greater than a predefined value with a specific value.

Claims

1. A vehicular image processing device configured to process an image acquired from a photographing unit mounted in a vehicle and detect a lane mark on a road where the vehicle is travelling from the processed image, comprising:

a kernel setting unit configured to set a kernel function for smoothing the image acquired from the photographing device so that the width of a smoothed image in a predefined direction is in a predefined range greater than the width of an image portion of the lane mark in the predefined direction;

a smoothing unit configured to smooth the acquired image according to a filtering process by the usage of the kernel function set by the kernel setting unit for each pixel in the image, the smoothing kernel is disposed with the pixel as the central pixel, and the smoothing process is performed;

a variation degree calculating unit configured to calculate, as a pixel value a variation degree, a difference between a pixel value of each pixel in the acquired image and a pixel value of each corresponding pixel in the smoothed image processed by the smoothing unit;

a pixel value replacing unit configured to replace in the smoothed image, for each of the pixels in the acquired image whose pixel value variation degree is equal to or smaller than a predefined value, the corresponding pixel value with a specific value; and

a lane mark detecting unit configured to detect the lane mark from the smoothed image which has been subjected to pixel value replacing by the pixel value replacing unit.

2. The vehicular image processing device according to claim 1, wherein the specific value is a fixed, preset value defined.

3. The vehicular image processing device according to claim 1, wherein the kernel setting unit sets the kernel function in such a way that a size for an image portion in the image corresponded to a predefined area on the road is set smaller as a distance from the vehicle to the predefined area on the road is becoming greater.

4. The vehicular image processing device according to claim 1, wherein the kernel setting unit sets the kernel function such that the smoothed image has a rectangular shape or a trapezoidal shape.

5. The vehicular image processing device according to claim 4, wherein the kernel setting unit sets the kernel function in such a way that the direction of inclination of the center line of the long side of the smoothed image with respect to the direction corresponded to the travelling direction of the vehicle in the smoothed image is equal to a predefined angle.

6. The vehicular image processing device according to claim 1, wherein the variation degree calculating unit calculates, as the pixel value variation degree, either the difference of pixel value of each pixel obtained by subtracting the pixel value of each pixel in the smoothed image from the pixel value of each pixel in the acquired image or a ratio of pixel value of each pixel obtained by dividing the pixel value of each pixel in the acquired image by the pixel value of each pixel in the smoothed image as the variation degree.

7. The vehicular image processing device according to claim 1, wherein luminance is used as the pixel value in the smoothed image processed by the smoothing unit.

8. The vehicular image processing device according to claim 1, wherein luminance or saturation calculated from color components of a color image is used as the pixel value in the smoothed image processed by the smoothing unit.

9. The vehicular image processing device according to claim 2, wherein the lane mark detecting unit detects an area composed of pixels whose pixel values have not been replaced by the pixel value replacing unit as an image portion corresponded to the lane mark on the road where the vehicle is travelling.

14. The vehicular image processing device according to claim 2, wherein the kernel setting unit sets the kernel function in such a way that a size for an image portion in the image corresponded to a predefined area on the road is set smaller as a distance from the vehicle to the predefined area on the road is becoming greater.

15. The vehicular image processing device according to claim 2, wherein the kernel setting unit sets the kernel function such that the smoothed image has a rectangular shape or a trapezoidal shape.

16. The vehicular image processing device according to claim 2, wherein the variation degree calculating unit calculates, as the pixel value variation degree, either the difference of pixel value of each pixel obtained by subtracting the pixel value of each pixel in the smoothed image from the pixel value of each pixel in the acquired image or a ratio of pixel value of each pixel obtained by dividing the pixel value of each pixel in the acquired image by the pixel value of each pixel in the smoothed image as the variation degree.

17. The vehicular image processing device according to claim 2, wherein luminance is used as the pixel value in the smoothed image processed by the smoothing unit.

18. The vehicular image processing device according to claim 1, wherein the smoothing unit sets the average of all pixel values contained in the range of the smoothing kernel equal to the value of the central pixel.

10. A vehicle which is provided with a photographing unit and has a function of processing an image acquired from the photographing unit and detecting a lane mark on a road where the vehicle is travelling, comprising:

a kernel setting unit configured to set a kernel function for smoothing the image acquired from the photographing device so that the width of a smoothed image in a predefined direction is in a predefined range greater than the width of an image portion of the lane mark in the predefined direction;

a smoothing unit configured to smooth the acquired image according to a filtering process by the usage of the kernel function set by the kernel setting unit for each pixel in the image, the smoothing kernel is disposed with the pixel as the central pixel, and the smoothing process is performed;

a variation degree calculating unit configured to calculate, as a pixel value a variation degree, a difference between a pixel value of each pixel in the acquired image and a pixel value of each corresponding pixel in the smoothed image processed by the smoothing unit;

a pixel value replacing unit configured to replace in the smoothed image, for each of the pixels in the acquired image whose pixel value variation degree is equal to or smaller than a predefined value, the corresponding pixel value with a specific value; and

a lane mark detecting unit configured to detect the lane mark from the smoothed image which has been subjected to pixel value replacing by the pixel value replacing unit.

11. The vehicle according to claim 10, wherein the specific value is a fixed, preset value defined.

12. A vehicular image processing program embedded in a non-transitory medium configured to causing a computer to process an image acquired from a photographing unit mounted in a vehicle and detect a lane mark on a road where the vehicle is travelling from the processed image, and the computer being caused to execute:

a kernel setting function of setting a kernel for smoothing the image acquired from the photographing device so that the width of a smoothed image in a predefined direction is in a predefined range greater than the width of an image portion of the lane mark in the predefined direction;

a smoothing function of smoothing the acquired image according to a filtering process by the usage of the kernel set by the kernel setting function for each pixel in the image, the smoothing kernel is disposed with the pixel as the central pixel, and the smoothing function is performed;

a variation degree function of calculating, as a pixel value a variation degree, a difference between a pixel value of each pixel between the acquired image and a pixel value of each corresponding pixel in the image smoothed by the smoothing function;

a pixel value replacing function of replacing in the smoothed image, for each of the pixels in the acquired image whose pixel value variation degree is equal to or smaller than a predefined value, the corresponding pixel value with a specific value; and

a lane mark detecting function of detecting the lane mark from the smoothed image which has been subjected to pixel value replacing by the pixel value replacing function.

13. The vehicular image processing program according to claim 12, wherein the specific value is a fixed, preset value defined.