Method and system for classifying painted road markings in an automotive driver-vehicle-asistance device
An automated, computerized method is provided for processing an image. The method includes the steps of arranging a digital camera on a vehicle body, operating the digital camera to provide an image file depicting an image of a scene related to vehicle operation on a road, in a computer memory, receiving from the memory the image file depicting pixels of an image of the scene related to vehicle operation on a road, and using an analysis of the pixels to generate an illumination invariant image of the scene. The illumination-invariant image is converted to a grayscale image and the grayscale image is then converted to an illumination-invariant color image.
1. For use in a vehicle, an automated, computerized method for processing an image, comprising the steps of:
receiving from a digital camera mounted on the vehicle, an image file depicting pixels of an image of a scene related to vehicle operation on a road, each one of the pixels having N band color values;
using a pixel analysis to generate an illumination-invariant image representation of the image based upon the N color bands of the pixels and as a function of a BIDR model, wherein the pixel analysis according to the BIDR model is based upon an estimate of lit road color;
converting the illumination-invariant image representation to an illumination-invariant grayscale image; and
converting the grayscale image to an illumination-invariant color image by calculating a fully lit intensity, for each pixel of the input image, as a function of the illumination-invariant grayscale image and adjusting each pixel of the N band color value image along an orientation according to the BIDR model, to an intensity that matches the calculated intensity value for the pixel, such that each pixel of the illumination-invariant color image is at an intensity set according to an intensity of a corresponding pixel of the grayscale image and having a color set to a color calculated as a function of the N color bands of a corresponding pixel of the image, adjusted to remove color shift caused by an interplay of incident and ambient illumination, according to the BIDR model.
2. A computer program product, disposed on a non-transitory computer readable media, the product including computer executable process steps operable to control a computer to:
receive from a digital camera mounted on a vehicle, a series of image files, to depict a road video comprising the series of image files, each one of the image files depicting pixels of an image of a scene related to vehicle operation on a road, each one of the pixels having N band color values;
for each one of a preselected number of the series of image files:
use a pixel analysis to generate an illumination-invariant image representation of the image based upon the N color bands of the pixels and as a function of a BIDR model, wherein the pixel analysis according to the BIDR model is based upon an estimate of lit road color;
convert the illumination-invariant image representation to an illumination-invariant grayscale image; and
convert the grayscale image to an illumination-invariant color image by calculating a fully lit intensity, for each pixel of the input image, as a function of the illumination-invariant grayscale image and adjusting each pixel of the N band color value image along an orientation according to the BIDR model, to an intensity that matches the calculated intensity value for the pixel, such that each pixel of the illumination-invariant color image is at an intensity set according to an intensity of a corresponding pixel of the grayscale image and having a color set to a color calculated as a function of the N color bands of a corresponding pixel of the image, adjusted to remove color shift caused by an interplay of incident and ambient illumination, according to the BIDR model.