Method and system for classifying painted road markings in an automotive driver vehicle-assistance device

摘要

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. A further process step includes using the illumination invariant image to analyze the road scene for painted road markings.

主权项

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, 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: transforming the N bands to log color space values in a log color space; generating a log chromaticity plane in the log color space; identifying a dominant orientation for orienting the log chromaticity plane in the dominant orientation, according to a BIDR model; and calculating a confidence level for the dominant orientation; for each remaining image file of the series of image files: transforming the N bands to log color space values in a log color space; generating a log chromaticity plane in the log color space; and identifying a dominant orientation for orienting the log chromaticity plane in the dominant orientation, according to a BIDR model, by calculating a best current estimate for the dominant orientation as a function of the confidence levels calculated for the preselected number of the series of image files; for each image file: projecting the log color space values to the log chromaticity plane to provide chromaticity representation values corresponding to the pixels of the image; and using the chromaticity representation values corresponding to the pixels to generate an illumination invariant image of the scene.