Boundary line recognition apparatus

Abstract

In a boundary line recognition apparatus, a boundary line candidate extracting part extracts boundary line candidates from image data obtained by an on-vehicle camera based on known image processing such as pattern matching and Hough transform. One or more kinds of boundary line feature calculating parts calculate one or more likelihoods of each boundary line candidate. The likelihood indicates a degree of probability to be the boundary line. A boundary line feature combining means multiplies the likelihoods of each boundary line candidate and outputs a combined likelihood. A boundary line candidate selecting part selects the boundary line candidate having a maximum likelihood as the boundary line. The boundary line feature calculating part further calculates the likelihood of the boundary line candidate using a dispersion of brightness and an internal edge amount, and changes the likelihood based on an additional likelihood obtained by a driving lane surface feature extracting part.

What is claimed is: 
     
         1 . A boundary line recognition apparatus comprising:
 an on-vehicle camera configured to acquire an image of an area around a vehicle and to output image data;   a boundary line candidate extracting processor extracting one or more boundary line candidates which are present on a driving lane of the vehicle from the image data obtained by the on-vehicle camera;   a driving lane surface feature extracting processor extracting, from the image data obtained by the on-vehicle camera, a feature containing a first pattern of an area outside of a subject boundary line candidate, and a feature containing a second pattern of the subject boundary line candidate, wherein the subject boundary line candidate is part of the one or more boundary line candidates;   a boundary line feature calculating processor calculating a likelihood which represents a degree of probability that the subject boundary line candidate is a boundary line on the driving lane, wherein the boundary line feature calculating processor decreases the likelihood of the subject boundary line candidate when a difference between the first pattern and the second pattern is not more than a predetermined value, and the likelihood is calculated for each of the one or more boundary line candidates; and   a boundary line selecting processor selecting a final boundary line candidate having a maximum likelihood as the boundary line on the driving lane from among the one or more boundary line candidates.   
     
     
         2 . The boundary line recognition apparatus according to  claim 1 , further comprising an edge feature extracting processor extracting from the image data obtained by the on-vehicle camera, a total edge amount of an area outside of the subject boundary line candidate on the driving lane, and a total edge amount of the subject boundary line candidate,
 wherein the boundary line feature calculating processor decreases the likelihood of the subject boundary line candidate when a difference in the total edge amount of the area outside of the subject boundary line candidate and the total edge amount of the subject boundary line candidate is a predetermined value.   
     
     
         3 . The boundary line recognition apparatus according to  claim 1 , further comprising a traffic sign detecting processor detecting a traffic sign painted on the driving lane of the vehicle from the image data obtained by the on-vehicle camera, wherein the boundary line feature calculating processor decreases the likelihood of the subject boundary line candidate when the traffic sign detecting processor detects a traffic sign. 
     
     
         4 . The boundary line recognition apparatus according to  claim 1 , further comprising a pair-boundary line candidate detecting processor detecting a presence of a pair of boundary line candidates, placed at both sides of the vehicle in the driving direction on the driving lane of the vehicle, in the one or more boundary line candidates extracted by the boundary line candidate extracting processor,
 wherein the boundary line feature calculating processor decreases the likelihood of the subject boundary line candidate placed in an area between the pair of boundary line candidates detected by the pair-boundary line candidate detecting processor when the pair-boundary line candidate detecting processor detects the pair of boundary line candidates.   
     
     
         5 . The boundary line recognition apparatus according to  claim 1 , wherein the feature containing the first pattern and the feature containing the second pattern do not include a brightness of the first and second patterns.