Method for calibrating vehicular vision system

Abstract

A method for calibrating a vehicular vision system includes providing a camera at a vehicle, with the camera having a field of view. Images are captured with the camera and a set of resultant images are acquired for a classification. Information is extracted related to image features in the set of resultant images, and an appropriate subset of coefficients is determined. For each classification, a classification vector of at least one appropriate weight is stored that corresponds to the determined subset of coefficients. The determined subset of coefficients is determined by processing sets of coefficients produced from a selection of calibration images and determining a subset of coefficients which acceptably discriminate between defined classifications. A set of resultant images is acquired by limiting the dynamic range of acquired images to obtain resultant images that include at least one region of interest.

1 . (canceled) 
     
     
         2 : A method for calibrating a vehicular vision system, said method comprising:
 providing a camera at a vehicle, said camera having a field of view;   capturing images with said camera;   acquiring a set of resultant images;   extracting information related to image features in the set of resultant images;   acquiring a plurality of classifications;   determining a subset of coefficients;   for each classification, storing a classification vector of at least one appropriate weight that corresponds to the determined subset of coefficients;   wherein the determined subset of coefficients is determined by processing sets of coefficients produced from a selection of calibration images and determining a subset of coefficients which acceptably discriminate between defined classifications; and   wherein acquiring a set of resultant images comprises limiting the dynamic range of acquired images to obtain resultant images that comprise at least one region of interest, which encompasses a region of the field of view that is less than the field of view of said camera.   
     
     
         3 : The method of  claim 2 , wherein said camera has a field of view interior of the vehicle. 
     
     
         4 : The method of  claim 3 , wherein the classifications are used to classify an occupancy of a vehicle seat and include (i) adult, (ii) child, (iii) empty seat, (iv) object and (v) child restraint seat. 
     
     
         5 : The method of  claim 4 , wherein, responsive to determining that the extracted information corresponds to one of the classifications, a passenger side airbag control is controlled. 
     
     
         6 : The method of  claim 2 , wherein a feature vector is provided to a classifier that processes the feature vector with a predefined library of calibration vectors corresponding to respective ones of a set of predefined classifications. 
     
     
         7 : The method of  claim 6 , wherein the classifier receives the feature vector and multiplies the feature vector with each of the calibration vectors in the library of calibration vectors to produce a corresponding score per classification, and wherein each of the scores indicates the likelihood that the region of interest has features within a respective one of the defined classifications, and wherein the classification having the highest determined score is then output as the determined classification. 
     
     
         8 : The method of  claim 2 , wherein the set of resultant images comprises images of a region of interest within the field of view of said camera and wherein the region of interest corresponds to the respective classification for that set of resultant images. 
     
     
         9 : The method of  claim 2 , comprising providing occlusion detection to detect an occlusion at least partially occluding the field of view of said camera. 
     
     
         10 : The method of  claim 9 , comprising providing an alert responsive to detection of an occlusion. 
     
     
         11 : The method of  claim 2 , wherein the acquired resultant images comprise images of at least two regions of interest within the field of view of said camera. 
     
     
         12 : The method of  claim 11 , wherein extracting image features in the set of resultant images is performed on the at least two regions of interest. 
     
     
         13 : The method of  claim 12 , wherein images of the set of resultant images are acquired by obtaining a first image illuminated by ambient light and a second image illuminated by ambient light and a second frequency range of light and subtracting the first image from the second image to obtain the resultant images. 
     
     
         14 : A method for calibrating a vehicular vision system, said method comprising:
 providing a camera at a vehicle, said camera having a field of view;   capturing images with said camera;   acquiring a set of resultant images;   wherein the acquired resultant images comprise images of at least two regions of interest within the field of view of said camera;   extracting information related to image features in the set of resultant images;   acquiring a plurality of classifications;   determining a subset of coefficients;   for each classification, storing a classification vector of at least one appropriate weight that corresponds to the determined subset of coefficients;   providing occlusion detection to detect an unacceptable occlusion at least partially occluding the field of view of said camera; and   providing an alert responsive to detection of an occlusion.   
     
     
         15 : The method of  claim 14 , wherein said camera has a field of view interior of the vehicle, and wherein the classifications are used to classify an occupancy of a vehicle seat and include (i) adult, (ii) child, (iii) empty seat, (iv) object and (v) child restraint seat. 
     
     
         16 : The method of  claim 15 , wherein, responsive to determining that the extracted information corresponds to one of the classifications, a passenger side airbag control is controlled, and wherein, responsive to determining that the extracted information is indicative of a child in the seat, actuation of the passenger side airbag is inhibited. 
     
     
         17 : The method of  claim 14 , wherein extracting image features in the set of resultant images is performed on the at least two regions of interest, and wherein images of the set of resultant images are acquired by obtaining a first image illuminated by ambient light and a second image illuminated by ambient light and a second frequency range of light and subtracting the first image from the second image to obtain the resultant images. 
     
     
         18 : A method for calibrating a vehicular vision system, said method comprising:
 providing a camera at a vehicle, said camera having a field of view;   capturing images with said camera;   acquiring a set of resultant images;   wherein the set of resultant images comprises images of a region of interest within the field of view of said camera and wherein the region of interest corresponds to the respective classification for that set of resultant images;   wherein acquiring a set of resultant images comprises limiting the dynamic range of acquired images to obtain resultant images that comprise at least one region of interest, which encompasses a region of the field of view that is less than the field of view of said camera;   extracting information related to image features in the set of resultant images;   acquiring a plurality of classifications;   determining a subset of coefficients;   for each classification, storing a classification vector of at least one appropriate weight that corresponds to the determined subset of coefficients; and   providing a feature vector to a classifier that processes the feature vector with a predefined library of calibration vectors corresponding to respective ones of a set of predefined classifications, and wherein the classifier receives the feature vector and multiplies a copy of feature vector with each of the calibration vectors in the library of calibration vectors to produce a corresponding score per classification, and wherein each of the scores indicates the likelihood that the region of interest has features within a respective one of the defined classifications, and wherein the classification having the highest determined score is then output as the determined classification.   
     
     
         19 : The method of  claim 18 , wherein said camera has a field of view interior of the vehicle, and wherein the classifications are used to classify an occupancy of a vehicle seat and include (i) adult, (ii) child, (iii) empty seat, (iv) object and (v) child restraint seat, and wherein, responsive to determining that the extracted information corresponds to one of the classifications, a passenger side airbag control is controlled, and wherein, responsive to determining that the extracted information is indicative of a child in the seat, actuation of the passenger side airbag is inhibited. 
     
     
         20 : The method of  claim 18 , wherein images of the set of resultant images are acquired by obtaining a first image illuminated by ambient light and a second image illuminated by ambient light and a second frequency range of light and subtracting the first image from the second image to obtain the resultant images. 
     
     
         21 : The method of  claim 18 , wherein the determined subset of coefficients is determined by processing sets of coefficients produced from a selection of calibration images and determining a subset of coefficients which acceptably discriminate between defined classifications.