Vehicle interior classification system and method

A system for determining a classification of an object of interest relating a vehicle, comprising:

• an image capture device disposed at a vehicle and having a field of view and operable to acquire an image;
• an image capture subsystem operable to process the image to limit the dynamic range of the image to obtain a resultant image that comprises at least one region of interest, which encompasses a region of the field of view that is less than the field of view of the image capture device;
• wherein said image capture subsystem processes image data of the resultant image with a two dimensional complex discrete wavelet transform to produce a selected set of coefficients related to features in the acquired resultant image;
• an image feature extractor operable to process image data representative of said at least one region of interest to extract information relating to a set of image features from the acquired resultant image while not processing image data outside of said at least one region of interest, in order to produce for the resultant image a set of values corresponding to features in the resultant image;
• a classifier operable to combine the set of values produced by the image feature extractor with a predetermined set of classification values, each classification value corresponding to a different possible predefined classification, the results of the combination representing the probability that each predefined classification is the current classification, the classifier operable to select and output the most probable classification;
• and
• wherein the results of the combination comprise a set of weights for each defined classification, the weights being multiplied with the set of coefficients to produce a score for each defined classification, the defined classification with the highest produced score being the most probable classification selected and output by the classifier.