3-D MODEL BASED METHOD FOR DETECTING AND CLASSIFYING VEHICLES IN AERIAL IMAGERY

摘要

A computer implemented method for determining a vehicle type of a vehicle detected in an image is disclosed. An image having a detected vehicle is received. A number of vehicle models having salient feature points is projected on the detected vehicle. A first set of features derived from each of the salient feature locations of the vehicle models is compared to a second set of features derived from corresponding salient feature locations of the detected vehicle to form a set of positive match scores (p-scores) and a set of negative match scores (n-scores). The detected vehicle is classified as one of the vehicle models models based at least in part on the set of p-scores and the set of n-scores.

主权项

1. A method performed by a processor for detecting presence of a vehicle in one or more images, comprising:
determining a region of interest (ROI) in the one or more images, without a priori knowledge of whether the vehicle is present in the ROI; computing a plurality of sets of image descriptors, each one of the sets of image descriptors corresponding to a location within the ROI; classifying each of the sets of descriptors, using a multi-class classifier comprising a structure of related classifiers for a set of associated vehicle parts, to obtain a likelihood value of whether a vehicle part is present at the location corresponding to the set of descriptors being classified; determining whether the vehicle is likely present within the ROI based on a comparison between a function of the obtained likelihood values and a predetermined threshold value.