摘要 |
A method for vehicle identification to determine at least one vehicle characteristic, comprising: obtaining an input image (301) of the vehicle from an image source (101); normalisation of the input image (301) of the vehicle in a normalisation unit (103, 104) to obtain a normalized image; determining the vehicle characteristic in a classification unit (111, 112) by comparing parameters of a normalised image obtained in a parametrisation unit (107, 108) with parameters of reference images obtained from a reference database (113, 114). Normalisation in the normalisation unit (103, 104) comprises the steps of: detecting a registration plate area (303) within the input image (301); processing the input image (301) basing on normalisation attributes defining at least one scaling coefficient (znorm, anorm, vnorm); choosing from the scaled image (307) a RoI area (308) of a normalised size and location dependent on the location of the registration plate area (303); and presenting data from the RoI area (308) as a normalised image (311). |
主权项 |
1. A method for vehicle type identification to determine at least one vehicle characteristic, the method comprising:
obtaining an input image of the vehicle from an image source; normalization of the input image of the vehicle in a normalization unit to obtain a normalized image by;
reading normalization attributes (znorm, anorm, vnorm) from a unit for calibration of normalization attributes;detecting a registration plate area within the input image processing the input image basing on normalization attributes defining at least one scaling coefficient (znorm, anorm, vnorm);choosing from the scaled image a RoI area of a normalized size and location dependent on the location of the registration plate area;and presenting data from the RoI area as a normalized image; and determining the vehicle characteristic in a classification unit by comparing parameters of a normalized image obtained in a parameterization unit with parameters of reference images obtained from a reference database;wherein:
the parameters of normalized image are obtained in the parameterization unit by:
performing a smoothing filtration of the normalized image to obtain a smoothed image (Ii);determining oriented gradient images (Oi,j) of brightness change for the smoothed image (Ii) in different directions (j);dividing the oriented gradient images (Oi,j) into blocks (Bi,j,n);determining a column vector (vi,n) having R dimensions and defined as
vi,n=[∇(Bi,0,n), . . . , ∇(Bi,j,n)]reducing dimension of the column vector (vi,n) by left multiplication by a casting matrix Pi,n having S dimensions, wherein S is lower than R to obtain a column vector c(I)i,n defined as:
c(I)i,n=Pi,n·*vi,n providing the column vector c as the output of the parameterisation unit describing parameters of the normalized image. |