Advantages of using a space filling curve for computing wavelet transforms of road traffic images

Abstract

The properties of computing wavelet transforms of road traffic image data are discussed. It is proposed to incorporate a Hilbert scan of image data and a wavelet transform factorised into lifting steps. Scanning an image, in space filling curve order, brings together pixels that are highly correlated. This is a desirable property, because the objects of interest - vehicles - comprise a bounded set of regular patches on an image. Applying a 1-dimensional wavelet transform requires a smaller number of processing steps than a separable two-dimensional transform. Such a solution is suitable for on site microcontroller or FPGA implementation.