Algorithm of Targets Detection Based on Integer Wavelet Transform and Realize on TV Tracking System

This paper presents an approach of detecting small targets based on integer wavelet transform and realize algorithm on hardware. The approach uses an integer-type lifting wavelet transform and the proposed approach doesn´t extract patterns similar to a template, but finds parts having the same feature in the targets. We utilize one of integer-type lifting wavelet transforms that contains rounding-off arithmetic for mapping integers to integers. The lifting term contains parameters that are learned by using standard training images of targets. We assume that the targets include many high frequency components. In order to obtain the features of the targets, the lifting parameters are determined by a condition that high frequency components are vanished in wavelet transform. The advantage of using integer-type wavelet transform is simple and robust to noise. Simulation illustrated the method can detect and track the moving targets in dim background. We would test our algorithm in the TV tracking system