Texture Cue Based Tracking System Using Wavelet Transform and a Fuzzy Grammar

This paper addresses a system for fast object tracking based on texture cues, by using the wavelet transform and a fuzzy grammar classifier. The method is based on wavelet type features. The feature vector consists of 6 characteristics extracted from the wavelet detail images for each colour component. These texture characteristics automatically generate a fuzzy rule using a fuzzy inference classifier based on a fuzzy grammar. A learning phase is required for each texture but only uses one sample. This 2D tracking system of textured objects in image sequences is demonstrated on a robotic application using the platform developed by Sony-AIBO robot. The application ensures a real time tracking approach and can be parameterized in order to be flexible in face of different types of textures.