Wavelet transform-based hierarchical active shape model for object tracking

This paper proposes a hierarchical approach to the active shape model (ASM) using a wavelet transform. Local structure model fitting in the ASM plays an important role in model-based pose and shape analysis. The proposed algorithm can robustly find good solutions in complex images by using wavelet decomposition. We also describe how to apply Kalman filtering for ASM-based, real-time video tracking. The proposed algorithm has been tested for various sequences containing human motion to demonstrate the improved performance of the proposed object tracking.