Integrating Lo cal Binary Patterns into Normalized Moment of Inertia for Up dating Tracking Templates

摘要

This paper presents an efficient visual tracking framework which is robust to rotation, scale vari-ation and occlusion. The target template is characterized by Local binary patterns (LBP), which exhibit invariance to rotation. The LBP features are then integrated into the Normalized moment of inertia (NMI) to decide whether the template requires update. This procedure enables an adaptive tem plate m atching strategy which addresses the tracking failures arising from scale variations. Kalman fil-tering is exploited for predicting the tra jectory of the tar-get when it is occluded. The matching efficiency is achieved by applying a locally pyramid searching scheme. Experi-m ental results validate the efficiency and effectiveness of our tracking framework.