Targets track predicting of IR image by CMAC

The centroid and attitude of target must by predicted in target tracking of IR image for increasing capture probability. CMAC estimator can effectually resolve conflict between operational counts and predicting precision. CMAC estimator is trained with a linear model, then the centroid and attitude are predicted. It is trained once by actual error in each frame to reduce the estimate error. CMAC has excellent predicting precision and small operational counts, it adapts to real-time processing for target tracking. The experimental results show that CMAC can accurately estimate the centroid and attitude of target. It adapts to change of model and has robustness.