Target tracking system using optical JTC peaks and Hopfield networks

Because the performance of a target tracking system is heavily dependent on the dimension of the target feature space, we propose a more advanced OptoNeural target tracking system based on the correlation peak values as well as the correlation position data of optical joint transform correlator (JTC) as the components of the target state variables, and the constant velocity model of Kalman filter and Hopfield networks for optimizing the data association constraints. From the computer simulation, it is shown that the new approach can reduce the mean square tracking error by 20% compared with the conventional approach.