The effective detection for small targets in low SNR images has becoming a hot research field these years.Bayes Target Detection Technique based on position,velocities of the moving point ,one can predict the possible target area in the next frame of image. To accomplish this task one can employ association methods and target's initial information. Then the tracker based upon these information uses Kalman filter predict the target's following states.The paper study Bayes mode, The data flow is bi-directional predicted state and its associated covariance: the tracker suggests the detector where to look for measurements and the detector returns what it finds. It better than NP, The latter threshold is fixed , The former is not. |