Initiation and tracking of dim target via fusion of feature probabilities with CNN-UM

CNN-UM-based automatic target initiation and tracking algorithm with the fusion of feature probabilities has been developed. The probability for each feature is created in the region of influence depending on the reliability and the strength of the feature. For computing the confidence of target, a fusion algorithm employing products of weighted sums of feature probabilities is proposed. New target initiation is done through the temporal accumulation of such confidence and the target decision is done with the confidence value obtained through the probability fusion. Due to the utilization of multiple features of target, robustness of target detection is possessed. On-chip experimental results are included in this paper.