However, the dimension of VCA feature is proportional to the number of targets, which may result in unfeasibility for HRRP-based RATR. Motivated by such an issue, a novel recognition method based on SVCA is proposed.
Section 3 discusses the proposed method and its application to HRRP-based RATR. In Section 4, experiments with simulated data and real data are carried out to evaluate the recognition performances of the proposed method.
Thus, how to reduce the computational complexity and achieve good performance are two most important tasks for HRRP-based RATR. As can be seen from (1), the dimension of the VCA feature increases proportionally with the number of targets.
Obviously, parallel implementation mode is much more computationally efficient, so it is selected for real-time RATR in this paper.