A whole scheme for aircraft target identification in HRRP

This paper describes the authorspsila efforts in practical high resolution range profile target automatic recognition. The practical high resolution range profile has more difference to simulation results, so this paper presents a novel algorithm to detect and extract the target range profile data and also create a whole scheme to deal with this difference. First it takes OS CAFR and binary accumulation algorithm to detect target. Here we lower self-adapt threshold to get more targets which maybe be false target. Then we use target trace management to remove the illusion target The novel algorithm, called as endpoint detection based on moving window, can get more valuable data to classification. Practical data has more noise and low PSN, so K-mean algorithm can remove the bad data. Due to variation of target high resolution range profile we build a suffice sample set, which require us to use PCA algorithm to reduce the computer time and memory. Classification is N near classifier, which can get a nonlinear classification effect. The test results prove that this scheme can get better recognition results.