Abstract
This paper proposes a new feature learning method for the recognition of radar high resolution range profile (HRRP) sequences. HRRPs from a period of continuous changing aspect angles are jointly modeled and discriminated by a single model named the discriminative infinite restricted Boltzmann machine (Dis-iRBM). Compared with the commonly used hidden Markov model (HMM)-based recognition method for HRRP sequences, which requires efficient preprocessing of the HRRP signal, the proposed method is an end-to-end method of which the input is the raw HRRP sequence, and the output is the label of the target. The proposed model can efficiently capture the global pattern in a sequence, while the HMM can only model local dynamics, which suffers from information loss. Last but not least, the proposed model learns the features of HRRP sequences adaptively according to the complexity of a single HRRP and the length of a HRRP sequence. Experimental results on the Moving and Stationary Target Acquisition and Recognition (MSTAR) database indicate that the proposed method is efficient and robust under various conditions.
Highlights
In the radar automatic target recognition (RATR) community, recognition techniques based on radar high-resolution range profile (HRRP) have been widely studied [1,2,3,4,5]
This paper provides an approach for efficiently recognizing radar HRRP sequences
The model sequences covering the whole aspect angles. It is more flexible and generalizes better than the shows some robustness to the change of angular sampling rate, the results with respect to ClassRBM
Summary
In the radar automatic target recognition (RATR) community, recognition techniques based on radar high-resolution range profile (HRRP) have been widely studied [1,2,3,4,5]. HRRP templates [13], HRRP stochastic modeling [2,3,5], time-frequency transform features [14,15], transform invariant features [16,17] All these feature extraction techniques have their own advantages and disadvantages, none of them is optimal for target recognition. Sensors 2017, 17, 1675 rate is dense, and the interval between adjacent HRRPs is often less than 0.1◦ In this case, the HMM tries to model HRRP sequences in a single frame. The features of the proposed method can be summarized as follows: It is an end-to-end model of which the input is the raw HRRP sequence and the output is the target class. All one-dimensional variables are formatted in italic; All vectors and matrices are formatted in boldface; p(x) represents the probability distribution of x
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
