Abstract
To improve the accuracy of Low Probability of Intercept (LPI) radar emitter signal identification at low Signal-to-Noise Ratio (SNR), we propose a new approach for LPI radar signal recognition with feature fusion based on time-frequency (T-F) transform. First, Choi-Williams distribution (CWD) and ambiguity function (AF) are used to convert the radar signals to T-F images, respectively. Then the fusion texture features of the preprocessed T-F images are extracted by gray level-gradient co-occurrence matrix (GLGCM). Finally, the recognition of the LPI radar emitter signal is realized by a Support Vector Machine (SVM). As shown in the simulation, the overall average recognition accuracy rate of eight radar signal modulation types reaches 91 % at SNR of - 6dB. The results demonstrate the good performance and feasibility of the proposed method under low SNR.
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
