ISAR Target Recognition Method Based on Time-Frequency Two-Dimensional Joint Domain Adversarial Learning Network

Based on the analysis of measured aircraft target data obtained by inverse synthetic aperture radar, an ISAR target recognition method based on a time-frequency two-dimensional joint-domain adversarial learning network is proposed. Time-frequency analysis is first used to map the signal into the time-frequency two-dimensional space to visualize the change of the Doppler frequency of the key components of the aircraft over time. Then the deep adversarial learning network is used to extract the deep features of ISAR targets in the time-frequency domain, which has a strong ability to fit the real distribution of the data, and improves the diversity of the samples and the generalization ability of the recognition network to a certain extent. In this paper, conventional narrowband radar measured data are processed to verify the effectiveness of the proposed ISAR target recognition method.