Classification and Recognition Method of Non-Cooperative Object Based on Transfer Learning.

• Simulation modeling and experimental testing of space non-cooperative targets. • The difficulty of micro-Doppler feature extraction under small data size increases. • Efficient use of similar features between simulated and experimental data. • Make the most of a small amount of experimental data. Classifying and identifying non-cooperative targets plays an important role in space missions in the present age. A micro-Doppler characteristic signal is an effective means to identify the target. In order to better extract the micro-Doppler features of the target in the case of very little experimental data, a pose recognition network based on the theory of transfer learning is proposed. The source domain dataset is constructed of the time–frequency spectrums obtained by short-time Fourier transform of the simulated echo signals. The time–frequency spectrums from experiment are made as target domain. Pre-training and domain adaptation is applied in this work. Finally, the test results demonstrate that the classification accuracy of our pose recognition network based on transfer learning is improved due to the good use of simulation data and the small amount of experimental data. [ABSTRACT FROM AUTHOR]