High-resolution and reliable automatic target recognition based on photonic ISAR imaging system with explainable deep learning

Automatic target recognition (ATR) based on inverse synthetic aperture radar (ISAR) images, which is extensively utilized to surveil environment in military and civil fields, must be high-precision and reliable. Photonic technologies' advantage of broad bandwidth enables ISAR systems to realize high-resolution imaging, which is in favor of achieving high-performance ATR. Deep learning (DL) algorithms have achieved excellent recognition accuracies. However, the lack of interpretability of DL algorithms causes the head-scratching problem of credibility. In this paper, we exploit the inner relationship between a photonic ISAR imaging system and behaviors of a convolutional neural network (CNN) to deeply comprehend the intelligent recognition. Specifically, we manipulate imaging physical process and analyze network outputs, the relevance between the ISAR image and network output, and the visualization of features in the network output layer. Consequently, the broader imaging bandwidths and appropriate imaging angles lead to more detailed structural and contour features and the bigger discrepancy among ISAR images of different targets, which contributes to the CNN recognizing and distinguishing objects according to physical laws. Then, based on the photonic ISAR imaging system and the explainable CNN, we accomplish a high-accuracy and reliable ATR. To the best of our knowledge, there is no precedent of explaining the DL algorithms by exploring the influence of the physical process of data generation on network behaviors. It is anticipated that this work can not only inspire the accomplishment of a high-performance ATR but also bring new insights to explore network behaviors and thus achieve better intelligent abilities.

Characterization of the frequency response of channel-interleaved photonic ADCs based on the optical time-division demultiplexer

We characterize the frequency response of channel-interleaved photonic analog-to-digital converters (CI-PADCs) theoretically and experimentally. The CI-PADC is composed of a photonic frontend for photonic sampling and an electronic backend for quantization. The photonic frontend includes a photonic sampling pulse generator for directly high-speed sampling and an optical time-division demultiplexer (OTDM) for channel demultiplexing. It is found that the frequency response of the CI-PADC is influenced by both the photonic sampling pulses and the OTDM, of which the combined impact can be characterized through demultiplexed pulse trains. First, the frequency response can be divided into multiple frequency intervals and the range of the frequency interval equals the repetition rate of demultiplexed pulse trains. Second, the analog bandwidth of the CI-PADC is determined by the optical spectral bandwidth of demultiplexed pulse trains which is broadened in the OTDM. Further, the effect of the OTDM is essential for enlarging the analog bandwidth of the CI-PADC employing the photonic sampling pulses with a limited optical spectral bandwidth.

Deep learning scheme for microwave photonic analog broadband signal recovery

In regular microwave photonic (MWP) processing paradigms, broadband signals are processed in the analog domain before they are transformed to the digital domain for further processing and storage. However, the quality of the signals may be degraded by defective photonic analog links, especially in a complicated MWP system. Here, we show a unified deep learning scheme that recovers the distorted broadband signals as they are transformed to the digital domain. The neural network could automatically learn the end-to-end inverse responses of the distortion effects of actual photonic analog links without expert knowledge and system priors. Hence, the proposed scheme is potentially generalized to various MWP processing systems. We conduct experiments by nontrivial MWP systems with complicated waveforms. Results validate the effectiveness, general applicability and the noise-robustness of the proposed scheme, showing its superior performance in practical MWP systems. Therefore, the proposed deep learning scheme facilitates the low-cost performance improvement of MWP processing systems, as well as the next-generation broadband information systems.