Although deeper convolutional neural networks (CNNs) generally obtain better performance on classification tasks, they incur higher computation costs. To address this problem, this study proposes the optronic convolutional neural network (OPCNN) in which all computation operations are executed in optics, and data transmission and control are executed in electronics. In OPCNN, we implement convolutional layers with multi input images by the lenslet 4f system, downsampling layers by optical-strided convolution and obtaining nonlinear activation by adjusting the camera’s curve and fully connected layers by optical dot product. The OPCNN demonstrates good performance on the classification tasks in simulations and experiments and achieves better performance than other current optical convolutional neural networks by comparison due to the more complex architecture. The scalability of OPCNN contributes to building deeper networks when facing complicated datasets.

Multichannel synthetic aperture radar systems in azimuth can effectively suppress azimuth ambiguity and are promising in high-resolution wide-swath imaging. However, unavoidable channel errors will significantly degrade the performance of ambiguity suppression. Conventional subspace calibration methods usually estimate phase error via decomposing a Doppler-variant covariance matrix from one Doppler bin, and then average these errors estimated from several Doppler bins to improve the estimation accuracy, which will result in a large computational load. This letter presents an improved channel error calibration method, which works on the undersampled data of the individual azimuth channel. By a proposed matrix transformation method, the Doppler-variant covariance matrices will be transformed into a constant covariance matrix. Therefore, the improved calibration algorithm needs to estimate and decompose the new covariance matrix only once. The computation load could be greatly reduced. Moreover, the new covariance matrix can be estimated by training samples not only from range bins but also from Doppler bins, which will improve the estimation accuracy. Theoretical analysis and experiments based on simulations and measurements showed the high accuracy, efficiency, and robustness of the improved method, particularly in low signal-to-noise ratio.

Imaging through scattering media is a common practice in many applications of biomedical imaging. Object image would deteriorate into unrecognizable speckle pattern when scattering media is presented. Many methods have been investigated to reconstruct the object image when only speckle pattern is available. In this paper, we demonstrate a method of single-shot imaging through scattering media. This method is based on classification and support vector regression of the measured speckle pattern. We prove the possibility of speckle pattern classification and related formulas are presented. The specified and limited imaging capability without speckle pattern classification is demonstrated. Our proposed approach, that is, speckle pattern classification based support vector regression method, makes up the deficiency. Experimental results show that, with our approach, speckle patterns could be utilized for classification when object images are unavailable, and object images can be reconstructed with high fidelity. The proposed approach for imaging through scattering media is expected to be applicable to various sensing schemes.

Multiple azimuth channels are usually employed to overcome the inherent limitation between high resolution and wide swath in synthetic aperture radar systems. However, unavoidable channel phase errors will significantly degrade the performance of ambiguity suppression. Conventional calibration methods usually regard these phase errors as constants during the whole observation time and ignore the azimuth-variant phase errors, which may not totally suppress azimuth ambiguities especially for very strong targets. This letter presents an azimuth-variant phase error calibration technique. The proposed technique first selects a strong point-like target as the calibration source. Then, the azimuth-variant phase errors can be estimated by comparing the phase of the calibration source and the corresponding steering vector in the range-compressed signals. Besides, a preprocessing method is presented to improve the calibration accuracy when the selected calibration source is affected by noise or interferences. Theoretical analysis and experiments demonstrate the feasibility of the proposed technique.