Amplitude-Phase CNN-Based SAR Target Classification via Complex-Valued Sparse Image

Abstract

It is known that a synthetic aperture radar (SAR) image obtained by matched filtering (MF)-based algorithms always suffers from serious noise, sidelobes, and clutters. However, the improvement of the image quality means the complexity of the SAR system will increase, which affects the application of the SAR image. The introduction of the sparse signal processing technique into SAR imaging proposes a new way to solve this problem. Sparse SAR image obtained by sparse recovery algorithms shows a better image performance than the typical complex SAR image with lower sidelobes and higher signal-to-noise ratio. As the most widely applied field of the SAR image, target classification relies on the SAR image with high quality. Therefore, a novel target classification model based on the amplitude and phase information of the sparse SAR image is introduced in this article. First, complex sparse image dataset is constructed by a novel iterative soft thresholding (BiIST) algorithm. Compared with typical regularization-based sparse recovery algorithms, BiIST not only can improve the quality of recovered image, but also can obtain a nonsparse solution with retaining phase information and background statistical distribution of the SAR image. Then, targets are classified by the proposed amplitude-phase convolutional neural network (AP-CNN). Typical SAR target classification networks imitate those on optical image, just using amplitude data. However, considering the particularity of the SAR image, the AP-CNN uses both amplitude and phase for training, which theoretically improves the classification accuracy. Experimental results show that the AP-CNN outperforms the typical amplitude-based CNN in target classification, both under standard operating conditions (SOCs) and extended operating conditions (EOCs). Results under SOC demonstrate that the AP-CNN improves the classification accuracy by 11.46% with only 1000 training samples. Even under EOC, the accuracy gap between the Manuscript

Single Radar Image Motion Deblurring Through PSF Estimation and Convolution Regularizer

“…Recent works have concentrated on employing complex-valued learning models to solve radar imaging tasks. For instance, in [43], an Amplitude Phase CNN (AP-CNN) was formulated to classify targets using radar image amplitude and phase information. This approach showcased substantial classification accuracy improvements even with smaller training datasets.…”

Hybrid Conv-Attention Networks for Synthetic Aperture Radar Imagery-Based Target Recognition

“…Despite the widespread adoption of this strategy, it is challenging to pinpoint a model that's intricately tailored for SAR images, as most are honed for publicly available data sets rather than the unique characteristics of SAR imagery. Recognizing this gap, several researchers have proposed models meticulously optimized for SAR image classification, aiming to enhance the precision and reliability of automated systems in processing and interpreting SAR imagery [3], [10], [15]- [25].…”

“…Zhang et al [3] proposed a domain adaptation-based method using heterogeneous features to overcome the vulnerability of noise from the A-ConvNets method. Deng et al [15] developed an amplitude-phase CNNs (AP-CNN), utilizing amplitude and phase data from sparse images, enhanced by a bi-iterative soft thresholding (BiIST) algorithm to improve quality. This approach improved classification accuracy more than traditional amplitude-based methods, especially with limited training data.…”

Effect of Magnitude and Phase of Millimeter-wave Images on Classification Accuracy

“…In [8], it was shown that many filters in image processing tasks, such as matched filter and image restoration can be effectively designed if both the magnitude and phase specifications are included. In [11], a classification algorithm, Amplitude Phase-CNN (AP-CNN), was developed based on the amplitude and phase of sparse Synthetic Aperture Radar (SAR) images. The AP-CNN model used both the amplitude and phase of the SAR images for training, which improved the classification accuracy of the model.…”