Millimeter-wave (MMW) 3-D imaging technology is becoming a research hotspot in the field of safety inspection, intelligent driving, etc., due to its all-day, all-weather, high-resolution and non-destruction feature. Unfortunately, due to the lack of a complete 3-D MMW radar dataset, many urgent theories and algorithms (e.g., imaging, detection, classification, clustering, filtering, and others) cannot be fully verified. To solve this problem, this paper develops an MMW 3-D imaging system and releases a high-resolution 3-D MMW radar dataset for imaging and evaluation, named as 3DRIED. The dataset contains two different types of data patterns, which are the raw echo data and the imaging results, respectively, wherein 81 high-quality raw echo data are presented mainly for near-field safety inspection. These targets cover dangerous metal objects such as knives and guns. Free environments and concealed environments are considered in experiments. Visualization results are presented with corresponding 2-D and 3-D images; the pixels of the 3-D images are $512\times 512\times 6$. In particular, the presented 3DRIED is generated by the W-band MMW radar with a center frequency of $79\mathrm{GHz}$, and the theoretical 3-D resolution reaches 2.8 mm × 2.8 mm × 3.75 cm. Notably, 3DRIED has 5 advantages: (1) 3-D raw data and imaging results; (2) high-resolution; (3) different targets; (4) applicability for evaluation and analysis of different post processing. Moreover, the numerical evaluation of high-resolution images with different types of 3-D imaging algorithms, such as range migration algorithm (RMA), compressed sensing algorithm (CSA) and deep neural networks, can be used as baselines. Experimental results reveal that the dataset can be utilized to verify and evaluate the aforementioned algorithms, demonstrating the benefits of the proposed dataset.

Compressed sensing (CS) shows significant potential in the field of active millimeter-wave (mmW) synthetic aperture radar (SAR) imaging due to the merits of reducing system complexity and achieving high-speed sensing. However, most CS-driven imaging methods suffer from the excessive computational burden, since the calculative steps always rely on vectorization and consequently lead to extremely large-scale matrix operations. To address this issue, we propose an efficient alternating direction method of multipliers (ADMMs) framework for mmW 3-D SAR imaging. In our scheme, we utilize the single-frequency holographic (SFH) technique and construct SFH-based forward/inverse sensing operators rather than converting the imaging process into a special case of “linear inverse problems,” by which the large-scale matrix inversions are avoided and consequently the computational complexity is reduced. Based on the SFH functional measurement model, the SFH-ADMM is derived to reconstruct the 3-D image from sparsely sampled measurement echo while suppressing noisy clutters and ambiguities. Besides, the SFH-ADMM iteration steps undergird a neural network design, yielding a tailored SFH-ADMM-Net with trainable parameters and layer-fixed structures, which further shorten the execution time and improve reconstruction performance. The network is trained by simulated data, which are generated according to the radar signal model. Extensive experiments, including simulations and laboratory tests, demonstrate the superiority of the proposed algorithms in terms of both reconstruction accuracy and computational speed.

Ship instance segmentation of high-resolution (HR) synthetic aperture radar (SAR) images is a valuable and challenging task due to the complex scattering and noise properties. In this article, we pioneered the construction of the low-level feature to discriminate the ships and complemented the super-resolution (SR) denoising techniques in the network modules, termed low-level feature guided network (LFG-Net), for precise ship instance segmentation in SAR images. LFG-Net consists of the low-level feature concerned pyramid (LFCP), the high-resolution feature interaction module (HR-FIM), and the compression recovery segmentation branch (CRSB). LFCP extends the vanilla feature pyramid network (FPN) with the ${P_{1}}$ layer and complements SR techniques to capture the regional and texture information at the image level for small object segmentation. HR-FIM interacts with the bounding box region of interest (RoI) feature and mask RoI feature at the instance level with HR techniques to enhance the mask RoI feature. CRSB aims at recovering the HR mask predictions to improve the ship segmentation performance. Comprehensive experiments on high-resolution SAR images dataset (HRSID), polygon segmentation SAR ship detection dataset (PSeg-SSDD), and AirSARShip indicate that LFG-Net* achieves 11.7%, 6.3%, and 12.7% AP increments compared with the Mask R-CNN baseline, respectively. Besides, it receives 9.5%, 4.9%, and 7.3% AP increments compared with the state-of-the-art method, which bridges the gap of instance segmentation precision in SAR images. In terms of the visualized instance segmentation results, LFG-Net ^* is capable of segmenting the complex scenes, e.g., the adjacent distributed ships and ships with strong reflection noise interference, in SAR images. The code is available at: https://github.com/Evarray/LFG-Net .

The regularization-based approaches offer promise in improving synthetic aperture radar (SAR) imaging quality while reducing system complexity. However, the widely applied $\ell_1$ regularization model is hindered by their hypothesis of inherent sparsity, causing unreal estimations of surface-like targets. Inspired by the edge-preserving property of total variation (TV), we propose a new complex-valued TV (CTV)-driven interpretable neural network with nested topology, i.e., CTV-Net, for 3-D SAR imaging. In our scheme, based on the 2-D holography imaging operator, the CTV-driven optimization model is constructed to pursue precise estimations in weakly sparse scenarios. Subsequently, a nested algorithmic framework, i.e., complex-valued TV-driven fast iterative shrinkage thresholding (CTV-FIST), is derived from the theory of proximal gradient descent (PGD) and FIST algorithm, theoretically supporting the design of CTV-Net. In CTV-Net, the trainable weights are layer-varied and functionally relevant to the hyperparameters of CTV-FIST, which aims to constrain the algorithmic parameters to update in a well-conditioned tendency. All weights are learned by end-to-end training based on a two-term cost function, which bounds the measurement fidelity and TV norm simultaneously. Under the guidance of the SAR signal model, a reasonably sized training set is generated, by randomly selecting reference images from the MNIST set and consequently synthesizing complex-valued label signals. Finally, the methodology is validated, numerically and visually, by extensive SAR simulations and real-measured experiments, and the results demonstrate the viability and efficiency of the proposed CTV-Net in the cases of recovering 3-D SAR images from incomplete echoes.

The sparse imaging method based on compressed sensing (CS) is widely used in the field of millimeter-wave (MMW) synthetic aperture radar (SAR) imaging. However, 3-D sparse imaging is limited by the difficult parameter tuning, the huge computational load, and the low processing efficiency. In addition, due to the motion errors and model mismatch, it is difficult to obtain well-focused results without error correction techniques. To address these issues, we propose a deep learning framework that integrates 3-D sparse imaging and autofocusing, named 3-D sparse autofocusing network (SAF-3DNet) for MMW SAR data processing. The network is constructed based on an auto-encoder, which can optimize parameters without effective ground truth. The backbone structure of the encoder is expanded by approximate message-passing (AMP), and the operators in the frequency domain are used to replace the traditional matrix-vector CS model, which avoids large-scale matrix multiplication and other operations, and greatly improves the operation efficiency. In addition, the 2-D phase error estimation in the cross-range plane is embedded into the sparse imaging models, enabling simultaneous 3-D imaging and autofocusing. The decoder is designed as a mapping from the autofocusing results to the echo data. Experimental results based on both simulated and measured data demonstrate the proposed SAF-3DNet can achieve well-focused 3-D reconstruction within an ephemeral time, which expresses the potential of 3-D MMW SAR real-time and high-quality imaging.

The application of the compressed sensing (CS) method in the radar field enables the radar imaging system to satisfy both low data cost and high reconstruction quality; however, it is accompanied by enormous iterative operations and difficult adjustments of parameters. In this article, we propose a learning-based split unfolding framework, dubbed as split iterative sparse reconstruction network (SISR-Net), for near-field 3-D millimeter-wave (mmW) radar sparse imaging. First, a split iterative sparse reconstruction algorithm, i.e., SISRA, is proposed to theoretically guide the structure of the imaging framework. Subsequently, by combining the model-based CS method and data-driven deep learning method, SISR-Net is constructed by SISRA to produce 3-D mmW radar images efficiently with excellent explainability and generalization ability. Combining the radar-imaging kernel, echo-generation kernel, and the split Bregman method, the efficiency and stability of SISR-Net are guaranteed, and all the parameters are layer-varied and learned steadily by end-to-end training to improve the convergence and robustness of the imaging network. Simulated data and echo from a high-resolution mmW radar dataset 3DRIED are used to train and test the SISR-Net based on the Adam optimizer. For both simulation and extensive 3-D mmW radar-measured experiments, the proposed SISR-Net outperforms other state-of-the-art imaging methods in terms of imaging accuracy and generalization ability.