Hyperspectral image (HSI) compression presents the challenge of preserving both spectral and spatial fidelity while achieving high compression rates. Current compression methods frequently depend on band-by-band compression or simplistic joint modeling, which complicates the balance between spectral consistency and perceptual quality. To address this issue, a compression driven generation framework (BRC-CDM) is proposed, which decouples the extraction of compressed representations from the reconstruction of high-quality images. We introduce reference band information through channel-level concatenation to guide the spectral residual compression network in collaboratively extracting residual information in both spatial and spectral domains. During the prediction phase, a spectral gaussian grid compensation structure is further integrated to enhance the accuracy of predictions for the target bands. Ultimately, by compressing the residual information based on the differences between the predicted bands and the true bands, an efficient representation of the residual information in the compressed domain is achieved. The predicted image is then fused with the compressed residual to obtain a more expressive and potentially compressed representation. During the decoding phase, the diffusion process of the conditional diffusion model (CDM) utilizes compressed representations as potential conditions to guide the model in progressively reconstructing images over multiple time steps. Experimental findings demonstrate that the bi-residual compression network achieves superior peak signal-to-noise ratio (PSNR) across nine datasets, with an improvement of approximately 1 dB over SOTA methods. Moreover, BRC-CDM attains a PSNR that surpasses that of the majority of current methodologies, while also delivering enhanced spectral fidelity and perceptual quality. To foster reproducibility and further development, we release the full implementation of BRC-CDM at https://github.com/Nicle-L/BRC-CDM.

The strong clutter typically impedes the accurate imaging and detection of targets for through-the-wall (TWR) system. In this letter, a joint dual-domain (JDD) clutter suppression method based on robust non-negative matrix factorization (RNMF) is proposed for TWR system. The proposed method exploits RNMF algorithm to remove the clutter in both the signal and image domains. Specifically, the exponentially weighted multiplication fusion is employed to fuse the two decluttered images in the signal and image domains. The optimal value of the exponential factor for fusion is determined using the minimum entropy criterion. The experimental results have shown that the proposed method can provide the better clutter suppression performance compared to the existing low rank and sparse decomposition (LRSD) based approaches.

Benefiting from the excellent texture recovery capability of generative adversarial networks (GANs), generated images are capable of maintaining clear texture features even when compressed into extremely low-bit streams. In recent years, the GAN has made great progress in extremely low-bit compression for natural images. However, a few studies have been conducted on extremely low-bit compression for the remote-sensing (RS) field. We find that a single GAN tends to generate visually pleasing texture information, and this characteristic may affect the visual effect and accuracy of other computer vision tasks. Therefore, we propose a coupled compression generation network (CCGN) that reconstructs the image content and detailed textures separately and fuses them to achieve a balanced image reconstruction task at extremely low bitrates for remote-sensing images. Specifically, a multidimensional residual attention mechanism (MRAM) is adopted to achieve extremely low-bit stream generation, whereas contentwise images and texturewise images are reconstructed using the same generator with different training strategies. We further optimize the texture generation strategy, and an enhanced perceptual-guided refinement stage (EPGRS) and a multiscale fusion discriminator (MSFD) are developed for a more realistic texture. The proposed method achieves outstanding results on compression tasks on the dataset for object detection in aerial images (DOTA), and the fused results of extremely low-bit streams also perform well in object detection tasks, significantly alleviating pressure from bandwidth and storage space.

The information of wall parameters is very important for the imaging performance of through-the-wall radar imaging (TWRI). The existing estimation methods usually require the calibration procedure to ensure the accuracy of the estimated wall parameters. To avoid the time-consuming calibration procedure, a sparse blind deconvolution method for wall parameters estimation is proposed in this letter. The proposed method uses the time-delay-only estimation (TDOE) strategy with the hybrid bistatic–monostatic measurement configuration to retrieve the unknown thickness, relative permittivity, and conductivity of the wall. In the estimation process, the sparse blind deconvolution algorithm is developed to retrieve the time delays of echoes reflected from the wall. The proposed sparse blind deconvolution method can precisely extract the time delays of echoes in the time domain without the calibration procedure to obtain the shape of the transmitted pulse and the frequency response of the antennas. The estimation results from the full-wave synthetic data have shown that the proposed method can also improve the estimation accuracy of the wall parameters.

The accurate imaging of stationary human targets in the indoor scene containing strong scatterers such as cabinets, tables, and chairs is very important for the through-the-wall radar (TWR) system. The convolution neural network (CNN) has been used to enhance radar imaging quality. In this letter, a novel multiresolution fusion network (MRFN) based on the deep layer aggregation (DLA) method is proposed for TWR imaging. The proposed MRFN can accurately localize the weak scattering human targets and provide the scattering intensity differences between the strong and weak targets. Both the simulated and real TWR data are used to evaluate the imaging performance of the proposed MRFN. The experimental results demonstrate the superiority of the proposed TWR imaging method over the existing CNN-based imaging methods.

Deep learning algorithms have been widely used in ship detection with synthetic aperture radar (SAR). However, the complex background, clutter noise, and large span of ship sizes have adverse effects on the feature extraction, which seriously limits the ship detection accuracy. To address this issue, a cross-scale regional prediction-aware network (CSRP-Net) is developed to advance the ship detection performance in SAR images. First, the cross-scale self-attention (CSSA) module is designed to suppress the influence of noise and complex backgrounds and enhance the ability to detect multiscale targets. Furthermore, a regional prediction-aware one-to-one (RPOTO) label assignment is proposed to select the foreground samples more conducive to classification and regression in the training stage. Extensive experiments have proved that the designed method can significantly improve the detection performance against several start-of-the-art algorithms on two classical benchmark datasets.

Synthetic aperture radar (SAR) image compression plays an important role in the manipulation of images. However, existing optical compression methods cannot properly handle SAR compression due to the absence of feature learning and representation for SAR images. In this letter, we propose an end-to-end trainable model to effectively fit the feature distribution and reduce information dependencies toward SAR image compression. To better parameterize the distribution of latent codes, a discretized Gaussian adaptive model is designed to achieve a flexible entropy process. To further remove the remaining redundancies, generalized subtractive normalization is introduced to reduce the statistical dependencies in SAR images. Extensive experiments show that the proposed compression method outperforms the traditional compression methods and learning-based algorithms on both the ICEYE and Sandia datasets.

Despite deep convolutional neural networks (DCNNs) having been used extensively in radar-based human activity recognition in recent years, their performance could not be fully implemented because of the lack of radar dataset. However, radar data acquisition is difficult to achieve due to the high cost of its measurement. Generative adversarial networks (GANs) can be utilized to generate a large number of similar micro-Doppler signatures with which to increase the training data set. For the training of DCNNs, the quality and diversity of data set generated by GANs is particularly important. In this paper, we propose using a more stable and effective Wasserstein generative adversarial network with gradient penalty (WGAN-GP) to augment the training data set. The classification results from the experimental data have shown the proposed method can improve the classification accuracy of human activity.

An innovative compressive sensing (CS) based Stolt migration imaging algorithm for short-pulse ground-penetrating radar (GPR) has been developed and will be presented here. The traditional Stolt migration algorithm requires a wideband signal and large antenna array for implementing a high-resolution imaging reconstruction, which traditionally suffers from high sampling rate requirements and long time for data collection. On the contrary, the proposed CS-based Stolt migration imaging algorithm establishes a sparse transform between the raw measurement data and the migrated imaging results, it considers the physical propagation process of the electromagnetic wave and does not require a prior knowledge of the transmitted pulse. This imaging algorithm can provide better imaging quality; while reducing both the required sampling rate and number of measurements. The accurate imaging results from the numerical simulation data presented here verified the effectiveness and validity of the proposed imaging algorithm.

Estimating unknown wall parameters is of great importance for the application of through-the-wall radar (TWR). The time-delay-only estimation (TDOE) method is able to efficiently retrieve the constitute parameters of the homogeneous wall under test. For the TDOE method, the estimation accuracy of time delays associated with wall reflections directly affects the accuracy of wall parameters estimation. In this paper, we propose a sparse recovery method for estimation of wall parameters, which utilizes the orthogonal matching pursuit (OMP) algorithm to perform the time delay estimation of echoes backscattered from the wall at each antenna separation. Numerical simulation results have shown that the proposed estimation method is capable of providing the estimation of wall parameters with higher accuracy.

In order to solve the problems of slow imaging speed and poor reconstruction accuracy of wall parameters under the condition of wall parameter fuzziness, an improved limited Broyden–Fletcher–Goldfarb–Shanno‐particle swarm optimisation (LBFGS‐PSO) algorithm was proposed. The LBFGS‐PSO algorithm model solves the problems of slow calculation speed and large errors of the traditional quasi‐Newton algorithm and particle swarm algorithm. The algorithm combined with block orthogonal matching pursuit algorithm can not only accurately reconstruct the position of the sidewall, but also can use the multi‐path information to accurately reconstruct the moving target and the stationary target. Compared with the traditional BFGS algorithm and PSO algorithm, the proposed algorithm can reduce the calculation time and provide more accurate estimation results. Simulation results and data analysis verify the performance of the proposed algorithm.

High-resolution ground-penetrating radar multiview-multistatic diffraction-tomographic (DT) imaging usually requires the wide signal bandwidth and large antenna aperture, which results in the great amount of imaging data. To solve the aforementioned problem, an innovative 2-D multiview-multistatic DT imaging algorithm based on the multitask Bayesian compressive sensing (MT-BCS) strategy is proposed in this letter. The reduction of the measurement data can be achieved by performing a reduced set of measurements in the frequency domain. In particular, a joint Bayesian sparse reconstruction scheme is used to recover the original frequency domain data from the reduced frequency measurements across all the measurement positions. Finally, the image of the investigation domain can be reconstructed by the traditional multiview-multistatic DT imaging algorithm. Numerical simulation results have shown that the proposed imaging method can not only reduce the frequency measurement data but also provide the satisfactory quality of the reconstructed image.

High-resolution diffraction tomographic (DT) ground-penetrating radar (GPR) image formation requires the use of wideband signal and large antenna array aperture, which leads to the generation of large amounts of imaging data. A compressive sensing multibistatic GPR DT imaging algorithm is presented in this letter. The proposed imaging algorithm can provide the advantage in terms of reducing the measured data in the frequency domain while maintaining the image quality of the reconstructed scenario. The imaging results reconstructed via the processing of synthetic data have verified the validity and effectiveness of the proposed imaging method.

Estimating the time delays of buried target echoes is particularly important for the application of ground penetrating radar (GPR). Due to its smaller computational burden, the estimation of signal parameters via rotational invariance technique (ESPRIT) is preferred to process the buried target echoes in the frequency domain and to obtain the accurate super-resolution time delays. In this letter, we give an in-depth analysis of the essential preprocessing steps for the application of ESPRIT to practical GPR measurement data. In particular, an improved spatial smoothing method is adopted to construct the correlation matrix for the robustness of the time-delay estimation result. The effectiveness of the algorithm is verified by the synthetic data from a horizontally stratified medium model using the finite-difference time-domain method, which explicitly takes into account surface scattering for a more realistic scenario.

For stepped frequency continuous wave ground penetrating radar (SFCW GPR), the image of buried targets is usually reconstructed by a combination of point-like scatters whose number is much smaller than that of pixels of target space image. The intrinsic sparseness of target space offers a migration imaging method to make the high-quality image of underground region based on compressive sensing (CS) theory. In this paper, the effects of air/ground interface and antenna beamwidth on CS-based SFCW GPR migration imaging are presented and analyzed. It is shown that the presence of the strong air/ground interface reflection and finite antenna beamwidth usually challenges the robust CS migration imaging algorithm in practice. To overcome this problem in the context of CS migration imaging, an improved CS migration imaging method for SFCW GPR system is proposed in this paper. Experimental results show that the approach is robust to deliver a high-quality image of underground region.

To achieve high-resolution 2-D images, through-wall imaging (TWI) radar with ultra-wideband and long antenna arrays faces considerable technical challenges such as a prolonged data collection time, a huge amount of data, and a high hardware complexity. This paper presents a novel data acquisition scheme and an imaging algorithm for TWI radar based on compressive sensing (CS), which states that a signal having a sparse representation can be reconstructed from a small number of nonadaptive randomized projections by solving a tractable convex program. Instead of measuring all spatial-frequency data, a few samples, by employing an overcomplete dictionary, are sufficient to obtain reliable target space images even at high noise levels. Preliminary simulated and experimental results show that the proposed algorithm outperforms the conventional delay-and-sum beamforming method even though many fewer CS measurements are used.

In the above titled paper (ibid., vol. 48, no. 3, pp. 1408-1415, Mar. 2010), there are two errors in the top line of (13) which we correct here.