Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

With the development of satellite technology, up to date imaging mode of synthetic aperture radar (SAR) satellite can provide higher resolution SAR imageries, which benefits ship detection and instance segmentation. Meanwhile, object detectors based on convolutional neural network (CNN) show high performance on SAR ship detection even without land-ocean segmentation; but with respective shortcomings, such as the relatively small size of SAR images for ship detection, limited SAR training samples, and inappropriate annotations, in existing SAR ship datasets, related research is hampered. To promote the development of CNN based ship detection and instance segmentation, we have constructed a High-Resolution SAR Images Dataset (HRSID). In addition to object detection, instance segmentation can also be implemented on HRSID. As for dataset construction, under the overlapped ratio of 25%, 136 panoramic SAR imageries with ranging resolution from 1m to 5m are cropped to $800 \times 800$ pixels SAR images. To reduce wrong annotation and missing annotation, optical remote sensing imageries are applied to reduce the interferes from harbor constructions. There are 5604 cropped SAR images and 16951 ships in HRSID, and we have divided HRSID into a training set (65% SAR images) and test set (35% SAR images) with the format of Microsoft Common Objects in Context (MS COCO). 8 state-of-the-art detectors are experimented on HRSID to build the baseline; MS COCO evaluation metrics are applicated for comprehensive evaluation. Experimental results reveal that ship detection and instance segmentation can be well implemented on HRSID.

/pdf/hrsid-a-high-resolution-sar-images-dataset-for-ship-1mwaxlmjdm.pdf

HRSID: A High-Resolution SAR Images Dataset for Ship Detection and Instance Segmentation

With the development of deep learning (DL) and synthetic aperture radar (SAR) imaging techniques, SAR automatic target recognition has come to a breakthrough. Numerous algorithms have been proposed and competitive results have been achieved in detecting different targets. However, due to the influence of various sizes and complex background of ships, detecting multiscale ships in SAR images is still challenging. To solve the problems, a novel network, called attention receptive pyramid network (ARPN), is proposed in this article. ARPN is a two-stage detector and designed to improve the performance of detecting multiscale ships in SAR images by enhancing the relationships among nonlocal features and refining information at different feature maps. Specifically, receptive fields block (RFB) and convolutional block attention module (CBAM) are employed and combined reasonably in attention receptive block to build a top-down fine-grained feature pyramid. RFB, composed of several branches of convolutional layers with specifically asymmetric kernel sizes and various dilation rates, is used for grabbing features of ships with large aspect ratios and enhancing local features with their global dependences. CBAM, which consists of channel and spatial attention mechanisms, is utilized to boost significant information and suppress interference caused by surroundings. To evaluate the effectiveness of ARPN, experiments are conducted on SAR Ship Detection Dataset and two large-scene SAR images. The detection results illustrate that competitive performance has been achieved by our method in comparison with several CNN-based algorithms, e.g., Faster-RCNN, RetinaNet, feature pyramid network, YOLOv3, Dense Attention Pyramid Network, Depth-wise Separable Convolutional Neural Network, High-Resolution Ship Detection Network, and Squeeze and Excitation Rank Faster-RCNN.

/pdf/attention-receptive-pyramid-network-for-ship-detection-in-4h5icl2rn3.pdf

Attention Receptive Pyramid Network for Ship Detection in SAR Images

Ship detection in synthetic aperture radar (SAR) images is becoming a research hotspot. In recent years, as the rise of artificial intelligence, deep learning has almost dominated SAR ship detection community for its higher accuracy, faster speed, less human intervention, etc. However, today, there is still a lack of a reliable deep learning SAR ship detection dataset that can meet the practical migration application of ship detection in large-scene space-borne SAR images. Thus, to solve this problem, this paper releases a Large-Scale SAR Ship Detection Dataset-v1.0 (LS-SSDD-v1.0) from Sentinel-1, for small ship detection under large-scale backgrounds. LS-SSDD-v1.0 contains 15 large-scale SAR images whose ground truths are correctly labeled by SAR experts by drawing support from the Automatic Identification System (AIS) and Google Earth. To facilitate network training, the large-scale images are directly cut into 9000 sub-images without bells and whistles, providing convenience for subsequent detection result presentation in large-scale SAR images. Notably, LS-SSDD-v1.0 has five advantages: (1) large-scale backgrounds, (2) small ship detection, (3) abundant pure backgrounds, (4) fully automatic detection flow, and (5) numerous and standardized research baselines. Last but not least, combined with the advantage of abundant pure backgrounds, we also propose a Pure Background Hybrid Training mechanism (PBHT-mechanism) to suppress false alarms of land in large-scale SAR images. Experimental results of ablation study can verify the effectiveness of the PBHT-mechanism. LS-SSDD-v1.0 can inspire related scholars to make extensive research into SAR ship detection methods with engineering application value, which is conducive to the progress of SAR intelligent interpretation technology.

LS-SSDD-v1.0: A Deep Learning Dataset Dedicated to Small Ship Detection from Large-Scale Sentinel-1 SAR Images

SAR Ship Detection Dataset (SSDD) is the first open dataset that is widely used to research state-of-the-art technology of ship detection from Synthetic Aperture Radar (SAR) imagery based on deep learning (DL). According to our investigation, up to 46.59% of the total 161 public reports confidently select SSDD to study DL-based SAR ship detection. Undoubtedly, this situation reveals the popularity and great influence of SSDD in the SAR remote sensing community. Nevertheless, the coarse annotations and ambiguous standards of use of its initial version both hinder fair methodological comparisons and effective academic exchanges. Additionally, its single-function horizontal-vertical rectangle bounding box (BBox) labels can no longer satisfy the current research needs of the rotatable bounding box (RBox) task and the pixel-level polygon segmentation task. Therefore, to address the above two dilemmas, in this review, advocated by the publisher of SSDD, we will make an official release of SSDD based on its initial version. SSDD’s official release version will cover three types: (1) a bounding box SSDD (BBox-SSDD), (2) a rotatable bounding box SSDD (RBox-SSDD), and (3) a polygon segmentation SSDD (PSeg-SSDD). We relabel ships in SSDD more carefully and finely, and then explicitly formulate some strict using standards, e.g., (1) the training-test division determination, (2) the inshore-offshore protocol, (3) the ship-size reasonable definition, (4) the determination of the densely distributed small ship samples, and (5) the determination of the densely parallel berthing at ports ship samples. These using standards are all formulated objectively based on the using differences of existing 75 (161 × 46.59%) public reports. They will be beneficial for fair method comparison and effective academic exchanges in the future. Most notably, we conduct a comprehensive data analysis on BBox-SSDD, RBox-SSDD, and PSeg-SSDD. Our analysis results can provide some valuable suggestions for possible future scholars to further elaborately design DL-based SAR ship detectors with higher accuracy and stronger robustness when using SSDD.

SAR Ship Detection Dataset (SSDD): Official Release and Comprehensive Data Analysis

This work focuses on 3D Radar imaging inverse problems. Current methods obtain undifferentiated results that suffer task-depended information retrieval loss and thus don’t meet the task’s specific demands well. For example, biased scattering energy may be acceptable for screen imaging but not for scattering diagnosis. To address this issue, we propose a new task-oriented imaging framework. The imaging principle is task-oriented through an analysis phase to obtain task's demands. The imaging model is multi-cognition regularized to embed and fulfill demands. The imaging method is designed to be generalized, where couplings between cognitions are decoupled and solved individually with approximation and variable-splitting techniques. Tasks include scattering diagnosis, person screen imaging, and parcel screening imaging are given as examples. Experiments on data from two systems indicate that the proposed framework outperforms the current ones in task-depended information retrieval.

Solving 3D Radar Imaging Inverse Problems with a Multi-cognition Task-oriented Framework

Image resolution is the key point for the 3-D synthetic aperture radar (SAR) application, especially in small-scale scene observation. The traditional filter-based image enhancement algorithms used for 3-D SAR may suffer from quality degeneration in case of parameter mismatch. This paper proposes a robust and efficient convolutional neural network (CNN) based U-net framework for 3-D SAR image enhancement. The U-net extracts image features in down sampling and up sampling, which is realized by max pooling and deconvolution layers. We use the mean square error(MSE) as the loss function to estimate the difference between the predicted images and the label, while Adam optimizer updates parameters to achieve the global minimum MSE. Both simulation and measured data verify the effectiveness of the network. The results demonstrate that the U-net outperform some traditional filter-based algorithms.

Image Enhancement of 3-D SAR via U-Net Framework

This work focuses on the problem of InSAR phase retrieval. Current methods consist of two cascaded tasks: phase filtering and phase unwrapping. Unavoidable accumulated errors cause precision loss, and serial computations cause efficiency loss. We propose a parallel dual-task learning work to address these issues for high-quality and efficient InSAR phase retrieval. Methodologically, we retrieve the InSAR phase in a parallel manner instead of a serially cascaded one. Specifically, three core phases throughout the whole processing chain are considered, including feature attraction, task learning, and task balance. First, for feature attraction, considering the InSAR image characteristics, we propose a hybrid Trans-Encoder module to attract features locally and nonlocally. Second, regarding the dual-task needs for feature learning, we propose a dual-decoder to denoise and unwrap parallelly. Third, considering the dual-task's different attributes for task balance, we propose an uncertainty-weighted loss to make balances between tasks. Experiments on both simulated and measured data verify the proposed method's higher precision and efficiency compared to other methods. An ability study is conducted that confirms the effectiveness of the proposed modules.

A Parallel Dual-Task Learning Network for InSAR Phase Retrieval

—Benefiting from a relatively larger aperture’s angle, and in combination with a wide transmitting bandwidth, near-field synthetic aperture radar (SAR) provides a high-resolution image of a target’s scattering distribution-hot spots. Meanwhile, imaging result suffers inevitable degradation from sidelobes, clutters, and noises, hindering the information retrieval of the target. To restore the image, current methods make simplified assumptions; for example, the point spread function (PSF) is spatially consistent, the target consists of sparse point scatters, etc. Thus, they achieve limited restoration performance in terms of the target’s shape, especially for complex targets. To address these issues, a preliminary study is conducted on restoration with the recent promising deep learning inverse technique in this work. We reformulate the degradation model into a spatially variable complex-convolution model, where the near-field SAR’s system response is considered. Ad-hering to it, a model-based deep learning network is designed to restore the image. A simulated degraded image dataset from multiple complex target models is constructed to validate the network. All the images are formulated using the electromagnetic simulation tool. Experiments on the dataset reveal their ef-fectiveness. Compared with current methods, superior performance is achieved regarding the target’s shape and energy esti-mation.

Near-filed SAR Image Restoration with Deep Learning Inverse Technique: A Preliminary Study

Non-line-of-sight (NLOS) imaging technique aims to reconstruct the hidden objects from multi-path echoes, which is a promising application in urban environment perception and autonomous driving. In this paper, we propose a total variation (TV) regularization based sparse reconstruct method for the hidden targets 3-D imaging in the seeing around corner situation for millimeter-wave (mmW) radar. Firstly, the 3-D imaging model of NLOS mmW radar is presented. Secondly, for preserving contour information, an effective imaging algorithm with compressed sensing theory and mirror projection, dubbed mirror symmetry sparse total variation (MSSTV) is proposed for 3-D image reconstruction. Finally, the MSSTV algorithm is validated by an NLOS 3-D imaging mmW experimental system with different kinds of targets.

Shunjun Wei

Papers

Solving 3D Radar Imaging Inverse Problems with a Multi-cognition Task-oriented Framework

Image Enhancement of 3-D SAR via U-Net Framework

A Parallel Dual-Task Learning Network for InSAR Phase Retrieval

Near-filed SAR Image Restoration with Deep Learning Inverse Technique: A Preliminary Study

Non-Line-of-Sight Millimeter-Wave Radar 3-D Sparse Reconstruct via MSSTV Method