Search

Multioriented object detection, an important yet challenging task because of the bird's-eye-view perspective, complex background, and densely packed objects, is in the spotlight of detection in remote sensing images. Although existing methods have recently experienced substantial progress based on oriented head, they learn little about essential rotation invariance of the objects. In this article, a novel framework is proposed that can learn high-quality rotation invariance features of the multioriented objects by three measures. Given a remote sensing image, the multiscale semantic segmentation feature fusion module first merges the global semantic segmentation features predicted by the semantic segmentation branch and the multiscale features extracted by the backbone with FPN in order to distinguish complex background. Then, the discriminative features are used by rotation mainstream, whose structure is similar to cascade R-CNN and can extract higher quality rotation invariance features and predict more accurate location information by adaptively adjusting the distribution of the samples through progressive intersection over union thresholds. And in order to improve the performance of mainstream to predict more accurate oriented bounding box, the horizontal tributaries that can fully leverage the reciprocal relationship between the oriented detection and horizontal detection were added to the latter two stages. Extensive experiments on three public datasets for remote sensing images, i.e., Gaofen Airplane, HRSC2016, and DOTA demonstrate that without bells and whistles, the proposed method achieves superior performances compared with the existing state-of-the-art methods for multioriented detection. Moreover, our overall system achieves 59.264% mAP of airplane Detection in 2020 Gaofen challenge, ranking third in the final.

Most deep-learning-based target detection methods have high computational complexity and memory consumption, and they are difficult to deploy on edge devices with limited computing resources and memory. To tackle this problem, this article proposes to learn a lightweight detector named Light-YOLOv4, and it is obtained from YOLOv4 through model compression. To this end, first, we perform sparsity training by applying L1 regularization to the channel scaling factors, so the less important channels and layers can be found. Second, channel pruning and layer pruning are enforced on the network to prune the less important parts, which could significantly reduce network's width and depth. Third, the pruned model is retrained with a knowledge distillation method to improve the detection accuracy. Fourth, the model is quantized from FP32 to FP16, and it could further accelerate the model with almost no loss of detection accuracy. Finally, to evaluate Light-YOLOv4's performance on edge devices, Light-YOLOv4 is deployed on NVIDIA Jetson TX2. Experiments on the SAR ship detection dataset (SSDD) demonstrate that the model size, parameter size, and FLOPs of Light-YOLOv4 have been reduced by 98.63%, 98.66%, and 91.30% compared with YOLOv4, and the detection speed has been increased to 4.2×. While the detection accuracy of Light-YOLOv4 is only slightly reduced, for example, the mAP has only reduced by 0.013. Besides, experiments on the Gaofen Airplane dataset also prove the feasibility of Light-YOLOv4. Moreover, compared with other state-of-the-art methods, such as SSD and FPN, Light-YOLOv4 is more suitable for edge devices.

Superpixel segmentation for polarimetric synthetic aperture radar (PolSAR) images plays a fundamental role in various PolSAR applications. Subject to the intrinsic limitations, the existing methods generally produce over or undersegmented superpixels in highly complex scenes of PolSAR images. In this article, we propose an efficient and effective scattering feature-driven superpixel segmentation method for PolSAR images, which is capable of preserving the global structure information and producing superpixels with both high boundary adherence and visual compactness. First, a hierarchical version of the refined five-component decomposition is proposed. The derived scattering features along with other well-used features are then combined to construct a low-dimensional feature vector. Second, a modified normalized cuts formulation using a distance measurement is presented, in which the feature similarity and the space proximity are both considered. During the superpixel segmentation, the edge information derived from our scattering mechanism-optimal contrast-based edge detector is incorporated. On this basis, a tradeoff factor according to the edge information and the equivalent number of looks is determined, which balances the relationship of feature similarity and space proximity so as to adaptively control the size and shape of superpixels. The performance of the proposed method is demonstrated and evaluated with fully PolSAR data over different test sites. The outputs show that the proposed method outperforms the state-of-the-art methods and the produced superpixels scale well especially for heterogeneous scattering cases.

With the rapid development of earth observation technology, high-resolution synthetic aperture radar (HR SAR) imaging satellites could provide more observational information for maritime surveillance. However, there are still some problems to detect ship targets in HR SAR images due to the complex surroundings, targets defocusing, and diversity of the scales. In this article, an anchor-free method is proposed for ship target detection in HR SAR images. First, fully convolutional one-stage object detection (FCOS) as the base network is applied to detect ship targets, achieving better detection performance through pixel-by-pixel prediction of the image. Second, the category-position (CP) module is proposed to optimize the position regression branch features in the FCOS network. This module can improve target positioning performance in complex scenes by generating guidance vector from the classification branch features. At the same time, target classification and boundary box regression methods are redesigned to shield the adverse effects of fuzzy areas in the network training. Finally, to evaluate the effectiveness of CP-FCOS, extensive experiments are conducted on High-Resolution SAR Images Dataset, SAR Ship Detection Dataset, IEEE 2020 Gaofen Challenge SAR dataset, and two complex large-scene HR SAR images. The experimental results show that our method can obtain encouraging detection performance compared with Faster-RCNN, RetinaNet, and FCOS. Remarkably, the proposed method was applied to SAR ship detection in the 2020 Gaofen Challenge. Our team ranked first among 292 teams in the preliminary contest and won seventh place in the final match.

Sea–land segmentation is a basic step in coastline extraction and nearshore target detection. Because of poor segmentation accuracy and complicated parameter adjustment, the traditional sea–land segmentation algorithm is difficult to adapt in practical applications. Convolutional neural networks, which can extract multiple hierarchical features of images, can be used as an alternative technical approach for sea–land segmentation tasks. Among them, BiSeNet exhibits good performance in the semantic segmentation of natural scene images and effectively balances segmentation accuracy and speed. However, for the sea–land segmentation of SAR images, BiSeNet cannot extract the contextual semantic and spatial information of SAR images; thus, the segmentation effect is poor. To address the aforementioned problem, this study reduced the number of convolution layers in the spatial path to reduce the loss of spatial information and selected the ResNet18 lightweight model as the backbone network for the context path to reduce the overfitting phenomenon and provide a broad receptive field. At the same time, strategies for edge enhancement and loss function are proposed to improve the segmentation performance of the network in the land and sea boundary region. Experimental results based on GF3 data showed that the proposed method effectively improves the prediction accuracy and segmentation rate of the network. The segmentation accuracy and F1 score of the proposed method are 0.9889 and 0.9915, respectively, and the processing rate of SAR image slices with the resolution of 1024 × 1024 is 12.7 frames/s, which are better than those of other state-of-the-art approaches. Moreover, the size of the network is more than half of that of BiSeNet and smaller than that of U-Net. Thus, the network exhibits strong generalization performance.

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.

SAR ship detection and recognition are important components of the application of SAR data interpretation, allowing for the continuous, reliable, and efficient monitoring of maritime ship targets, in view of the present situation of SAR interpretation applications. On the one hand, because of the lack of high-quality datasets, most existing research on SAR ships is focused on target detection. Additionally, there have been few studies on integrated ship detection and recognition in complex SAR images. On the other hand, the development of deep learning technology promotes research on the SAR image intelligent interpretation algorithm to some extent. However, most existing algorithms only focus on target recognition performance and ignore the model’s size and computational efficiency. Aiming to solve the above problems, a lightweight model for ship detection and recognition in complex-scene SAR images is proposed in this paper. Firstly, in order to comprehensively improve the detection performance and deployment capability, this paper applies the YOLOv5-n lightweight model as the baseline algorithm. Secondly, we redesign and optimize the pyramid pooling structure to effectively enhance the target feature extraction efficiency and improve the algorithm’s operation speed. Meanwhile, to suppress the influence of complex background interference and ships’ distribution, we integrate different attention mechanism into the target feature extraction layer. In addition, to improve the detection and recognition performance of densely parallel ships, we optimize the structure of the model’s prediction layer by adding an angular classification module. Finally, we conducted extensive experiments on the newly released complex-scene SAR image ship detection and recognition dataset, named the SRSDDv1.0 dataset. The experimental results show that the minimum size of the model proposed in this paper is only 1.92 M parameters and 4.52 MB of model memory, which can achieve an excellent F1-Score performance of 61.26 and an FPS performance of 68.02 on the SRSDDv1.0 dataset.

Due to its great application value in the military and civilian fields, ship detection in synthetic aperture radar (SAR) images has always attracted much attention. However, ship targets in High-Resolution (HR) SAR images show the significant characteristics of multi-scale, arbitrary directions and dense arrangement, posing enormous challenges to detect ships quickly and accurately. To address these issues above, a novel YOLO-based arbitrary-oriented SAR ship detector using bi-directional feature fusion and angular classification (BiFA-YOLO) is proposed in this article. First of all, a novel bi-directional feature fusion module (Bi-DFFM) tailored to SAR ship detection is applied to the YOLO framework. This module can efficiently aggregate multi-scale features through bi-directional (top-down and bottom-up) information interaction, which is helpful for detecting multi-scale ships. Secondly, to effectively detect arbitrary-oriented and densely arranged ships in HR SAR images, we add an angular classification structure to the head network. This structure is conducive to accurately obtaining ships’ angle information without the problem of boundary discontinuity and complicated parameter regression. Meanwhile, in BiFA-YOLO, a random rotation mosaic data augmentation method is employed to suppress the impact of angle imbalance. Compared with other conventional data augmentation methods, the proposed method can better improve detection performance of arbitrary-oriented ships. Finally, we conduct extensive experiments on the SAR ship detection dataset (SSDD) and large-scene HR SAR images from GF-3 satellite to verify our method. The proposed method can reach the detection performance with precision = 94.85%, recall = 93.97%, average precision = 93.90%, and F1-score = 0.9441 on SSDD. The detection speed of our method is approximately 13.3 ms per 512 × 512 image. In addition, comparison experiments with other deep learning-based methods and verification experiments on large-scene HR SAR images demonstrate that our method shows strong robustness and adaptability.

Shape is considered to be one of the most promising tools to represent and recognise an object. In this study, an effective and rigorous shape matching algorithm is developed based on a new descriptor and relaxation labelling technique. For each contour point, the descriptor captures the distribution of all points within the shape region along the vector perpendicular to that from the centroid to the point. In addition to stable affine invariance, the descriptor is robust to noise since it makes use of all points in the shape region. The descriptor distance is used to initialise the contour point matching probability, and relaxation labelling technique is utilised to update the matching probability using a new compatibility coefficient function, which is defined based on the shape projection preserving characteristic. The experiments on synthetic and real remote sensing data are provided to test the performance of the authors’ proposed algorithm. Compared to other four state‐of‐the‐art contour‐based shape matching algorithms, their algorithm is more robust and capable of shape matching under affine transformations and noise.

Scattering characterization of obliquely oriented buildings (OOBs) from polarimetric synthetic aperture radar (PolSAR) data is challenging since the general double-bounce scattering does not support their dominant scattering mechanism. In this paper, a physical scattering model combining the eigenvalues of coherency matrix is proposed to characterize the scattering of OOBs. The coherency matrix is first operated by eigenvalue decomposition and a refined OOB descriptor is presented based on these eigenvalues. Considering the actual proportions of co-polarization and cross-polarization components, the descriptor is then adopted to modify the matrix elements of the well-known cross scattering model, thus introducing the OOB scattering model. Finally, strategies of model parameter solution are designed and the involved decomposition is complete accordingly. The proposed method is tested on spaceborne and airborne PolSAR data and the results confirm its effectiveness, which clearly call for further research and application.

Moment has been widely used for contour matching. To use the moment to achieve contour matching under affine transformations, the affine‐invariant support point set (SPS) should be constructed first. Then, a novel method of acquiring SPS based on the contour projection (SPS‐CP) is proposed here. For an arbitrary selected contour point, the contour is projected onto the line vertical to the vector connecting the contour centroid and the selected point, and the contour points with the sampled projection values are picked up to form the SPS‐CP of the point. SPS‐CP which captures the global structure of the contour is stably affine‐invariant. Experiments on synthetic and real data demonstrate that moments generated from SPS‐CP outperform those generated from SPSs sampled by uniform spacing or affine length.

Synthetic aperture radar (SAR) has been widely used in ocean surveillance. As an important part of shipping management and military applications, ship monitoring is a study hotspot in SAR image interpretation; hence, many researches focus on ship targets. Among these studies, ship segmentation is a basic work, but still remains challenging due to the speckle noise and the complicated backscattering phenomenology in SAR images. To solve the problems, this paper proposes a new method for ship segmentation by nonlocal processing. Firstly, the proposed nonlocal energy describes the nonlocal comparison of patches and optimizes regions with spatially-varying features. Secondly, we rewrite the energy functional by introducing a ratio distance defined with respect to the probability density functions of regions to overcome the influence of the multiplicative noise. Finally, the integral histogram is introduced into the pairwise interactions to fasten the speed of convergence. Several rounds of comparative experiments are implemented on real SAR data with different resolutions and bands. The results demonstrate that the proposed method is robust to the speckle noise and intensity variations and could achieve refined segmentation for ship targets.

Micro-Doppler signals analysis has been emerging as an important topic in target identification, and relative research has been focusing on features extraction and separation of the radar signals. As a time-frequency representation, the Hilbert-Huang transform (HHT) could extract the accurate instantaneous micro-Doppler signature from the radar signals by empirical mode decomposition and Hilbert transform. However, HHT has the shortcoming that it cannot decompose the signals with close-frequency components. To solve this problem, an innovative decomposition method for multicomponent micro-Doppler signals based on Hilbert–Huang transform and analytical mode decomposition (HHT-AMD) is proposed. In this method, the multicomponent micro-Doppler signals are firstly decomposed by empirical mode decomposition, and the decomposed signal components are transformed by Hilbert transform to get the Hilbert-Huang spectrum and marginal spectrum. Through the spectrum processing, we get the frequency distribution of each signal component. The next step is to judge whether there exists frequency aliasing in each signal component. If there is aliasing, the AMD method is used to decompose the signal until all the decomposed signals are mono-component signals. Evaluation considerations are covered with numerical simulations and experiments on measured radar data. The results demonstrate that compared with conventional HHT, the proposed method yields accurate decomposition for multicomponent micro-Doppler signals and improves the robustness of decomposition. The method presented here can also be applied in various settings of non-stationary signal analysis and filtering.

The overestimation of volume scattering (OVS) is an intrinsic drawback in model-based polarimetric synthetic aperture radar (PolSAR) target decomposition. It severely impacts the accuracy measurement of scattering power and leads to scattering mechanism ambiguity. In this paper, a hierarchical extended general four-component scattering power decomposition method (G4U) is presented. The conventional G4U is first proposed by Singh et al. and it has advantages in full use of information and volume scattering characterization. However, the OVS still exists in the G4U and it causes a scattering mechanism ambiguity in some oriented urban areas. In the proposed method, matrix rotations by the orientation angle and the helix angle are applied. Afterwards, the transformed coherency matrix is applied to the four-component decomposition scheme with two refined models. Moreover, the branch condition applied in the G4U is substituted by the ratio of correlation coefficient (RCC), which is used as a criterion for hierarchically implementing the decomposition. The performance of this approach is demonstrated and evaluated with the Airborne Synthetic Aperture Radar (AIRSAR), Uninhabited Aerial Vehicle Synthetic Aperture Radar (UAVSAR), Radarsat-2, and the Advanced Land Observing Satellite (ALOS) Phased Array type L-band Synthetic Aperture Radar (PALSAR) fully polarimetric data over different test sites. Comparison studies are carried out and demonstrated that the proposed method exhibits promising improvements in the OVS and scattering mechanism characterization.