Man-made targets subjected to different polarized waves will produce different depolarization effects, and these differences contain abundant information beneficial for recognition. However, traditional manually designed features struggle to fully utilize polarimetric information for scattering characterization. This letter proposes a target scattering characteristic learning network based on the Null-Pol response, which adaptively extracts the proportions of typical scattering mechanisms from mixed scattering mechanisms. Firstly, by leveraging polarimetric modulation, the Discrete Null-Pol Synthesis Pattern (DNSP) is designed to fully reveal the differences in target scattering mechanisms. On this basis, we propose an end-to-end scattering inversion network module to learn the DNSPs of different typical targets under scattering ambiguity conditions, obtaining polarimetric scattering contribution of 10 typical structures. Finally, we conduct structure recognition experiments to demonstrate the effectiveness of the proposed module. The results show that the proposed method can effectively characterize scattering behavior and significantly improve the performance of target structure recognition.

Vehicle detection is an important application of polarimetric synthetic aperture radar (PolSAR). Geometrical perturbation polarimetric notch filter (GP-PNF) establishes a feature space based on the local background polarimetric characteristics to achieve adaptive detection of ship targets. However, the complexity of the ground background presents additional challenges compared to sea surface. In this work we model the distribution of the GP-PNF and prove its effectiveness and accuracy compared with other common distribution models based on real airborne mini-SAR data. And then we introduce a numerical calculation of logarithm cumulants for parameters estimation, derive the constant false alarm rate (CFAR) threshold computation formula and apply the filter to vehicle detection. Experiments performed on real high-resolution PolSAR images verify the good performance of the detection method.

A lightweight SAR ship detection algorithm is necessary to further meet the demands of military applications. This paper proposes an end-to-end efficient SAR ship target detection algorithm based on RT-DETR called YO-DETR. In the feature extraction network, a CNN-based backbone network is used to replace the transformer-based encoder structure, which retains the original feature extraction capability while reducing the number of parameters. Additionally, in order to retain the characteristic of long-distance feature dependency in transformers, the IRMB module is incorporated into the CNN network to enhance long-distance feature interaction. Finally, the introduction of the decoder head reduces the additional time overhead of traditional NMS during inference. Ultimately, the YO-DETR method achieves a 98.2% mAP on the SSDD dataset with only 5.37M parameters and 10.5M weight size, while the FPS (when batch size is set to 32) also achieves 220.4.

Deep learning methods have made profound advancements in the field of synthetic aperture radar (SAR) target recognition. Typically, a significant amount of training data is required. However, due to the high degree of prior expert knowledge required for the annotation of SAR images, it is challenging to obtain a large amount of labeled data, which significantly impacts the performance of target recognition. To address this issue, this paper introduces an Azimuth-Aware Multi-Head Residual Self-Attention Network (MHRA-Net) that can extract high discriminative features of targets. Initially, this model employs a sub-aperture decomposition method to expand target information across multiple azimuth angles. Subsequently, we design a multi-head residual self-attention mechanism that can extract salient features of targets from multiple perspectives. Finally, a multi-scale feature fusion module is used to extract both global and local information about the target, enhancing model robustness and allowing the network to achieve satisfactory recognition performance even under sample-constrained conditions. Experimental results on a 10-class vehicle SAR image dataset demonstrate the effectiveness of the proposed approach.

Ship detection in polarimetric synthetic aperture radar (PolSAR) images has attracted widespread attention in recent years. However, pixel level detection methods are heavily affected by inherent speckle noise. In this letter, we proposed a detection method that enhances the ship-sea contrast beforehand by combining local statistical saliency and scattering mechanism coherence in superpixel-level. Firstly, simple linear iterative clustering (SLIC) based segmentation method is adopted for PolSAR images to generate superpixels. Then, local saliency is calculated based on superpixel-level similarity from the perspective of statistical characteristics. Based on this, the superpixel-level modified polarimetric coherence metric is obtained from the perspective of physical scattering mechanisms, which can help distinguish small ships with low saliency and strong sea clutters with high saliency. Ship detection is achieved by combining the two features above. The experimental results based on real PolSAR data show that compared with other classic and state-of-the-art methods, the proposed method has improved the figure of merit by at least 4.28% and has increased the target clutter ratio by at least 8.43 decibel (dB) on average.

Superpixel segmentation is essential to the rapid information extraction and image interpretation. In this paper, we develop a superpixel segmentation method for polarimetric synthetic aperture radar (PolSAR) images, utilizing minimum spanning tree algorithm (MST) to achieve a hierarchy of superpixels. Thereinto, the revised Wishart distance and region intensity distance is applied to accurately measure the dissimilarity between two neighboring pixels. The proposed method can generate superpixels of different scales in real time, so it has significant application value. The performance of the proposed method is validated on experimental PolSAR dataset from the ESAR system.

In recent years, deep learning has made breakthroughs in the field of computer vision, the single-stage detection algorithm represented by You Only Look Once (YOLO) has achieved satisfying detection results in SAR ship target detection. For the multi-scale problem of SAR ship targets in complex scenes, we proposed an improved YOLOv5 detection method using Convolutional Block Attention Module (CBAM) and Bidirectional Feature Pyramid Network (BiFPN). The CBAM module and BiFPN are added in YOLOv5 so that it can fully learn the feature information of space and channel dimensions, and enhance information fusion transfer between multi-scale targets. Experiments on our dataset show that the proposed YOLOv5 algorithm achieves 92.8% Average Precision (AP), which gains a 1.9% improvement in AP compared to the standard YOLOv5 algorithm in SAR ship target detection. The problem of missed detection of multi-scale targets is well solved.

Current synthetic aperture radar (SAR) ship detectors achieve excellent performance with sufficient samples while encountering degraded results when the sensors and imaging conditions change. The mismatch of view, shape, and illumination inevitably result in the variations of feature distribution between source domain and target domain, which will lead to detection performance degradation. Therefore, devising a detector with well transferability to new domains remains a challenging issue. To this end, this letter proposes a novel domain adaptive YOLOv5 framework for cross-domain SAR ship detection, which is composed of the following keypoints: 1) a cross-domain co- attention feature correlation module, which models spatial and semantic interdependencies by capturing pixel correspondence between source and target domain in a bidirectional way; 2) a multilevel feature alignment module, which constrains the inter-domain difference of features from different scales by inserting three domain classifiers; and 3) teacher–student mutual learning, which makes full use of unlabeled target data and iteratively generates higher-quality pseudo-labels, thus further improving a teacher model with narrowed domain gap. Model performance is evaluated on three SAR ship datasets, and comprehensive results demonstrate the superiority of our method on multiple domain transfer scenarios, i.e., cross resolution, cross-sensor adaptation, and cross-resolution adaptation under the same sensor.

This paper addresses the problem of joint tracking and classification (JTC) of a single extended target with a complex shape. To describe this complex shape, the spatial extent state is first modeled by star-convex shape via a random hypersurface model (RHM), and then used as feature information for target classification. The target state is modeled by two vectors to alleviate the influence of the high-dimensional state space and the severely nonlinear observation model on target state estimation, while the Euclidean distance metric of the normalized Fourier descriptors is applied to obtain the analytical solution of the updated class probability. Consequently, the resulting method is called the “JTC-RHM method.” Besides, the proposed JTC-RHM is integrated into a Bernoulli filter framework to solve the JTC of a single extended target in the presence of detection uncertainty and clutter, resulting in a JTC-RHM-Ber filter. Specifically, the recursive expressions of this filter are derived. Simulations indicate that: (1) the proposed JTC-RHM method can classify the targets with complex shapes and similar sizes more correctly, compared with the JTC method based on the random matrix model; (2) the proposed method performs better in target state estimation than the star-convex RHM based extended target tracking method; (3) the proposed JTC-RHM-Ber filter has a promising performance in state detection and estimation, and can achieve target classification correctly.

Deep neural networks have achieved great progress in 3D scene understanding. However, recent methods mainly focused on objects with canonical orientations in contrast with random postures in reality. In this letter, we propose a hierarchical neural network, named Local Frame Network (LFNet), based on the local rotation invariant coordinate frame for robust point cloud analysis. The local point patches in different orientated objects are transformed into an identical distribution based on this coordinate frame, and the transformed coordinates are taken as input features to eliminate the influence of rotations at the input level. Meanwhile, a discrete convolution operator is defined in the constructed coordinate frame to extract rotation invariant features from local patches, which can further remove the influence of rotations at the convolution level. Moreover, a Spatial Feature Encoder (SFE) module is utilized to perceive the spatial structure of the local region. Mathematical analysis and experimental results on two public datasets demonstrate that the proposed method can eliminate the influence of rotations without data augmentation and outperforms other state-of-the-art methods.

Object detection for optical remote sensing images have undergone rapid development in recent years, due to the advanced techniques of deep learning. However, the diverse objects with different scales and aspect ratios increase the difficulty of detection. In this paper, we improve the detection performance by applying guided anchor generation and feature fusion. In specific, the guided anchoring block directly predicts the positions and shapes of the anchor boxes, taking the place of sliding windows and preset shapes in the original region proposal network (RPN). Then, it can obtain diverse and adaptable anchor boxes, avoiding the generation of redundant and monotonous anchor boxes. In addition, the RoI features obtained from different pyramid levels are fused together to predict the categories and locations of the objects. The experiments conducted on DOTA dataset demonstrate the effectiveness of the proposed method.

Semantic segmentation of 3D scenes is a fundamental problem in 3D computer vision. In this paper, we propose a deep neural network for 3D semantic segmentation of raw point clouds. A multi-scale feature learning block is first introduced to obtain informative contextual features in 3D point clouds. A global and local feature aggregation block is then extended to improve the feature learning ability of the network. Based on these strategies, a powerful architecture named 3DMAX-Net is finally provided for semantic segmentation in raw 3D point clouds. Experiments have been conducted on the Stanford large-scale 3D Indoor Spaces Dataset using only geometry information. Experimental results have clearly shown the superiority of the proposed network.

In this paper, a superpixel-based segmentation method is proposed for PolSAR images by utilizing hierarchical region merging and segment refinement. The loss of the energy function, which determines the consistency of two adjacent regions from the statistical aspect, is applied to guide the merging procedure. In addition to the edge penalty term, the homogeneity measurement is also employed to prevent merging the regions that are from different land covers or objects. Based on the merged segments, the segment refinement is applied to further improve the segmentation accuracy by iteratively relabeling the edge pixels. It uses a maximum a posterior (MAP) criterion using the statistical distribution of the pixels and the Markov random field (MRF) model. The performance of the proposed method is validated on an experimental PolSAR dataset from the ESAR system.

This paper presents a global localization method for mobile robots based on the geometric information of structured indoor environments. With a global/local point cloud and projection map, lines are extracted from the projection maps using Hough transform. According to the directions of the obtained lines, the orientations of projection maps and point clouds are normalized. Next, the template matching algorithm is applied to the normalized global and local projection maps. Once coarse localization is completed, final accurate localization is achieved using the Iterative Closest Points (ICP) algorithm. Experimental results on several point clouds show that the proposed method can achieve high localization accuracy in real-time. The proposed method can be used for other global localization applications in structured environments.

The use of contextual information is beneficial to improve both the accuracy and reliability of image classification. Based on the robust fuzzy${c}$-means (RFCM) clustering method and an adaptive Markov random field model, this letter proposes a contextual${H}/{\bar {\alpha }}$classifier for polarimetric synthetic aperture radar images. At each iterative step of RFCM clustering, the prior probability extracted from the local neighborhood is combined with the fuzzy membership derived from inherent polarimetric characteristics, thus the enhanced fuzzy membership is more reliable. In addition, an adaptive smoothing factor is proposed for use during contextual information retrieval, which can prevent oversmoothing and preserve the local spatial details. The experimental results implemented using AIRSAR and ESAR L-band data validate the efficacy of the proposed method. Compared with the iterated Wishart classifier and fuzzy${H}/{\bar {\alpha }}$classifier, the proposed method significantly improves the classification accuracy, with less noise and increased preservation of details.

Point-cloud registration plays a significant role in the area of mobile LiDAR data processing. This paper proposes an automatic markerless registration algorithm for lidar point-clouds. It first introduces a local feature for point-cloud representation. The feature is invariant to rotations and translations of a point-cloud. It then presents a point-cloud registration method using geometric consistency check and the Iterative Closest Points (ICP) algorithm. Comparative experiments were performed on a publicly available dataset. Experimental results show that our algorithm is very accurate and outperforms the spin image and SHOT based algorithms.

In stepped-frequency (SF) radar systems, the high-order phase error due to target motion in each burst can blur the range profile seriously. The methods based on motion parameter estimation perform well in most cases. However, the motion parameter estimation is time consuming, which challenges the real-time imaging of a radar target. To solve this problem, a new easy-to-implement variant of SF signal format is proposed in this paper. By employing the new signal, the high-order phase error can be simply eliminated, and the motion parameter estimation is unnecessary, which makes the imaging efficient. The effectiveness of the proposed method is illustrated and analyzed with both simulations and real data.