Semantic context plays a significant role in image segmentation. However, few prior works have explored semantic contexts for 3D point cloud segmentation. In this paper, we propose a simple yet effective Point Context Encoding (PointCE) module to capture semantic contexts of a point cloud and adaptively highlight intermediate feature maps. We also introduce a Semantic Context Encoding loss (SCE-loss) to supervise the network to learn rich semantic context features. To avoid hyperparameter tuning and achieve better convergence performance, we further propose a geometric mean loss to integrate both SCE-loss and segmentation loss. Our PointCE module is general and lightweight, and can be integrated into any point cloud segmentation architecture to improve its segmentation performance with only marginal extra overheads. Experimental results on the ScanNet, S3DIS and Semantic3D datasets show that consistent and significant improvement can be achieved for several different networks by integrating our PointCE module. The code of this work will be publicly available online.

The exploitation of multi-view synthetic aperture radar (SAR) images can effectively improve the performance of target recognition. However, due to the various extended operating conditions (EOCs) in practical applications, some of the collected views may not be discriminative enough for target recognition. Therefore, each of the input views should be examined before being passed through to multi-view recognition. This paper proposes a novel structure for multi-view SAR target recognition. The multi-view images are first classified by sparse representation-based classification (SRC). Based on the output residuals, a reliability level is calculated to evaluate the effectiveness of a certain view for multi-view recognition. Meanwhile, the support samples for each view selected by SRC collaborate to construct an enhanced local dictionary. Then, the selected views are classified by joint sparse representation (JSR) based on the enhanced local dictionary for target recognition. The proposed method can eliminate invalid views for target recognition while enhancing the representation capability of JSR. Therefore, the individual discriminability of each valid view as well as the inner correlation among all of the selected views can be exploited for robust target recognition. Experiments are conducted on the moving and stationary target acquisition recognition (MSTAR) dataset to demonstrate the validity of the proposed method.

Anomaly detection is an important task in hyperspectral imagery (HSI) processing. It provides a new way to find targets that have significant spectral differences from the majority of the dataset. Recently, the representation-based methods have been proposed for detecting anomaly targets in HSIs. It is essential for this type of method to construct a valid background dictionary to distinguish anomaly and background accurately. In this paper, a novel hyperspectral anomaly detection method based on background estimation and adaptive weighted sparse representation has been proposed. Firstly, to obtain the effective background dictionary without anomaly information, a new background dictionary construction strategy is designed. Secondly, the sparse representation based on the constructed background dictionary is utilized on the dataset. Anomalies and background are distinguished through the response of the residual matrix. Thirdly, the residual matrix is weighted adaptively from global and local domains, which makes anomalies and background more discriminative. An important advantage of the proposed method is that it considers the properties of anomalies in both spectral and spatial domains. Experiments on three HSI datasets reveal that our proposed method achieves an outstanding detection performance compared with the other anomaly detection algorithms.

Hyperspectral anomaly detection plays an important role in the field of remote sensing. It provides a way to distinguish interested targets from the background without any prior knowledge. The majority of pixels in the hyperspectral dataset belong to the background, and they can be well represented by several endmembers, so the background has a low-rank property. Anomalous targets usually account for a tiny part of the dataset, and they are considered to have a sparse property. Recently, the low-rank and sparse matrix decomposition (LRaSMD) technique has drawn great attention as a method for solving anomaly detection problems. In this letter, a new anomaly detection method based on LRaSMD and cluster weighting is proposed. We concentrate on the sparse part, which contains most of anomaly information, and calculate the initial anomaly matrix based on this part. To suppress background regions and discriminate anomalies from the background more distinctly, a weighting strategy in terms of the clustering result is used, and then the anomaly matrix is updated. The judgement of anomalies is made according to the responses on the matrix. Our proposed method considers the characteristics of anomalies from the spectral dimension and the spatial distribution simultaneously. Experiments on three hyperspectral datasets demonstrate the outstanding performance of the proposed method.

Numerous hyperspectral anomaly detection (AD) methods suffer from complex background compositions and subpixel objects due to their inadequate Gaussian-distributed representations for nonhomogeneous backgrounds or their low discrimination between subpixel anomalies and the background. To alleviate these issues, a novel hyperspectral AD weighting strategy based on tensor decomposition and cluster weighting is proposed in this letter. Equipped with this simple but effective strategy as a postprocess, the detection performances of generic AD methods can be significantly boosted. In this strategy, Tucker decomposition is adopted to remove the major background information. A parameter-adaptive k-means clustering method is then applied on the decomposed anomaly/noise data cube to assemble homogeneous regions. After segmenting the clustering result into a number of nonoverlapping eight-connected domains, corresponding weights are assigned to large domains according to an improved Gaussian weight function. Finally, the resulting weight matrix is multiplied by the results of the detectors to achieve a performance boost. Experiments on two hyperspectral data sets validate the effectiveness of the proposed strategy.

Recently, deep learning has been widely used in synthetic aperture radar (SAR) aircraft detection. However, the complex environment of the airport—consider the boarding bridges, for instance—greatly interferes with aircraft detection. Besides, the detection speed is also an important indicator in practical applications. To alleviate these problems, we propose a lightweight detection model (LDM), mainly including a reuse block (RB) and an information correction block (ICB) based on the Yolov3 framework. The RB module helps the neural network extract rich aircraft features by aggregating multi-layer information. While the RB module brings more effective information, there is also redundant and useless information aggregated by the reuse block, which is harmful to detection precision. Therefore, to accurately extract more aircraft features, we propose an ICB module combining scattering mechanism characteristics by extracting the gray features and enhancing spatial information, which helps suppress interference in a complex environment and redundant information. Finally, we conducted a series of experiments on the SAR aircraft detection dataset (SAR-ADD). The average precision was 0.6954, which is superior to the precision values achieved by other methods. In addition, the average detection time of LDM was only 6.38 ms, making it much faster than other methods.