The detection of objects concealed under people’s clothing is a very challenging task, which has crucial applications for security. When testing the human body for metal contraband, the concealed targets are usually small in size and are required to be detected within a few seconds. Focusing on weapon detection, this paper proposes using a real-time detection method for detecting concealed metallic weapons on the human body applied to passive millimeter wave (PMMW) imagery based on the You Only Look Once (YOLO) algorithm, YOLOv3, and a small sample dataset. The experimental results from YOLOv3-13, YOLOv3-53, and Single Shot MultiBox Detector (SSD) algorithm, SSD-VGG16, are compared ultimately, using the same PMMW dataset. For the perspective of detection accuracy, detection speed, and computation resource, it shows that the YOLOv3-53 model had a detection speed of 36 frames per second (FPS) and a mean average precision (mAP) of 95% on a GPU-1080Ti computer, more effective and feasible for the real-time detection of weapon contraband on human body for PMMW images, even with small sample data.

Tomographic synthetic aperture radar (TomoSAR) has been widely used in three-dimensional (3D) reconstruction of urban buildings. However, due to the baseline distribution and the limitations of the algorithm itself, the building point cloud after tomographic imaging is flooded by substantial noise and/or false targets. Thus, TomoSAR point clouds must be extracted from these unwanted factors to reconstruct the building structure. Existing line-based extraction methods can only detect straight lines, which results in the loss of non-linear point clouds. Thus, inspired by density clustering, we propose a point cloud extraction method using the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) algorithm. The DBSCAN can preserve the building structure more completely by enabling the extraction of various shapes of the buildings. Since the detection of point clouds is density-based, noise and false targets that exhibit low-density distribution can be accurately detected and rejected. The experimental results demonstrated the effectiveness of our method for TomoSAR point cloud extraction, as well as the structural protection of buildings, which achieves a higher extraction accuracy compared to linear detection.

The change detection of urban buildings is currently a hotspot in the research area of remote sensing, which plays a vital role in urban planning, disaster assessments and surface dynamic monitoring. SAR images have unique characteristics compared with traditional optical images, mainly including abundant image information and large data volume. However, the majority of currently used SAR images for the detection of changes in buildings have the problems of missing the detection of small buildings and poor edge segmentation. Therefore, this paper proposes a new approach based on deep learning for changing building detection, which we called CD-TransUNet. It should be noted that CD-TransUNet is an end-to-end encoding–decoding hybrid Transformer model that combines the UNet and Transformer. Additionally, to enhance the precision of feature extraction and to reduce the computational complexity, the CD-TransUNet integrates coordinate attention (CA), atrous spatial pyramid pooling (ASPP) and depthwise separable convolution (DSC). In addition, by sending the differential images to the input layer, the CD-TransUNet can focus more on building changes over a large scale while ignoring the changes in other land types. At last, we verify the effectiveness of the proposed method using a pair of ALOS-2(L-band) acquisitions, and the comparative experimental results obtained from other baseline models show that the precision of the CD-TransUNet is much higher and the Kappa value can reach 0.795. Furthermore, the low missed alarms and the accurate building edge reflect that the proposed method is more appropriate for building changing detection tasks.

Unlike optical satellites, synthetic aperture radar (SAR) satellites can operate all day and in all weather conditions, so they have a broad range of applications in the field of ocean monitoring. The ship targets’ contour information from SAR images is often unclear, and the background is complicated due to the influence of sea clutter and proximity to land, leading to the accuracy problem of ship monitoring. Compared with traditional methods, deep learning has powerful data processing ability and feature extraction ability, but its complex model and calculations lead to a certain degree of difficulty. To solve this problem, we propose a lightweight YOLOV5-MNE, which significantly improves the training speed and reduces the running memory and number of model parameters and maintains a certain accuracy on a lager dataset. By redesigning the MNEBlock module and using CBR standard convolution to reduce computation, we integrated the CA (coordinate attention) mechanism to ensure better detection performance. We achieved 94.7% precision, a 2.2 M model size, and a 0.91 M parameter quantity on the SSDD dataset.

Tomographic synthetic aperture radar (TomoSAR) produces 3-D point clouds with unavoidable noise or false targets that seriously deteriorate the quality of 3-D images and the building reconstruction over urban areas. In this paper, a Hough transform was adopted to detect the outline of a building; however, on one hand, the obtained outline of a building with Hough transform is broken, and on the other hand, some of these broken lines belong to the same segment of a building outline, but the parameters of these lines are slightly different. These problems will lead to that segment of a building outline being represented by multiple different parameters in the Hough transform. Therefore, an unsupervised clustering method was employed for clustering these line parameters. The lines gathered in the same cluster were considered to correspond to a same segment of a building outline. In this way, different line parameters corresponding to a segment of a building outline were integrated into one and then the continuous outline of the building in cloud points was obtained. Steps of the proposed data processing method were as follows. First, the Hough transform was made use of to detect the lines on the tomography plane in TomoSAR point clouds. These detected lines lay on the outline of the building, but they were broken due to the density variation of point clouds. Second, the lines detected using the Hough transform were grouped as a date set for training the building outline. Unsupervised clustering was utilized to classify the lines in several clusters. The cluster number was automatically determined via the unsupervised clustering algorithm, which meant the number of straight segments of the building edge was obtained. The lines in each cluster were considered to belong to the same straight segment of the building outline. Then, within each cluster, which represents a part or a segment of the building edge, a repaired straight line was constructed. Third, between each two clusters or each two segments of the building outline, the joint point was estimated by extending the two segments. Therefore, the building outline was obtained as completely as possible. Finally, taking the estimated building outline as the clustering center, supervised learning algorithm was used to classify the building cloud point and the noise (or false targets), then the building cloud point was refined. Then, our refined and unrefined data were fed into the neural network for building the 3-D construction. The comparison results show the correctness and the effectiveness of our improved method.

Reservoir bank landslides are a frequent phenomenon, and the stability of these landslides is affected by two essential factors: rainfall and reservoir level changes. Studying the response patterns of reservoir bank landslide movements to these variables is crucial in preventing their occurrence and mitigating their effects. To this end, this study employed 103 European Space Agency (ESA) Copernicus Sentinel-1 images and the SBAS-InSAR (small baseline subset interferometric synthetic aperture radar) technique to obtain a time series of the Guobu slope deformation from September 2015 to December 2019. The Guobu slope showed significant toppling damage. The satellite line of sight (LOS) detected a maximum subsidence rate of −447 mm/y (the negative sign indicates movement away from the satellite, i.e., subsidence) in the upper section of the slope. Subsequently, three wavelet tools were used to quantitatively analyze the effect of rainfall and reservoir water level on the deformation of the Guobu slope. The results demonstrate a positive correlation between rainfall and the deformation of the Guobu slope. Moreover, the deformation lags behind the rainfall by approximately 70 days. In contrast, the reservoir water level and the deformation of the Guobu slope exhibit an inverse relationship. The deformation of the leading edge of the slope body lags behind the reservoir level by approximately 19 days, while the middle and upper sections of the slope body, which have the most significant rate of variability, lag by about 80 days. Among these factors, rainfall plays a dominant role in the deformation of the Guobu slope, while reservoir levels play a synergistic role. The findings of this study highlight the importance of monitoring and understanding the impact of changes in rainfall and reservoir water levels on the stability of reservoir bank landslides. This understanding is crucial in preventing the occurrence of such landslides and minimizing their impact. The use of remote sensing techniques, together with wavelet analysis, enables the accurate and timely monitoring of the deformation of the Guobu slope, providing valuable insights for disaster warnings and disaster prevention and reduction efforts.