Explore the vast range of titles available.

As an active microwave imaging sensor for the high-resolution earth observation, synthetic aperture radar (SAR) has been extensively applied in military, agriculture, geology, ecology, oceanography, etc., due to its prominent advantages of all-weather and all-time working capacity. Especially, in the marine field, SAR can provide numerous high-quality services for fishery management, traffic control, sea-ice monitoring, marine environmental protection, etc. Among them, ship detection in SAR images has attracted more and more attention on account of the urgent requirements of maritime rescue and military strategy formulation. Nowadays, most researches are focusing on improving the ship detection accuracy, while the detection speed is frequently neglected, regardless of traditional feature extraction methods or modern deep learning (DL) methods. However, the high-speed SAR ship detection is of great practical value, because it can provide real-time maritime disaster rescue and emergency military planning. Therefore, in order to address this problem, we proposed a novel high-speed SAR ship detection approach by mainly using depthwise separable convolution neural network (DS-CNN). In this approach, we integrated multi-scale detection mechanism, concatenation mechanism and anchor box mechanism to establish a brand-new light-weight network architecture for the high-speed SAR ship detection. We used DS-CNN, which consists of a depthwise convolution (D-Conv2D) and a pointwise convolution (P-Conv2D), to substitute for the conventional convolution neural network (C-CNN). In this way, the number of network parameters gets obviously decreased, and the ship detection speed gets dramatically improved. We experimented on an open SAR ship detection dataset (SSDD) to validate the correctness and feasibility of the proposed method. To verify the strong migration capacity of our method, we also carried out actual ship detection on a wide-region large-size Sentinel-1 SAR image. Ultimately, under the same hardware platform with NVIDIA RTX2080Ti GPU, the experimental results indicated that the ship detection speed of our proposed method is faster than other methods, meanwhile the detection accuracy is only lightly sacrificed compared with the state-of-art object detectors. Our method has great application value in real-time maritime disaster rescue and emergency military planning.

The goal of semantic segmentation is to classify each pixel in the image, so as to segment out the specific contour of the target. Most previous semantic segmentation models cannot generate enough semantic information for each pixel to understand the content of complex scenes. In this paper, we propose a novel semantic segmentation model Ince-DResAsppNet based on dense convoluted separation convolution. Unlike the previous model, our model revolves around reducing semantic information loss and enhancing detailed information. In the feature extraction part of the model, the idea of Dense and Ince is introduced to expand the number of channels on the basis of feature reuse. In the feature fusion part, Dense and Atrous’s idea of ​​dense dilated based on coprime factors is introduced, combined with multi-scale feature information to expand the receptive field and collect more dense pixels. Experiments conducted on the dataset PASCAL VOC 2012 and the CityScapes dataset show that our method performs better than the existing semantic segmentation model. Our model achieves 83.3% and 78.1% segmentation accuracy on the mIoU indicator, which surpasses many classical semantic segmentation models.

An accurate prediction of the machining tool condition during the cutting process is crucial for enhancing the tool life, improving the production quality and productivity, optimizing the labor and maintenance costs, and reducing workplace accidents. Currently, tool condition monitoring is usually based on machine learning algorithms, especially deep learning algorithms, to establish the relationship between sensor signals and tool wear. However, deep mining of feature and fusion information of multi-sensor signals, which are strongly related to the tool wear, is a critical challenge. To address this issue, in this study, an integrated prediction scheme is proposed based on deep learning algorithms. The scheme first extracts the local features of a single sequence and a multi-dimensional sequence from DenseNet incorporating a heterogeneous asymmetric convolution kernel. To obtain more perceptual historical data, a “dilation” scheme is used to extract features from a single sequence, and one-dimensional dilated convolution kernels with different dilation rates are utilized to obtain the differential features. At the same time, asymmetric one-dimensional and two-dimensional convolution kernels are employed to extract the features of the multi-dimensional signal. Ultimately, all the features are fused. Then, the time-series features hidden in the sequence are extracted by establishing a depth-gated recurrent unit. Finally, the extracted in-depth features are fed to the deep fully connected layer to achieve the mapping between features and tool wear values through linear regression. The results indicate that the average errors of the proposed model are less than 8%, and this model outperforms the other tool wear prediction models in terms of both accuracy and generalization.

The use of high-spatial-resolution remote sensing image technology on mobile and embedded equipment is an important and effective way for emergency rescue and evaluation decision-makers to quickly and accurately detect landslide areas. Deep learning-based landslide detection models include one-stage and two-stage models. The two-stage landslide detection models are slower. The one-stage landslide detection models are faster but less accurate. Both types of detection models have many parameters. This research aims to improve the speed, accuracy, and parameters of landslide detection models. A you only look once-small attention (YOLO-SA) landslide detection model is proposed. YOLO-SA is an improved version of the one-stage detection model YOLOv4. First, the group convolution (Gconv) and ghost bottleneck (G-bneck) residual modules are used to replace the convolution components and residual module consisting of standard convolution. The purpose is to reduce the parameters of the model. Then, on this basis, an attention mechanism is added to improve the detection accuracy of the model. Finally, the position of the attention mechanism is adjusted to determine the framework of YOLO-SA. Qiaojia and Ludian counties in Yunnan Province, China, are used as the study area to acquire three-channel (red, green, blue) historical landslide optical remote sensing images from Google Earth, with a total of 1818 images, for training the model. YOLO-SA is compared with 11 advanced models, including Faster-RCNN, 3 types of EfficientDet, 2 types of Centernet, SSD-efficient, and 4 types of YOLOv4 models. The results show that the number of YOLO-SA parameters is reduced to 1.472 mb compared to EfficientDet-D0; the accuracy is improved to 94.08% compared to Centernet-hourglass; and the speed is up to 42 f/s. In addition, the effectiveness of the YOLO-SA model for potential landslide detection is verified, with an F1 score of 90.65%.

The two-step backward differential formula (BDF2) with unequal time-steps is applied to construct an energy stable convex-splitting scheme for the Cahn–Hilliard model. We focus on the numerical influences of time-step variations by using the recent theoretical framework with the discrete orthogonal convolution kernels. Some novel discrete convolution embedding inequalities with respect to the orthogonal convolution kernels are developed such that a concise L 2 norm error estimate is established at the first time under an updated step-ratio restriction 0 < r k : = τ k / τ k - 1 ≤ r user , where r user can be chosen by the user such that r user < 4.864 . The stabilized convex-splitting BDF2 scheme is shown to be mesh-robustly convergent in the sense that the convergence constant (prefactor) in the error estimate is independent of the adjoint time-step ratios. The suggested method is proved to preserve a modified energy dissipation law at the discrete levels if 0 < r k ≤ r user , such that it is mesh-robustly stable in an energy norm. On the basis of ample tests on random time meshes, a useful adaptive time-stepping strategy is applied to efficiently capture the multi-scale behaviors and to accelerate the long-time simulation approaching the steady state.

The positive definiteness of real quadratic forms with convolution structures plays an important role in stability analysis for time-stepping schemes for nonlocal operators. In this work, we present a novel analysis tool to handle discrete convolution kernels resulting from variable-step approximations for convolution operators. More precisely, for a class of discrete convolution kernels relevant to variable-step L1-type time discretizations, we show that the associated quadratic form is positive definite under some easy-to-check algebraic conditions. Our proof is based on an elementary constructing strategy by using the properties of discrete orthogonal convolution kernels and discrete complementary convolution kernels. To the best of our knowledge, this is the first general result on simple algebraic conditions for the positive definiteness of variable-step discrete convolution kernels. Using the unified theory, the stability for some simple non-uniform time-stepping schemes can be obtained in a straightforward way.

Air pollution is a serious environmental problem that has attracted much attention. Air quality prediction can provide useful information for urban environmental governance decision-making and residents’ daily health control. However, existing research methods have suffered from a weak ability to capture the spatial correlations and fail to model the long-term temporal dependencies of air quality. To overcome these limitations, we propose a multi-scale spatiotemporal graph convolution network (MST-GCN), which consists of a multi-scale block, several spatial-temporal blocks and a fusion block. We first divide the extracted features into several groups based on their domain categories, and represent the spatial correlations across stations as two graphs. Then we combine the grouped features and the constructed graphs in pairs to form a multi-scale block that feeds into spatial-temporal blocks. Each spatial-temporal block contains a graph convolution layer and a temporal convolution layer, which can model the spatial correlations and long-term temporal dependencies. To capture the group interactions, we use a fusion block to fuse multiple groups. Extensive experiments on a real-world dataset demonstrate that our model achieves the highest performance compared with state-of-the-art and baseline models for air quality prediction.

Accurate traffic forecasting is a critical function of intelligent transportation systems, which remains challenging due to the complex spatial and temporal dependence of traffic data. GNN-based traffic forecasting models typically utilize predefined graphical structures based on prior knowledge and do not adapt well to dynamically changing traffic characteristics, which may limit their performance. The transformer is a compelling architecture with an innate global self-attention mechanism, but cannot capture low-level detail very well. In this paper, we propose a novel Spatial-Temporal Gated Hybrid Transformer Network (STGHTN), which leverages local features from temporal gated convolution, spatial gated graph convolution respectively and global features by transformer to further improve the traffic flow forecasting results. First, in the temporal dimension, we take full advantage of the local properties of temporal gated convolution and the global properties of transformer to effectively fuse short-term and long-term temporal dependence. Second, we mutually integrate two modules to complement each representation by utilizing spatial gated graph convolution to extract local spatial dependence and transformer to extract global spatial dependence. Furthermore, we propose a multi-graph model that constructs a road connection graph, a similarity graph, and an adaptive dynamic graph to exploit the static and dynamic associations between road networks. Experiments on four real datasets confirm the proposed method’s state-of-the-art performance. Our implementation of the STGHTN code via PyTorch is available at https://github.com/JianSoL/STGHTN.

Deep learning (DL)-based object detection algorithms have gained impressive achievements in natural images and have gradually matured in recent years. However, compared with natural images, remote sensing images are faced with severe challenges due to the complex backgrounds and difficult detection of small objects in dense scenes. To address these problems, a novel one-stage object detection model named MDCT is proposed based on a multi-kernel dilated convolution (MDC) block and transformer block. Firstly, a new feature enhancement module, MDC block, is developed in the one-stage object detection model to enhance small objects’ ontology and adjacent spatial features. Secondly, we integrate a transformer block into the neck network of the one-stage object detection model in order to prevent the loss of object information in complex backgrounds and dense scenes. Finally, a depthwise separable convolution is introduced to each MDC block to reduce the computational cost. We conduct experiments on three datasets: DIOR, DOTA, and NWPU VHR-10. Compared with the YOLOv5, our model improves the object detection accuracy by 2.3%, 0.9%, and 2.9% on the DIOR, DOTA, and NWPU VHR-10 datasets, respectively.

To solve the tracking accuracy degradation problem in scenarios with large displacements or nonrigid motion during target tracking, this paper proposes an optical flow estimation method based on multiscale anisotropic convolution. The network structure is improved in a step-by-step manner by extracting the data flow from the network according to the observed features. For the low-level neural network, a layered multiscale structure is used to build a cascade network by using hybrid dilated convolution to obtain feature information at different scales while ensuring the tracking accuracy. For the upper-layer neural network, hybrid inflated deformable convolution is used by learning the contextual long-range correlations and multidirectional adaptive offsets of features. Experiments are conducted on the Flying Chairs, KITTI, and MPI datasets. The results show that compared with various popular algorithm methods, the model in this paper reduces endpoint errors while retaining edge information in regions with large displacements or nonrigid motion. Code is available at https://github.com/yifanna/MACFlow-pytorch.