A5100449076- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Remote Sensing and LiDAR Applications
- Advanced Image Fusion Techniques
- Soil Geostatistics and Mapping
- Soil Moisture and Remote Sensing
- Image and Signal Denoising Methods
- Oil Spill Detection and Mitigation
- Automated Road and Building Extraction
- Advanced Algorithms and Applications
- Advanced Image and Video Retrieval Techniques
- Machine Fault Diagnosis Techniques
- Industrial Technology and Control Systems
- Flood Risk Assessment and Management
- Climate change and permafrost
- Advanced Sensor and Control Systems
- Advanced Measurement and Detection Methods
- Advanced Computational Techniques and Applications
- Remote Sensing in Agriculture
- Industrial Vision Systems and Defect Detection
- Gear and Bearing Dynamics Analysis
- Earthquake Detection and Analysis
- Landslides and related hazards
- Meteorological Phenomena and Simulations
- Precipitation Measurement and Analysis
China University of Petroleum, East China
2018-2025
State Grid Corporation of China (China)
2013-2025
Ministry of Water Resources of the People's Republic of China
2025
Ministry of Natural Resources
2025
State Power Investment Corporation (China)
2024
Northeast Forestry University
2024
Northeast Normal University
2024
China Earthquake Administration
2019-2023
Nanjing Drum Tower Hospital
2023
Guilin University of Electronic Technology
2023
Standard deviational ellipse (SDE) has long served as a versatile GIS tool for delineating the geographic distribution of concerned features. This paper firstly summarizes two existing models calculating SDE, and then proposes novel approach to constructing same SDE based on spectral decomposition sample covariance, by which concept is naturally generalized into higher dimensional Euclidean space, named standard hyper-ellipsoid (SDHE). Then, rigorous recursion formulas are derived confidence...
Accurate monitoring of tree species diversity is crucial for understanding the dynamic changes in and its relationships with other services functions forest ecosystems. Traditional optical remote sensing data have been widely used based on spectral variation hypothesis (SVH). However, this method cannot capture three-dimensional structural variations complex compositions under different stand conditions. In study, we modeled terms complexity a typical natural secondary Northeast China by...
This letter presents a semi-automatic approach to delineating road networks from very high resolution satellite images. The proposed method consists of three main steps. First, the geodesic is used extract initial segments that link seed points prescribed in advance by users. Next, probability map produced based on these coarse and further direct thresholding operation separates image into two classes surfaces: nonroad classes. Using class image, kernel density estimation generated, upon...
Rapid identification of post-earthquake collapsed buildings can be used to conduct immediate damage assessments (scope and extent), which could potentially conducive the formulation emergency response strategies. Up present, earthquake are mainly achieved through artificial field investigations, time-consuming cannot meet urgent requirements quick-response relief allocation. In this research study, an intelligent assessment method based on deep-learning, super-pixel segmentation,...
Marine oil spill pollution has caused serious impacts on marine ecological environments, resources and economy. Synthetic Aperture Radar (SAR), especially polarmetric SAR (PolSAR), been proven to be a powerful efficient tool for detection. In general, traditional detection methods mainly rely artificially-extracted polarization characteristics, the accuracy is limited by quality of feature extraction. Recently proposed Convolutional neural network (CNN) capable mining spatial from large data...
Abstract The pseudocapacitive performance of MnO 2 is intrinsically determined by its electronic structure, especially the spin state. However, correlation between electrochemical behavior and state electrode materials remains ill‐defined, efficient regulation strategies for are thus lacking. Herein, study reports laser thermal shock electrochemically deposited regulation. combined use theoretical calculation experimental investigation indicates that induces oxygen vacancy in to reduce...
Accurate road centerline extraction plays an important role in practical remote sensing applications. Most existing methods have many limitations when the classified image contains complicated objects such as curvilinear, close, or short extent features. To cope with these limitations, this study presents a novel accurate method that integrates tensor voting, principal curves, and geodesic method. The proposed consists of three main steps. Tensor voting is first used to extract feature...
Marine oil spills are one of the most serious problems marine environmental pollution. Hyperspectral remote sensing has been proven to be an effective tool for monitoring spills. To make full use spectral and spatial features, this study proposes a spectral-spatial features integrated network (SSFIN) applies it hyperspectral detection spill. Specifically, 1-D 2-D convolutional neural (CNN) models have employed extraction respectively. During stage feature extraction, three consecutive...
This report presents our new findings in microscopic fluid flow based on digital rocks. Permeability of rocks can be estimated by pore-scale simulations using the Stokes equation, but computational cost extremely high due to complicated pore geometry and large number voxels. In this study, a novel method is proposed simplify three-dimensional simulation multiple decoupled two- dimensional ones, each two-dimensional provides velocity distribution over slice. By approach, expensive equation...
Deep learning-based SAR oil spill detection faces significant challenges due to limited labeled training data. To address this, we propose SinGAN-Labeler, an enhanced framework that generates high-quality synthetic images and their labels from minimal input. The model integrates adaptive module automate scale parameter optimization, accelerating training, a hybrid attention combining spatial, channel, global contextual mechanisms enhance feature extraction. By leveraging multi-scale with...
With the transformation of global energy structure and rapid development new power generation technologies, system planning faces challenge multi-source–storage coordinated deployment. This paper proposes a method, collaborative source–grid–load–storage, considering wind photovoltaic systems. First, taking into account access renewable such as solar power, output model is constructed. Secondly, typical intraday dispatch constructed; on this basis, by adding constraints different types...
For the remote sensing classification task, ability of a single data source to identify ground objects remains limited due lack feature diversity. As typical sources, hyperspectral imagery (HSI) and light detection ranging (LiDAR) can provide complementary spectral features elevation information, respectively. To enhance ability, multi-scale Pseudo-Siamese Network with attention mechanism (MA-PSNet) is proposed by fusing HSI LiDAR data. In network, two sub-branch networks are designed for...
Point cloud filtering is an important prerequisite for three-dimensional surface modeling with high precision based on LiDAR data. To cope the issues of low accuracy or excessive model complexity in traditional algorithms, this paper proposes a method point multi-scale convolutional neural network incorporated attention mechanism. Firstly, regular image patch centering each constructed elevation information clouds. As thus, problem transformed into classification problem. Then, considering...