A5040357722- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Advanced SAR Imaging Techniques
- Geology and Paleoclimatology Research
- Advanced Image Fusion Techniques
- Coastal wetland ecosystem dynamics
- Geological formations and processes
- Radar Systems and Signal Processing
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Advanced Radiotherapy Techniques
- Coastal and Marine Dynamics
- Remote Sensing and LiDAR Applications
- Marine and coastal ecosystems
- Higher Education and Teaching Methods
- Microwave Imaging and Scattering Analysis
- Remote Sensing in Agriculture
- Flood Risk Assessment and Management
- Advanced Neural Network Applications
- Coastal and Marine Management
- Oceanographic and Atmospheric Processes
- Environmental Changes in China
- Meteorological Phenomena and Simulations
- Oil Spill Detection and Mitigation
- Advanced Image and Video Retrieval Techniques
- Arctic and Antarctic ice dynamics
China University of Petroleum, East China
2016-2025
Yantaishan Hospital
2025
Heilongjiang Provincial Academy of Agricultural Sciences
2024
State Key Laboratory of Vehicle NVH and Safety Technology
2017-2024
Ocean University of China
2024
Nanjing University
2017-2024
Jiangxi Normal University
2023-2024
Shanghai Electric (China)
2017-2024
Qingdao Institute of Bioenergy and Bioprocess Technology
2024
Chinese Academy of Sciences
2024
Synthetic aperture radar (SAR) imaging is used to identify ships, which a vital task in the maritime industry for managing fisheries, marine transit, and rescue operations. However, some problems, like complex background interferences, various size ship feature variations, indistinct tiny characteristics, continue be challenges that tend defy accuracy improvements SAR detection. This research study multiscale ships detection has developed an upgraded YOLOv5s technique address these issues....
This study highlights the coastline position changes of Qingdao coastal area from 2000 to 2019, using GIS and remote sensing technologies through Digital Shoreline Analysis System LANDSAT images. Understanding movement by suitable method is an important challenge for this extremely dynamic coast. The shoreline were statistically measured three techniques, namely; Linear Regression Rate, End Point Rate Net Movement. For automatic extraction, different methods applied, but among them most...
This study is conducted in accordance with a systematic literature review (SLR) protocol. SLR tasked finding publications, publishers, deep learning types, enhanced and adapted techniques, impacts, proactive approaches, key parameters, applications the field of remote sensing. It also expected to identify current research directions, gaps, unsolved issues order provide understanding recommendations for future studies. The data collected from important papers published recognized journals...
Ship tracking technology is crucial for emergency rescue in the event of a disaster. Quickly identifying position and status vessels vital teams to be able deploy efficiently disaster areas. When responding emergencies or natural disasters, ship plays critical role supporting operations resource allocation, improving overall resilience maritime transportation system. However, research on multi-object (MOT) algorithms has primarily focused optical image datasets. In contrast, data from...
Helical tomotherapy has been developed at the University of Wisconsin, and 'Hi-Art II' clinical machines are now commercially manufactured. At core each machine lies a ring-gantry-mounted short linear accelerator which generates x-rays that collimated into fan beam intensity-modulated radiation by binary multileaf, modulation being variable with gantry angle. Patients treated lying on couch is translated continuously through bore as rotates. Highly conformal dose-distributions can be...
Autoencoders (AEs) are commonly utilized for acquiring low-dimensional data representations and performing reconstruction, which makes them suitable hyperspectral unmixing. However, AE networks trained pixel by those employing localized convolutional filters disregard the global material distribution distant interdependencies, resulting in loss of necessary spatial feature information essential unmixing process. To overcome this limitation, we propose an innovative deep neural network model...
Deep learning (DL) has gained popularity in hyperspectral unmixing (HU) applications recently due to its powerful and data-fitting capabilities. As an baseline network, the autoencoder (AE) framework performs well HU by automatically low-dimensional embeddings reconstructing data. Nevertheless, there are spectral variability nonlinear mixing problems highly mixed region of images, which can cause interference structures using only AE. Therefore, inspired effectiveness mask modeling, we...
Abstract To investigate the impact of changes in Changjiang catchment on estuarine coast‐shelf sedimentary system, variations transport, distribution, and budget 210 Pb sediment subaqueous delta (CSD) Zhejiang‐Fujian coastal mud belt (ZFCMB) system were analyzed before after impounding Three Gorges Dam (TGD). The results indicate that ex activity surficial sediments CSD‐ZFCMB decreased significantly 2003 vertical distribution CSD changed substantially due to intensified redistribution....
Finding an appropriate and accurate technology for early detection of disease is significantly important to research treatments. We proposed some novel automatic classification systems based on the stationary wavelet transform (SWT) improved support vector machine (SVM). Magnetic Resonance Imaging (MRI) commonly used brain imaging as a non-invasive diagnostic tool assist pre-clinical diagnosis. However, MRI generates large information set, which poses challenge classification. To deal with...
Target recognition from remote sensing images is commonly challenging because of large-scale variations and small objects, these challenges are more prominent in satellite video images. The current object detection algorithms have some difficulties fine-grained feature extraction classification for multi-scale objects. We propose a novel model called the SVSDet method based on YOLOv5 improvement to address abovementioned issues. In this method, we introduced Space-to-depth module into...
Abstract Many large estuaries are threatened by intensifying hypoxia. However, due to the limited duration of available observations, uncertainties persist regarding level contemporary hypoxia intensity in a longer-term context and relative contributions climate versus human factors. Here we present sediment records for associated environmental parameters Yangtze Estuary over past three centuries. The results show that has been increasing during last half century anthropogenic...
Diabetic retinopathy, a retinal disorder resulting from diabetes mellitus, is prominent cause of visual degradation and loss among the global population. Therefore, identification classification diabetic retinopathy are utmost importance in clinical diagnosis therapy. Currently, these duties extensively carried out by manual examination utilizing human system. Nevertheless, sometimes arduous, time-consuming, prone to errors. Deep learning-based methods have recently demonstrated encouraging...