A5100780028- Oil Spill Detection and Mitigation
- Toxic Organic Pollutants Impact
- Marine and coastal ecosystems
- Remote-Sensing Image Classification
- Petroleum Processing and Analysis
- Atmospheric and Environmental Gas Dynamics
- Advanced Optical Sensing Technologies
- Remote Sensing and Land Use
- Infrared Target Detection Methodologies
- Water Quality Monitoring and Analysis
- Atmospheric aerosols and clouds
- Remote Sensing and LiDAR Applications
- Nasal Surgery and Airway Studies
- Flood Risk Assessment and Management
- Climate variability and models
- Soil erosion and sediment transport
- Meteorological Phenomena and Simulations
- Ocular and Laser Science Research
- Ocular Disorders and Treatments
- Facial Rejuvenation and Surgery Techniques
University of Electronic Science and Technology of China
2025
China Meteorological Administration
2023
Dalian Maritime University
2017-2021
Changchun Institute of Optics, Fine Mechanics and Physics
2018
Spectral characteristics play an important role in the classification of oil film, but presence too many bands can lead to information redundancy and reduced accuracy. In this study, a model that combines spectral indices-based band selection (SIs) one-dimensional convolutional neural networks was proposed realize automatic films using hyperspectral remote sensing images. Additionally, for comparison, minimum Redundancy Maximum Relevance (mRMR) tested reducing number bands. The support...
Early detection of periocular aging is a common concern in cosmetic surgery. Traditional diagnostic and treatment methods often require hospital visits consultations with plastic surgeons, which are costly time-consuming. This study aims to develop evaluate an AI-based decision-making system for surgery, utilizing Hierarchical Attention Transformer (HATrans) model designed multi-label classification conditions, allowing home-based early identification. cross-sectional was conducted at the...
The identification of oil species and their characteristics in spills is particularly important for efficient disposal. Since aromatic hydrocarbons (AHs) with various are the major fluorescent components oils seawater, they can be used to detect different seawater. Here, we developed a composition method using fluorescence spectra eight AH categories analyzed by gas chromatography-mass spectrometry (GC-MS) evaluate contribution AHs total six species. Qualitative quantitative difference...
Marine oil spill detection is vital for strengthening the emergency commands of accidents and repairing marine environment after a disaster. Polarimetric Synthetic Aperture Radar (Pol-SAR) can obtain abundant information targets by measuring their complex scattering matrices, which conducive to analyze interpret mechanism slicks, look-alikes, seawater realize extraction slicks. The polarimetric features quad-pol SAR have now been extended detection. Inspired this advancement, we proposed set...
A fast piecewise-defined neural network (PDNN) method is presented to produce accurate atmospheric temperature and humidity profiles from satellite hyperspectral infrared (IR) microwave (MW) observations in all-sky conditions. The PDNN relies on a novel classification approach principal component-based (NN) function better capture the nonlinear relationship between spectral radiances state vectors. algorithm was designed only rely measurements. Large datasets were used for training make...
This study employs polarimetric synthetic aperture radar (Pol-SAR) to examine the scattering properties of continuous slow-release oil slicks on sea surface. The objective is extract and analyze general polarization slicks, i.e., those that consist substances released at a fairly slow relatively constant rate, determine influence slick formation process these properties. Using multi-polarization feature parameters derived from averaged coherency matrix, we find mechanisms related differ...
The current methods that use hyperspectral remote sensing imagery to extract and monitor marine oil spills are quite popular. However, the automatic extraction of endmembers from remains a challenge. This paper proposes data field-spectral preprocessing (DSPP) algorithm for endmember extraction. method first derives set extreme points field an image. At same time, it identifies spectrally pure in spectral space. Finally, fuses with calculation generate new subset candidates following...
Polarimetric synthetic aperture radar is an important tool in the effective detection of marine oil spills. In this study, two cases Radarsat-2 Fine mode quad-polarimetric datasets are exploited to detect a well-known seep area that collected over Gulf Mexico using same research area, sensor, and time. A novel spill scheme based on multi-polarimetric features model matching method spectral pan-similarity measure (SPM) proposed. curve generated optimal polarimetric selected Jeffreys-Matusita...
The extraction and capture of the target by medium-long wave infrared optical system is mainly achieved based on gray difference between image background image. Under complex conditions, such as air-to-ground alarms or detection will be strongly disturbed environment. Especially under dynamic are in a rapid change, how to detect real-time ground-to-air missile seeker other weak targets very difficult. It one technical difficulties current processing field quickly locate extract from...
Marine oil spills is a matter of great concern since it causes environmental disasters and threats the ecological system, thus capability to detect precisely analyze sufficiently significant guarantee realize management followed by spill. The Synthetic Aperture Radar (SAR) has recognized as key remote sensing tool for spill monitoring detecting. This paper uses modified GBVS model extract area region interest based on difference between oil-covered background sea-water. First, normalize mean...