A5048851567- Spectroscopy and Chemometric Analyses
- Water Quality Monitoring Technologies
- Meat and Animal Product Quality
- Advanced Chemical Sensor Technologies
- Water Quality Monitoring and Analysis
- Image Enhancement Techniques
- Oil Spill Detection and Mitigation
- Microplastics and Plastic Pollution
- Advanced Image Fusion Techniques
- Remote-Sensing Image Classification
- Recycling and Waste Management Techniques
- Smart Agriculture and AI
- Spectroscopy Techniques in Biomedical and Chemical Research
- Image Processing Techniques and Applications
- Remote Sensing in Agriculture
- Underwater Acoustics Research
- Fish Biology and Ecology Studies
- Animal Nutrition and Physiology
- Photoacoustic and Ultrasonic Imaging
- Identification and Quantification in Food
- Optical Polarization and Ellipsometry
- Coral and Marine Ecosystems Studies
- Toxic Organic Pollutants Impact
- Leaf Properties and Growth Measurement
- Effects of Environmental Stressors on Livestock
Zhejiang University
2015-2024
Zhejiang Ocean University
2015-2024
Recherches Scientifiques Luxembourg
2023-2024
University of Luxembourg
2023-2024
Sanya University
2021-2024
South China University of Technology
2023-2024
Hangzhou Academy of Agricultural Sciences
2021-2022
Zhejiang Environmental Monitoring Center
2019
Wuyi University
2019
Ministry of Industry and Trade
2019
Microplastics (MPs) have been recognized as prominent anthropogenic pollutants that inflict significant harm to marine ecosystems. Various approaches proposed mitigate the risks posed by MPs. Gaining an understanding of morphology plastic particles can provide valuable insights into source and their interaction with organisms, which assist development response measures. In this study, we present automated technique for identifying MPs through segmentation in microscopic images using a deep...
The open-ended coaxial probe has been widely used to measure the permittivity of different materials. Input power and frequency are two important factors that affect sensing depth an probe. Existing studies in literature on effect input probes mainly qualitative variation at a particular power. However，the central prerequisite for accurate sample preparation is precise knowledge magnitude any frequency. In this paper, (0.5 GHz 20 GHz) (-20 dBm dBm) variations investigated first time from...
Underwater spectral imaging is a promising method for mapping, classification and health monitoring of coral reefs seafloor inhabitants. However, the spectrum light distorted during underwater process due to wavelength-dependent attenuation by water. This paper presents model-based that accurately restores brightness images captured with narrowband filters. A model built imaging. The structure derived from physical principles, representing absorption, scattering refraction water optical...
Among aquatic biota, corals provide shelter with sufficient nutrition to a wide variety of underwater life. However, severe decline in the coral resources can be noted last decades due global environmental changes causing marine pollution. Hence, it is paramount importance develop and deploy swift monitoring system alleviate destruction corals. Performing semantic segmentation on images one most efficient methods for automatic investigation Firstly, design system, RGB spectral various types...
Vital transportation of hazardous and noxious substances (HNSs) by sea occasionally suffers spill incidents causing perilous mutilations to off-shore on-shore ecology. Consequently, it is essential monitor the spilled HNSs rapidly mitigate damages in time. Focusing on on-site early processing, this paper explores potential deep learning single-spectrum ultraviolet imaging (UV) for detecting spills. Images three floating HNSs, including benzene, xylene, palm oil, captured different natural...
Marbling is an important quality attribute of pork. Detection pork marbling usually involves subjective scoring, which raises the efficiency costs to processor. In this study, ability predict using near-infrared (NIR) hyperspectral imaging (900-1700 nm) and proper image processing techniques were studied. Near-infrared images collected from after evaluation according current standard chart National Pork Producers Council. Image analysis techniques-Gabor filter, wide line detector, spectral...
In the past decade, underwater spectral imaging (USI) has shown great potential in exploration for its high and spatial resolution. This proposal presents a stare-type USI system combined with liquid crystal tunable filter (LCTF) splitting device. Considering working features of LCTF theoretical model USI, core structure containing “imaging lens-LCTF-imaging sensor” is designed developed. The compact, optical geometry constructed minimally. calibration test analysis proved that response...
Spectral reflectance detection of the targeted object is considered a vital inherent optical property for its potential to provide abundant spectral information, which crucial in underwater imaging. However, coarse condition environment due turbidity causes extreme distortions high absorption and scattering light. To cope with effects light degradation on accuracy, rate impacts should be examined thoroughly. Therefore, we utilize stare-type imaging system based liquid crystal tunable filter...
Driven by abundant satellite imagery, machine learning-based approaches have recently been promoted to generate high-resolution crop cultivation maps support many agricultural applications. One of the major challenges faced these is limited availability ground truth labels. In absence truth, existing work usually adopts "direct transfer strategy" that trains a classifier using historical labels collected from other regions and then applies trained model target region. Unfortunately, spectral...
Long-tail learning has garnered widespread attention and achieved significant progress in recent times. However, even with pre-trained prior knowledge, models still exhibit weaker generalization performance on tail classes. The promising Sharpness-Aware Minimization (SAM) can effectively improve the capability of by seeking out flat minima loss landscape, which, however, comes at cost doubling computational time. Since update rule SAM necessitates two consecutive (non-parallelizable) forward...