A5061149885- Solar Radiation and Photovoltaics
- Photovoltaic System Optimization Techniques
- Energy Load and Power Forecasting
- Remote-Sensing Image Classification
- Spectroscopy and Chemometric Analyses
- Advanced Image Fusion Techniques
- Smart Agriculture and AI
- Air Quality and Health Impacts
- Remote Sensing and Land Use
- Toxic Organic Pollutants Impact
- Industrial Vision Systems and Defect Detection
- Advanced Steganography and Watermarking Techniques
- Advanced Chemical Sensor Technologies
- Air Quality Monitoring and Forecasting
- Remote Sensing in Agriculture
- Solar Thermal and Photovoltaic Systems
- Image Enhancement Techniques
- Leaf Properties and Growth Measurement
- Biocrusts and Microbial Ecology
- Greenhouse Technology and Climate Control
- Land Use and Ecosystem Services
- Flood Risk Assessment and Management
- Video Surveillance and Tracking Methods
- Image Processing Techniques and Applications
- Building materials and conservation
Naval University of Engineering
2009-2024
Nanjing Forestry University
2019-2024
Northeast Agricultural University
2023
Dalian Jiaotong University
2023
Southeast University
2009-2022
Tianjin University
2022
Hohai University
2022
Luoyang Normal University
2021
The Scarborough Hospital
2020-2021
University of Toronto
2020-2021
This paper reports the outcomes of 2014 Data Fusion Contest organized by Image Analysis and Technical Committee (IADF TC) IEEE Geoscience Remote Sensing Society (IEEE GRSS). As for previous years, IADF TC a data fusion contest aiming at fostering new ideas solutions multisource remote sensing studies. In edition, participants considered multiresolution multisensor between optical acquired 20-cm resolution long-wave (thermal) infrared hyperspectral 1-m resolution. The was proposed as...
In this study, urban building change detection is investigated, considering that buildings are one of the most dynamic structures in areas. To aim, a novel approach for multitemporal high-resolution images proposed based on recently developed morphological index (MBI), which able to automatically indicate presence from images. MBI-based framework, changed information decomposed into MBI, spectral, and shape conditions. A variation MBI basic condition indication buildings. Besides, spectral...
Wood veneer defect detection plays a vital role in the wood production industry. Studies on usually focused accuracy for industrial applications but ignored algorithm execution speed; thus, their methods do not meet required speed of online detection. In this paper, new method is proposed that achieves high and suitable production. Firstly, 2838 images were collected using data collection equipment developed laboratory labeled by experienced workers from company. Then, an integrated model,...
Mulch film is usually mixed in with cotton during machine-harvesting and processing, which reduces the quality. This paper presents a novel sorting algorithm for online detection of on using hyperspectral imaging spectral region 1000 - 2500 nm. The consists group stacked autoencoders, two optimization modules an extreme learning machine (ELM) classifier. variable-weighted autoencoders (VW-SAE) are constructed to extract features from images, artificial neural network (ANN), one module,...
In the process of classifying fresh-cut flowers, classification accuracy algorithm plays a vital role in control quality stability, uniformity, and price while speed an determines possibility industrial application. Currently, research on flower focuses breakthrough accuracy, ignoring real-time processing terminal, which seriously affects use online technology. this study, RGB images depth information data for 434 rose flowers were collected using binocular stereo camera. Combined with...
Boosted by a strong solar power market, the electricity grid is exposed to risk under an increasing share of fluctuant power. To increase stability grid, accurate forecast needed evaluate such fluctuations. In terms forecast, irradiance key factor generation, which affected atmospheric conditions, including surface meteorological variables and column integrated variables. These involve multiple numerical time-series images. However, few studies have focused on processing method data types in...
Photovoltaic power generation is highly valued and has developed rapidly throughout the world. However, fluctuation of solar irradiance affects stability photovoltaic system endangers safety grid. Therefore, ultra-short-term predictions are widely used to provide decision support for dispatching systems. Although a great deal research been done, there still room improvement regarding prediction accuracy including global horizontal irradiance, direct normal diffuse irradiance. This study took...
The installed capacity of photovoltaic power generation occupies an increasing proportion in the system, and its stability is greatly affected by fluctuation solar radiation. Accurate prediction radiation important prerequisite for ensuring grid security electricity market transactions. current mainstream method deep learning method, structure design data selection determine accuracy speed network. In this paper, we propose a novel long short-term memory (LSTM) model based on attention...
In this work, emulsion-filled gels were prepared from natural and pH-shifting combined with ultrasound β-conglycinin (7S) as emulsifiers. The emulsifier modification emulsion concentrations (5, 10, 15, 20 wt%) evaluated on the structural β-carotene release properties of gels. Compared to 7S hydrogel, exhibited better water-holding textural properties. increase in concentration resulted altered water distribution improved microstructure rheological dense homogeneous gel network was formed at...
With the increase of public concern about health and smoking, authorities have gradually tightened control tar content in cigarettes, making reconstituted tobacco a growing for companies. Tobacco stems are used as main raw material tobacco, but they contain large number small broken impurities mainly from cigarette butts, which difficult to remove efficiently by air selection manual methods. Detection schemes butt based on computer vision deep learning still difficult. The scarcity images...
Ground-based cloud images can provide information on weather and conditions, which are important for monitoring PV power generation forecasting. Prediction of short-time movement from is a major means intra-hourly irradiation forecasting solar also precipitation However, there lack advanced complete methods prediction ground-based images, traditional techniques based image processing motion vector calculations have difficulty in predicting morphological changes, makes accurate (especially...
Abstract A nonlinear method has been developed to estimate climate feedbacks based on the Neural Network (NN) taking advantage of its self‐learning skills. The NN model here is trained using a reanalysis data set and predicts radiation flux globally from atmospheric surface variables. radiative temperature, water vapor, albedo, cloud in interannual variations estimated are agreement with those broadly used kernel method. However, demonstrates significant advantages: (1) it withdraws...
Grading the quality of fresh cut flowers is an important practice in flower industry. Based on maturing status, a classification method based deep learning and depth information was proposed for grading quality. Firstly, RGB image bud were collected transformed into fused RGBD information. Then, set as inputs convolutional neural network to determine status. Four models (VGG16, ResNet18, MobileNetV2, InceptionV3) adjusted four-dimensional (4D) input classify flowers, their performances...
In pace with rapid urbanization, urban areas in many countries are undergoing huge changes. The large spectral variance and spatial heterogeneity within the 'buildings' land cover class, as well similar properties between buildings other structures, make building change detection a challenging problem. this work, we propose set of novel indices (BCIs) by combining morphological index (MBI) slow feature analysis (SFA) for from high-resolution imagery. MBI is recently developed automatic...
This paper presents a novel motion vector (MV) steganalysis method. MV-based steganographic methods exploite the variability of MV to embed messages by modifying slightly. However, we have noticed that modified MVs after steganography cannot follow optimal matching rule which is target estimation. It means conflict with basic principle video compression. Aiming at this difference, proposed feature based on Subtractive Probability Optimal Matching(SPOM), statistics MV's (POM) around its...