A5103784124- Water-Energy-Food Nexus Studies
- Water resources management and optimization
- 3D Surveying and Cultural Heritage
- 3D Shape Modeling and Analysis
- Irrigation Practices and Water Management
- Water Systems and Optimization
- Climate change impacts on agriculture
- Safety and Risk Management
- Hydrology and Drought Analysis
- Image Processing and 3D Reconstruction
- Rice Cultivation and Yield Improvement
- Agricultural Systems and Practices
- Remote Sensing and Land Use
- Flood Risk Assessment and Management
- Advanced Numerical Analysis Techniques
- Hydrology and Watershed Management Studies
South China University of Technology
2025
China Institute of Water Resources and Hydropower Research
2023-2025
Ministry of Water Resources of the People's Republic of China
2023-2025
Sinopec (China)
2024
Deakin University
2022
China Agricultural University
2017-2020
Ministry of Agriculture and Rural Affairs
2020
Heilongjiang Provincial Institute of Hydraulic Research
2019
Abstract Among natural disasters, flash floods are the most destructive events, causing significant damage to economy and posing a serious threat human life property. Comprehensive risk assessment of these sudden is key strategy mitigate their impact. Accurate analysis flood hazards can greatly enhance prevention efforts inform critical decision‐making processes, ultimately improving our ability protect communities from fast‐onset disasters. This study analyzed driving forces...
Current normal estimation methods for 3D point clouds often show limited accuracy in predicting normals at sharp features (e.g., edges and corners) less robustness to noise. In this paper, we propose a novel method which consists of two phases: (a) feature encoding learn representations local patches, (b) that takes the learned representation as input regresses vector. We are motivated patches on isotropic anisotropic surfaces respectively have similar distinct normals, these separable or...
Existing 3D pose datasets of object categories are limited to generic types and lack fine-grained information. In this work, we introduce a new large-scale dataset that consists 409 31,881 images with accurate annotation. Specifically, augment three existing recognition (StanfordCars, CompCars FGVC-Aircraft) by finding specific model for each sub-category from ShapeNet manually annotating 2D image adjusting full set 7 continuous perspective parameters. Since the shapes allow models better...