A5101418479- Infrastructure Maintenance and Monitoring
- 3D Surveying and Cultural Heritage
- Catalytic Processes in Materials Science
- Dam Engineering and Safety
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Concrete Corrosion and Durability
- Non-Destructive Testing Techniques
- Industrial Vision Systems and Defect Detection
- Catalysis and Oxidation Reactions
- Advanced Algorithms and Applications
- Catalysis and Hydrodesulfurization Studies
- Electrocatalysts for Energy Conversion
- Ammonia Synthesis and Nitrogen Reduction
- Civil and Geotechnical Engineering Research
- Image Enhancement Techniques
- Hydrology and Sediment Transport Processes
- Advanced Sensor and Control Systems
- Remote Sensing and LiDAR Applications
- Advanced Measurement and Detection Methods
- Underwater Vehicles and Communication Systems
- Geophysical Methods and Applications
- Gear and Bearing Dynamics Analysis
- Advanced Computational Techniques and Applications
- Power Line Inspection Robots
Tsinghua University
2019-2025
Tsinghua Sichuan Energy Internet Research Institute
2019-2025
Nanchang University
2023-2024
National Institute of Clean and Low-Carbon Energy
2017-2023
Jiangjin Central Hospital
2022
Chongqing University
2007-2022
Third Hospital of Hebei Medical University
2022
Hebei Medical University
2022
Guangdong University of Technology
2021
Southwest Jiaotong University
2021
Cloud computing offers the possibility to store and process massive amounts of remotely sensed hyperspectral data in a distributed way. Dimensionality reduction is an important task imaging, as often contains redundancy that can be removed prior analysis repositories. In this regard, development dimensionality techniques cloud environments provide both efficient storage preprocessing data. paper, we develop parallel implementation widely used technique for reduction: principal component...
Crack detection on dam surfaces is an important task for safe inspection of hydropower stations. More and more object methods based deep learning are being applied to crack detection. However, most the can only achieve classification rough location cracks. Pixel-level provide intuitive accurate results health assessment. To realize pixel-level detection, a method surface (CDDS) using convolution network proposed. First, we use unmanned aerial vehicle (UAV) collect images along predetermined...
Abstract An increasing number of detection methods based on computer vision are applied to detect cracks in water conservancy infrastructure. However, most studies directly use existing feature extraction networks extract crack information, which proposed for open-source datasets. As the distribution and pixel features different from these data, extracted information is incomplete. In this paper, a deep learning-based network dam surface proposed, mainly addresses semantic segmentation...
Timely detection of defects is essential for ensuring safe and stable operation concrete buildings. Automatic segmentation buildings’ surfaces challenging due to the high diversity crack appearance, detailed information, unbalanced proportion pixels background pixels. In this work, Double Feature Pyramid Network designed high-precision segmentation. Our work reached state-of-the-art level in segmentation, with key contributions outlined as follows: firstly, considering shapes, network...
A high-surface area (572 m2 g–1) dendritic mesoporous silica (KCC-1) was synthesized successfully and used as a support to confine Pt–Ni bimetallic nanoparticles (NPs). It is revealed that the NPs are highly dispersed with an ultra-small size of 1.0 nm, large specific surface well abundant structure KCC-1 can effectively promote dispersion thermal stability nanoparticles, thus significantly improving CO oxidation activity. Compared monometallic 1% Pt/KCC-1 Ni/KCC-1 catalysts, combination Pt...
Dam is an essential structure in hydraulic engineering, and its surface cracks pose significant threats to integrity, impermeability, durability. Automated crack detection methods based on computer vision offer substantial advantages over manual approaches with regard efficiency, objectivity precision. However, current face challenges such as misidentification, discontinuity, loss of details when analyzing real-world dam images. These images often exhibit characteristics low contrast,...
Principal component analysis (PCA) is an important method for feature extraction of hyperspectral remote sensing image. With the development sensors, magnitude data grows quickly, and it a challenging task to efficiently reduce dimension compress massive volumes in imaging. In this paper, distributed parallel optimization PCA algorithm (PCA_DP) presented on cloud computing architecture. The realization proposed using Apache Hadoop MapReduce model described evaluated. experiments conducted...
Abstract Underwater structure inspections are essential for infrastructure maintenance, such as hydraulic facilities, bridges, and ports. Due to the influence of turbidity, dark light, distortion, traditional methods cannot satisfy requirements on-site inspection applications. This paper proposed a methodology point cloud data capture in turbid underwater environment. The method consisted an acquisition device, distortion correction algorithm, parameter optimization approach. device was...
Abstract When acquiring object point cloud data by three-dimensional scanning technology, noise is generated due to instrument accuracy and external factors. Existing algorithms rarely consider the characteristics of different noises regional when solving denoising problem, this results in a limited effect on denoising. This paper presents an algorithm for based types regions cloud. The includes large-scale removal small-scale smoothing. Remove points relationship between local global For...