A5071838109- Remote-Sensing Image Classification
- Land Use and Ecosystem Services
- Flood Risk Assessment and Management
- Advanced MIMO Systems Optimization
- Anomaly Detection Techniques and Applications
- Millimeter-Wave Propagation and Modeling
- Indoor and Outdoor Localization Technologies
- Remote Sensing and LiDAR Applications
- Image and Signal Denoising Methods
- Antenna Design and Optimization
- Remote Sensing in Agriculture
- Advanced Image Fusion Techniques
- Satellite Communication Systems
- Robotics and Automated Systems
University of Georgia
2024
Beijing Normal University
2023
China University of Geosciences
2022
Semantic change detection (SCD) aims to recognize land cover transitions from remote sensing images of the given scene acquired at different times. The semantic maps produced by SCD can provide not only locations changes but also detailed types (e.g., "from-to" type). This exhaustive information plays a significant role in various applications. Postclassification methods with multitemporal have been widely used SCD. However, many existing suffer accumulation misclassification errors. In this...
The fusion between the low resolution hyperspectral image (LRHSI) and panchromatic (PAN) could obtain high-resolution (HRHSI). Recently, deep learning (DL)-based methods have been explored widely due to their powerful feature ability. However, most DL-based that use one-step manner can suffer from blurring effect. In addition, they not fully utilized spatial spectral information of two input images, which hinders improvement resulting quality. Therefore, mitigate effect utilize we propose a...
Surface water is a fundamental resource in urban environments. Monitoring the spatio-temporal distribution of surface from remotely sensed images crucial for planning and management. Unfortunately, due to limitation spatial resolution, method based on low/medium resolution difficult extract small bodies accurately. Recently, very high (VHR) have shown considerable potential compositions mapping. However, fewer spectral bands, shadows, heterogeneity VHR hinder application traditional methods....
The accurate modeling of indoor radio propagation is crucial for localization, monitoring, and device coordination, yet remains a formidable challenge, due to the complex nature environments where can propagate along hundreds paths. These paths are resulted from room layout, furniture, appliances even small objects like glass cup. They also influenced by object material surface roughness. Advanced machine learning (ML) techniques have potential take such non-linear hard-to-model factors into...