- Remote Sensing and LiDAR Applications
- 3D Surveying and Cultural Heritage
- Image and Signal Denoising Methods
- Advanced Image Fusion Techniques
- Underwater Acoustics Research
- Advanced Optical Sensing Technologies
- Remote Sensing in Agriculture
- Underwater Vehicles and Communication Systems
- Meteorological Phenomena and Simulations
- Seismic Imaging and Inversion Techniques
- Advanced Neural Network Applications
- Aerospace Engineering and Energy Systems
- Image Processing Techniques and Applications
Peng Cheng Laboratory
2022-2025
Shenzhen University
2021-2022
Ministry of Natural Resources
2021
First Institute of Oceanography
2017-2021
Hohai University
2017
Shandong University of Science and Technology
2010
In the stratosphere, use of winds to navigate balloons has emerged as a practical approach for Earth observation, collecting meteorological data, and other applications. However, controlling such is challenging due imperfect wind data need real-time decisions. Research in this field predominantly concentrates on station-keeping missions, but there an absence studies stratospheric balloon path planning. work, we employ deep reinforcement learning train controller that guides from random...
In an airborne laser bathymetry system, the full-waveform echo signal is usually recorded by discrete sampling. The accuracy of recognition and amount effective information that can be extracted conventional methods are limited. To improve validity reliability data to extract more better understand water reflection characteristics, we select portion original waveform for further research, suppress random noise, decompose selected progressively using half-wavelength Gaussian function with...
Ocean waves are a vital environmental factor that affects the accuracy of airborne laser bathymetry (ALB) systems. As regional water surface undulates with randomness, propagation direction through air–water will change and impact underwater topographic result from ALB system, especially for small divergence system. However, natural ocean changes rapidly over time, uneven point clouds scanning cause an uncertain estimation direction; therefore, self-adaptive correction method based on...
Airborne Light Detection And Ranging (LiDAR) Bathymetry (ALB) has an unparalleled advantage in integrated sea-land measurements, especially the acquisition of topographic data shallow water areas. Sea surface waves are important factor affecting quality ALB data. This paper presents a method that strictly corrects sea wave-induced refraction error for each seabed laser pulse without any complex modeling surface. In this method, adaptive neighborhood selection is first used to calculate...
Well logs play a very important role in exploration and even exploitation of energy resources, but they usually contain kinds noises which affect the results geological interpretation them. It is common knowledge that wavelet transform does better than Fourier noise removal suppression such non-stationary signals as logging signals. However, there are variable choices parameters basis (mother function), thresholding rule decomposition level etc. denoising with transform. In this paper,...
Airborne laser bathymetry (ALB) systems with digital full-waveform signal collection can obtain corresponding temporal positions from several backscattering surfaces by beam irradiation. This information help describe the multi-elevation structures of target and explore echo attenuation response in different nonuniform mediums during propagation. Therefore, a is quite practical for integrated water-land detection. However, wavelength used ALB system generally visible band range 470~580 nm,...
LiDAR-unmanned aerial system (LiDAR-UAS) technology can accurately and efficiently obtain detailed accurate three-dimensional spatial information of objects. The classification objects in estuarine areas is highly important for management, planning, ecosystem protection. Owing to the presence slopes areas, distinguishing between dense vegetation (lawns trees) on ground at tops difficult. In addition, imbalance number point clouds also poses a challenge directly from cloud data. A...
State-of-the-art (SOTA) video denoising methods employ multi-frame simultaneous mechanisms, resulting in significant delays (e.g., 16 frames), making them impractical for real-time cameras. To overcome this limitation, we propose a multi-fusion gated recurrent Transformer network (GRTN) that achieves SOTA performance with only single-frame delay. Specifically, the spatial module extracts features from current frame, while reset gate selects relevant information previous frame and fuses it...