A5101584422- 3D Surveying and Cultural Heritage
- Remote Sensing and LiDAR Applications
- 3D Shape Modeling and Analysis
- Robotics and Sensor-Based Localization
- Advanced Sensor and Control Systems
- Advanced Algorithms and Applications
- Guidance and Control Systems
- Underwater Vehicles and Communication Systems
- Remote Sensing in Agriculture
- Remote-Sensing Image Classification
- Robotic Path Planning Algorithms
- Computer Graphics and Visualization Techniques
- Hydrocarbon exploration and reservoir analysis
- Energy Efficient Wireless Sensor Networks
- Chaos-based Image/Signal Encryption
- Air Traffic Management and Optimization
- Image and Object Detection Techniques
- Space Satellite Systems and Control
- Coal Properties and Utilization
- CO2 Sequestration and Geologic Interactions
- Advanced Neural Network Applications
- Vehicle License Plate Recognition
- Cryospheric studies and observations
- Machine Learning and Algorithms
- Wireless Sensor Networks and IoT
Capital Normal University
2019-2024
Xidian University
2024
Research Institute of Petroleum Exploration and Development
2023
National University of Defense Technology
2022
China University of Petroleum, Beijing
2022
Chinese Academy of Surveying and Mapping
2019
North China Electric Power University
2014
Nankai University
2008-2010
Schlumberger (British Virgin Islands)
2010
Anhui University of Technology
2007
The efficient separation of coal and gangue in the mining process is great significance for improving efficiency reducing environmental pollution. Automatic detection key foundation gangue. In this paper, we proposed a hierarchical framework based on deep learning models. framework, Gaussian pyramid principle first used to construct multi-level training data, leading sets image features with multiple scales. Then, regional proposal networks (CG-RPN) are designed determine candidate regions...
This paper presents a novel framework to extract metro tunnel cross sections (profiles) from Terrestrial Laser Scanning point clouds. The entire consists of two steps: central axis extraction and section determination. In extraction, we propose slice-based method obtain an initial axis, which is further divided into linear nonlinear circular segments by enhanced Random Sample Consensus (RANSAC) segmentation algorithm. algorithm transforms the problem hybrid segment sole elements defined at...
Since the 1970s, land subsidence has been rapidly developing on Beijing Plain, and systematic study of evolutionary mechanism this is great significance in sustainable development regional economy. On basis Interferometric Synthetic Aperture Radar (InSAR) results, employed Mann–Kendall method for first time to determine mutation information Plain from 2004 2015. By combining hydrogeological conditions, “southern water” project, other data, we attempted analyse reasons mutations. First,...
Large-scale 3D point clouds are rich in geometric shape and scale information but they also scattered, disordered unevenly distributed. These characteristics lead to difficulties learning cloud semantic segmentations. Although many works have performed well this task, most of them lack research on spatial information, which limits the ability learn understand complex structure scenes. To end, we propose multispatial dual adaptive (MSIDA) module, consists a encoding (MSI) block (DA) blocks....
CO2 flooding is a significant technology for oil recovery, to reveal the microcosmic mechanism of flooding, slim tube experiments, long core gas chromatography analysis and numerical simulations were carried out. The results show that miscibility increase can improve effect dissolution diffusion in CO2-crude system, easing finger entry phenomena, delaying breakthrough time. Besides, -crude interaction enhanced by increasing pressure difference between injection well production well, which...
A modified APF (artificial potential field) based method is proposed for mobile robot path planning. To address the local minima problem in classical APF, a composed of regression and field filling proposed. Futhermore, by adjusting environment dynamically, collision also well settled. Simulation experiments, which eight sonar transmitters are supposed to be used measurement, carried out verify performance planning paper. The simulation results show that has better than an unknown environment.
Quadrupole acoustic logging is used to measure shear in the logging‐while‐drilling (LWD) environment. Evaluation of slowness quadrupole requires an inversion method that takes into account dispersion mode, including tool‐presence effects. The was developed adopt a semblance processing based on waveform back propagation, assuming homogeneous isotropic (HI) formation model with optimizes and also includes optimization mud as internal parameter compensate for effects undetermined slowness. A...
In close-range or unmanned aerial vehicle (UAV) photogrammetry, Schneider concentric circular coded targets (SCTs), which are public, widely used for image matching and as ground control points. GSI point-distributed (GCTs), only mainly applied in a video-simultaneous triangulation resection system (V-STARS), non-public rarely UAV photogrammetry. this paper, we present our innovative detailed solution to identify GCTs. First, analyze the structure of GCT. Then, special 2D P2-invariant five...
The accuracy with which a neural network interprets point cloud depends on the quality of features expressed by network. Addressing this issue, we propose multi-level feature extraction layer (MFEL) collects local contextual and global information modeling clouds at different levels. MFEL is mainly composed three independent modules, including aggregated GAPLayer, spatial position perceptron, RBFLayer, learn from scales. GAPLayer aggregates geometry neighboring points in coordinate system to...
Wireless sensor network has been widely used and its real-time data processing capability is very limited. This paper puts forward a new solution, which the novel wireless node design with hyperchaos encryption based on FPGA. With wide application ZigBee protocol, we encrypt transported in using by FPGA, combines their flexibility rapid free configuration FPGA enhances security of data. Then can make full use advantages achieve good node.
Accurate and effective classification of lidar point clouds with discriminative features expression is a challenging task for scene understanding. In order to improve the accuracy robustness cloud based on single features, we propose novel set multi-level aggregation extraction fusion method multi-scale max pooling latent Dirichlet allocation (LDA). To this end, in hierarchical feature extraction, sets different levels sizes are first adaptively generated through clustering. Then, more...
Urban street shadows can provide essential information for many applications, such as the assessment and protection of ecology environment, livability evaluation, etc. In this research, we propose an effective rapid method to quantify diurnal spatial changes urban shadows, by taking Beijing city example. method, explore a novel way transferring characteristics semantically segment street-level panoramic images using DeepLabv3+. Based on segmentation results, shading situation is further...
Airborne laser scanning (ALS) point cloud classification is a challenge due to factors including complex scene structure, various densities, surface morphology, and the number of ground objects. A method presented in this paper, based on content-sensitive multilevel objects (point clusters) consideration density distribution The space projection first used convert three-dimensional into two-dimensional (2D) image. image then mapped 2D manifold space, restricted centroidal Voronoi...
Towards electrode control system of LF furnace, a adaptive inverse algorithm based on RBF NN is presented, which identifies real-time and decoupling by on-line, designs computer software WinAC. The results application show that this able to adapt with load change external interference very well, could overcome the dithering effectively, especially have good tacking characteristic.