A5103189443- Advanced Image Fusion Techniques
- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Fire Detection and Safety Systems
- Remote Sensing and LiDAR Applications
- Periodontal Regeneration and Treatments
- Additive Manufacturing Materials and Processes
- Advanced Optical Sensing Technologies
- Robotic Path Planning Algorithms
- Reconstructive Surgery and Microvascular Techniques
- Target Tracking and Data Fusion in Sensor Networks
- Welding Techniques and Residual Stresses
- Underwater Vehicles and Communication Systems
- Laser-induced spectroscopy and plasma
- Advanced Measurement and Detection Methods
- Image Enhancement Techniques
- Advanced Computational Techniques and Applications
- Image and Signal Denoising Methods
- Robotics and Sensor-Based Localization
North University of China
2024
Zhengzhou University
2024
Xinjiang University
2017-2018
Harbin Engineering University
2015
Traditional image change detection based on a non-subsampled contourlet transform always ignores the neighborhood information's relationship to coefficients, and results are susceptible noise interference. To address these disadvantages, we propose denoising method domain that uses Hidden Markov Tree model (NSCT-HMT) for of remote sensing images. First, ENVI software is used calibrate original After that, mean-ratio operation adopted obtain difference will be denoised by NSCT-HMT model....
For the application of multi-beam echo sounder data in constructing underwater digital terrain map (UDTM), general approach gridding is introduced. Simultaneously, advantage and disadvantage several familiar fast methods are compared, including distance weighted method, multi points average method Gauss-weighted method. Gridding process made UDTM constructed according to different using MBES from sea test, results analyzed shape contour lines. At last, interpolation inversion made, which...
Laser-Induced Breakdown Spectroscopy (LIBS) combined with traditional mathematical methods for quantitative analysis of material composition often relies on specific prior knowledge, leading to issues such as poor accuracy and weak generalization performance. In order mitigate the impact knowledge method simultaneously enhance accuracy, this study proposes a 1d CNN model based ResNet-18. The is specifically designed four elements (Cu, Mo, P, S) in steel. Subsequently, better serve edge...
Image dehazing technology is a hot topic in the fields of image processing and computer vision, aiming to obtain details texture features original scene from foggy images, then clear fog free images. Most existing research methods are suitable for tasks low scenarios. As concentration increases, reconstruction quality algorithm significantly decreases, accompanied by detail loss distortion. In addition, most algorithms require large amount datasets during model training, training takes long...