A5100624892- Remote-Sensing Image Classification
- Image Processing Techniques and Applications
- Sparse and Compressive Sensing Techniques
- Infrared Target Detection Methodologies
- Image and Signal Denoising Methods
- Remote Sensing and Land Use
- Remote Sensing and LiDAR Applications
- Industrial Vision Systems and Defect Detection
- Landslides and related hazards
- Synthetic Aperture Radar (SAR) Applications and Techniques
- Optical Systems and Laser Technology
- Advanced Image Fusion Techniques
- Vehicle License Plate Recognition
- Advanced Computational Techniques and Applications
- Medical Image Segmentation Techniques
- Video Surveillance and Tracking Methods
- Complex Network Analysis Techniques
- Metaheuristic Optimization Algorithms Research
- Laser Material Processing Techniques
- Microfluidic and Bio-sensing Technologies
- Image Processing and 3D Reconstruction
- Seismic Imaging and Inversion Techniques
- Geological Modeling and Analysis
- Advanced machining processes and optimization
- Advanced Multi-Objective Optimization Algorithms
University of Manchester
2001-2024
Nanjing Medical University
2024
Chengdu University of Technology
2021-2024
Jilin University
2024
Jiujiang University
2024
Northwestern Polytechnical University
2016-2023
Naval Aeronautical and Astronautical University
2019-2023
Lanzhou University
2023
China Waterborne Transport Research Institute
2023
Guangdong University of Technology
2022
Carbon fibre reinforced polymer (CFRP) is increasingly being used in the aerospace, marine, and land transport due to its lightweight, corrosion resistance, high strength. However, hole drilling during assembly remains challenging extensive tool wear delamination. Laser processing, typically for machining, often produces heat effects or low efficiency if ultrashort pulse lasers are used. Here, we report an optimised result a tailored sequence multiple-ring scanning laser method that...
Abstract Low-light visual perception problems, such as night Simultaneous Localization and Mapping (SLAM) or Structure-from-Motion (SfM) have attracted increasing attention, the performance of keypoint detection local feature description play a crucial role. Many traditional algorithms machine learning methods been widely used to detect describe features. However, existing techniques in face highly low-light scenes will be drastically degraded, resulting subsequent practical application...
The macropores within carbon skeleton-supported FeSe 2 /NiSe derived from MOF assemblies are meticulously engineered at the micrometer scale and OER electrocatalytic performance exhibits a significant dependence on micrometer-scale dimensions.
Image fusion model based on autoencoder network gets more attention because it does not need to design rules manually. However, most autoencoder-based networks use two-stream CNNs with the same structure as encoder, which are unable extract global features due local receptive field of convolutional operations and lack ability unique from infrared visible images. A novel image consist encoder module, module decoder is constructed in this paper. For CNN Transformer combined capture feature...
This paper proposes a novel method based on deformable dictionary learning for detecting the regions of change between multitemporal image pairs. We build our previous work, which constructed pair dictionaries. The main shortcoming this was its dependence large amount training data. In practice, there is often shortage ground-truthed images, limits expression capability resulting overcomes challenge by incorporating concept deformation, wherein each atom no longer simple patch, but instead...
Accurately translating medical images across different modalities (e.g., CT to MRI) has numerous downstream clinical and machine learning applications. While several methods have been proposed achieve this, they often prioritize perceptual quality with respect output domain features over preserving anatomical fidelity. However, maintaining anatomy during translation is essential for many tasks, e.g., when leveraging masks from the input develop a segmentation model translated domain. To...
Abstract The earthquake doublet of Mw 6.5 and 6.9 occurred along the west-dipping Central Range fault (CRF) adjacent to east-dipping creep segment Longitudinal Valley in eastern Taiwan on 17–18 September 2022. faulting model derived from Interferometric Synthetic Aperture Radar Global Positioning System observation suggests that CRF rupture is responsible for two mainshocks. Meanwhile, major earthquakes resulted ∼100 km slip double-convergent plate boundary faults near Taiwan. 2022 Chihshang...
Abstract The 2019 Mw 6.1 Castillejos earthquake occurred in the Zambales range of central Luzon Island Philippines. No active fault was reported around seismogenic zone according to previous investigations. This draws attention for assessment seismic risk along Marikina Valley system (MVFS) near Manila dense metropolitan population. Coulomb failure stress (CFS) change on MVFS is estimated by coseismic faulting model derived from inversion deformation field observed Differential...
We report on a wave-driven microfluidic ultrasonic shaker that can stably trap and oscillate microparticles in water microchannel. The shaking system mainly consists of chip two orthogonally excited piezoelectric transducers: one for creating radiation force potential wells three-dimensional trapping the other generating sound destabilization to shake trapped microparticles. It is shown standing waves different but close frequencies provide [approximately...
Change detection result is usually obtained by clustering or classifying; however, the spatial information of pixels rarely considered during classification process. In this letter, we propose a practical method to improve performance existing change algorithms on remote-sensing images without prior information. First, regarded as an initial result. Second, it takes advantage with neighborhood select training data, then random forest classifier trained for precise classification. Finally,...
Raw polarimetric images are captured by a focal plane polarimeter which is covered micro-polarizer array (MPA). The design of the MPA plays crucial role in imaging. MPAs predominantly designed according to expert engineering experience and rules thumb. Typically, only one optimization criterion, maximizing bandwidth, used MPA. To select design, an exhaustive search usually performed on very limited set available polarizing patterns, must be constrained order make tractable. In contrast, this...
In combinational logic circuits, expressing functions in terms of Mixed Polarity Reed-Muller (MPRM) expansions draws more and attention for its advantages over Boolean Fixed (FPRM) expansions. For n-variable MPRM function, the polarity directly determines expression form then influences power dissipation circuit. However, many literatures tend to research optimization ignoring traversal sequence large-scale circuits. This paper presents an Improved Adaptive Genetic Algorithm (IAGA) optimize...
Print mottle is problematic in the print and paper industry. In this report, a mathematical evaluation model of was generated after analyzing several methods. The images can be evaluated by based on theory wavelet image denoising analyses that use multi-scale fast algorithm. then applied to analyze four business papers (inkjet papers, newsprint art double-coated offset printing papers). correlation between results method human visual system (HVS) calculated evaluated. Experimental showed...
We suggest the azimuthal distribution of mean transverse (radial) rapidity final state particles as a more direct measure motion source than standard multiplicity distribution. Using sample generated by AMPT model with string melting, we demonstrate that amplitude suggested characterizes anisotropic radial flow, and coincides parameter extracted from generalized blast-wave parametrization.