A5101958960- Remote-Sensing Image Classification
- Advanced Image Fusion Techniques
- Cryospheric studies and observations
- 3D Surveying and Cultural Heritage
- Winter Sports Injuries and Performance
- Polar Research and Ecology
- Advanced Image and Video Retrieval Techniques
- Remote Sensing and Land Use
- Air Quality Monitoring and Forecasting
- Video Surveillance and Tracking Methods
- Remote Sensing and LiDAR Applications
- Image Processing Techniques and Applications
- Water Quality Monitoring Technologies
- Underwater Vehicles and Communication Systems
- Polysaccharides and Plant Cell Walls
- Soybean genetics and cultivation
- Dermatology and Skin Diseases
- Advanced Optical Sensing Technologies
- Peanut Plant Research Studies
- Atmospheric chemistry and aerosols
- Advanced Algorithms and Applications
- Advanced Neural Network Applications
- Geoscience and Mining Technology
- Advanced Computational Techniques and Applications
- Domain Adaptation and Few-Shot Learning
North Carolina State University
2024
Ministry of Agriculture and Rural Affairs
2024
Hangzhou Dianzi University
2021-2022
Tsinghua University
2019-2021
Naval Aeronautical and Astronautical University
2019-2021
Zhejiang University
2012
Change detection in heterogeneous remote sensing images is crucial for disaster damage assessment. Recent methods use homogenous transformation, which transforms the optical and synthetic aperture radar (SAR) into same feature space, to achieve change detection. Such transformations mainly operate on low-level space may corrupt semantic content, deteriorating performance of To solve this problem, article presents a new homogeneous transformation model termed deep fusion (DHFF) based image...
Change detection in heterogeneous remote sensing images is crucial for emergencies, such as disaster assessment. Existing methods based on homogeneous transformation suffer from the high computational cost that makes change tasks time-consuming. To solve this problem, article presents a new semisupervised Siamese network (S <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup> N) transfer learning. In proposed S N, low- and deep-level features...
Abstract Subglacial lake exploration is of great interest to the science community. RECoverable Autonomous Sonde (RECAS) provides an tool measure and sample subglacial environments while remains isolated from glacier surface atmosphere. This paper presents electronic control system design 200 m prototype RECAS. The proposed consists a system, downhole power transfer communication system. core element RECAS, responsible for sonde status monitoring, motion control, water sampling in situ...
Space-borne synthetic aperture radar (SAR) and optical sensors are important tools for building damage detection. Fusion of SAR images improves detection performance. However, when the resolutions two different kinds differ, performance existing pixel-level fusion methods deteriorates significantly due to interpolation-induced distortion. To solve this problem, paper presents a new superpixel-based belief (SBBF) model The superpixels on identified by segmentation pre-earthquake image perform...
Vehicle detection in aerial images is a challenging task. The complexity of the background information and redundancy area are main obstacles that limit successful operation vehicle based on anchors very-high-resolution (VHR) remote sensing images. In this paper, an anchor-free target method proposed to solve problems above. First, multi-attention feature pyramid network (MA-FPN) was designed address influence noise by fusing attention (FPN) structure. Second, more precise foveal (MPFA)...
Abstract Drilling and sampling are the most direct effective methods available to study Antarctic subglacial lakes. Based on Philberth probe, a Recoverable Autonomous Sonde (RECAS) allows for in situ lake water measurement sampling, through addition of an upper thermal tip cable recoiling mechanism. RECAS-200, prototype RECAS, has drilling depth 200 m, surface supply voltage 800 VAC downhole power ~9.6 kW during drilling. In this study, heating control system RECAS-200 was designed. The...
Late leaf spot (LLS) is one of important diseases that causes severe yield losses in peanut. Peanut has various sources resistance to LLS, and the identification resistant QTLs development related molecular markers are great importance for breeding LLS-resistant In this study, 173 individual lines a recombinant inbred line (RIL) population 48K SNP array genotyping were used construct high-density genetic map with 1475 marker 20 linkage groups. A total 11 obtained through QTL analysis using...
Homogeneous transformation receives considerable attention in recent years as it is essential for change detection heterogeneous images. However, most existing methods perform the homogeneous based on low-level features. It leads to inaccurate representations of images and accordingly causes unsatisfied performance detection. To solve this problem, paper presents a new model that utilizes deep- level features instead Experimental results real remote sensing data show that, proposed method...
Atopic dermatitis (AD) is a common multifactorial skin disease characterized by chronic inflammation, unbearable itching, and significant physical mental burden on patients. In recent years, there has been extensive studied the use of natural polysaccharides in anti-inflammatory therapy, due to their low toxicity multi-target pharmacological activity. The unique biological activities from sources as functional food additives cosmeceuticals present new option for treatment AD. This review...
Retracted.
The ice core from polar sheet is one of the most valuable archives past climate and environment. visual stratigraphy, based on optical scanning analysis, provides intuitive information micro-particles and/or air bubbles in ice. At present, only few labs can perform high quality stratigraphy analysis world. Here, we develop an slice tool line-scan camera. machine uses high-resolution characteristics camera to complete imaging slices through linkage with linear light sources. A motor drive...
The status that domestic technology forming the high-pressure gas bottles surface leading to poor marking quality is analyzed. rapid image processing method based on Binarization presented identify defects position and profile from region quickly, it designed with four steps: CCD capture, pixel enhancement, edge identification feature extractions. By statistical analysis of project practice, defined as typical types in shape, then through BP neural network training type effectively driving...
The underwater control system is the "brain" of various types Unmanned Underwater Vehicles (UUVs), and premise guarantee for UUVs to complete expected tasks. existing systems UUV all adopt one-piece dry or oil-filled sealing structure. As a result, it can only use highly customized integrated embedded system, which not lacks reliability, but also difficult maintain. Aiming solve above problems, this study proposes implements an modular controller (OFMC) that combines compactness modularity...