A5100644664- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Geographic Information Systems Studies
- Remote Sensing and LiDAR Applications
- Data Management and Algorithms
- Remote Sensing in Agriculture
- Advanced Image Fusion Techniques
- Human Mobility and Location-Based Analysis
- Automated Road and Building Extraction
- Land Use and Ecosystem Services
- 3D Modeling in Geospatial Applications
- Advanced Computational Techniques and Applications
- 3D Surveying and Cultural Heritage
- Soil Geostatistics and Mapping
- Robotics and Sensor-Based Localization
- Advanced Vision and Imaging
- Urban Transport and Accessibility
- Landslides and related hazards
- Atmospheric chemistry and aerosols
- Video Coding and Compression Technologies
- Geological Modeling and Analysis
- Satellite Image Processing and Photogrammetry
- Traffic Prediction and Management Techniques
- Simulation and Modeling Applications
- Transportation Planning and Optimization
Hong Kong Polytechnic University
2016-2025
Huaiyin Normal University
2025
Hohai University
2016-2024
Anhui Agricultural University
2024
Beijing University of Agriculture
2024
Aerospace Information Research Institute
2021-2024
Chinese Academy of Sciences
2020-2024
China Electric Power Research Institute
2024
Nanchang Hangkong University
2024
National Astronomical Observatories
2023
Change detection based on remote sensing (RS) data is an important method of detecting changes the Earth’s surface and has a wide range applications in urban planning, environmental monitoring, agriculture investigation, disaster assessment, map revision. In recent years, integrated artificial intelligence (AI) technology become research focus developing new change methods. Although some researchers claim that AI-based approaches outperform traditional approaches, it not immediately obvious...
Change detection based on remote sensing (RS) images has a wide range of applications in many fields. However, existing approaches for detecting changes RS with complex land covers still have room improvement. In this article, high-resolution image change approach deep feature difference convolutional neural network (CNN) is proposed. This uses CNN to learn the features from and then transfer learning compose two-channel shared weight generate multiscale multidepth map detection. The trained...
Standard deviational ellipse (SDE) has long served as a versatile GIS tool for delineating the geographic distribution of concerned features. This paper firstly summarizes two existing models calculating SDE, and then proposes novel approach to constructing same SDE based on spectral decomposition sample covariance, by which concept is naturally generalized into higher dimensional Euclidean space, named standard hyper-ellipsoid (SDHE). Then, rigorous recursion formulas are derived confidence...
Road information has a fundamental role in modern society. extraction from optical satellite images is an economic and efficient way to obtain update transportation database. This paper presents integrated method extract urban main-road centerlines images. The proposed four main steps. First, general adaptive neighborhood introduced implement spectral-spatial classification segment the into two categories: road nonroad groups. Second, groups homogeneous property, measured by local Geary's C,...
Airborne laser scanners and multi‐spectral provide information on height spectra that offer exciting possibilities for extracting features in complicated urban areas. We apply an object‐based approach to building extraction from image data differs conventional per‐pixel approaches. Since objects are extracted based the thematic geometric components of objects, quality assessments will have be made with respect these components. The known per‐pixel‐based methods assessing been examined new...
Abstract Rapid global economic development has resulted in a corresponding intensification of urbanization, which turn impacted the ecology vast regions world. A series problems have thus been introduced, such as changes land-use/land-cover (LULC) and local climate. The process urbanization predominantly represents land-use, is deemed by researchers to be chief cause climate change ecological change. One principal purposes research this field find ways mitigate influence land-use on or...
Road centerline extraction from remotely sensed imagery can be used to update a Geographic Information System (GIS) database. The common road high-resolution is based on spectral information only; it difficult separate features background completely, and thinning algorithm always results in short spurs which reduce the smoothness of centerline. To overcome aforementioned shortcomings existing algorithms, this letter presents new method extract shape multivariate adaptive regression splines...
Understanding the spatial scale sensitivity of cellular automata is crucial for improving accuracy land use change simulation. We propose a framework based on response surface method to comprehensively explore Markov chain (CA-Markov) model, and present hybrid evaluation model expressing simulation that merges strengths Kappa coefficient Contagion index. Three Landsat-Thematic Mapper remote sensing images Wuhan in 1987, 1996, 2005 were used extract information. The results demonstrate...
Landslide inventory mapping (LIM) plays an important role in hazard assessment and relief. Even though much research has taken place past decades, there is space for improvements accuracy the usability of systems. In this paper, a new landslide framework proposed based on integration majority voting method multiscale segmentation postevent images, making use spatial feature landslide. Compared with some similar state-of-the-art methods, three advantages: 1) generation LIM almost automatic;...
It is a technological challenge to recognize landslides from remotely sensed (RS) images automatically and at high speeds, which fundamentally important for preventing controlling natural landslide hazards. Many methods have been developed, but there remains room improvement stable, higher accuracy, high-speed recognition large areas with complex land cover. In this article, novel integrated approach combining deep convolutional neural network (CNN) change detection proposed RS images....
Landscape transformations in rapidly urbanizing Guangdong, Hong Kong, and Macao (GHKM) regions of South China represent the most complex dynamic processes altering local ecology environment. In this study, Land Change Modeler (LCM) is applied to land use cover (LULC) maps for years 2005, 2010, 2017, derived from Landsat images, with aim understanding change patterns during 2005–2017 and, further, predict future scenario 2024 2031. Furthermore, changes spatial structural are quantified...
The family Nymphalidae is the largest group of butterflies with high species richeness. Rhinopalpapolynice (Cramer, [1779]), a forest species, was discovered in mid-stream Yuanjiang-Red River Valley Yunnan Province for first time, which represents record genus Rhinopalpa China.The R. polynice [1779]) from China. specimen collected Province. female genitalia are described time.