A5058213496- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Land Use and Ecosystem Services
- Video Surveillance and Tracking Methods
- Automated Road and Building Extraction
- Advanced Image and Video Retrieval Techniques
- Topic Modeling
- Advanced Neural Network Applications
- Remote Sensing and LiDAR Applications
- Graphene research and applications
- Infrared Target Detection Methodologies
- Advanced Graph Neural Networks
- Geographic Information Systems Studies
- Geochemistry and Geologic Mapping
- Underwater Acoustics Research
- Advanced Battery Materials and Technologies
- Text and Document Classification Technologies
- Advancements in Battery Materials
- Smart Agriculture and AI
- Advanced Image Fusion Techniques
- Data Quality and Management
- Topological Materials and Phenomena
- Food Supply Chain Traceability
- Groundwater and Watershed Analysis
- Plasmonic and Surface Plasmon Research
China University of Geosciences
2019-2025
Shandong University
2022-2024
ORCID
2021
Hunan Vocational Institute of Technology
2018
Urban Informal Settlements (UIS) denote densely populated locales characterized by inadequate urban infrastructure standards, often exhibiting an amalgamation of rural and attributes, primarily situated within the confines major cities or metropolitan regions. UIS mapping is a typical task that aims to identify pixels corresponding informal settlements in remote sensing images. The extremely similar visual characteristics, sample uncertainty, highly manual costs bring large-scale noteworthy...
Geological remote sensing interpretation can extract elements of interest from multiple types images, which is vital in geological survey and mapping, especially inaccessible regions. However, due to numerous classes, high interclass similarities, complex distributions, sample imbalances elements, the results machine-learning (ML)-based methods are understandably worse than manual visual interpretation. Additionally, scholars have mainly carried out their works interpret a single element...
Urban informal settlements (UIS) are high-density population areas with low urban infrastructure standards. UIS classification, which automates identifying UIS, is of great significance for various computing tasks. Fast and accurate extraction has the following difficulties. First, from a high-resolution perspective, buildings in settlement low-floor dense, complex spatial relationships. Second, settlements' remote sensing observation characteristics highly inconspicuous, caused by shooting...
Constructing a knowledge graph of geological hazards literature can facilitate the reuse and provide reference for hazard governance. Named entity recognition (NER), as core technology constructing graph, has to face challenges that named entities in are diverse form, ambiguous semantics, uncertain context. This introduce difficulties designing practical features during NER classification. To address above problem, this paper proposes deep learning-based model; namely, deep, multi-branch...
Submeter high-resolution remote sensing image land cover classification could provide significant help for urban monitoring, management, and planning. Deep learning (DL)-based models have achieved remarkable performance in many tasks through end-to-end supervised learning. However, the excellent of DL-based relies heavily on a large number well-annotated samples, which is impossible practical scenarios. Additionally, training set contain all different types. To overcome these problems, this...
Urban informal settlements (UIS) are high-density population with low standards of living and supply. UIS semantic segmentation, which identifies pixels corresponding to in remote sensing images, is crucial the estimation poor communities, urban management, resource allocation, future planning, particularly megacities. However, most studies on settlement mapping either based parcels (image classification) or (semantic segmentation). Few utilize object information improve mapping. Since...
The discovery of graphene has led to the devotion intensive efforts, theoretical and experimental, produce two-dimensional (2D) materials that can be used for developing functional devices. This work provides a brief review recent developments in lattice models 2D Dirac their relevant real material counterparts are crucial understanding origins cones electronic band structures as well design device applications. We focus on roles symmetry, atomic orbital hybridization, spin–orbit coupling...
Data and knowledge of spatial-temporal dynamics multiple types water body are significant for resources management but remain very limited. Using the Landsat satellite data weakly supervised deep learning techniques long term mapping, we report annual maps inland bodies on urban agglomeration scale in middle reaches Yangtze River (MRYR) during 1990-2021 at 30m spatial resolution. Accuracy assessment from 14000 validation points seven years indicates an overall accuracy 94.50%. Quantitative...
Urban open spaces (UO) play a crucial role in urban environments, particularly areas where social and economic activities are rapidly increasing. However, the challenges of high inter-class similarity, complex environmental surroundings, scale variations often result suboptimal performance UO mapping. To address these issues, this paper proposes UOSAM, novel approach that leverages Segment Anything Model (SAM) for efficient mapping using high-resolution remote sensing images. Our method...
Remote sensing image scene classification, which aims to identify the types of land cover, is a fundamental task in remote analysis. images contain variety land-cover objects. These objects form complex and diverse through spatial combination correlation, makes imagery scenes classification difficult. In addition, redundant information that has negative impact on rather challenging. Recently, there are many deep learning based methods, have achieved remarkable performance an end-to-end...
Object detection, aiming to recognize and locate objects of interest in aerial images, has historically played a significant role the remote sensing community. Following remarkable improvements Earth observation technologies, high-resolution (HRRS) images with bird's eye view perspective have revealed many categories sufficient variations appearance on complex backgrounds that make HRRS object detection an active but challenging task. The selection positive samples negative training...
Mountain roads are of great significance to traffic navigation and military road planning. Extracting mountain based on high-resolution remote sensing images (HRSIs) is a hot spot in current extraction research. However, massive terrain objects, blurred edges, sand coverage complex environments make it challenging extract from HRSIs. Complex result weak research results targeted models lack corresponding datasets. To solve the above problems, first, we propose new dataset: Road Datasets...
Urban Villages (UV) refer to areas of urban informal settlements lagging behind the rapid urbanization process. Recent studies focus on using satellite images classify UV. However, only capture objects from a bird-eye perspective, thus cannot obtain complex spatial relationships between objects. In UV areas, buildings and are usually dense, small in size, obscure each other. Therefore, it is challenging accurately with perspectives. this paper, solve problem, we proposed novel method that...
Urban functional zones (UFZs are the urban spaces divided by various activities and basic units of daily human activities. UFZ mapping, which identifies categories in different spatial areas a city, is considerable significance to management, design, sustainable development. Various deep learning-based (DL-based methods, achieved remarkable results an end-to-end supervised process, were proposed for mapping. However, excellent performance DL-based models relies heavily on large number...
Graphene has significantly influenced advanced photonics, due to its exceptional ability confine light at atomic scales. However, the presence of isotropic Dirac cones (DCs) in graphene restricts capability support hyperbolic surface plasmon polaritons (SPPs) propagation without specific patterning treatments. Additionally, frequency is highly sensitive Fermi level, making it unstable under external perturbations. In this study, we present a dual anisotropic cone (DADC) model that addresses...