A5023925857- Remote-Sensing Image Classification
- Advanced Image Fusion Techniques
- Image and Signal Denoising Methods
- Sparse and Compressive Sensing Techniques
- Advanced Image Processing Techniques
- Remote Sensing in Agriculture
- Spectroscopy and Chemometric Analyses
- Remote Sensing and Land Use
- Image Processing Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Anomaly Detection Techniques and Applications
- Atmospheric aerosols and clouds
- Advanced Algorithms and Applications
- Oil Spill Detection and Mitigation
- Higher Education and Teaching Methods
- Atmospheric chemistry and aerosols
- Atmospheric and Environmental Gas Dynamics
- Face and Expression Recognition
- Advanced Vision and Imaging
- Industrial Vision Systems and Defect Detection
- Remote Sensing and LiDAR Applications
- Image Enhancement Techniques
- Marine and coastal ecosystems
- Advanced Chemical Sensor Technologies
- Atmospheric Ozone and Climate
Aerospace Information Research Institute
2019-2025
Chinese Academy of Sciences
2016-2025
Beijing Institute of Technology
2009-2025
Tsinghua University
2015-2025
Shandong Agricultural University
2022-2025
Beijing Forestry University
2023-2024
Taishan University
2024
Yunnan University
2024
East China University of Science and Technology
2024
Chinese Research Academy of Environmental Sciences
2024
We have entered an era of big data. It is popular to refer the three Vs when characterizing data: remarkable growths in volume, velocity and variety However, this statement too general. Remote-sensing data has several concrete special characteristics: multi-source, multi-scale, high-dimensional, dynamic-state, isomer, non-linear characteristics. This survey explains these characteristics detail. Furthermore, according whether are closely related instruments or methods acquisition, we points...
Abstract. Knowledge of aerosol size and composition is important for determining radiative forcing effects aerosols, identifying sources improving satellite retrieval algorithms. The ability to extrapolate composition, or type, from intensive optical properties can help expand the current knowledge spatiotemporal variability in type globally, particularly where chemical measurements do not exist concurrently with property measurements. This study uses medians scattering Ångström exponent...
Seismic landslides are the most common and highly destructive earthquake-triggered geological hazards. They large in scale occur simultaneously many places. Therefore, obtaining landslide information quickly after an earthquake is key to disaster mitigation relief. The survey results show that of landslide-information extraction methods involve too much manual participation, resulting a low degree automation inability provide effective for rescue time. In order solve abovementioned problems...
In the past decades, remote sensing (RS) data fusion has always been an active research community. A large number of algorithms and models have developed. Generative adversarial networks (GANs), as important branch deep learning, show promising performances in a variety RS image fusions. This review provides introduction to GANs for fusion. We briefly frequently used architecture characteristics comprehensively discuss how use realize homogeneous RS, heterogeneous ground observation (GO)...
Due to the limitation of technology and budget, it is often difficult for sensors a single remote sensing satellite have both high temporal resolution spatial (HTHS) at same time. In this paper, we proposed new Multi-level Feature Fusion with Generative Adversarial Network (MLFF-GAN) generating fusion HTHS images. MLFF-GAN mainly uses U-net-like architecture its generator composed three stages: feature extraction, fusion, image reconstruction. extraction reconstruction stage, employs...
A large group of dictionary learning algorithms focus on adaptive sparse representation data. Almost all them fix the number atoms in iterations and use unfeasible schemes to update process. It's difficult, therefore, for train a from Big Data. new algorithm is proposed here by extending classical K-SVD method. In method, when each batch data samples added training process, are selectively introduced into dictionary. Furthermore, only small as subspace controls current orthogonal matching...
Nowadays, our ability to acquire remote sensing data has been improved an unprecedented level.[...]
Due to the trade-off of temporal resolution and spatial resolution, spatiotemporal image-fusion uses existing high-spatial-low-temporal (HSLT) high-temporal-low-spatial (HTLS) images as prior knowledge reconstruct high-temporal-high-spatial (HTHS) images. However, some algorithms ignore issue that information HTLS is insufficient support acquisition information, which leads unsatisfactory accuracy fusion result. To introduce more algorithm in this article Cycle-generative adversarial...
Landslides are the most common and destructive secondary geological hazards caused by earthquakes. It is difficult to extract landslides automatically based on remote sensing data, which import for scenario of disaster emergency rescue. The literature review showed that current extraction methods mostly depend expert interpretation was low automation thus unable provide sufficient information earthquake rescue in time. To solve above problem, an end-to-end improved Mask R-CNN model proposed....
Ocean oil spills cause serious damage to the marine environment, especially around coastal waters. Synthetic aperture radar (SAR) has been proven be a useful tool for spill detection under low moderate wind conditions. SAR operates in microwave band and data is not affected by cloud cover day/night However, operational application of ocean limited false alarm targets or lookalike phenomena such as speed, natural films, etc. In this study, we develop analysis variance (ANOVA) extract features...
The fusion of remote sensing images with different spatial and temporal resolutions is needed for diverse Earth observation applications. A small number spatiotemporal methods that use sparse representation appear to be more promising than weighted- unmixing-based in reflecting abruptly changing terrestrial content. However, none the existing dictionary-based consider downsampling process explicitly, which degradation from high-resolution corresponding low-resolution images. In this paper,...
Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful plenty tasks. The current learning-based change method mainly based on conventional long short-term memory (Conv-LSTM), which does not have spatial characteristics. Since a process with both spatiality temporality, it necessary propose end-to-end spatiotemporal network. To achieve this, Conv-LSTM,...
Fusion of remote sensing images with different spatial and temporal resolutions is highly needed by diverse earth observation applications. A small number spatiotemporal fusion methods using sparse representation appear to be more promising than traditional linear mixture in reflecting abruptly changing terrestrial content. However, one the main difficulties that results have reduced expressional accuracy; this due part insufficient prior knowledge. For images, cluster joint structural...