A5100392346- Remote-Sensing Image Classification
- Remote Sensing and Land Use
- Advanced Optical Imaging Technologies
- Remote Sensing in Agriculture
- Video Surveillance and Tracking Methods
- Photorefractive and Nonlinear Optics
- Advanced Optical Sensing Technologies
- Anomaly Detection Techniques and Applications
- Climate change and permafrost
- Service-Oriented Architecture and Web Services
- Automated Road and Building Extraction
- Remote Sensing and LiDAR Applications
- Surface Roughness and Optical Measurements
- Cryospheric studies and observations
- Quantum optics and atomic interactions
- Optical and Acousto-Optic Technologies
- Hydrology and Watershed Management Studies
- Interactive and Immersive Displays
- Environmental Changes in China
- Advanced optical system design
- Land Use and Ecosystem Services
- Image Processing Techniques and Applications
- Advanced Image and Video Retrieval Techniques
- Optical measurement and interference techniques
- Augmented Reality Applications
Nanjing University of Science and Technology
2025
China National Commission for Disaster Reduction
2014-2024
Ministry of Civil Affairs
2014-2021
Shandong Jiaotong University
2019
Shanghai Jiao Tong University
2011
Shanghai Institute of Optics and Fine Mechanics
2004
Chinese Academy of Sciences
2004
Research Institute of Highway
1992
This paper proposes a deep convolutional neural networks (CNNs) based method to automatically detect suburban buildings from high resolution Google Earth imagery. Traditional methods on low-level hand-engineered features or mid-level bag of have great limitations in complex environment, especially areas. Inspired by the astounding achievement CNNs object recognition and detection, we develop novel cluttered images which consists three main steps. Firstly, multi-scale saliency computation is...
Disaster damage assessment is an important basis for the objective of social impacts disasters and planning recovery reconstruction. It also research field with regard to disaster mitigation risk management. Quantitative physical refers determination state exposed elements in a area, reflecting aggregate quantities damages. plays key role comprehensive major natural hazard-induced disasters. The National Reduction Center China has established technical work flow quantitative using remote...
In the landscape of recent technological advancements, advent 4D millimeter-wave radar has ushered in a new era data quality improvements, showcasing potential to rival, or even surpass, Lidar systems. Despite its innovative prowess, lower density and accuracy radar's point clouds, comparison those generated by Lidar, pose significant limitations technology's broader application. Addressing these constraints, our research introduces comprehensive, end-to-end methodology for augmenting cloud...
The Chinese Government and citizens face enormous challenges of disaster management as widespread devastation, economic damages, loss human lives caused by increasing natural disasters. Disaster requires a complicated iterative process that includes monitoring, early detection, forecasting, assessment, efficient analysis reduction. Each task typically involves the use technologists multiple geospatial information resources, including sensors, data sources, models, geo-tools, software...
Change threshold selection (CTS) plays an important role in land cover change detection. The traditional CTS methods are mainly proposed by using the information contained grayscale histogram distributions or pixel neighborhoods. However, is highly spatially heterogeneous, and changes different types characterized magnitudes. Unfortunately, few studies have considered effects of both type spatial heterogeneity on CTS, potentially leading to false alarms missed alarms. To address this...
Land cover change detection plays an important role in natural disaster monitoring, tracking urban expansion, and many social benefit areas. The spectral-based direct comparison (SDC) methods are commonly used for detection, but such vulnerable to the influence of external factors. In general, land changes among different types have characters magnitude. class probability-based (CPDC) consider type information reduce factors, these strongly dependent on training samples. To address above...
Image radiometric distortion is problematic to many remote sensing based image change detection methods. Thus normalization critical successful and other analysis. Histogram matching (HM) method has been widely used for normalization. However, when two corresponding scenes have partial changes, these changes will introduce additional distortions in the histogram process. Obviously, if areas images can be excluded from matching, avoided. Thus, a novel, iterative HM algorithm proposed this...
Building structural types (BSTs) information is vital for seismic risk and vulnerability modeling. However, obtaining this kind of not a trivial task. The conventional method involves labor-intensive inefficient manual inspection process each building. Nowadays, few methods have explored to use remote sensing images some building-related knowledge (BRK) realize automated BSTs recognition. these many limitations, such as insufficient mining multimodal difficulty BRK, which hinders their...
Topological building extraction in remote sensing images is vital for city planning, disaster assessment, and other real-world applications. To meet the requirements of applications, existing approaches predict topological by vectorization binary masks using multiple refinement stages, leading to complex methodology poor generalization. tackle this issue, we propose a approach directly predicting serialized vertices each instance. We observe that order from one inherently bidirectional,...
The idea of combining a flexible fiber bundle with the microscopic imaging system provides possibility cross-scale detection defects and textures on large-scale complex components. However, pixelization artifacts caused by inter-core spacing fibers degrade image quality make it difficult to identify micro-features. A high-resolution reconstruction strategy is proposed based dictionary learning. By training high- low-resolution pairs after registration, coupled obtained. Then high-quality...
The Talbot effect is one of the most basic optical phenomena that has received extensive investigations both because its new results provide us more understanding fundamental Fresnel diffraction and also wide applications. We summarize our recent on this subject. Symmetry effect, which was reported in Optics Communications 1995, now realized as key to reveal other rules for explanation array illumination. regularly rearranged-neighboring-phase-differences (RRNPD) rule, a completely set...
Array illuminator based on Talbot effect is an important optical element that has wide applications in interconnection, communication, and computing. This paper summarizes our recent results this subject. Symmetry of the effect, was reported Optics Communication 115, 40 (1995), now realized as first step to revealing other rules for explanation array illumination. The prime-number decomposing rule (Applied 40, 607 (2001)) shows number phase level a related with prime number. Along study...
Small satellite constellation of environment and disaster's monitoring predicting (shorted for HJ-1) is not a mapping satellite, its parameters attitude orbit cannot satisfy the requirement geometric correction using strict imaging model. On other hand, due to 12000 CCD detectors large overlay multispectral payload named carried by HJ-1 error caused distortion be ignored. Aiming at these problems HJ-1, this paper proposes model algorithm based on Ground Control Point (GCP) collinear...
Talbot effect is one of the most basic optical phenomena that has received extensive investigations both because it a fundamental Fresnel diffraction and also its wide applications. As important applications fractional effect, array illuminators have been in-depth studied since Lohmann Thomas put forward for first time. illuminator become an element in interconnection, communication computing high efficiency, simple structure, compactness low-cost. Researches proposed different...
The aspheric surfaces can be tested by using interference type computer-generated holograms (CGH). However, the measurement results are affected system errors that exist in optical arrangement. In order to improve test accuracy, a quantitative method for processing has been investigated. Experimental show this is feasible and effective.