Most unsupervised or semisupervised hyperspectral anomaly detection(HAD)methods train background reconstruction models in the original spectral domain.However,due to the noise and spatial resolution limitations,there ...Most unsupervised or semisupervised hyperspectral anomaly detection(HAD)methods train background reconstruction models in the original spectral domain.However,due to the noise and spatial resolution limitations,there may be a lack of discrimination between backgrounds and anomalies.This makes it easy for the autoencoder to capture the lowlevel features shared between the two,thereby increasing the difficulty of separating anomalies from the backgrounds,which runs counter to the purpose of HAD.To this end,the authors map the original spectrums to the fractional Fourier domain(FrFD)and reformulate it as a mapping task in which restoration errors are employed to distinguish background and anomaly.This study proposes a novel frequency‐to‐spectrum mapping generative adversarial network for HAD.Specifically,the depth separable features of backgrounds and anomalies are enhanced in the FrFD.Due to the semisupervised approach,FTSGAN needs to learn the embedded features of the backgrounds,thus mapping and restoring them from the FrFD to the original spectral domain.This strategy effectively prevents the model from focussing on the numerical equivalence of input and output,and restricts the ability of FTSGAN to restore anomalies.The comparison and analysis of the experiments verify that the proposed method is competitive.展开更多
China has experienced unprecedented urbanization in the past decades,resulting in dramatic changes in the physical,limnological,and hydrological characteristics of lakes in urban landscapes.However,the spatiotemporal ...China has experienced unprecedented urbanization in the past decades,resulting in dramatic changes in the physical,limnological,and hydrological characteristics of lakes in urban landscapes.However,the spatiotemporal dynamics in distribution and abundance of urban lakes in China remain poorly understood.Here,we characterized the spatiotemporal change patterns of urban lakes in China’s major cities between 1990 and 2015 using remote-sensing data and landscape metrics.The results showed that the urban lake landscape patterns have experienced drastic changes over the past 25 years.The total surface area of the urban lakes has decreased by 17,620.02 ha,a decrease of 24.22%,with a significant increase in the landscape fragmentation and a reduction in shape complexity.We defined three lake-shrinkage types and found that vanishment was the most common lake-shrinkage pattern,followed by edge-shrinkage and tunneling in terms of lake area.Moreover,we also found that urban sprawl was the dominant driver of the lake shrinkage,accounting for 67.89%of the total area loss,and the transition from lakes to cropland was also an important factor(19.86%).This study has potential for providing critical baseline information for government decision-making in lake resources management and urban landscape design.展开更多
Hyperspectral image provides abundant spectral information for remote discrimination of subtle differences in ground covers.However,the increasing spectral dimensions,as well as the information redundancy,make the ana...Hyperspectral image provides abundant spectral information for remote discrimination of subtle differences in ground covers.However,the increasing spectral dimensions,as well as the information redundancy,make the analysis and interpretation of hyperspectral images a challenge.Feature extraction is a very important step for hyperspectral image processing.Feature extraction methods aim at reducing the dimension of data,while preserving as much information as possible.Particularly,nonlinear feature extraction methods (e.g.kernel minimum noise fraction (KMNF) transformation) have been reported to benefit many applications of hyperspectral remote sensing,due to their good preservation of high-order structures of the original data.However,conventional KMNF or its extensions have some limitations on noise fraction estimation during the feature extraction,and this leads to poor performances for post-applications.This paper proposes a novel nonlinear feature extraction method for hyperspectral images.Instead of estimating noise fraction by the nearest neighborhood information (within a sliding window),the proposed method explores the use of image segmentation.The approach benefits both noise fraction estimation and information preservation,and enables a significant improvement for classification.Experimental results on two real hyperspectral images demonstrate the efficiency of the proposed method.Compared to conventional KMNF,the improvements of the method on two hyperspectral image classification are 8 and 11％.This nonlinear feature extraction method can be also applied to other disciplines where high-dimensional data analysis is required.展开更多
Close-range hyperspectral images are a promising source of information in plant biology,in particular,for in vivo study of physiological changes.In this study,we investigate how data fusion can improve the detection o...Close-range hyperspectral images are a promising source of information in plant biology,in particular,for in vivo study of physiological changes.In this study,we investigate how data fusion can improve the detection of leaf elements by combining pixel reflectance and morphological information.The detection of image regions associated to the leaf structures is the first step toward quantitative analysis on the physical effects that genetic manipulation,disease infections,and environmental conditions have in plants.We tested our fusion approach on Musa acuminata (banana) leaf images and compared its discriminant capability to similar techniques used in remote sensing.Experimental results demonstrate the efficiency of our fusion approach,with significant improvements over some conventional methods.展开更多
Various platforms,such as satellite,aircraft,ground-based,some emerging aspects (e.g.internet) have resulted in a dramatic improvement in the capabilities of earth observations (EO).The numerous remote sensing data pr...Various platforms,such as satellite,aircraft,ground-based,some emerging aspects (e.g.internet) have resulted in a dramatic improvement in the capabilities of earth observations (EO).The numerous remote sensing data promote an enhanced possibility to assess,monitor,and predict the dynamics of land-covers,anthropologic processes,and influence to the environments.Nonetheless,the properties of the data acquired by such diverse sources pose challenges to the processing methodologies,and hence,development of a series of new methods for the analysis of remote sensing images is required,The aim of this special issue of Geospatial Information Science is to develop new ideas and technologies to facilitate the utility of remote sensing data and to further explore its potential in various applications.展开更多
基金supported by the National Natural Science Foundation of China under Grant 62161160336Grant 41871245in part by the Belgium Vlaio project(AI ICON‐2021‐0599:Smart industrial spectral cameras via artificial intelligence).
文摘Most unsupervised or semisupervised hyperspectral anomaly detection(HAD)methods train background reconstruction models in the original spectral domain.However,due to the noise and spatial resolution limitations,there may be a lack of discrimination between backgrounds and anomalies.This makes it easy for the autoencoder to capture the lowlevel features shared between the two,thereby increasing the difficulty of separating anomalies from the backgrounds,which runs counter to the purpose of HAD.To this end,the authors map the original spectrums to the fractional Fourier domain(FrFD)and reformulate it as a mapping task in which restoration errors are employed to distinguish background and anomaly.This study proposes a novel frequency‐to‐spectrum mapping generative adversarial network for HAD.Specifically,the depth separable features of backgrounds and anomalies are enhanced in the FrFD.Due to the semisupervised approach,FTSGAN needs to learn the embedded features of the backgrounds,thus mapping and restoring them from the FrFD to the original spectral domain.This strategy effectively prevents the model from focussing on the numerical equivalence of input and output,and restricts the ability of FTSGAN to restore anomalies.The comparison and analysis of the experiments verify that the proposed method is competitive.
基金the National Natural Science Foundation of China(Grants No.41522110 and 41771360)the National Key Research and Development Program of China(Grant No.2016YFB0501403)。
文摘China has experienced unprecedented urbanization in the past decades,resulting in dramatic changes in the physical,limnological,and hydrological characteristics of lakes in urban landscapes.However,the spatiotemporal dynamics in distribution and abundance of urban lakes in China remain poorly understood.Here,we characterized the spatiotemporal change patterns of urban lakes in China’s major cities between 1990 and 2015 using remote-sensing data and landscape metrics.The results showed that the urban lake landscape patterns have experienced drastic changes over the past 25 years.The total surface area of the urban lakes has decreased by 17,620.02 ha,a decrease of 24.22%,with a significant increase in the landscape fragmentation and a reduction in shape complexity.We defined three lake-shrinkage types and found that vanishment was the most common lake-shrinkage pattern,followed by edge-shrinkage and tunneling in terms of lake area.Moreover,we also found that urban sprawl was the dominant driver of the lake shrinkage,accounting for 67.89%of the total area loss,and the transition from lakes to cropland was also an important factor(19.86%).This study has potential for providing critical baseline information for government decision-making in lake resources management and urban landscape design.
基金the National Natural Science Foundation of China [Grant Number 41722108],(Grant Number 91638201)%FWO project:data fusion for image analysis in remote sensing(Grant Number G037115N)
文摘Hyperspectral image provides abundant spectral information for remote discrimination of subtle differences in ground covers.However,the increasing spectral dimensions,as well as the information redundancy,make the analysis and interpretation of hyperspectral images a challenge.Feature extraction is a very important step for hyperspectral image processing.Feature extraction methods aim at reducing the dimension of data,while preserving as much information as possible.Particularly,nonlinear feature extraction methods (e.g.kernel minimum noise fraction (KMNF) transformation) have been reported to benefit many applications of hyperspectral remote sensing,due to their good preservation of high-order structures of the original data.However,conventional KMNF or its extensions have some limitations on noise fraction estimation during the feature extraction,and this leads to poor performances for post-applications.This paper proposes a novel nonlinear feature extraction method for hyperspectral images.Instead of estimating noise fraction by the nearest neighborhood information (within a sliding window),the proposed method explores the use of image segmentation.The approach benefits both noise fraction estimation and information preservation,and enables a significant improvement for classification.Experimental results on two real hyperspectral images demonstrate the efficiency of the proposed method.Compared to conventional KMNF,the improvements of the method on two hyperspectral image classification are 8 and 11％.This nonlinear feature extraction method can be also applied to other disciplines where high-dimensional data analysis is required.
文摘Close-range hyperspectral images are a promising source of information in plant biology,in particular,for in vivo study of physiological changes.In this study,we investigate how data fusion can improve the detection of leaf elements by combining pixel reflectance and morphological information.The detection of image regions associated to the leaf structures is the first step toward quantitative analysis on the physical effects that genetic manipulation,disease infections,and environmental conditions have in plants.We tested our fusion approach on Musa acuminata (banana) leaf images and compared its discriminant capability to similar techniques used in remote sensing.Experimental results demonstrate the efficiency of our fusion approach,with significant improvements over some conventional methods.
文摘Various platforms,such as satellite,aircraft,ground-based,some emerging aspects (e.g.internet) have resulted in a dramatic improvement in the capabilities of earth observations (EO).The numerous remote sensing data promote an enhanced possibility to assess,monitor,and predict the dynamics of land-covers,anthropologic processes,and influence to the environments.Nonetheless,the properties of the data acquired by such diverse sources pose challenges to the processing methodologies,and hence,development of a series of new methods for the analysis of remote sensing images is required,The aim of this special issue of Geospatial Information Science is to develop new ideas and technologies to facilitate the utility of remote sensing data and to further explore its potential in various applications.
