Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectra...Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectral similarity between buildings and backgrounds,sensor variations,and insufficient computational efficiency.To address these challenges,this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network(MewCDNet),which integrates the advantages of Convolutional Neural Networks and Transformers,balances computational costs,and achieves high-performance building change detection.The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction,integrates multi-level feature maps through a multi-scale fusion strategy,and incorporates two key modules:Cross-temporal Difference Detection(CTDD)and Cross-scale Wavelet Refinement(CSWR).CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semanticaware Euclidean distance weighting to enhance the distinction between true changes and background noise.CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms,enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes.Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods:achieving F1 scores of 91.54%on LEVIR,93.70%on WHUCD,and 64.96%on S2Looking for building change detection.Furthermore,MewCDNet exhibits optimal performance on the multi-class⋅SYSU dataset(F1:82.71%),highlighting its exceptional generalization capability.展开更多
In recent years,convolutional neural networks(CNN)and Transformer architectures have made significant progress in the field of remote sensing(RS)change detection(CD).Most of the existing methods directly stack multipl...In recent years,convolutional neural networks(CNN)and Transformer architectures have made significant progress in the field of remote sensing(RS)change detection(CD).Most of the existing methods directly stack multiple layers of Transformer blocks,which achieves considerable improvement in capturing variations,but at a rather high computational cost.We propose a channel-Efficient Change Detection Network(CE-CDNet)to address the problems of high computational cost and imbalanced detection accuracy in remote sensing building change detection.The adaptive multi-scale feature fusion module(CAMSF)and lightweight Transformer decoder(LTD)are introduced to improve the change detection effect.The CAMSF module can adaptively fuse multi-scale features to improve the model’s ability to detect building changes in complex scenes.In addition,the LTD module reduces computational costs and maintains high detection accuracy through an optimized self-attention mechanism and dimensionality reduction operation.Experimental test results on three commonly used remote sensing building change detection data sets show that CE-CDNet can reduce a certain amount of computational overhead while maintaining detection accuracy comparable to existing mainstream models,showing good performance advantages.展开更多
The objective of this study is to address semantic misalignment and insufficient accuracy in edge detail and discrimination detection,which are common issues in deep learning-based change detection methods relying on ...The objective of this study is to address semantic misalignment and insufficient accuracy in edge detail and discrimination detection,which are common issues in deep learning-based change detection methods relying on encoding and decoding frameworks.In response to this,we propose a model called FlowDual-PixelClsObjectMec(FPCNet),which innovatively incorporates dual flow alignment technology in the decoding stage to rectify semantic discrepancies through streamlined feature correction fusion.Furthermore,the model employs an object-level similarity measurement coupled with pixel-level classification in the PixelClsObjectMec(PCOM)module during the final discrimination stage,significantly enhancing edge detail detection and overall accuracy.Experimental evaluations on the change detection dataset(CDD)and building CDD demonstrate superior performance,with F1 scores of 95.1%and 92.8%,respectively.Our findings indicate that the FPCNet outperforms the existing algorithms in stability,robustness,and other key metrics.展开更多
Change Detection(CD)provides a research basis for environmental monitoring,urban expansion and reconstruction as well as disaster assessment,by identifying the changes of ground objects in different time periods.Tradi...Change Detection(CD)provides a research basis for environmental monitoring,urban expansion and reconstruction as well as disaster assessment,by identifying the changes of ground objects in different time periods.Traditional CD focused on the Binary Change Detection(BCD),focusing solely on the change and no-change regions.Due to the dynamic progress of earth observation satellite techniques,the spatial resolution of remote sensing images continues to increase,Multi-class Change Detection(MCD)which can reflect more detailed land change has become a hot research direction in the field of CD.Although many scholars have reviewed change detection at present,most of the work still focuses on BCD.This paper focuses on the recent progress in MCD,which includes five major aspects:challenges,datasets,methods,applications and future research direction.Specifically,the background of MCD is first introduced.Then,the major difficulties and challenges in MCD are discussed and delineated.The benchmark datasets for MCD are described,and the available open datasets are listed.Moreover,MCD is further divided into three categories and the specific techniques are described,respectively.Subsequently,the common applications of MCD are described.Finally,the relevant literature in the main journals of remote sensing in the past five years are analyzed and the development and future research direction of MCD are discussed.This review will help researchers understand this field and provide a reference for the subsequent development of MCD.Our collections of MCD benchmark datasets are available at:https://zenodo.org/record/6809804#.YsfvxXZByUk.展开更多
Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A light...Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A lightweight network of two channels is bulit based on the combination of convolutional neural network(CNN)and graph convolutional network(GCN).CNNs learn feature difference maps of multitemporal images,and attention modules adaptively fuse CNN-based and graph-based features for different scales.GCNs with a new kernel filter adaptively distinguish between nodes with the same and those with different labels,generating change maps.Experimental evaluation on two datasets validates the efficacy of the pro-posed method in addressing false alarms.展开更多
In this paper,a feature interactive bi-temporal change detection network(FIBTNet)is designed to solve the problem of pseudo change in remote sensing image building change detection.The network improves the accuracy of...In this paper,a feature interactive bi-temporal change detection network(FIBTNet)is designed to solve the problem of pseudo change in remote sensing image building change detection.The network improves the accuracy of change detection through bi-temporal feature interaction.FIBTNet designs a bi-temporal feature exchange architecture(EXA)and a bi-temporal difference extraction architecture(DFA).EXA improves the feature exchange ability of the model encoding process through multiple space,channel or hybrid feature exchange methods,while DFA uses the change residual(CR)module to improve the ability of the model decoding process to extract different features at multiple scales.Additionally,at the junction of encoder and decoder,channel exchange is combined with the CR module to achieve an adaptive channel exchange,which further improves the decision-making performance of model feature fusion.Experimental results on the LEVIR-CD and S2Looking datasets demonstrate that iCDNet achieves superior F1 scores,Intersection over Union(IoU),and Recall compared to mainstream building change detectionmodels,confirming its effectiveness and superiority in the field of remote sensing image change detection.展开更多
Remote sensing Change Detection(CD)involves identifying changing regions of interest in bi-temporal remote sensing images.CD technology has rapidly developed in recent years through the powerful learning ability of Co...Remote sensing Change Detection(CD)involves identifying changing regions of interest in bi-temporal remote sensing images.CD technology has rapidly developed in recent years through the powerful learning ability of Convolutional Neural Networks(CNN),affording complex feature extraction.However,the local receptive fields in the CNN limit modeling long-range contextual relationships in semantic changes.Therefore,this work explores the great potential of Siamese Transformers in CD tasks and proposes a general CD model entitled STCD that relies on Swin Transformers.In the encoding process,pure Transformers without CNN are used to model the long-range context of semantic tokens,reducing computational overhead and improving model efficiency compared to current methods.During the decoding process,the 3D convolution block obtains the changing features in the time series and generates the predicted change map in the deconvolution layer with axial attention.Extensive experiments on three binary CD datasets and one semantic CD dataset demonstrate that the proposed STCD model outperforms several popular benchmark methods considering performance and the required parameters.Among the STCD variants,the F1-Score of the Base-STCD on the three binary CD datasets LEVIR,DSIFN,and SVCD reached 89.85%,54.72%,and 93.75%,respectively,and the mF1-Score and mIoU on the semantic CD dataset SECOND were 75.60%and 66.19%.展开更多
Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance o...Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.展开更多
Semantic change detection is extension of change detection task in which it is not only used to identify the changed regions but also to analyze the land area semantic(labels/categories)details before and after the ti...Semantic change detection is extension of change detection task in which it is not only used to identify the changed regions but also to analyze the land area semantic(labels/categories)details before and after the timelines are analyzed.Periodical land change analysis is used for many real time applications for valuation purposes.Majority of the research works are focused on Convolutional Neural Networks(CNN)which tries to analyze changes alone.Semantic information of changes appears to be missing,there by absence of communication between the different semantic timelines and changes detected over the region happens.To overcome this limitation,a CNN network is proposed incorporating the Resnet-34 pre-trained model on Fully Convolutional Network(FCN)blocks for exploring the temporal data of satellite images in different timelines and change map between these two timelines are analyzed.Further this model achieves better results by analyzing the semantic information between the timelines and based on localized information collected from skip connections which help in generating a better change map with the categories that might have changed over a land area across timelines.Proposed model effectively examines the semantic changes such as from-to changes on land over time period.The experimental results on SECOND(Semantic Change detectiON Dataset)indicates that the proposed model yields notable improvement in performance when it is compared with the existing approaches and this also improves the semantic segmentation task on images over different timelines and the changed areas of land area across timelines.展开更多
Detailed analysis of Land Use/Land Cover （LULC） using remote sensing data in complex irrigated basins provides complete profile for better water resource management and planning. Using remote sensing data, this stud...Detailed analysis of Land Use/Land Cover （LULC） using remote sensing data in complex irrigated basins provides complete profile for better water resource management and planning. Using remote sensing data, this study provides detailed land use maps of the Lower Chenab Canal irrigated region of Pakistan from 2005 to 2012 for LULC change detection. Major crop types are demarcated by identifying temporal profiles of NDVI using MODIS 250 m × 250 m spatial resolution data. Wheat and rice are found to be major crops in rabi and kharif seasons, respectively. Accuracy assessment of prepared maps is performed using three dif- ferent techniques： error matrix approach, comparison with ancillary data and with previous study. Producer and user accuracies for each class are calculated along with kappa coeffi- cients （K）. The average overall accuracies for rabi and kharif are 82.83% and 78.21%, re- spectively. Producer and user accuracies for individual class range respectively between 72.5% to 77% and 70.1% to 84.3% for rabi and 76.6% to 90.2% and 72% to 84.7% for kharif. The K values range between 0.66 to 0.77 for rabi with average of 0.73, and from 0.69 to 0.74 with average of 0.71 for kharif. LULC change detection indicates that wheat and rice have less volatility of change in comparison with both rabi and kharif fodders. Transformation be- tween cotton and rice is less common due to their completely different cropping conditions. Results of spatial and temporal LULC distributions and their seasonal variations provide useful insights for establishing realistic LULC scenarios for hydrological studies.展开更多
A large number of publications have incorporated deep learning in the process of remote sensing change detection.In these Deep Learning Change Detection(DLCD)publications,deep learning methods have demonstrated their ...A large number of publications have incorporated deep learning in the process of remote sensing change detection.In these Deep Learning Change Detection(DLCD)publications,deep learning methods have demonstrated their superiority over conventional change detection methods.However,the theoretical underpinnings of why deep learning improves the performance of change detection remain unresolved.As of today,few in-depth reviews have investigated the mechanisms of DLCD.Without such a review,five critical questions remain unclear.Does DLCD provide improved information representation for change detection?If so,how?How to select an appropriate DLCD method and why?How much does each type of change benefits from DLCD in terms of its performance?What are the major limitations of existing DLCD methods and what are the prospects for DLCD?To address these five questions,we reviewed according to the following strategies.We grouped the DLCD information assemblages into the four unique dimensions of remote sensing:spectral,spatial,temporal,and multi-sensor.For the extraction of information in each dimension,the difference between DLCD and conventional change detection methods was compared.We proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools:separate and coupled models.Their advantages,limitations,applicability,and performance were thoroughly investigated and explicitly presented.We examined the variations in performance between DLCD and conventional change detection.We depicted two limitations of DLCD,i.e.training sample and hardware and software dilemmas.Based on these analyses,we identified directions for future developments.As a result of our review,we found that DLCD’s advantages over conventional change detection can be attributed to three factors:improved information representation;improved change detection methods;and performance enhancements.DLCD has to surpass the limitations with regard to training samples and computing infrastructure.We envision this review can boost developments of deep learning in change detection applications.展开更多
Due to inappropriate planning and management, accelerated urban growth and tremendous loss in land, especially cropland, have become a great challenge for sustainable urban development in China, especially in develope...Due to inappropriate planning and management, accelerated urban growth and tremendous loss in land, especially cropland, have become a great challenge for sustainable urban development in China, especially in developed urban area in the coastal regions; therefore, there is an urgent need to effectively detect and monitor the land use changes and provide accurate and timely information for planning and management. In this study a method combining principal component analysis (PCA) of multisensor satellite images from SPOT (systeme pour l'observation de la terre or earth observation satellite)-5 multispectral (XS) and Landsat-7 enhanced thematic mapper (ETM) panchromatic (PAN) data, and supervised classification was used to detect and analyze the dynamics of land use changes in the city proper of Hangzhou. The overall accuracy of the land use change detection was 90.67% and Kappa index was 0.89. The results indicated that there was a considerable land use change (10.03% of the total area) in the study area from 2001 to 2003, with three major types of land use conversions: from cropland into built-up land, construction site, and water area (fish pond). Changes from orchard land into built-up land were also detected. The method described in this study is feasible and useful for detecting rapid land use change in the urban area.展开更多
This paper presents a framework for road network change detection in order to update the Canadian National Topographic DataBase (NTDB). The methodology has been developed on the basis of road extraction from IRS\|pan ...This paper presents a framework for road network change detection in order to update the Canadian National Topographic DataBase (NTDB). The methodology has been developed on the basis of road extraction from IRS\|pan images (with a 5.8 m spatial resolution) by using a wavelet approach. The feature matching and conflation techniques are used to road change detection and updating. Elementary experiments have showed that the proposed framework could be used for developing an operational road database updating system.展开更多
Causes of land salinization were determined via land cover and hydrological process change detection in a typical part of Songnen Plain. The area of saline land increased from 4627 km2 in 1980 to 5416 km2 in 2000, and...Causes of land salinization were determined via land cover and hydrological process change detection in a typical part of Songnen Plain. The area of saline land increased from 4627 km2 in 1980 to 5416 km2 in 2000, and then decreased to 5198 km2 in 2015. The transformation between saline land and other land covers happened mainly before 2000, and saline land had transformation relationship mainly with cropland, grassland, and water body. From 1979 to 2007, groundwater depth fluctuated to increase and was mainly deeper than 3.3 m. Spatially, the area of the region where groundwater depth was deeper than 3.3 m increased from 46.7% in 1980 to 84% in 2000, while the area of the region almost occupied the whole region after 2000. Precipitation and evaporation changed little, while runoff decreased substantially. Shallow groundwater, change of cropland, grassland, and water body induced from human activities and decrease of runoff and increase of irrigation and water transfer from outer basin were the main reasons for land salinization before 2000. After 2000, groundwater with relatively great depth could not exert great influence on land salinization. Protection of grassland and wetland prevented the increase of the area of saline land.展开更多
Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and search.However,even the most advanced models require large amounts of data for mode...Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and search.However,even the most advanced models require large amounts of data for model training and testing.Therefore,sufficient labeled images with different imaging conditions are needed.Inspired by computer graphics,we present a cloning method to simulate inland-water scene and collect an auto-labeled simulated dataset.The simulated dataset consists of six challenges to test the effects of dynamic background,weather,and noise on change detection models.Then,we propose an image translation framework that translates simulated images to synthetic images.This framework uses shared parameters(encoder and generator)and 22×22 receptive fields(discriminator)to generate realistic synthetic images as model training sets.The experimental results indicate that:1)different imaging challenges affect the performance of change detection models;2)compared with simulated images,synthetic images can effectively improve the accuracy of supervised models.展开更多
The problems and difficulty of current change detection techniques are presented.Then,according to whether image registration is done before change detection algorithms,the authors classify the change detection into t...The problems and difficulty of current change detection techniques are presented.Then,according to whether image registration is done before change detection algorithms,the authors classify the change detection into two categories:the change detection after image registration and the change detection simultaneous with image registration.For the former,four topics including the change detection between new image and old image,the change detection between new image and old map,the change detection between new image/old image and old map,and the change detection between new multi-source images and old map/image are introduced.For the latter,three categories,i.e.the change detection between old DEM,DOM and new non-rectification image,the change detection between old DLG,DRG and new non-rectification image,and the 3D change detection between old 4D products and new multi-overlapped photos,are discussed.展开更多
Geographic landscapes in all over the world may be subject to rapid changes induced,for instance,by urban,forest,and agricultural evolutions.Monitoring such kind of changes is usually achieved through remote sensing.H...Geographic landscapes in all over the world may be subject to rapid changes induced,for instance,by urban,forest,and agricultural evolutions.Monitoring such kind of changes is usually achieved through remote sensing.However,obtaining regular and up-to-date aerial or satellite images is found to be a high costly process,thus preventing regular updating of land cover maps.Alternatively,in this paper,we propose a low-cost solution based on the use of groundlevel geo-located landscape panoramic photos providing high spatial resolution information of the scene.Such photos can be acquired from various sources:digital cameras,smartphone,or even web repositories.Furthermore,since the acquisition is performed at the ground level,the users’immediate surroundings,as sensed by a camera device,can provide information at a very high level of precision,enabling to update the land cover type of the geographic area.In the described herein method,we propose to use inverse perspective mapping(inverse warping)to transform the geo-tagged ground-level 360◦photo onto a top-down view as if it had been acquired from a nadiral aerial view.Once re-projected,the warped photo is compared to a previously acquired remotely sensed image using standard techniques such as correlation.Wide differences in orientation,resolution,and geographical extent between the top-down view and the aerial image are addressed through specific processing steps(e.g.registration).Experiments on publicly available data-sets made of both ground-level photos and aerial images show promising results for updating land cover maps with mobile technologies.Finally,the proposed approach contributes to the crowdsourcing efforts in geo-information processing and mapping,providing hints on the evolution of a landscape.展开更多
Conventional change detection approaches are mainly based on per-pixel processing,which ignore the sub-pixel spectral variation resulted from spectral mixture.Especially for medium-resolution remote sensing images use...Conventional change detection approaches are mainly based on per-pixel processing,which ignore the sub-pixel spectral variation resulted from spectral mixture.Especially for medium-resolution remote sensing images used in urban landcover change monitoring,land use/cover components within a single pixel are usually complicated and heterogeneous due to the limitation of the spatial resolution.Thus,traditional hard detection methods based on pure pixel assumption may lead to a high level of omission and commission errors inevitably,degrading the overall accuracy of change detection.In order to address this issue and find a possible way to exploit the spectral variation in a sub-pixel level,a novel change detection scheme is designed based on the spectral mixture analysis and decision-level fusion.Nonlinear spectral mixture model is selected for spectral unmixing,and change detection is implemented in a sub-pixel level by investigating the inner-pixel subtle changes and combining multiple composition evidences.The proposed method is tested on multi-temporal Landsat Thematic Mapper and China–Brazil Earth Resources Satellite remote sensing images for the land-cover change detection over urban areas.The effectiveness of the proposed approach is confirmed in terms of several accuracy indices in contrast with two pixel-based change detection methods(i.e.change vector analysis and principal component analysis-based method).In particular,the proposed sub-pixel change detection approach not only provides the binary change information,but also obtains the characterization about change direction and intensity,which greatly extends the semantic meaning of the detected change targets.展开更多
Up to now,detailedstrategies and algorithms of automaticchange detection for road networksbased on GIS have not been discussed.This paper discusses two differentstrategies of automatic change detec-tion for images wit...Up to now,detailedstrategies and algorithms of automaticchange detection for road networksbased on GIS have not been discussed.This paper discusses two differentstrategies of automatic change detec-tion for images with low resolution andhigh resolution using old GIS data,and presents a buffer detection andtracing algorithm for detecting roadfrom low-resolution images and a newprofile tracing algorithm for detectingroad from high-resolution images.Forfeature-level change detection(FL-CD),a so-called buffer detection algo-rithm is proposed to detect changes offeatures.Some ideas and algorithms ofusing GIS prior information and somecontext information such as substructures of road in high-resolution imagesto assist road detection and extractionare described in detail.展开更多
An unsupervised change-detection method that considers the spatial contextual information in a log-ratio difference image generated from multitemporal SAR images is proposed. A Markov random filed (MRF) model is parti...An unsupervised change-detection method that considers the spatial contextual information in a log-ratio difference image generated from multitemporal SAR images is proposed. A Markov random filed (MRF) model is particularly employed to exploit statistical spatial correlation of intensity levels among neighboring pixels. Under the assumption of the independency of pixels and mixed Gaussian distribution in the log-ratio difference image, a stochastic and iterative EM-MPM change-detection algorithm based on an MRF model is developed. The EM-MPM algorithm is based on a maximiser of posterior marginals (MPM) algorithm for image segmentation and an expectation-maximum (EM) algorithm for parameter estimation in a completely automatic way. The experiment results obtained on multitemporal ERS-2 SAR images show the effectiveness of the proposed method.展开更多
基金supported by the Henan Province Key R&D Project under Grant 241111210400the Henan Provincial Science and Technology Research Project under Grants 252102211047,252102211062,252102211055 and 232102210069+2 种基金the Jiangsu Provincial Scheme Double Initiative Plan JSS-CBS20230474,the XJTLU RDF-21-02-008the Science and Technology Innovation Project of Zhengzhou University of Light Industry under Grant 23XNKJTD0205the Higher Education Teaching Reform Research and Practice Project of Henan Province under Grant 2024SJGLX0126。
文摘Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning,disaster emergency response,and resource management.However,existing methods face challenges such as spectral similarity between buildings and backgrounds,sensor variations,and insufficient computational efficiency.To address these challenges,this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network(MewCDNet),which integrates the advantages of Convolutional Neural Networks and Transformers,balances computational costs,and achieves high-performance building change detection.The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction,integrates multi-level feature maps through a multi-scale fusion strategy,and incorporates two key modules:Cross-temporal Difference Detection(CTDD)and Cross-scale Wavelet Refinement(CSWR).CTDD adopts a dual-branch architecture that combines pixel-wise differencing with semanticaware Euclidean distance weighting to enhance the distinction between true changes and background noise.CSWR integrates Haar-based Discrete Wavelet Transform with multi-head cross-attention mechanisms,enabling cross-scale feature fusion while significantly improving edge localization and suppressing spurious changes.Extensive experiments on four benchmark datasets demonstrate MewCDNet’s superiority over comparison methods:achieving F1 scores of 91.54%on LEVIR,93.70%on WHUCD,and 64.96%on S2Looking for building change detection.Furthermore,MewCDNet exhibits optimal performance on the multi-class⋅SYSU dataset(F1:82.71%),highlighting its exceptional generalization capability.
基金supported by Henan Province Key R&D Project(241111210400)Henan Provincial Science and Technology Research Project(242102211007 and 242102211020)+1 种基金Jiangsu Science and Technology Programme-General Programme(BK20221260)Science and Technology Innovation Project of Zhengzhou University of Light Industry(23XNKJTD0205).
文摘In recent years,convolutional neural networks(CNN)and Transformer architectures have made significant progress in the field of remote sensing(RS)change detection(CD).Most of the existing methods directly stack multiple layers of Transformer blocks,which achieves considerable improvement in capturing variations,but at a rather high computational cost.We propose a channel-Efficient Change Detection Network(CE-CDNet)to address the problems of high computational cost and imbalanced detection accuracy in remote sensing building change detection.The adaptive multi-scale feature fusion module(CAMSF)and lightweight Transformer decoder(LTD)are introduced to improve the change detection effect.The CAMSF module can adaptively fuse multi-scale features to improve the model’s ability to detect building changes in complex scenes.In addition,the LTD module reduces computational costs and maintains high detection accuracy through an optimized self-attention mechanism and dimensionality reduction operation.Experimental test results on three commonly used remote sensing building change detection data sets show that CE-CDNet can reduce a certain amount of computational overhead while maintaining detection accuracy comparable to existing mainstream models,showing good performance advantages.
文摘The objective of this study is to address semantic misalignment and insufficient accuracy in edge detail and discrimination detection,which are common issues in deep learning-based change detection methods relying on encoding and decoding frameworks.In response to this,we propose a model called FlowDual-PixelClsObjectMec(FPCNet),which innovatively incorporates dual flow alignment technology in the decoding stage to rectify semantic discrepancies through streamlined feature correction fusion.Furthermore,the model employs an object-level similarity measurement coupled with pixel-level classification in the PixelClsObjectMec(PCOM)module during the final discrimination stage,significantly enhancing edge detail detection and overall accuracy.Experimental evaluations on the change detection dataset(CDD)and building CDD demonstrate superior performance,with F1 scores of 95.1%and 92.8%,respectively.Our findings indicate that the FPCNet outperforms the existing algorithms in stability,robustness,and other key metrics.
基金supported by the National Natural Science Foundation of China[grant number 41901306]the Key Lab of Spatial Data Mining&Information Sharing of Ministry of Education[grant number 2022LSDMIS09].
文摘Change Detection(CD)provides a research basis for environmental monitoring,urban expansion and reconstruction as well as disaster assessment,by identifying the changes of ground objects in different time periods.Traditional CD focused on the Binary Change Detection(BCD),focusing solely on the change and no-change regions.Due to the dynamic progress of earth observation satellite techniques,the spatial resolution of remote sensing images continues to increase,Multi-class Change Detection(MCD)which can reflect more detailed land change has become a hot research direction in the field of CD.Although many scholars have reviewed change detection at present,most of the work still focuses on BCD.This paper focuses on the recent progress in MCD,which includes five major aspects:challenges,datasets,methods,applications and future research direction.Specifically,the background of MCD is first introduced.Then,the major difficulties and challenges in MCD are discussed and delineated.The benchmark datasets for MCD are described,and the available open datasets are listed.Moreover,MCD is further divided into three categories and the specific techniques are described,respectively.Subsequently,the common applications of MCD are described.Finally,the relevant literature in the main journals of remote sensing in the past five years are analyzed and the development and future research direction of MCD are discussed.This review will help researchers understand this field and provide a reference for the subsequent development of MCD.Our collections of MCD benchmark datasets are available at:https://zenodo.org/record/6809804#.YsfvxXZByUk.
基金This work was supported by the Natural Science Foundation of Heilongjiang Province(LH2022F049).
文摘Overlooking the issue of false alarm suppression in heterogeneous change detection leads to inferior detection per-formance.This paper proposes a method to handle false alarms in heterogeneous change detection.A lightweight network of two channels is bulit based on the combination of convolutional neural network(CNN)and graph convolutional network(GCN).CNNs learn feature difference maps of multitemporal images,and attention modules adaptively fuse CNN-based and graph-based features for different scales.GCNs with a new kernel filter adaptively distinguish between nodes with the same and those with different labels,generating change maps.Experimental evaluation on two datasets validates the efficacy of the pro-posed method in addressing false alarms.
基金supported in part by the Fund of National Sensor Network Engineering Technology Research Center(No.NSNC202103)the Natural Science Research Project in Colleges and Universities of Anhui Province(No.2022AH040155)the Undergraduate Teaching Quality and Teaching Reform Engineering Project of Chuzhou University(No.2022ldtd03).
文摘In this paper,a feature interactive bi-temporal change detection network(FIBTNet)is designed to solve the problem of pseudo change in remote sensing image building change detection.The network improves the accuracy of change detection through bi-temporal feature interaction.FIBTNet designs a bi-temporal feature exchange architecture(EXA)and a bi-temporal difference extraction architecture(DFA).EXA improves the feature exchange ability of the model encoding process through multiple space,channel or hybrid feature exchange methods,while DFA uses the change residual(CR)module to improve the ability of the model decoding process to extract different features at multiple scales.Additionally,at the junction of encoder and decoder,channel exchange is combined with the CR module to achieve an adaptive channel exchange,which further improves the decision-making performance of model feature fusion.Experimental results on the LEVIR-CD and S2Looking datasets demonstrate that iCDNet achieves superior F1 scores,Intersection over Union(IoU),and Recall compared to mainstream building change detectionmodels,confirming its effectiveness and superiority in the field of remote sensing image change detection.
基金supported by the Military Commission Science and Technology Committee Leading Fund[grant number 18-163-00-TS-004-080-01].
文摘Remote sensing Change Detection(CD)involves identifying changing regions of interest in bi-temporal remote sensing images.CD technology has rapidly developed in recent years through the powerful learning ability of Convolutional Neural Networks(CNN),affording complex feature extraction.However,the local receptive fields in the CNN limit modeling long-range contextual relationships in semantic changes.Therefore,this work explores the great potential of Siamese Transformers in CD tasks and proposes a general CD model entitled STCD that relies on Swin Transformers.In the encoding process,pure Transformers without CNN are used to model the long-range context of semantic tokens,reducing computational overhead and improving model efficiency compared to current methods.During the decoding process,the 3D convolution block obtains the changing features in the time series and generates the predicted change map in the deconvolution layer with axial attention.Extensive experiments on three binary CD datasets and one semantic CD dataset demonstrate that the proposed STCD model outperforms several popular benchmark methods considering performance and the required parameters.Among the STCD variants,the F1-Score of the Base-STCD on the three binary CD datasets LEVIR,DSIFN,and SVCD reached 89.85%,54.72%,and 93.75%,respectively,and the mF1-Score and mIoU on the semantic CD dataset SECOND were 75.60%and 66.19%.
文摘Real-time indoor camera localization is a significant problem in indoor robot navigation and surveillance systems.The scene can change during the image sequence and plays a vital role in the localization performance of robotic applications in terms of accuracy and speed.This research proposed a real-time indoor camera localization system based on a recurrent neural network that detects scene change during the image sequence.An annotated image dataset trains the proposed system and predicts the camera pose in real-time.The system mainly improved the localization performance of indoor cameras by more accurately predicting the camera pose.It also recognizes the scene changes during the sequence and evaluates the effects of these changes.This system achieved high accuracy and real-time performance.The scene change detection process was performed using visual rhythm and the proposed recurrent deep architecture,which performed camera pose prediction and scene change impact evaluation.Overall,this study proposed a novel real-time localization system for indoor cameras that detects scene changes and shows how they affect localization performance.
文摘Semantic change detection is extension of change detection task in which it is not only used to identify the changed regions but also to analyze the land area semantic(labels/categories)details before and after the timelines are analyzed.Periodical land change analysis is used for many real time applications for valuation purposes.Majority of the research works are focused on Convolutional Neural Networks(CNN)which tries to analyze changes alone.Semantic information of changes appears to be missing,there by absence of communication between the different semantic timelines and changes detected over the region happens.To overcome this limitation,a CNN network is proposed incorporating the Resnet-34 pre-trained model on Fully Convolutional Network(FCN)blocks for exploring the temporal data of satellite images in different timelines and change map between these two timelines are analyzed.Further this model achieves better results by analyzing the semantic information between the timelines and based on localized information collected from skip connections which help in generating a better change map with the categories that might have changed over a land area across timelines.Proposed model effectively examines the semantic changes such as from-to changes on land over time period.The experimental results on SECOND(Semantic Change detectiON Dataset)indicates that the proposed model yields notable improvement in performance when it is compared with the existing approaches and this also improves the semantic segmentation task on images over different timelines and the changed areas of land area across timelines.
文摘Detailed analysis of Land Use/Land Cover （LULC） using remote sensing data in complex irrigated basins provides complete profile for better water resource management and planning. Using remote sensing data, this study provides detailed land use maps of the Lower Chenab Canal irrigated region of Pakistan from 2005 to 2012 for LULC change detection. Major crop types are demarcated by identifying temporal profiles of NDVI using MODIS 250 m × 250 m spatial resolution data. Wheat and rice are found to be major crops in rabi and kharif seasons, respectively. Accuracy assessment of prepared maps is performed using three dif- ferent techniques： error matrix approach, comparison with ancillary data and with previous study. Producer and user accuracies for each class are calculated along with kappa coeffi- cients （K）. The average overall accuracies for rabi and kharif are 82.83% and 78.21%, re- spectively. Producer and user accuracies for individual class range respectively between 72.5% to 77% and 70.1% to 84.3% for rabi and 76.6% to 90.2% and 72% to 84.7% for kharif. The K values range between 0.66 to 0.77 for rabi with average of 0.73, and from 0.69 to 0.74 with average of 0.71 for kharif. LULC change detection indicates that wheat and rice have less volatility of change in comparison with both rabi and kharif fodders. Transformation be- tween cotton and rice is less common due to their completely different cropping conditions. Results of spatial and temporal LULC distributions and their seasonal variations provide useful insights for establishing realistic LULC scenarios for hydrological studies.
文摘A large number of publications have incorporated deep learning in the process of remote sensing change detection.In these Deep Learning Change Detection(DLCD)publications,deep learning methods have demonstrated their superiority over conventional change detection methods.However,the theoretical underpinnings of why deep learning improves the performance of change detection remain unresolved.As of today,few in-depth reviews have investigated the mechanisms of DLCD.Without such a review,five critical questions remain unclear.Does DLCD provide improved information representation for change detection?If so,how?How to select an appropriate DLCD method and why?How much does each type of change benefits from DLCD in terms of its performance?What are the major limitations of existing DLCD methods and what are the prospects for DLCD?To address these five questions,we reviewed according to the following strategies.We grouped the DLCD information assemblages into the four unique dimensions of remote sensing:spectral,spatial,temporal,and multi-sensor.For the extraction of information in each dimension,the difference between DLCD and conventional change detection methods was compared.We proposed a taxonomy of existing DLCD methods by dividing them into two distinctive pools:separate and coupled models.Their advantages,limitations,applicability,and performance were thoroughly investigated and explicitly presented.We examined the variations in performance between DLCD and conventional change detection.We depicted two limitations of DLCD,i.e.training sample and hardware and software dilemmas.Based on these analyses,we identified directions for future developments.As a result of our review,we found that DLCD’s advantages over conventional change detection can be attributed to three factors:improved information representation;improved change detection methods;and performance enhancements.DLCD has to surpass the limitations with regard to training samples and computing infrastructure.We envision this review can boost developments of deep learning in change detection applications.
基金supported by the National Natural Science Foundation of China (NSFC) (No.30571112).
文摘Due to inappropriate planning and management, accelerated urban growth and tremendous loss in land, especially cropland, have become a great challenge for sustainable urban development in China, especially in developed urban area in the coastal regions; therefore, there is an urgent need to effectively detect and monitor the land use changes and provide accurate and timely information for planning and management. In this study a method combining principal component analysis (PCA) of multisensor satellite images from SPOT (systeme pour l'observation de la terre or earth observation satellite)-5 multispectral (XS) and Landsat-7 enhanced thematic mapper (ETM) panchromatic (PAN) data, and supervised classification was used to detect and analyze the dynamics of land use changes in the city proper of Hangzhou. The overall accuracy of the land use change detection was 90.67% and Kappa index was 0.89. The results indicated that there was a considerable land use change (10.03% of the total area) in the study area from 2001 to 2003, with three major types of land use conversions: from cropland into built-up land, construction site, and water area (fish pond). Changes from orchard land into built-up land were also detected. The method described in this study is feasible and useful for detecting rapid land use change in the urban area.
文摘This paper presents a framework for road network change detection in order to update the Canadian National Topographic DataBase (NTDB). The methodology has been developed on the basis of road extraction from IRS\|pan images (with a 5.8 m spatial resolution) by using a wavelet approach. The feature matching and conflation techniques are used to road change detection and updating. Elementary experiments have showed that the proposed framework could be used for developing an operational road database updating system.
基金Key Deployment Project of CAS,No.KFZD-SW-314National Natural Science Foundation of China,No.91547114
文摘Causes of land salinization were determined via land cover and hydrological process change detection in a typical part of Songnen Plain. The area of saline land increased from 4627 km2 in 1980 to 5416 km2 in 2000, and then decreased to 5198 km2 in 2015. The transformation between saline land and other land covers happened mainly before 2000, and saline land had transformation relationship mainly with cropland, grassland, and water body. From 1979 to 2007, groundwater depth fluctuated to increase and was mainly deeper than 3.3 m. Spatially, the area of the region where groundwater depth was deeper than 3.3 m increased from 46.7% in 1980 to 84% in 2000, while the area of the region almost occupied the whole region after 2000. Precipitation and evaporation changed little, while runoff decreased substantially. Shallow groundwater, change of cropland, grassland, and water body induced from human activities and decrease of runoff and increase of irrigation and water transfer from outer basin were the main reasons for land salinization before 2000. After 2000, groundwater with relatively great depth could not exert great influence on land salinization. Protection of grassland and wetland prevented the increase of the area of saline land.
基金supported in part by the Science and Technology Innovation 2030-Key Project of“New Generation Artificial Intelligence”(2018AAA0102303)the Young Elite Scientists Sponsorship Program of China Association of Science and Technology(YESS20210289)+1 种基金the China Postdoctoral Science Foundation(2020TQ1057,2020M682823)the National Natural Science Foundation of China(U20B2071,U1913602,91948204)。
文摘Change detection(CD)is becoming indispensable for unmanned aerial vehicles(UAVs),especially in the domain of water landing,rescue and search.However,even the most advanced models require large amounts of data for model training and testing.Therefore,sufficient labeled images with different imaging conditions are needed.Inspired by computer graphics,we present a cloning method to simulate inland-water scene and collect an auto-labeled simulated dataset.The simulated dataset consists of six challenges to test the effects of dynamic background,weather,and noise on change detection models.Then,we propose an image translation framework that translates simulated images to synthetic images.This framework uses shared parameters(encoder and generator)and 22×22 receptive fields(discriminator)to generate realistic synthetic images as model training sets.The experimental results indicate that:1)different imaging challenges affect the performance of change detection models;2)compared with simulated images,synthetic images can effectively improve the accuracy of supervised models.
基金the Open Research Fund Program of LIESMARS of Wuhan University(No.(01)0304)
文摘The problems and difficulty of current change detection techniques are presented.Then,according to whether image registration is done before change detection algorithms,the authors classify the change detection into two categories:the change detection after image registration and the change detection simultaneous with image registration.For the former,four topics including the change detection between new image and old image,the change detection between new image and old map,the change detection between new image/old image and old map,and the change detection between new multi-source images and old map/image are introduced.For the latter,three categories,i.e.the change detection between old DEM,DOM and new non-rectification image,the change detection between old DLG,DRG and new non-rectification image,and the 3D change detection between old 4D products and new multi-overlapped photos,are discussed.
文摘Geographic landscapes in all over the world may be subject to rapid changes induced,for instance,by urban,forest,and agricultural evolutions.Monitoring such kind of changes is usually achieved through remote sensing.However,obtaining regular and up-to-date aerial or satellite images is found to be a high costly process,thus preventing regular updating of land cover maps.Alternatively,in this paper,we propose a low-cost solution based on the use of groundlevel geo-located landscape panoramic photos providing high spatial resolution information of the scene.Such photos can be acquired from various sources:digital cameras,smartphone,or even web repositories.Furthermore,since the acquisition is performed at the ground level,the users’immediate surroundings,as sensed by a camera device,can provide information at a very high level of precision,enabling to update the land cover type of the geographic area.In the described herein method,we propose to use inverse perspective mapping(inverse warping)to transform the geo-tagged ground-level 360◦photo onto a top-down view as if it had been acquired from a nadiral aerial view.Once re-projected,the warped photo is compared to a previously acquired remotely sensed image using standard techniques such as correlation.Wide differences in orientation,resolution,and geographical extent between the top-down view and the aerial image are addressed through specific processing steps(e.g.registration).Experiments on publicly available data-sets made of both ground-level photos and aerial images show promising results for updating land cover maps with mobile technologies.Finally,the proposed approach contributes to the crowdsourcing efforts in geo-information processing and mapping,providing hints on the evolution of a landscape.
基金partially supported by the National Natural Science Foundation of China(No.41171323)Jiangsu Provincial Natural Science Foundation(No.BK2012018)+2 种基金the Key Laboratory of Geo-Informatics of National Administration of Surveying,Mapping and Geoinformation of China(No.201109)partially supported by the Priority Academic Program Development of Jiangsu Higher Education Institutions(PAPD)the Fundamental Research Funds for the Central Universities.
文摘Conventional change detection approaches are mainly based on per-pixel processing,which ignore the sub-pixel spectral variation resulted from spectral mixture.Especially for medium-resolution remote sensing images used in urban landcover change monitoring,land use/cover components within a single pixel are usually complicated and heterogeneous due to the limitation of the spatial resolution.Thus,traditional hard detection methods based on pure pixel assumption may lead to a high level of omission and commission errors inevitably,degrading the overall accuracy of change detection.In order to address this issue and find a possible way to exploit the spectral variation in a sub-pixel level,a novel change detection scheme is designed based on the spectral mixture analysis and decision-level fusion.Nonlinear spectral mixture model is selected for spectral unmixing,and change detection is implemented in a sub-pixel level by investigating the inner-pixel subtle changes and combining multiple composition evidences.The proposed method is tested on multi-temporal Landsat Thematic Mapper and China–Brazil Earth Resources Satellite remote sensing images for the land-cover change detection over urban areas.The effectiveness of the proposed approach is confirmed in terms of several accuracy indices in contrast with two pixel-based change detection methods(i.e.change vector analysis and principal component analysis-based method).In particular,the proposed sub-pixel change detection approach not only provides the binary change information,but also obtains the characterization about change direction and intensity,which greatly extends the semantic meaning of the detected change targets.
基金the Open Research Fund Program of LIESMARS of Wuhan University(No.(01)0304).
文摘Up to now,detailedstrategies and algorithms of automaticchange detection for road networksbased on GIS have not been discussed.This paper discusses two differentstrategies of automatic change detec-tion for images with low resolution andhigh resolution using old GIS data,and presents a buffer detection andtracing algorithm for detecting roadfrom low-resolution images and a newprofile tracing algorithm for detectingroad from high-resolution images.Forfeature-level change detection(FL-CD),a so-called buffer detection algo-rithm is proposed to detect changes offeatures.Some ideas and algorithms ofusing GIS prior information and somecontext information such as substructures of road in high-resolution imagesto assist road detection and extractionare described in detail.
文摘An unsupervised change-detection method that considers the spatial contextual information in a log-ratio difference image generated from multitemporal SAR images is proposed. A Markov random filed (MRF) model is particularly employed to exploit statistical spatial correlation of intensity levels among neighboring pixels. Under the assumption of the independency of pixels and mixed Gaussian distribution in the log-ratio difference image, a stochastic and iterative EM-MPM change-detection algorithm based on an MRF model is developed. The EM-MPM algorithm is based on a maximiser of posterior marginals (MPM) algorithm for image segmentation and an expectation-maximum (EM) algorithm for parameter estimation in a completely automatic way. The experiment results obtained on multitemporal ERS-2 SAR images show the effectiveness of the proposed method.
