Search

Change detection is the amount of changes that can guide to more concrete understandings into essential method concerning land cover, land usage and ecological variations. This paper deals with an intelligent methodology to optimize the solution out of the solution space that improves the efficiency of the change detection process. To support the theme, an integrated semi-supervised method is designed with a focus on image fusion, semi supervised clustering and binary swarm based optimization. A new approach of handling fusion using sparse coding is referred to expand the amount of information. Using the extracted information, change detection process is carried out by a constrained clustering technique to provide a solution reflecting the level of changes occurred in the region of investigation. To improve the accuracy by proposing a global optimum solution, still the result is refined through binary swarm based optimization process and hence the results are accelerated towards the increased level of accuracy followed by which the change map is reconstructed to show case changes prominently. To determine the accurateness of the proposed methodology quantitative and qualitative analysis has been done with different datasets. The proposed method has been evaluated with existing techniques such as k-means, AKM, FCM, ECKM and ASCC to show the efficiency and proved to be the preeminent change detection methodology compared to the state-of-art methods.

The coastline of the Nile Delta is a dynamic zone in Egypt that is received considerable attention. This region contains many major cities and it also contains a number of economically important harbors such as Damietta, Port Said and Alexandria. This research focuses attention on applying Geographical Information System (GIS) tool to assess prospective changes along the coast of the Nile Delta, Egypt during the past thirty-four years. In this paper, changes to the coastline were monitored using twelve scenes of Landsat images from 1984 to 2018. After the extraction of shorelines from Landsat images, Digital Shoreline Analysis System (DSAS) was used to calculate shoreline displacement rate. The results showed that about 44.2% of the study area was under erosion and 45% was under accretion while it was stable at 10.8% between 1984 and 2018. The results illustrated that Rosetta and Damietta promontories are displayed higher rates of erosion than other coastal regions of the Nile Delta. National measures must be implemented to protect the entire coast in threatened areas.

Forest cover requires large scale and frequent monitoring as an indicator of biodiversity and progress towards United Nations and World Bank Sustainable Development Goal 15. Measuring change in forest cover over time is an essential task in order to track and preserve quality habitats for species around the world. Due to the prohibitive expense and impracticality of mass field data collection to monitor forest cover at regular intervals, satellite images are a key data source for monitoring forest cover globally. A challenge of working with satellite images is missing data due to clouds. Existing methods for interpolating the missing data based on past images, such as compositing, are effective for stable land cover but can be inaccurate for dynamic and substantially changing landscapes. Here we present an adaptation of our recent stochastic spatial random forest (SS‐RF) method, which combines observed data from a prior image and modelled estimates of the current image to produce interpolated land cover values and associated probabilities of those values. Results show our SS‐RF method accurately detected simulated land cover change under both clear felling (0.83 average overall accuracy) and tree thinning (0.85 average overall accuracy). Our method detected forest cover change substantially more accurately than compositing, offering 39% and 12% increases in average overall accuracy for clear felling and tree thinning simulations respectively. However, when natural fluctuation occurs and there is minimal change in land cover, compositing has equivalent or more accurate performance than our method. Overall we find that our SS‐RF method produces accurate estimates under a range of simulated forest clearing scenarios and has a more accurate and robust performance than compositing when modelling noticeably changing landscapes.

The main objective of this research is to evaluate change detection techniques to monitoring land-cover changes that occurred between 2016 and 2017 in the study area located in new administrative capital region in Cairo Governorate, Egypt. The Study area is 77.350 km2. Image data is two Satellite images covering the study area, both are by Landsat_8 OLI/TIRS satellite with a low spatial resolution 30 m * 30 m. Reference data is two Satellite images covering the study area, both are by Nanosat satellite with a high spatial resolution 3 m * 3 m. The Study area was classified into roads, sand, rocks, bare soil, routes and buildings using Maximum Likelihood Classifier. Three change detection techniques namely; post-classification, independent component analysis and principal component analysis were applied. Quantitative evaluations for the results of these techniques were performed to determine the most appropriate change detection technique which will provide the highest accuracy for identifying the nature and extent of land-cover changes in New capital. The results indicated that the post classification change detection technique provided the highest accuracy while the principal component analysis technique gave the least accuracy. And the results show that the post classification change detection technique is straightforward because it is direct and its accuracy is mainly dependent upon the accuracy of the initial classifications of the two images. In the other two change detection techniques, more processing stages are required such as transformation stage

Scene change detection is an image processing problem related to partitioning pixels of a digital image into foreground and background regions. Mostly, visual knowledge-based computer intelligent systems, like traffic monitoring, video surveillance, and anomaly detection, need to use change detection techniques. Amongst the most prominent detection methods, there are the learning-based ones, which besides sharing similar training and testing protocols, differ from each other in terms of their architecture design strategies. Such architecture design directly impacts on the quality of the detection results, and also in the device resources capacity, like memory. In this work, we propose a novel Multiscale Cascade Residual Convolutional Neural Network that integrates multiscale processing strategy through a Residual Processing Module, with a Segmentation Convolutional Neural Network. Experiments conducted on two different datasets support the effectiveness of the proposed approach, achieving average overall $\boldsymbol{F\text{-}measure}$ results of $\boldsymbol{0.9622}$ and $\boldsymbol{0.9664}$ over Change Detection 2014 and PetrobrasROUTES datasets respectively, besides comprising approximately eight times fewer parameters. Such obtained results place the proposed technique amongst the top four state-of-the-art scene change detection methods., Published in: 2020 33rd SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)

Summary A nonparametric framework for changepoint detection, based on scan statistics utilizing graphs that represent similarities among observations, is gaining attention owing to its flexibility and good performance for high-dimensional and non-Euclidean data sequences. However, this graph-based framework faces challenges when there are repeated observations in the sequence, which is often the case for discrete data such as network data. In this article we extend the graph-based framework to solve this problem by averaging or taking the union of all possible optimal graphs resulting from repeated observations. We consider both the single-changepoint alternative and the changed-interval alternative, and derive analytical formulas to control the Type I error for the new methods, making them readily applicable to large datasets. The extended methods are illustrated on an application in detecting changes in a sequence of dynamic networks over time. All proposed methods are implemented in an $\texttt{R}$ package $\texttt{gSeg}$ available on CRAN.

As a result of the development of cities and inclination towards urbanization, natural areas decreased while urban areas increased. In this respect, determination of impermeable surfaces is important for the problems covering; effects of urbanization on natural environment, global environmental variation, urban atmospheric process, human activities and the effects of urbanization on the environment.Remote sensing images are used to examine and classify land cover/uses. Traditional classification methods are mainly divided into supervised classification and unsupervised classification. The aim of this study is to classify land cover/use and to state temporal change using the Support Vector Machines (SVM) approach, which is a supervised classification method. Arnavutkoy district of Istanbul was chosen as the study area for land use and change detection analysis. Landsat 5/7/8 satellite images of Arnavutkoy district were obtained and SVM process was applied to obtain these images. Firstly, four classes were created for each image: urban areas, vegetation, bare soils and wetlands SVM was applied and accuracy analysis was performed to the images classes of which were created before. CAD software and GIS software were used for image processing. The classification accuracy for SVM was found to be 98.66%, 98.31%, 98.95%, 97.99%, 96.37%, 97.90% (from 1995 to 2019). In addition, ROC analysis was used for comparison of accuracy analysis. As a result of this study, land cover/use change of Arnavutkoy district in the last 20 years has been determined. The urban area of the district was 40.99 〖"km" 〗^"2" in 1995 and 93.76 〖"km" 〗^"2" in 2019. In addition, the impact of the Europe's largest airport on land cover / use has been examined. The results showed that the accuracy of using SVM to classify land use/cover is high. Therefore, it has been proposed that this algorithm is used as an optimal classifier for land use/cover maps.

Expected shortfall (ES) is a popular risk measure and plays an important role in risk and portfolio management. Recently, change-point detection of risk measures has been attracting much attention in finance. Based on the self-normalized CUSUM statistic in Fan, Glynn and Pelger (2018) and the Wild Binary Segmentation (WBS) algorithm in Fryzlewicz (2014), this paper proposes a variant WBS procedure to detect and estimate change points of ES in time series. The strengthened Schwarz information criterion is also introduced to determine the number of change points. Monte Carlo simulation studies are conducted to assess the finite-sample performance of our variant WBS procedure about ES in time series. An empirical application is given to illustrate the usefulness of our procedure.

We consider together the retrospective and the sequential change-point detection in a general class of integer-valued time series. The conditional mean of the process depends on a parameter $$\theta ^*$$ which may change over time. We propose procedures which are based on the Poisson quasi-maximum likelihood estimator of the parameter, and where the updated estimator is computed without the historical observations in the sequential framework. For both the retrospective and the sequential detection, the test statistics converge to some distributions obtained from the standard Brownian motion under the null hypothesis of no change and diverge to infinity under the alternative; that is, these procedures are consistent. Some results of simulations as well as real data application are provided.

The analysis of topographic time series is often based on bitemporal change detection and quantification. For 3D point clouds, acquired using laser scanning or photogrammetry, random and systematic noise has to be separated from the signal of surface change by determining the minimum detectable change. To analyse geomorphic change in point cloud data, the multiscale model-to-model cloud comparison (M3C2) approach is commonly applied, which provides a statistical significance test. This test assumes planar surfaces and a uniform registration error. For natural surfaces, the planarity assumption does not necessarily apply, in which cases the value of minimal detectable change (Level of Detection) is overestimated. To overcome these limitations, we quantify an uncertainty information for each 3D point by propagating the uncertainty of the measurements themselves and of the alignment uncertainty to the 3D points. This allows the calculation of 3D covariance information for the point cloud, which we use in an extended statistical test for equality of multivariate means. Our method, called M3C2-EP, gives a less biased estimate of the Level of Detection, allowing a more appropriate significance threshold in typical cases. We verify our method in two simulated scenarios, and apply it to a time series of terrestrial laser scans of a rock glacier at two different timespans of three weeks and one year. Over the three-week period, we detect significant change at 12.5% fewer 3D locations, while quantifying additional 25.2% of change volume, when compared to the reference method of M3C2. Compared with manual assessment, M3C2-EP achieves a specificity of 0.97, where M3C2 reaches 0.86 for the one-year timespan, while sensitivity drops from 0.72 for M3C2 to 0.60 for M3C2-EP. Lower Levels of Detection enable the analysis of high-frequency monitoring data, where usually less change has occurred between successive scans, and where change is small compared to local roughness. Our method further allows the combination of data from multiple scan positions or data sources with different levels of uncertainty. The combination using error propagation ensures that every dataset is used to its full potential.

Successful geotechnical projects occur when the design is based on a thorough understanding of the geologic and environmental systems and the interaction of these systems over time. The ability to examine and track movement through space and time has been an essential part of the geoprofessional’s toolkit since the onset of the practice. Since the early 2000s, high-resolution three-dimensional (3D) topographic data have begun to transform how we map and understand movement through time across spatially extensive regions at unprecedented levels of accuracy and confidence. This paper examines how high-resolution 3D topographical data, four-dimensional (4D) analysis, and visualization of data in 3D environments can improve our ability to better understand changes in the morphology and material behaviour through time, leading to better decisions and better outcomes. Evolution of advancements made over the past 20 years is presented through case studies where positive impacts were realized through the adoption of 3D remote sensing and 4D analysis, and cases where data could be used in the future to improve outcomes. The paper presents current research being done to further improve processing techniques and exploit new data collection and computational processing capabilities, pushing the capability of time-dependant 4D geotechnical monitoring to new limits.

Automatic change detection from remotely sensed imagery is extremely important for many applications, including land use mapping. In recent years, a growing number of researchers have applied capable deep-learning methods to the research on change detection. The majority of deep learning-based change detection methods currently perform pixel-by-pixel classification at the original image scale, but they can hardly avoid the false changes caused by strong parallax effects and projected shadows, without considering the totality of changed objects/regions. In this study, we propose an object-level change detection framework to detect changed geographic entities (such as newly built buildings or changed artificial structures) by paying more attention to the overall characteristics and context association of changed object instances. The detected changed objects are represented as bounding boxes, which are simple, regular, and convenient to use in object feature extraction. In terms of data handling, a special data augmentation method for change detection called Alternative-Mosaic is proposed to effectively accelerate model training and improve model performance. For the model, we propose a one-stage change detection network called dual correlation attention-guided detector (DCA-Det) to detect the changed objects. In particular, we feed the dual-temporal images into a weight-shared backbone network to extract the change features of different scales. The change features on the same scale are further refined, and then the features between different scales are fused by the correlation attention-guided feature fusion neck. Finally, the change detection heads output the prediction results of the changed objects/regions of different scales. Experiments were conducted on public LEVIR building change detection and aerial imagery change detection (AICD) datasets. The quantitative evaluation and visualization results proved the superiority and robustness of our framework. Our DCA-Det can obtain state-of-the-art performance on object-level metrics (99.50% AP IoU = . 50 and 79.72% AP IoU = . 50 : . 05 : . 95 ) on the AICD-2012 dataset.

Change detection in remote sensing images aims to accurately determine any significant land surface changes based on acquired multi-temporal image data, being a pivotal task of remote sensing image processing. Over the past few years, owing to its powerful learning and expression ability, deep learning has been widely applied in the general field of image processing and has demonstrated remarkable potentials in performing change detection in images. However, a majority of the existing deep learning-based change detection mechanisms are modified from single-image semantic segmentation algorithms, without considering the temporal information contained within the images, thereby not always appropriate for real-world change detection. This paper proposes a High-Resolution Triplet Network (HRTNet) framework, including a dynamic inception module, to tackle such shortcomings in change detection. First, a novel triplet input network is introduced, which is capable of learning bi-temporal image features, extracting the temporal information reflecting the difference between images over time. Then, a network is employed to extract high-resolution image features, ensuring the learned features preserving high-resolution characteristics with minimal reduction of information. The paper also proposes a novel dynamic inception module, which helps improve the feature expression ability of HRTNet, enriching the multi-scale information of the features extracted. Finally, the distances between feature pairs are measured to generate a high-precision change map. The effectiveness and robustness of HRTNet are verified on three popular high-resolution remote sensing image datasets. Systematic experimental results show that the proposed approach outperforms state-of-the-art change detection methods.

In many countries digital maps are generally created and provided by Cadastre, Land Registry or National Mapping Agencies. These maps must be accurate and well maintained. However, in most cases, the update process of these maps is still done by hand, often using satellite or aerial imagery. Supporting this process via automatic change detection based on traditional classification algorithms is difficult due to the high level of noise in the data, such as introduced by temporary changes (e.g. cars being parked). This paper describes a method to detect changes between two time steps using 2.5D data and to transfer these insights to a digital map. For every polygon in the map, several attributes are collected from the input data, which are used to train a machine-learning model based on gradient boosting. A case study in Haarlem, in the Netherlands, was conducted to test the performance of this proposed approach. Results show that this methodology can recognize a substantial amount of changes and can support – and speed up – the manual updating process.

Motivated by the wind turbine anomaly detection, we propose a Bayesian hierarchical model (BHM) for the mean-change detection in multivariate sequences. By combining the exchange random order distr...

The use of remote sensing data, whether for change detection, spatial and temporal analysis, or numerical simulation of water bodies, requires a complete data set. Here, high temporal and spatial r...

A limited number of studies have focused on the hydroclimate dynamics of tropical Caribbean islands. The present study aims to analyze the rainfall regime in Barbados. CHIRPS gridded dataset, at a resolution of 0.05°×0.05°, providing daily rainfall data from January 1981 until 2018 was used. The variables analyzed were the annual and seasonal maximum rainfall, the total annual and seasonal rainfall, and the number of rainy days per year and per season. Potential change points in rainfall time-series were detected with a Bayesian multiple change point detection procedure. Time series were then analyzed for detection of trends using the modified Mann-Kendall test. The true temporal slopes of the rainfall time series were obtained with the Theil-Sen’s statistic. The links between rainfall and various global climate oscillation indices were also investigated. Results indicate that no change points or significant trends were observed in the annual rainfall time series. However, it was found that some climate indices have a strong correlation with precipitation on the island, especially for the total rainfall and the number of rainy days. A stationary and non-stationary frequency analysis is carried out on the rainfall annual variables using climate oscillation indices as covariates, and uncertainties on quantile estimates are identified. It is shown that non-stationary models lead to a better fit to rainfall data. Empirical mode decomposition (EMD) is used for the long-term prediction of hydro-climatic time series. Rainfall annual time series were extended with this method for a period of 20 years. Results indicate that, within that period, annual maximum rainfall will increase by about 12 mm (or 0.6 mm/year), total annual rainfall will increase by about 200 mm (or 10 mm/year) and the number of rainy days per year will see a slight decrease by about 3 days (or 0.15 day/year).

Change detection plays a crucial role in observing earth surface transition and has been widely investigated using deep learning methods. However, the current deep learning methods for pixel-wise change detection still suffer from limited accuracy, mainly due to their insufficient feature extraction and context aggregation. To address this limitation, we propose a novel Cross Layer convolutional neural Network (CLNet) in this paper, where the UNet structure is used as the backbone and newly designed Cross Layer Blocks (CLBs) are embedded to incorporate the multi-scale features and multi-level context information. The designed CLB starts with one input and then split into two parallel but asymmetric branches, which are leveraged to extract the multi-scale features by using different strides; and the feature maps, which come from the opposite branches but have the same size, are concatenated to incorporate multi-level context information. The designed CLBs aggregate the multi-scale features and multi-level context information so that the proposed CLNet can reuse extracted feature information and capture accurate pixel-wise change in complex scenes. Quantitative and qualitative experiments were conducted on a public very-high-resolution satellite image dataset (VHR-Dataset), a newly released building change detection dataset (LEVIR-CD Dataset) and an aerial building change detection dataset (WHU Building Dataset). The CLNet reached an F1-score of 0.921 and an overall accuracy of 98.1% with the VHR-Dataset, an F1-score of 0.900 and an overall accuracy of 98.9% with the LEVIR-CD Dataset, and an F1-score of 0.963 and an overall accuracy of 99.7% with the WHU Building Dataset. The experimental results with all the selected datasets showed that the proposed CLNet outperformed several state-of-the-art (SOTA) methods and achieved competitive accuracy and efficiency trade-offs. The code of CLNet will be released soon at: https://skyearth.org/publication/project/CLNet .

A novel and effective change detection method based on manifold regularized joint non-negative matrix factorization (MJNMF) framework is proposed in this paper, which detects the changes that occurred in multi-temporal remote sensing images. Most change detection methods, including dictionary learning, principal component analysis (PCA), etc., do not consider the non-negativity among image pixels. However, image itself is a non-negative signal, and the non-negative constraint has better interpretability in practical applications. Nonnegative Matrix Factorization, which incorporates the non-negativity constraint and thus learns object parts, obtains the parts-based representation as well as enhancing the interpretability of the issue correspondingly. In this paper, our proposed approach based on MJNMF framework aims to establish a pair of joint basis matrices by unchanged training samples from unchanged area. Then, unchanged pixels can be well reconstructed by the corresponding basis matrix, while changed pixels cannot be reconstructed from the basis matrix corresponding to the knowledge of unchanged samples, or a larger reconstruction error can be generated even if changed pixels are reconfigurable. In order to suppress similar information and highlight different information, the cross-reconstruction error is used to generate the difference image. Finally, the binary image is obtained by the robust fuzzy local information c-means (FLICM) clustering algorithm. In addition, inspired by manifold learning, we incorporate manifold regularization into the proposed method to keep the geometric structure of data and improve the accuracy of change detection. Experimental results obtained on simulated and real remote sensing images confirm the effectiveness of the proposed method.

The Multi-Kink Quantile Regression (MKQR) model is an important tool for analyzing data with heterogeneous conditional distributions, especially when quantiles of response variable are of interest, due to its robustness to outliers and heavy-tailed errors in the response. It assumes different linear quantile regression forms in different regions of the domain of the threshold covariate but are still continuous at kink points. In this paper, we investigate parameter estimation, kink point detection and statistical inference in MKQR models. We propose an iterative segmented quantile regression algorithm for estimating both the regression coefficients and the locations of kink points. The proposed algorithm is much more computationally efficient than the grid search algorithm and not sensitive to the selection of initial values. Asymptotic properties, such as selection consistency of the number of kink points, asymptotic normality of the estimators of both regression coefficients and kink effects, are established to justify the proposed method theoretically. A score test, based on partial subgradients, is developed to verify whether the kink effects exist or not. Test-inversion confidence intervals for kink location parameters are also constructed. Intensive simulation studies conducted show the proposed methods work very well when sample size is finite. Finally, we apply the MKQR models together with the proposed methods to the dataset about secondary industrial structure of China and the dataset about triceps skinfold thickness of Gambian females, which leads to some very interesting findings. A new R package MultiKink is developed to implement the proposed methods., 39pages, 4 figures

Understanding urban land-use changes and accurately quantifying urban land transitions is essential to global land-change research. The present study aimed to capture non-linear land transitions within urban areas using an automated change detection technique in a satellite image time series. Traditional land-use and cover maps used to map and monitor urban areas assume land change is a linear process and that urbanization is the last stage of land transition. In reality, however, most land transitions are non-linear. The present study focused on Delhi National Capital Territory, in India, and its adjacent major cities. A popular time-series analysis method was applied on MODIS NDVI time-series (2000–2017) data to detect change within the impervious surface area of the region. Overall validation and analysis of the results showed that the method was able to capture the direction and timing of the changes very well within all levels of urban density (except very high-density areas with more than 98% built-up density). The majority of urban areas in the region experienced interrupted, abrupt, and gradual greening. The results show different examples of non-linear land transitions detected from satellite images. Until recently, these land transitions could only be observed via long-term field surveys and/or local knowledge. The results reveal that the land-change trajectories can be different based on the level of built-up density, size of the urban area, physical proximity, and accessibility to relatively bigger urban areas. Knowledge gained from this study can be useful in better understanding the micro-climatic patterns and environmental quality within a city.

Sequentially detecting multiple changepoints in a data stream is a challenging task. Difficulties relate to both computational and statistical aspects, and in the latter, specifying control parameters is a particular problem. Choosing control parameters typically relies on unrealistic assumptions, such as the distributions generating the data, and their parameters, being known. This is implausible in the streaming paradigm, where several changepoints will exist. Further, current literature is mostly concerned with streams of continuous-valued observations, and focuses on detecting a single changepoint. There is a dearth of literature dedicated to detecting multiple changepoints in transition matrices, which arise from a sequence of discrete states. This paper makes the following contributions: a complete framework is developed for adaptively and sequentially estimating a Markov transition matrix in the streaming data setting. A change detection method is then developed, using a novel moment matching technique, which can effectively monitor for multiple changepoints in a transition matrix. This adaptive detection and estimation procedure for transition matrices, referred to as ADEPT-M, is compared to several change detectors on synthetic data streams, and is implemented on two real-world data streams – one consisting of over nine million HTTP web requests, and the other being a well-studied electricity market data set.

With the rapid development of remote sensing technologies, the frequency of observations of the same location is increasing, and many satellites and sensors produced a large amount of time series images. These images make long-term change detection and dynamic characteristic estimation of ground features possible. However, conventional remote sensing image change detection methods mostly rely on manual visual interpretation and supervised or unsupervised computer-aided classification. Traditional methods always face many bottlenecks when processing big and fast-growing datasets, such as low computational efficiency, low level of automation, and different identification standards and accuracies caused by different operators. With the rapid accumulation of remote sensing data, it has become an important but more challenging task to conduct change detection in a more precise, automated and standardized way. The development of geointelligent computing technologies provides a means of solving these problems and improve the accuracy and efficiency of remote sensing image change detection. In this paper, we presented a novel deep learning model called nest network(NestNet) based on a convolutional neural network to improve the accuracy of the automatic change detection task by using remotely sensed time series images. NestNet extracts the respective features of bi-temporal images using an encoding parallel module and subsequently employs absolute different operations to process the features of two images. Compared with change detection method based on U-Shaped network plus plus (UNet++), the parallel module improves the efficiency of NestNet. Finally, a decoding module is used to generate a predicted change image. This paper compares NestNet to traditional methods and state-of-the-art deep learning models on two datasets. The experimental results demonstrate that the accuracy of NestNet is better than that of state-of-the-art methods. It can be concluded that the NestNet model is a potential approach for change detection using high resolution remote sensing images.

Synthetic aperture radar (SAR) polarimetry has demonstrated high efficiency in the detection of landslides in vegetated mountainous areas. In such places, post-landslide soil layers appear to correspond to the typical surface scattering mechanism, which is significantly different from the volume scattering behaviour of the surrounding vegetation. However, a landslide in the complex surroundings of various landforms, involving naked hillslopes, construction fields, bare farmlands, and other such aspects, may not be accurately identified owing to the occurrence of surface scattering behaviours. In order to detect landslides using SAR polarimetry without the limitation of vegetated mountainous areas, we propose a novel method of combining change detection (CD) and an analytic hierarchy process (AHP) based on the Yamaguchi decomposition (YD) to identify landslides while ensuring fewer false alarms. In particular, CD is applied to a pair of pre- and post-event datasets to determine the regions modified by landslides or human activities, and the AHP is performed over the post-event dataset to identify the suspect landslide region characterised by the surface scattering mechanism. Finally, the two results are fused by a logical operation to identify the actual landslide by removing the non-modified surface scattering regions. A case study of the Shenzhen landslide in complex surroundings was considered to verify the performance of the proposed method (CD-AHP). The results indicate that the method could clearly define the main body of the Shenzhen landslide from the city suburbs with a small number of false alarms. Therefore, this method provides a considerable perspective for landslide detection in complex surroundings using SAR polarimetry.

We study a monitoring system in which the distributions of sensors' observations change from a nominal distribution to an abnormal distribution in response to an adversary's presence. The system uses the quickest change detection procedure, the Shewhart rule, to detect the adversary that uses its resources to affect the abnormal distribution, so as to hide its presence. The metric of interest is the probability of missed detection within a predefined number of time-slots after the changepoint. Assuming that the adversary's resource constraints are known to the detector, we find the number of required sensors to make the worst-case probability of missed detection less than an acceptable level. The distributions of observations are assumed to be Gaussian, and the presence of the adversary affects their mean. We also provide simulation results to support our analysis.

Existing deep learning-based change detection methods in the field of polarimetric synthetic aperture radar (POLSAR) usually directly deal with intensity images. Methods can be easily transferred f...

Made available in DSpace on 2021-06-25T10:25:36Z (GMT). No. of bitstreams: 0 Previous issue date: 2021-01-01 Over the past decades, the Southeast Atlantic Forest in Paraíba do Sul River Valley has suffered intense deforestation and human disturbances. Due to the Atlantic Forest biodiversity and the economic relevance of such a region in Brazil, spatial-temporal analyses are of crucial importance to protect the forest, as well as to support economic decision-making of public and private agents. In this context, the use of change detection techniques applied to remote sensing imagery arises as a powerful tool to track and map the Earth’s surface transformations. Therefore, this work investigates the effectiveness and practical feasibility of distinct unsupervised change detection approaches when they are applied to reveal the spatial-temporal dynamics in Paraíba do Sul River Valley across the last four decades. Different change detection approaches such as Change Vector Analysis (CVA), a K-Means and Principal Component Analysis (PCA-KM) framework, and a Alternating Sequential Filtering (ASF) based process were taken and properly tuned to cope with Landsat image series. The analysis of the results revealed a permanent land cover change rate over the last decades. Moreover, these changes do not necessary occur in the same locations, as it was confirmed the existence of successive modifications in original coverage of the study area. Another observed aspect is that the simplest technique for detecting changes, CVA, turned out to be the best approach to map the changes in the examined region. Institute of Science and Technology São Paulo State University (Unesp) Department of Energy Engineering São Paulo State University (Unesp) Institute of Science and Technology São Paulo State University (Unesp) Department of Energy Engineering São Paulo State University (Unesp)

Automatic change detection is an important and difficult task in the field of remote sensing. In this study, a deep Siamese convolutional network based on the fusion of high- and low-level features...

An improved graph-cut-based change detection method is proposed in this paper to make full use of the spectral and spatial information from multispectral remote-sensing images. The proposed method ...

Small unmanned aerial systems, or sUAS, remote sensing has much potential for monitoring vegetation cover and other phenomena due to its innate ability to capture very high spatial resolution image...

Geographic observation benefits from the increasing availability of time series of 3D geospatial data, which allow analysis of change processes at high temporal detail and over extensive periods. In this context, the demand for advanced methods to detect and extract topographic surface changes from these 4D geospatial data emerges. Changes in natural scenes occur with varying magnitude, duration, spatial extent, and change rate, and the timing of their occurrence is not known. Standard pairwise change detection requires the selection of fixed analysis periods and the specification of magnitude thresholds to determine accumulation or erosion forms. In settings with continuous surface morphology and dynamic changes to the surface due to material transport, such change forms are typically temporary and may be missed or aggregated if they occur with spatial and/or temporal overlap. This is overcome with the extraction of 4D objects-by-change (4D-OBCs). These objects are obtained by firstly detecting surface changes in the temporal domain at locations in the scene. Subsequently, they are spatially delineated by considering the full history of surface change during region growing from the seed location of a detected change. To perform this spatiotemporal segmentation systematically for entire 3D time series, we develop a fully automatic approach of seed detection and selection, combined with locally adaptive thresholding for region growing of individual objects with varying change properties. We apply our workflow to a five-months hourly time series of around 3,000 terrestrial laser scanning point clouds acquired for coastal monitoring at a sandy beach in The Netherlands. This provides 2,021 4D-OBCs as extracted accumulation or erosion forms. Results are validated through majority agreement of six expert analysts, who evaluate the segmentation performance at sample locations throughout the scene. Accordingly, our method extracts surface changes with an error of omission of 4.7% and an error of commission of 16.6%. We examine the results and provide considerations how postprocessing of segments can further improve the change analysis workflow. The developed approach thereby provides a powerful tool for automatic change analysis in 4D geospatial data, namely to detect and delineate natural surface changes across space and time.

Nalsarovar Bird Sanctuary, a natural freshwater lake (a relict sea) that is the largest natural wetland in the Thar Desert Bio-geographic Province and represents a dynamic environment with salinity and depth varying depending on rainfall. For maintaining ecological balance in coastal and inland environments, wetlands play an important role and the changes in wetland environment can be monitored using satellite remote sensing technique. The present study was carried out using Landsat-7 TM (Feb-2002), Landsat-5 TM (Feb- 2009) and Sentinel-2 multi-spectral data (Feb-2018) covering Nalsarovar area in Ahmedabad district. The study area of Nalsarovar with 10 km buffer was extracted from the satellite digital data. Various spectral indices like Normalized difference Vegetation Index (NDVI), Normalized difference Water Index (NDWI) and Normalized difference Turbidity Index (NDTI) were generated for better identification and delineation of water body and aquatic vegetation in the Nalsarovar. The composite images of these indices were also generated to map and monitor changes in water spread and aquatic vegetation in the Nalsarovar. The water spread and aquatic vegetation in the Nalsarovar along with the land use classes were mapped using False Colour Composite (FCC) images of differed years. The result indicates that the water spread in Nalsarovar has changed from 2002, 2009 and 2018 depending on the monsoon pattern during these years. During drought year of 2002 total precipitation was very less resulting drastic reduction in the water spread in Nalsarovar. The aquatic vegetation has changed from 146.81 ha during 2002 to 510.93 ha during 2018. The land use change indicates that agriculture land, built-up, water body & wetland has increased and barren land, salt affected area has decreased. The aquatic vegetation in Nalsarovar was clearly visible on composite images generated using NDVI, NDWI and NDTI of different years. This study gives clear idea for land use change detection and water spread monitoring using two different techniques using Composite image of NDVI, NDWI and NDTI.

Photovoltaic (PV) soiling profiles exhibit a sawtooth shape, where cleaning events and soiling deposition periods alternate. Generally, the rate at which soiling accumulates is assumed to be constant within each deposition period. In reality, changes in rates can occur because of sudden variations in climatic conditions, e.g., dust storms or prolonged periods of rain. The existing models used to extract the soiling profile from the PV performance data might fail to capture the change points and occasionally estimate incorrect soiling profiles. This work analyzes how the introduction of change points can be beneficial for soiling extraction. Data from nine soiling stations and a 1-MW site were analyzed by using piecewise regression and three change point detection algorithms. The results showed that accounting for change points can provide significant benefits to the modeling of soiling even if not all the change point algorithms return the same improvements. Considering change points in historical trends is found to be particularly important for studies aiming to optimize cleaning schedules.

Constructing a change magnitude map (CMM) is a key component of binary change detection. Recently, integrating multiple features to obtain a comprehensive CMM has become a popular research topic. H...

Forest cover change analyses have an essential role in forest management. Thus, this study adopted Landsat satellite imagery to assess the decadal spatiotemporal forest cover changes that occurred ...

Dense time series of stripmap RADARSAT-2 data acquired in the Multilook Fine mode were used for detecting and mapping the extent of selective logging operations in the tropical forest area in the northern part of the Republic of the Congo. Due to limited radiometric sensitivity to forest biomass variation at C-band, basic multitemporal change detection approach was supplemented by spatial texture analysis to separate disturbed forest from intact. The developed technique primarily uses multi-temporal aggregation of orthorectified synthetic aperture radar (SAR) imagery that are acquired before and after the logging operations. The actual change analysis is based on textural features of the log-ratio image calculated using two SAR temporal composites compiled of SAR scenes acquired before and after the logging operations. Multitemporal aggregation and filtering of SAR scenes decreased speckle and made the extracted textural features more prominent. The overall detection accuracy was around 80%, with some underestimation of the area of forest disturbance compared to reference based on optical data. The user’s accuracy for disturbed forest varied from 76.7% to 94.9% depending on the accuracy assessment approach. We conclude that change detection utilizing RADARSAT-2 time series represents a useful instrument to locate areas of selective logging in tropical forests.

Landslide poses severe threats to the natural landscape of the Lesser Himalayas and the lives and economy of the communities residing in that mountainous topography. This study aims to investigate whether the landscape change has any impact on landslide occurrences in the Kalsi-Chakrata road corridor by detailed investigation through correlation of the landslide susceptibility zones and the landscape change, and finally to demarcate the hotspot villages where influence of landscape on landslide occurrence may be more in future. The rational of this work is to delineate the areas with higher landslide susceptibility using the ensemble model of GIS-based multi-criteria decision making through fuzzy landslide numerical risk factor model along the Kalsi-Chakrata road corridor of Uttarakhand where no previous detailed investigation was carried out applying any contemporary statistical techniques. The approach includes the correlation of the landslide conditioning factors in the study area with the changes in land use and land cover (LULC) over the past decade to understand whether frequent landslides have any link with the physical and hydro-meteorological or, infrastructure, and socioeconomic activities. It was performed through LULC change detection and landslide susceptibility mapping (LSM), and spatial overlay analysis to establish statistical correlation between the said parameters. The LULC change detection was performed using the object-oriented classification of satellite images acquired in 2010 and 2019. The inventory of the past landslides was formed by visual interpretation of high-resolution satellite images supported by an intensive field survey of each landslide area. To assess the landslide susceptibility zones for 2010 and 2019 scenarios, the geo-environmental or conditioning factors such as slope, rainfall, lithology, normalized differential vegetation index (NDVI), proximity to road and land use and land cover (LULC) were considered, and the fuzzy LNRF technique was applied. The results indicated that the LULC in the study area was primarily transformed from forest cover and sparse vegetation to open areas and arable land, which is increased by 6.7% in a decade. The increase in built-up areas and agricultural land by 2.3% indicates increasing human interference that is continuously transforming the natural landscape. The landslide susceptibility map of 2019 shows that about 25% of the total area falls under high and very high susceptibility classes. The result shows that 80% of the high landslide susceptible class is contained by LULC classes of open areas, scrubland, and sparse vegetation, which point out the profound impact of landscape change that aggravate landslide occurrence in that area. The result acclaims that specific LULC classes, such as open areas, barren-rocky lands, are more prone to landslides in this Lesser Himalayan road corridor, and the LULC-LSM correlation can be instrumental for landslide probability assessment concerning the changing landscape. The fuzzy LNRF model applied has 89.6% prediction accuracy at 95% confidence level which is highly satisfactory. The present study of the connection of LULC change with the landslide probability and identification of the most fragile landscape at the village level has been instrumental in delineation of landslide susceptible areas, and such studies may help the decision-makers adopt appropriate mitigation measures in those villages where the landscape changes have mainly resulted in increased landslide occurrences and formulate strategic plans to promote ecologically sustainable development of the mountainous communities in India's Lesser Himalayas.

The methods for detecting environmental changes using two multispectral multispectral space images of the Earth, which can be used to assess changes in the ecological and geological environment to control the dynamics of processes in real time, in order to prevent environmental emergencies. The creation and operation of a system of continuous geoecological monitoring based on space information involves the detection of relative changes in the environment on two multispectral space images of the Earth, obtained after a certain period of time. To do this, it is necessary to develop and apply adaptive methods (indices) for detecting relative changes. Three methods are proposed that are adapted to specific images to find the optimal solution that maximizes the relative changes in two different time multispectral space images of the Earth. The first method selects one optimal channel from all channels of the space image, the second method - two optimal channels from all channels and the third - four optimal channels from all channels. There are known methods that assess the presence or absence of changes in two space images at different times, but they do not provide information about the direction of changes. The proposed indices can take positive and negative values, reflecting the trend of changes on the ground. The negative values of the indices obtained in the area near the village of Solotvyno, Tyachiv district, Zakarpattia region, correspond to the areas with the most dynamic changes in the environment of such exogenous processes as karst funnels and lakes, and positive values correspond to increasing vegetation areas. The results of comparing the application of the change detection index on two different multispectral space images of the Earth on four, two channels and one channel showed that increasing the number of channels can give a more reasonable picture of changes, but to concretize these changes requires ground-based observations.

The Middle East (ME), as an arid and semi-arid region, is prone to environmental risks and stresses, such as drought are inseparable phenomena of the region. In this study, an approach for identifying sustained vegetation cover (SVC) is suggested to identify the connection between SVC and drought. Normalized difference vegetation index (NDVI) and land surface temperature (LST) were used to filter zones of rich vegetation cover from poorly vegetated or non-vegetated regions of the ME. The change detection of vegetation cover was computed by the NDVI differencing technique, and the vegetation condition index (VCI) and normalized vegetation supply water index (NVSWI) were used to derive drought indices. The standardized precipitation index (SPI) and rainfall anomaly index (RAI) were used to monitor the intensity of meteorological drought events. A comparison of the estimates of vegetation change, remote sensing-based VCI, and meteorological drought indices revealed that the highest SVC is concurrent with the occurrence of drought. Moreover, it was found that the most severe meteorological drought and VCL-based drought condition occurred in 2008 and that the highest percentage of SVC was also obtained for this year. The results suggest the possibility of using the SVC instead of other spectral indices, such as the NDVI, VCI, NVSWI, and NVSWI, for the superior assessment and detection of environmental stresses such as drought.

Mapping and monitoring of the glacier changes over different regions of Earth surface is a challenging task due to regional rugged topography and climate conditions. This study focused on the monitoring of snow or ice cover changes over Chhota-Shigri glacier, Western Himalaya, India. A subpixel-based change detection (SCD) approach is proposed, aiming to identify the transition zones (mixed pixels) between the two class categories. The SCD approach involves the integration of subpixel classification and change vector analysis (CVA) to define the changes in the form of magnitude and direction between two multitemporal dates at the subpixel level. To check the efficacy of proposed SCD, experimental outcomes have also been compared with existing neural-network (NN) based SCD (NN‒SCD). The result analysis has shown that proposed SCD achieved better accuracy (84.80%) as compared to NN‒SCD (78.80%). In addition, a time series data was acquired using the Landsat series (Landsat 5, 7 and 8 as per availability) to perform the trend analysis over Chhota-Shigri glacier, during the period 2001–2019. This study offers the effective way of estimating the bi-temporal snow/ice changes especially over rugged terrains around the globe.

The present study illustrates the Spatial-temporal dynamics of Land use/Land cover (LULC), and locate land suitability for agricultural use. Landsat satellite images of three different years 1990, 2000 and 2018 over 28 years were acquired from Global Land Cover Facility Site (GLCF) and earth explorer. Land suitability for agriculture use was assessed on five criteria; rainfall, temperature, slope percentage, soil types and water Wells distribution. The different geospatial layers were transferred using suitability coding system to produce the suitability maps for rainfed and irrigated areas using weighted overlay method. Ma’an Governorate covers approximately 37% of the total area of Jordan, and consists mostly of uncultivated land 33304.66 km2 (99.49%). Three main LULC classes were identified of the three years; 1990, 2000 and 2018; forest and irrigated areas have been fluctuated between 86.00 km2 (0.26%), 108.06 km2 (0.32) and 102.68 km2 (0.31%), built-up area increased by 24.00 km2, (0.07%), 41.88 km2 (0.13%) and 68.66 km2 (0.21%), while the bare land has been decreased from 33366 km2 (99.67%),33476 km2 (99.55%) and 33304.66 km2 (99.49%) during 1990, 2000 and 2018 respectively. land suitability for the agricultural use (rainfed areas and irrigated crops); Data from the five parameters (mentioned above) are used for spatial analysis applying weighted overlay method. The results showed that only about (0.2%) from the total area of Ma’an is highly suitable for agriculture dependent on rainfall. While about (1.4%) is high suitable for the irrigation crops. The main reason of the low levels of land suitability for agriculture is very low soil fertility, and the water scarcity.

The change detection via remote sensing offers a cost-effective solution to monitor the earth surface variations and manage natural resources. Change vector analysis (CVA) is one of the most appropriate suitable amongst various change detection techniques that attract the interest of researchers due to its potential and overall applicability. However, the effectiveness of recently developed CVA methods is yet to be explored over the mountainous region like Himalayas with most commonly used satellite sensors such as MODIS and Landsat-8. In the present analysis, we have performed the qualitative and quantitative analysis of advanced CVA algorithms such as improved CVA (ICVA), posterior probability-based CVA (CVAPS), median CVA (MCVA) and fuzzy-based CVA (FCVA). Two experiments were conducted on different study sites of western Himalayas (Himachal Pradesh, India) using topographically corrected MODIS and Landsat-8 datasets. The experimental outcomes of change maps confirm the effectiveness of FCVA (86.80–87.6%) as compared to MCVA (78.4–83.6%), CVAPS (82.8–84%) and ICVA (73.6–80.4%). This study provides a comprehensive framework to explore the potential of different CVA algorithms to detect the land use and land cover changes especially over rugged terrain region.

Horizontal visibility is of utmost importance in climate and air quality studies as it can provide key information related to changes in meteorological conditions, air quality, and their impact on human health. In this study, multiple trend analysis methods were applied to investigate the annual and seasonal horizontal visibility trends based on 1985 to 2018 at 23 locations in Saudi Arabia. Different forms of the Mann-Kendall (MK) test were conducted for the trend analysis, which includes the MK test with (without) autocorrelation corrections. In addition to that, Sen’s slope estimator and Kendall’s Tau were used to examine horizontal visibility trends and trend magnitudes. The sequential Mann-Kendall test was used to locate trend fluctuations over time and to detect abrupt changes in the horizontal visibility. It was found that 64.4% of the time series have significant decreasing trends (visibility decreasing with time). The average trend magnitude for Saudi Arabia was − 0.024 km/year over the evaluated period. Stations in the North-East quadrant (NE-Region) had a higher visibility degradation in spring and lower visibility degradation in summer. Stations in the Western area (W-Region) have higher visibility degradation in winter and lower visibility degradation in autumn. Northeastern part of the NE-Region showed the highest visibility deterioration. The sequential MK test detected increasing visibility trends in the early 1990s to the early 2000s, while during the mid-2000s to 2018, most of the data showed decreasing trends. The time series of annual horizontal variability in most of the stations located in the NE-Region showed more significant decreasing abrupt changes; however, few stations located in these two regions revealed insignificant increasing abrupt changes.

A significant limitation in biodiversity conservation has been the effective implementation of laws and regulations that protect species' habitats from degradation. Flexible, efficient, and effective monitoring and enforcement methods are needed to help conservation policies realize their full benefit. As remote sensing data become more numerous and accessible, they can be used to identify and quantify land-cover changes and habitat loss. However, these data remain underused for systematic conservation monitoring in part because of a lack of simple tools. We adapted 2 algorithms that automatically identify differences between pairs of images. We used free, publicly available satellite data to evaluate their ability to rapidly detect land-cover changes in a variety of land-cover types. We compared algorithm predictions with ground-truthed results at 100 sites of known change in the United States. We also compared algorithm predictions to manually created polygons delineating anthropogenic change in 4 case studies involving imperiled species' habitat: oil and gas development in the range of the Greater Sage Grouse (Centrocercus urophasianus); sand mining operations in the range of the dunes sagebrush lizard (Sceloporus arenicolus); loss of Piping Plover (Charadrius melodus) coastal habitat after Hurricane Michael (2018); and residential development in St. Andrew beach mouse (Peromyscus polionotus peninsularis) habitat. Both algorithms effectively discriminated between pixels corresponding to land-cover change and unchanged pixels as indicated by area under a receiver operating characteristic curve0.90. The algorithm that was most effective differed among the case-study habitat types, and both effectively delineated habitat loss as indicated by low omission (min. = 0.0) and commission (min. = 0.0) rates, and moderate polygon overlap (max. = 47%). Our results showed how these algorithms can be used to help close the implementation gap of monitoring and enforcement in biodiversity conservation. We provide a free online tool that can be used to run these analyses (https://conservationist.io/habitatpatrol).Respaldo a la Conservación de Hábitat con la Detección Automatizada de Cambio en Google Earth Resumen Una limitación significativa en la conservación de la biodiversidad ha sido la implementación efectiva de las leyes y regulaciones que protegen los hábitats de las especies de la degradación. El monitoreo flexible, eficiente y efectivo y los métodos de aplicación son necesarios para que las normas de conservación puedan llevar a cabo su potencial completo. Conforme los datos de telemetría se vuelven cada vez más numerosos y accesibles, su uso puede extenderse a la identificación y cuantificación de los cambios en la cobertura del suelo y la pérdida del hábitat. Sin embargo, estos datos todavía están subutilizados en cuanto al monitoreo sistemático de la conservación en parte debido a la falta de herramientas simples y sencillas. Adaptamos dos algoritmos que identifican automáticamente las diferencias entre pares de imágenes. Utilizamos datos satelitales gratuitos y disponibles para el público para con ellos evaluar la habilidad que tienen los algoritmos para detectar rápidamente los cambios en la cobertura del suelo dentro de una variedad de tipos de cobertura de suelo. Comparamos las predicciones algorítmicas con los resultados de algunas investigaciones en 100 sitios con cambios conocidos en los Estados Unidos. También comparamos las predicciones algorítmicas con polígonos creados manualmente que delinean el cambio antropogénico en cuatro estudios de caso que involucran al hábitat de una especie en peligro: desarrollos de petróleo y gas en la distribución de Centrocercus urophasianus; minas de arena en la distribución de Sceloporus arenicolus; la pérdida del hábitat costero de Charadrius melodus después del huracán Michael (2018); y los desarrollos residenciales en el hábitat de Peromyscus polionotus peninsularis. Ambos algoritmos discriminaron efectivamente entre los píxeles que correspondían al cambio en la cobertura del suelo y los píxeles sin cambio así indicados por el área bajo la curva de característica de receptor operante0.90. El algoritmo más efectivo difirió entre los tipos de hábitat para los estudios de caso, mientras que ambos algoritmos delinearon efectivamente la pérdida de hábitat así indicada por la baja tasa de omisión (min. = 0.0) y comisión (min. = 0.0) y el traslape moderado de polígonos (max. = 47%). Nuestros resultados mostraron cómo pueden usarse estos algoritmos para ayudar a cerrar la brecha en la implementación del monitoreo y aplicación en la conservación de la biodiversidad. Proporcionamos una herramienta gratuita en línea que puede usarse para realizar estos análisis: https://conservationist.io/habitatpatrol.

Using remote sensing and GIS technique, we analyse the change detection of different land use/land cover (LULC) types that has taken place in Puthimari river basin during a two-decade period from 1999 to 2019. Supervised classification method with maximum likelihood algorithm have been applied to prepare the LULC maps. The LULC change detection has been performed employing a post-classification detection method. Puthimari is a north bank sub-catchment of River Brahmaputra, the northern part of which falls in Bhutan and the rest falls in the Assam state of India. The primary LULC types of the basin are, dense vegetation which is predominant in the upper catchment, crop land and rural settlement. Thus, five different classes have been considered for the analysis, viz., dense vegetation, water bodies, silted water, cropland and rural settlement. The results showed that the rural settlement and water bodies in the basin increased by 42.70% and 30.31% from 1999 to 2019. However, dense vegetation, silted water and cropland decreased by 9.24%, 27.47% and 28.10% during these two decades.

When using very high-resolution (VHR) remote sensing images acquired at different times to detect building changes, the building positional inconsistencies caused by different satellite imaging angles are an outstanding issue. To tackle this problem, a novel building change detection method based on pseudo-orthorectification (PO) is proposed. First, to determine the building displacement value, a fast line detection method is used to accurately extract the building vertical facade contour lines under the constraint of the Object Space Positioning Consistency (OSPC). Second, the building roof sample selection is automatically conducted under the constraint of building facade contour lines, and the Grab-Cut algorithm is used to extract the roofs combining with corresponding geometric rules. Then, the roof of each building is shifted along the elevation line to its real location. Finally, subtraction is applied to generate the difference image, and reliable change information is obtained by integrating NDVI and shadow information of the building. Three sets of WorldView and QuickBird satellite images are used to compare the proposed method with three state-of-the-art methods. The experimental results show that the average accuracy of the proposed method can reach 92.80%, which is 12.66% higher than that of compared methods.

The logging is the leading cause for the reduction in the forest area in the world. At the same time, the number of forest clearcuts continues to grow. However, despite the massive scale, such incidents are difficult to track in time. As a result, huge areas of forests are gradually being cut down. Therefore, there is a need for regular and effective monitoring of changes in forest cover. The multitemporal data sources like Copernicus Sentinel-2 allow enhancing the potential of monitoring the Earth's surface and environmental dynamics including forest plantations. In this article, we present a baseline U-Net model for deforestation detection in the forest-steppe zone. Training and evaluation are conducted on our own dataset created on Sentinel-2 imagery for the Kharkiv region of Ukraine (31 400 km2). As a part of the research, we present several models with the ability to work with time-dependent imagery. The main contribution of this article is to provide a baseline model for the forest change detection inside Ukraine and improve it adding the ability to use several sequential images as an input of the segmentation model.

As the manual detection of building footprint is inefficient and labor-intensive, this study proposed a method of building footprint extraction and change detection based on deep convolutional neural networks. The study modified the existing U-Net model to develop the “PRU-Net” model. PRU-Net incorporates pyramid scene parsing (PSP) to allow multiscale scene parsing, a residual block (RB) in ResNet for feature extraction, and focal loss to address sample imbalance. Within the proposed method, building footprint extraction is conducted as follows: 1) unmanned aerial vehicle images are cropped, denoised, and semantically marked, and datasets are created (including training/validation and prediction datasets); 2) the training/validation and prediction datasets are input into the full convolutional neural network PRU-Net for model training/validation and prediction. Compared with the U-Net, PSP+U-Net (PU-Net), and U-Net++ models, PRU-Net offers improved footprint extraction of buildings with a range of sizes and shapes. The large-scale experimental results demonstrated the effectiveness of the PSP module for multiscale scene analysis and the RB module for feature extraction. After demonstrating the improvements in building extraction offered by PRU-Net, the building footprint results were further processed to generate a building change map.

Using high-resolution satellite image to detect change has been a hotspot in the field of remote sensing for a long time series. The change detection method combining feature extraction and machine learning could extract the change information effectively, but the manual sample selection is a huge workload for a wide range remote sensing images, and it is also difficult to ensure the accuracy of the pre-detection sample using a single difference image. Therefore, in this paper, a new method for change detection has been put forward based on multi-feature fusion of D-S evidence theory. In this approach, the texture difference image has calculated by structural similarity, because the difference image based on structural similarity plays a great role in change detection, which was verified in experiments. The difference images based on texture features and traditional spectral features are fused by D-S evidence theory, and texture features and spectral features have been fully utilized. Setting rules to select samples with high confidence based on pixels, and SLIC super-pixel segmentation has applied in order to improve further the credibility of the sample. Finally, the samples selected by SLIC segmentation optimization are sent to the classifier training to obtain the final result. The experimental results show that texture features play a very important role in the change detection of high-resolution remote sensing images, and D-S evidence theory could effectively fuse spectral texture features to improve the accuracy of change detection. The proposed method has high accuracy and good performance in change detection.

Urban change detection (CD) using remote sensing images is of great significance for monitoring and analyzing the spatial and temporal distribution of changes within cities, which can be used to guide urban management. In order to reduce false detections and improve the CD automation, a novel CD framework for high resolution images is proposed in this article. First, a novel multilevel matching feature is presented, combining structural invariant features with multiscale dense matching features to comprehensively describe the invariant properties of ground objects at different levels. Second, a newly automatic training sample extraction strategy is proposed, in which sufficient and accurate no-change samples can be obtained by Gaussian-weighted Dempster–Shafer evidence theory and L1-norm, meanwhile, typical change samples can be extracted by sequential spectral change vector analysis. Utilizing the automatic extracted samples, the final CD results are obtained using four supervised classifiers, respectively (k-nearest neighbor, support vector machine, rotation forest, and extra-trees). To validate the proposed CD framework, experiments are conducted in four datasets with spectral variability, spectral confusion between the changed objects and unchanged backgrounds, and misregistration. The results demonstrate that the proposed multilevel matching feature and automatic sample extraction strategy can obtain better results with different types of supervised classifiers, and can effectively improve automation of CD, which is applicable to the large spatial extent scene.