Change Detection Method Research Articles

ENTROPY-BASED INDOOR CHANGE DETECTION USING LIDAR DATA AND A 3D MODEL

Abstract. Indoor change detection is important for building monitoring, building management and model-based localization and navigation systems because the real building environment may not always be the same as the design model. This paper presents a novel indoor building change detection method based on entropy. A sequence of real LiDAR scans is acquired with a static LiDAR scanner and the pose of the LiDAR scanner for each scan is then estimated. Synthetic LiDAR scans are generated with the pose of the LiDAR scanner using the 3D model. The real LiDAR scans and synthetic LiDAR scans are sliced horizontally with a certain angular interval and the entropy of all slices of LiDAR scans is then calculated. Differenced entropy between two corresponding slices of real LiDAR scans and synthetic LiDAR scans is calculated for the classification of the changes. Each slice of real LiDAR scans will be classified into one of the four categories of changes: unchanged, moving objects, structural change and non-structural change. Experimental results show that unchanged slices and slices containing moving objects can be accurately detected, achieving 100% accuracy while non-structural and structural changes are detected with an accuracy of 98.5% and 86.3% respectively.

Transformer-based network with difference information aware attention module

Existing great progress has been made through remote sensing image change detection (CD) methods, which use convolutions and transformations appropriately. However, due to the complexity of the objects photographed on satellites, the out-of-phase of the same object may exhibit a fine feature diversity and a wide range of variations. Meanwhile, in the previous work, pure convolutional networks and Transformer networks that focus on local information perform better on non-local information. Therefore, current methods still have the problem of insufficient discrimination between irregular changes and diverse boundaries. Here, to solve this biphasic dilemma, we put forward a network that uses the difference information between bitemporal images as a guide to refine features. We use one feature map to subtract another and use multi-scale convolution to refine the difference map. We then designed an attention module similar to self-attention using differential information. In addition, considering the need for both local and global information in change detection, we use the full Swin Transformer framework with shift window self-attention to pass information between local areas. In addition, in order to enhance the network’s ability to recognize, members of our team reformulate supervised, traditional saliency map prediction through saliency and edge prediction. Notably, our proposed model significantly outperforms existing single-branch methods and state-of-the-art performance was achieved on four famous public datasets in terms of the F1-score index, interest in joint indices, and population indices.

Spaceborne SAR Time-Series Images Change Detection Based on SAR-SIFT-Logarithm Background Subtraction

Synthetic Aperture Radar (SAR) image change detection aims to detect changes with images of the same area acquired at different times. It has wide applications in environmental monitoring, urban planning and resource management. Traditional change detection methods for spaceborne SAR time-series images typically adopt a pairwise comparison strategy to obtain multi-temporal change information. However, this kind of method has the problem of losing the overall change information, which is time consuming. To address this problem, this paper proposes a new change detection algorithm for spaceborne SAR time-series data based on SAR-SIFT-Logarithm Background Subtraction. This algorithm combines the SAR-SIFT image registration technology with Logarithm Background Subtraction. The method first preprocesses the input time-series data with steps like noise reducing and radiometric calibration. Then, the images will be coregistered by the SAR-SIFT step to avoid mismatches-induced detection performance degradation. Next, the parts that remained unchanged throughout the time period are modeled with a median filter to obtain the static background. The change information is then obtained via the subtraction of background and CFAR detection and clustering. The proposed algorithm is validated using the Sentinel-1 GRD and PAZ-1 time-series dataset. Experimental results demonstrate that the proposed method effectively detects the overall change information and reduces processing time compared to traditional pairwise comparison methods.

Intelligent Segmentation and Change Detection of Dams Based on UAV Remote Sensing Images

Guilin is situated in the southern part of China with abundant rainfall. There are 137 reservoirs, which are widely used for irrigation, flood control, water supply and power generation. However, there has been a lack of systematic and full-coverage remote sensing monitoring of reservoir dams for a long time. According to the latest public literature, high-resolution unmanned aerial vehicle (UAV) remote sensing has not been used to detect changes on the reservoir dams of Guilin. In this paper, an intelligent segmentation change detection method is proposed to complete the detection of dam change based on multitemporal high-resolution UAV remote sensing data. Firstly, an enhanced GrabCut that fuses the linear spectral clustering (LSC) superpixel mapping matrix and the Sobel edge operator is proposed to extract the features of reservoir dams. The edge operator is introduced into GrabCut to redefine the new energy function’s smooth item, which makes the segmentation results of enhanced GrabCut more robust and accurate. Then, through image registration, the multitemporal dam extraction results are unified to the same coordinate system to complete the difference operation, and finally the dam change results are obtained. The experimental results of two representative reservoir dams in Guilin show that the proposed method can achieve a very high accuracy of change detection, which is an important reference for related research.

Evaluation of Bone Mineral Changes in Panoramic Radiographs of Hypothyroid and Hyperthyroid Patients Using Fractal Dimension Analysis

Objective Hyperthyroidism and hypothyroidism are endocrinopathies that cause a decrease in bone mineral density. The aim of this study is to investigate possible bone changes in the mandible caused by hyperthyroidism and hypothyroidism using fractal analysis (FA) on panoramic radiographs.Material and Methods Panoramic radiographs of a total of 180 patients, including 120 patient groups (60 hyperthyroid, 60 hypothyroid) and 60 healthy control groups, were used. Five regions of interests (ROI) were determined from panoramic radiographs and FA was performed. ROI1: geometric midpoint of mandibular notch and mandibular foramen, ROI2: geometric midpoint of mandibular angle, ROI3: anterior of mental foramen, ROI4: basal cortical area from distal mental foramen to distal root of first molar, ROI5: geometric center of mandibular foramen and mandibular ramus.Results While a significant difference was observed between the patient and control groups regarding ROI1 and ROI2 (p < 0.05); there was no significant difference between the groups in relation to ROI3, ROI4, and ROI5. All FA values were lower in the hyperthyroid group than in the hypothyroid group.Conclusion Fractal analysis proves to be an effective method for early detection of bone mass changes. In the present study, it was concluded that while the mandibular cortical bone was intact, trabecular rich regions were affected by osteoporosis caused by thyroid hormones. Necessary precautions should be taken against the risk of osteoporosis in patients with thyroid hormone disorders.

Mapping and Pre- and Post-Failure Analyses of the April 2019 Kantutani Landslide in La Paz, Bolivia, Using Synthetic Aperture Radar Data

Urban landslides have brought challenges to developing countries undergoing urbanization. Rapid approaches to assess ground deformation are required when facing the challenge of insufficient geological survey methods. Additionally, it is indeed a challenge to map landslide-affected areas, especially precipitation-induced landslides, through optical remote sensing methods. This study applied SAR change detection methods to map the slope failure event of the San Jorge Kantutani landfill site in La Paz, Bolivia, which occurred in April 2019, and Multi-Temporal Synthetic Aperture Radar Interferometry (MTInSAR) methods to assess pre- and post-failure ground stability related to this event. We found that the amplitude information of high-resolution COSMO-SkyMed SAR imagery and its texture information can be very useful in landslide mapping, especially in situations in which optical images are not available because of complex meteorological conditions and the similar spectral characteristics between the original land cover and landslide deposits. The MTInSAR analyses found that there was already significant deformation of more than 50 mm/year along the slope direction over this site before the landslide, and such deformation could be clearly discriminated from the surrounding environment. After the landslide event and the remobilization of the landslide deposit, the slope still shows a deformation velocity of more than 30 mm/year. The SAR amplitude change detection and MTInSAR fully exploited the SAR data in landslide studies and were useful in back analyzing the occurred landslides; this could be a good method for monitoring the ground stability of La Paz or even on a national scale over the long term for reducing the catastrophic effects of geological hazards in this landslide-prone city.

EFP-Net: A Novel Building Change Detection Method Based on Efficient Feature Fusion and Foreground Perception

Over the past decade, deep learning techniques have significantly advanced the field of building change detection in remote sensing imagery. However, existing deep learning-based approaches often encounter limitations in complex remote sensing scenarios, resulting in false detections and detail loss. This paper introduces EFP-Net, a novel building change detection approach that resolves the mentioned issues by utilizing effective feature fusion and foreground perception. EFP-Net comprises three main modules, the feature extraction module (FEM), the spatial–temporal correlation module (STCM), and the residual guidance module (RGM), which jointly enhance the fusion of bi-temporal features and hierarchical features. Specifically, the STCM utilizes the temporal change duality prior and multi-scale perception to augment the 3D convolution modeling capability for bi-temporal feature variations. Additionally, the RGM employs the higher-layer prediction map to guide shallow layer features, reducing the introduction of noise during the hierarchical feature fusion process. Furthermore, a dynamic Focal loss with foreground awareness is developed to mitigate the class imbalance problem. Extensive experiments on the widely adopted WHU-BCD, LEVIR-CD, and CDD datasets demonstrate that the proposed EFP-Net is capable of significantly improving accuracy in building change detection.

Change detection in VHR Remote Sensing Images by automatic sample selection and progressive classification

ABSTRACT This paper proposes an automatic method for land cover change detection in very-high-spatial-resolution optical remote sensing images based on the automatic selection of training samples using expectation-maximization (EM) and an extreme learning machine classifier, which has two key characteristics: (1) combining the advantages of supervised and unsupervised methods with progressive mask classification. (2) training samples of three classes (changed, unchanged, and unknown) were automatically selected by K-Means and EM, and then further refined by the likelihood function. The method was validated by one dataset of SuperView-1 imagery with a spatial resolution of 2.0 m, two datasets of TripleSat-2 imagery with a spatial resolution of 3.2 m, and one open dataset of Zi-Yuan-3 imagery with a spatial resolution of 5.8 m, and the results were compared with that of three unsupervised methods (iterative slow feature analysis, multivariate alteration detection, and adaptive object-oriented spatial-contextual extraction algorithm), two deep learning methods (convolutional-wavelet neural networks and dual-domain networks), and three supervised classifiers (support vector machine, random forest, and Naive Bayes), showing the effectiveness of this method in decrease of false-positive rates and increase of change detection accuracy. The average and maximum of the accuracy metric F1 score of our method are 0.6842 and 0.8708, respectively; the average F1 score of the unsupervised, deep learning, and supervised methods are 0.5049, 0.4943, and 0.633, respectively.

The Spatial Planning in Purworejo Regency-based Flood Hazard using Sentinel-1A Imagery

Flood disasters in Indonesia increased by 23% over a period of 70 years. In Central Java Province, the incidence of floods has also experienced a significant increase, including flooding in Purworejo Regency. Floods in Purworejo Regency occur in almost every rainy season in the same location. In 2020 and 2021, floods hit the same 13 villages. The utilization of the Sentinel-1A Imagery technology can quickly and accurately visualize the distribution of locations where there are indications of flood inundation. This research aims to do rapid flood mapping for spatial planning. The method used in this research is the processing of Sentinel-1A imagery, flood mapping in Purworejo Regency, validation test of processed Saentinel-1A imagery, and flood analysis with the Purworejo Regency Spatial Planning. The Sentinel-1A data processing is in the form of a combination process between Composite RGB and the Change Detection and Thresholding (CDAT) method. Sentinel-1A imagery was taken at two different times, namely when there was a flood and when there was no flood. The Flood Map Processed by Saentinel-1A imagery will be verified and validated. The validity test results using the Kappa coefficient are 0.841, and the accuracy value is 94%. The Kappa coefficient value and accuracy show that the flooding results from the Saentinel-1A image processing are valid and accurate. The results of the analysis between spatial planning and flood inundation in Purworejo Regency are > 50% of the flooded areas in the form of paddy fields and plantations.

Collaborative sparse unmixing-based hyperspectral change detection method

Collaborative sparse unmixing-based hyperspectral change detection method

Semi-Supervised Urban Change Detection Using Multi-Modal Sentinel-1 SAR and Sentinel-2 MSI Data

Urbanization is progressing at an unprecedented rate in many places around the world. The Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 MultiSpectral Instrument (MSI) missions, combined with deep learning, offer new opportunities to accurately monitor urbanization at a global scale. Although the joint use of SAR and optical data has recently been investigated for urban change detection, existing data fusion methods rely heavily on the availability of sufficient training labels. Meanwhile, change detection methods addressing label scarcity are typically designed for single-sensor optical data. To overcome these limitations, we propose a semi-supervised urban change detection method that exploits unlabeled Sentinel-1 SAR and Sentinel-2 MSI data. Using bitemporal SAR and optical image pairs as inputs, the proposed multi-modal Siamese network predicts urban changes and performs built-up area segmentation for both timestamps. Additionally, we introduce a consistency loss, which penalizes inconsistent built-up area segmentation across sensor modalities on unlabeled data, leading to more robust features. To demonstrate the effectiveness of the proposed method, the SpaceNet 7 dataset, comprising multi-temporal building annotations from rapidly urbanizing areas across the globe, was enriched with Sentinel-1 SAR and Sentinel-2 MSI data. Subsequently, network performance was analyzed under label-scarce conditions by training the network on different fractions of the labeled training set. The proposed method achieved an F1 score of 0.555 when using all available training labels, and produced reasonable change detection results (F1 score of 0.491) even with as little as 10% of the labeled training data. In contrast, multi-modal supervised methods and semi-supervised methods using optical data failed to exceed an F1 score of 0.402 under this condition. Code and data are made publicly available.

A new change detection method for wetlands based on Bi-Temporal Semantic Reasoning UNet++ in Dongting Lake, China

The utility of semantic change detection in myriad change scenarios has garnered considerable attention in contemporary research; however, its applicability in monitoring alterations in wetland ecosystems remains incompletely elucidated. To surmount the constraints associated with binary change detection methodologies—chiefly their insufficiency in the extraction of bi-temporal attributes—we introduced the Bi-Temporal Semantic Reasoning UNet++ (Bi-SRUNet++) algorithm. This algorithm leverages the architectural strengths of UNet++ as its foundational network to precisely delineate features pertinent to multi-class change detection. As a preliminary step, the study focused on the Dongting Lake wetland in China and conducted an analysis of feature trends predicated upon the monthly Normalized Difference Water Index (NDWI) and Normalized Difference Vegetation Index (NDVI), as derived from Landsat 8 data spanning 2021–2022. Subsequently, the optimal temporal phases for change detection were ascertained through differential analyses between NDWI and NDVI metrics. Implementing the Bi-SRUNet++ algorithm on a pair of Sentinel-2 images, captured during the optimal phases, yielded augmented change information. Comparative evaluations reveal that the Bi-SRUNet++ algorithm, conceptualized on the framework of Bi-Temporal Semantic Reasoning Network (Bi-SRNet), surpasses the performance indices of its counterpart Semantic Segmentation and Change Detection Late Fusion (SSCD-l). Furthermore, the incorporation of the UNet++ backbone network amplifies the algorithm's capacity for semantic feature extraction, thereby enhancing the efficacy of Bi-SRUNet++ in wetland change detection. The analysis divulges that the total altered area of Dongting Lake during the 2021–2022 period amounts to 1187.97 km2, comprising a water loss of 1186.16 km2, a 715.34 km2 transformation into vegetation, and a conversion of 469.96 km2 into mudflats. The codes and partial dataset in this paper are available at: https://github.com/vivianmiumiu/Bi-SRUNetplusplus-for-SCD.

Consistency-guided lightweight network for semi-supervised binary change detection of buildings in remote sensing images

ABSTRACT Precise identification of binary building changes through remote sensing observations plays a crucial role in sustainable urban development. However, many supervised change detection (CD) methods overly rely on labeled samples, thus limiting their generalizability. In addition, existing semi-supervised CD methods suffer from instability, complexity, and limited applicability. To overcome these challenges and fully utilize unlabeled samples, we proposed a consistency-guided lightweight semi-supervised binary change detection method (Semi-LCD). We designed a lightweight dual-branch CD network to extract image features while reducing model size and complexity. Semi-LCD fully exploits unlabeled samples by data augmentation, consistency regularization, and pseudo-labeling, thereby enhancing its detection performance and generalization capability. To validate the effectiveness and superior performance of Semi-LCD, we conducted experiments on three building CD datasets. Detection results indicate that Semi-LCD outperforms competing methods, quantitatively and qualitatively, achieving the optimal balance between performance and model size. Furthermore, ablation experiments validate the robustness and advantages of the Semi-LCD in effectively utilizing unlabeled samples.

Radar (sentinel 1 data)-based flood mapping in Rivers State, Nigeria

The existence of floods in Nigeria, a notable environmental issue, is primarily linked to human-induced causes. These are largely linked to global warming causing shifts in climate patterns. Flooding is not always a direct result of preceding factors like heavy rain or dam overflow. Instead, it is frequently triggered by human actions such as overloading main rivers or inappropriate land use. The purpose of this study was to pinpoint areas prone to flooding in Rivers State. The main goals included the development of a spatial map depicting areas susceptible to floods. The research leverages multiple data sources, Shuttle Radar Topography Mission Digital Elevation and Rivers State Administrative Map, as well as Sentinel-1 SAR data. Assessment of potential surface runoff and identifying low probability flood-prone areas was conducted through Change Detection method on Google Earth Engine platform. ArcGIS and QGIS played a significant role in assessing the vulnerability to flood risks. The primary analyses conducted involved overlaps analysis. The study shows a vulnerability to flooding in Rivers State across a total area of 29,660 hectares, equating to 2.75% of the state's total size. This research provides important information that can aid decision-making processes in disaster preparedness, land use planning, and the implementation of effective risk reduction measures in Rivers State, and Nigeria at large. We strongly endorse the creation of Geospatial Information Systems to record the documentation of flood zones.

Examining the impact of Green Riyadh Project on alleviating urban heat island effects

The increase of land surface temperature (LST) because of the urban growth and spatial expansion specially in developing country have shown many negative impacts on the health and quality of life of people, nowadays some cities experience much warmer temperatures than nearby rural areas, causes what is known as the urban heat island (UHI) phenomenon. This study investigates alterations in vegetation and land surface temperature over space and time due to the Green Riyadh Project, employing remote sensing techniques. Multi-temporal Landsat images of the study area from 2018 and 2022, were processed in order to derive The Normalized Difference Vegetation Index (NDVI) and LST are being considered. Change detection methods were used to indicate the changes between the two time periods. Based on the results of this study, NDVI values show that the vegetated areas in Riyadh have not increased between (2018 and 2022). While the LST values show that the total area of UHIs has increased between (2018 and 2022). The change detection in vegetation indicates that there was a decrease in vegetation, mostly in urban areas. Where the change detection of surface temperature indicates huge areas where temperature has increased, mostly in the rural are-as, leaving few areas where the temperature has decreased. This means that the present amount of vegetation has still not made an impact in terms of decreasing the LST. Therefore, there is a need for more effort to be made in increasing the green areas within the urban environment of Riyadh.

Multispectral Remote Sensing Image Change Detection Based on Twin Neural Networks

Remote sensing image change detection can effectively show the change information of land surface features such as roads and buildings at different times, which plays an indispensable role in application fields such as updating building information and analyzing urban evolution. At present, multispectral remote sensing images contain more and more information, which brings new development opportunities to remote sensing image change detection. However, this information is difficult to use effectively in change detection. Therefore, a change-detection method of multispectral remote sensing images based on a Siamese neural network is proposed. The features of dual-temporal remote sensing images were extracted based on the ResNet-18 network. In order to capture the semantic information of different scales and improve the information perception and expression ability of the algorithm for the input image features, an attention module network structure is designed to further enhance the extracted feature maps. Facing the problem of false alarms in change detection, an adaptive threshold comparison loss function is designed to make the threshold more sensitive to the remote sensing images in the data set and improve the robustness of the algorithm model. Moreover, the threshold segmentation method of the measurement module is used to determine the change area to obtain a better change-detection map domain. Finally, our experimental tests show that the proposed method achieves excellent performance on the multispectral OSCD detection data sets.

Anomalous Change Detection in Drilling Process Using Variational Autoencoder with Temperature Near Drill Edge

The different flexibility and diversity requirements for respective manufacturing units have made modern cutting tool management much more crucial and complicated, as a greater variety of tools and more frequent tool changes are required to enhance production efficiency and avoid unplanned manufacturing downtime. Developing in-process anomalous change detection methods has been identified as an essential challenge. Machine learning techniques have been widely applied in tool condition monitoring and anomalous change detection. As anomaly data is rare in manufacturing processes, supervised machine learning approaches (such as regression and classification) are not applied to the anomalous change detection problem. Rather, self-supervised machine learning (a representative type of unsupervised machine learning) is applied. This study describes a variational autoencoder (VAE) neural network and proposes a VAE-based method for tool condition monitoring and change detection in a drilling process using the temperature near a drill edge. The proposed VAE evaluates the drill tool condition based on the reconstruction error between the input temperature and its estimate per a drill unit process through the trained network. Computational simulations demonstrate that the proposed VAE network model can avoid overfitting to the anomaly data and that its expressive power is greater than that of the conventional autoencoder model.

An improved change detection method for tacking remote sensing time series trends

ABSTRACT To improve the accuracy of detecting changes in remote sensing time series, an improved algorithm based on the combination of the antileakage least-squares spectral analysis (ALLSSA) algorithm and detecting breakpoints and estimating segments in trends (DBEST) algorithm is proposed and applied. The method uses the ALLSSA algorithm to decompose the time series and identify the trend components in the time series. Then, the trend segmentation mechanism of the DBEST algorithm is used to detect the changes in the trend component. In this paper, the improved algorithm is evaluated using a simulated time series data set, a time series data set with multiple change points, and data set based on the moderate resolution imaging spectroradiometer (MODIS) normalized difference vegetation index (NDVI) remote sensing time series. The results demonstrate that the average detection accuracies of the improved algorithm and DBEST algorithm are 98.4% and 85.2%, respectively, for the simulated time series data set. For the time series data set with multiple change points, the average root mean square errors (RMSEs) of the trend data for the improved and DBEST algorithms are 0.0386 and 0.0331, respectively. The mean normalized residual norms (MNRNs) of the improved and DBEST algorithms are 0.0252 and 0.0351, respectively. Finally, the improved algorithm, DBEST algorithm, and breaks for additive season and trend (BFAST) algorithm are applied to MODIS NDVI data, and their performance with remote sensing data is compared. The improved algorithm has higher detection accuracy and a smaller MNRN, indicating that more information is included in the trend and seasonal components. Therefore, the proposed method is useful for analysing trends in remote sensing time series data.

Superpixel-based change detection for GPR time-lapse slices using fuzzy c-means and the Markov random field method

Ageing and complex underground utility infrastructure present a significant challenge for modern society, requiring long-term monitoring and maintenance to prevent economic and social costs associated with infrastructure degradation and failure. In this study, we proposed an unsupervised superpixel-based change-detection method using ground-penetrating radar time-lapse slices combining fuzzy c-means and the Markov random field model to investigate an invisible subsurface change due to buried void using time-series measurements. First, simple linear iterative clustering was applied to the difference image, which was generated using paired time-lapse images after intensity registration to create different scales superpixel maps. Then, fuzzy c-means clustering was used to generate superpixel-based change maps. Finally, the Markov random field model was used to integrate the information of adjacent neighbourhoods in three dimensions to iteratively refine the change map. We designed two underground cavities (one representing shallow local voids and the other representing voids near pipeline networks) to verify the capability and adaptability of the proposed method. The experimental results demonstrate the feasibility of the method, with F1-scores of 0.82, 0.69, 0.69, and 0.65 and kappa coefficients of 0.81, 0.69, 0.68, and 0.64. Our method represents a significant contribution to the field of GPR-based change detection and has the potential to improve the long-term monitoring and maintenance of complex underground utility infrastructure.

Bitemporal Remote Sensing Image Change Detection Network Based on Siamese-Attention Feedback Architecture

Recently, deep learning-based change detection methods for bitemporal remote sensing images have achieved promising results based on fully convolutional neural networks. However, due to the inherent characteristics of convolutional neural networks, if the previous block fails to correctly segment the entire target, erroneous predictions might accumulate in the subsequent blocks, leading to incomplete change detection results in terms of structure. To address this issue, we propose a bitemporal remote sensing image change detection network based on a Siamese-attention feedback architecture, referred to as SAFNet. First, we propose a global semantic module (GSM) on the encoder network, aiming to generate a low-resolution semantic change map to capture the changed objects. Second, we introduce a temporal interaction module (TIM), which is built through each encoding and decoding block, using the feature feedback between two temporal blocks to enhance the network’s perception ability of the entire changed target. Finally, we propose two auxiliary modules—the change feature extraction module (CFEM) and the feature refinement module (FRM)—which are further used to learn the fine boundaries of the changed target. The deep model we propose produced satisfying results in dual-temporal remote sensing image change detection. Extensive experiments on two remote sensing image change detection datasets demonstrate that the SAFNet algorithm exhibits state-of-the-art performance.