Search

Real-world multi-objective optimization problems encounter different types of uncertainty that may affect the quality of solutions. One common type is the stochastic noise that contaminates the objective functions. Another type of uncertainty is the different forms of dynamism including changes in the objective functions. Although related work in the literature targets only a single type, in this paper, we study Dynamic Multi-objective Optimization problems (DMOPs) contaminated with stochastic noises by dealing with the two types of uncertainty simultaneously. In such problems, handling uncertainty becomes a critical issue since the evolutionary process should be able to distinguish between changes that come from noise and real environmental changes that resulted from different forms of dynamism. To study both noisy and dynamic environments, we propose a flexible mechanism to incorporate noise into the DMOPs. Two novel techniques called Multi-Sensor Detection Mechanism (MSD) and Welford-Based Detection Mechanism (WBD) are proposed to differentiate between real change points and noise points. The proposed techniques are incorporated into a set of Dynamic Multi-objective Evolutionary Algorithms (DMOEAs) to analyze their impact. Our empirical study reveals the effectiveness of the proposed techniques for isolating noise from real dynamic changes and diminishing the noise effect on performance.

Change detection (CD), as one of the central problems in Earth observation, has attracted a lot of research interest over recent decades. Due to the rapid development of satellite sensors in recent years, we have witnessed an enrichment of the CD source data with the availability of very-high-resolution (VHR) multispectral imagery, which provides abundant change clues. However, precisely locating real changed areas still remains a challenge. In this article, we propose an end-to-end superpixel-enhanced CD network (ESCNet) for VHR images, which combines differentiable superpixel segmentation and a deep convolutional neural network (DCNN). Two weight-sharing superpixel sampling networks (SSNs) are tailored for the feature extraction and superpixel segmentation of bitemporal image pairs. A UNet-based Siamese neural network is then employed to mine the different information. The superpixels are then leveraged to reduce the latent noise in the pixel-level feature maps while preserving the edges, where a novel superpixelation module is used to serve this purpose. Furthermore, to compensate for the dependence on the number of superpixels, we propose an innovative adaptive superpixel merging (ASM) module, which has a concise form and is fully differentiable. A pixel-level refinement module making use of the multilevel decoded features is also appended to the end of the framework. Experiments on two public datasets confirmed the superiority of ESCNet compared to the traditional and state-of-the-art (SOTA) deep learning-based CD (DLCD) methods.

With the development of Earth observation technology, very-high-resolution (VHR) image has become an important data source of change detection. Nowadays, deep learning methods have achieved conspicuous performance in the change detection of VHR images. Nonetheless, most of the existing change detection models based on deep learning require annotated training samples. In this paper, a novel unsupervised model called kernel principal component analysis (KPCA) convolution is proposed for extracting representative features from multi-temporal VHR images. Based on the KPCA convolution, an unsupervised deep siamese KPCA convolutional mapping network (KPCA-MNet) is designed for binary and multi-class change detection. In the KPCA-MNet, the high-level spatial-spectral feature maps are extracted by a deep siamese network consisting of weight-shared PCA convolution layers. Then, the change information in the feature difference map is mapped into a 2-D polar domain. Finally, the change detection results are generated by threshold segmentation and clustering algorithms. All procedures of KPCA-MNet does not require labeled data. The theoretical analysis and experimental results demonstrate the validity, robustness, and potential of the proposed method in two binary change detection data sets and one multi-class change detection data set.

The wide availability of embedded sensor platforms and lowcost cameras—together with the developments in wireless communication—make it now possible the conception of pervasive intelligent systems based on vision. Such systems may be understood as distributed and collaborative sensor networks, able to produce, aggregate and process images in order to understand the observed scene and communicate the relevant information found about it. In this paper, we investigate the peculiarities of visual sensor networks with respect to standard vision systems and we identify possible strategies to accomplish image processing and analysis tasks over them. Although the rather strong constraints in computational and transmission power of embedded platforms that may prevent the use of state of the art computer vision and pattern recognition methods, we argue that multinode processing methods may be envisaged to decompose a complex task into a hierarchy of computationally simpler problems to be solved over the nodes of the network. These ideas are illustrated by describing an application of visual sensor network to infomobility. In particular, we consider an experimental setting in which several views of a parking lot are acquired by the sensor nodes in the network. By integrating the various views, the network is capable to provide a description of the scene in terms of the available spaces in the parking lot.

Mapping, analysis, and monitoring of landuse and landcover in micro region is necessary for sustainable land development, planning and management. The present study is, therefore, aimed to identify the spatio-temporal change of LULC in two central administrative C.D. blocks of North 24 Parganas in West Bengal, India during period 1987-2020. To figure out the essence of the transition, the supervised classification along with post-classification change detection using the 'From'-'To' approach was employed. Furthermore, hotspot analysis has been utilized to identify all of the areas that are the most variable in terms of change potentiality. Besides, cellular automata were also introduced to find out the character of urban growth and future trend of LULC change. The results show that between 1987 and 2020, agricultural area and vegetation with settlement decreased by -11.60 % and -4.34 %, respectively, while dense set-tlement increased by +15.69 % due to significant population growth and overcrowding from neighboring countries. The prediction model also supports this argument. So, the very high and uncontrolled growth of urban settlement in the study area, may become a big challenge for the district authority to control the unplanned urban expansion.

Flexibility and evolution have been a hot topic in the context of business process management. Business process drift detection is a family of methods to detect changes by analyzing the event log, but existing methods have some disadvantages in dealing with concept drifts. First, most of these methods detect changes depending on an exploration of a potentially large feature space and are time consuming. Second, with the size of lag period becoming small, the accuracies of some methods will drop rapidly. In this paper, we address these problems by proposing a novel drift detection technique called LCDD that significantly differs from existing methods. The core idea is to find out new features and disappeared features from traces after the log fragment meets local completeness. To begin with, we use the relations of direct succession as the lightweight feature, which are compared between complete window and detection window. Then, we find new direct successions and stable disappeared direct successions by just moving detection window. Finally, the forgetting mechanism is used to abandon some direct successions after finding a change point. An extensive empirical evaluation shows that LCDD is faster and more accurate.

Models for financial risk often assume that underlying asset returns are stationary. However, there is strong evidence that multivariate financial time series entail changes not only in their within-series dependence structure, but also in the cross-sectional dependence among them. In particular, the stressed Value-at-Risk of a portfolio, a popularly adopted measure of market risk, cannot be gauged adequately unless such structural breaks are taken into account in its estimation. A method for consistent detection of multiple change points in high-dimensional panel data set is proposed where both conditional variance of individual time series and their correlations are allowed to change over time. The consistency of the proposed method in multiple change point estimation is proved, and its good performance is demonstrated through simulation studies and an application to the Value-at-Risk problem on a real dataset. The change point detection methodology is implemented in the R package segMGarch , available from CRAN.

Smart retail stores started to take place in our lives. Several computer vision and sensor-based systems are working together to achieve such a complex and automated operation. Besides, the retail sector has several open and challenging problems which can be solved by embedded computer vision systems. One important problem to be tackled is shelf control or stock out detection. Here, shelves in a store should be controlled regularly such that no item is missing in the shelf. In this study, we propose an embedded computer vision system to solve this problem. To do so, we frame the shelf control operation as change detection. Due to the constraints posed by the retail sector, we formed the system by an ultra-low or low power microcontroller with an embedded camera attached to it. We provided all the implementation details of the system both from software and hardware perspectives. We also tested the proposed shelf control system from different perspectives. Hence, the reader can form such a system for retail sector or for a broad class of change detection problems in which stand-alone embedded system usage is mandatory.

Detecting the changes of bike sharing demands, which are evoked by event disturbances, is critical to evaluating the event impacts on a bike sharing system. Although there has been a proliferation of studies that investigate the problem of demand change detection, most, if not all, of them focus exclusively on the short-term changes lasting for hours or few days. In this research, we propose to detect the abrupt, substantial and persistent changes in the changing regularity of daily demands. We develop a Bayesian hierarchical model, where the upper layer captures the state sequence using a Dirichlet process, and the lower layer captures the state-specific changing regularity of daily demands using linear regression. We estimate the parameters of our model based on the Markov Chain Monte Carlo method. We conduct numerical experiments using the publicly available bike sharing records collected in New York. Results show that our model identifies the demand changes evoked by three bike sharing system expansions and significantly improves the average log marginal likelihood per region.

Visual change detection in video is one of the essential tasks in computer vision applications. Recently, a number of supervised deep learning methods have achieved top performance over the benchmark datasets for change detection. However, inconsistent training-testing data division schemes adopted by these methods have led to documentation of incomparable results. We address this crucial issue through our own propositions for benchmark comparative analysis. The existing works have evaluated the model in scene dependent evaluation setup which makes it difficult to assess the generalization capability of the model in completely unseen videos. It also leads to inflated results. Therefore, in this paper, we present a completely scene independent evaluation strategy for a comprehensive analysis of the model design for change detection. We propose well-defined scene independent and scene dependent experimental frameworks for training and evaluation over the benchmark CDnet 2014, LASIESTA and SBMI2015 datasets. A cross-data evaluation is performed with PTIS dataset to further measure the robustness of the models. We designed a fast and lightweight online end-to-end convolutional network called ChangeDet (speed-58.8 fps and model size-1.59 MB) in order to achieve robust performance in completely unseen videos. The ChangeDet estimates the background through a sequence of maximum multi-spatial receptive feature (MMSR) blocks using past temporal history. The contrasting features are produced through the assimilation of temporal median and contemporary features from the current frame. Further, these features are processed through an encoder-decoder to detect pixel-wise changes. The proposed ChangeDet outperforms the existing state-of-the-art methods in all four benchmark datasets.

In this paper, the problem of detecting accidents using speed sensors distributed spatially on a freeway is considered. Due to the significant impact of road accidents on health and development, early and accurate detection of accidents is crucial. To address this issue, a novel Bayesian quickest change detection formulation is introduced, which considers both average detection delay and false alarm rate. The optimum strategy is derived via dynamic programming and shown to compare a recursively computed statistic with a function of false alarm to identify accidents as they happen. Considering that post-accident conditions are typically not known, two methods are proposed that recursively estimate multiple unknown parameters during the accident detection process. Further, four aggregation methods are proposed to improve performance exploiting spatial correlations between sensors. Extensive evaluation results demonstrate improvement up to 65.2% and 87.2% in average detection delay and false alarm rate, respectively, against prior work.

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.

Remote sensing (RS) image change detection (CD) is a basic application in the military and people's livelihood. The imaging results of multitemporal and multispectral RS images have interference effects such as spectral information difference, imaging light difference, sensor noise, so the accuracy and robustness of traditional CD algorithms are restricted. In this study, we propose an unsupervised fully connected multivariate alteration detection (UFMAD) algorithm. First, UFMAD is used to extract the deep difference feature of normalized multitemporal RS images. The weighted map was obtained by using the chi-square distance of the deep difference feature and weighted with the input data. Then, the UFMAD is iteratively optimized under the three proposed constraints of variance maximization, similarity maximization, and uncorrelation of deep features. Finally, the deep feature was clustered to get the change results. By analyzing the experimental results of six advanced CD algorithms on three sets of data, the highest relative detection accuracy of UFMAD has increased by 7.0% . It is verified that the algorithm proposed in this thesis has obvious performance advantages.

Monitoring forest dynamics is of critical importance for both sustainable forest management and conservation purposes. Light detection and ranging (lidar) data provide a detailed representation of the 3-D structure of forest stands that can be used to analyze a number of trees and stand characteristics. Recently, multiple lidar acquisitions over the same area are becoming more common allowing changes in stand attributes to be assessed over time. In order to effectively utilize such multitemporal data sets for forest dynamics monitoring, we propose a method for unsupervised change detection (CD) of lidar data based on polar change vector analysis (CVA). The proposed method involves extracting relevant lidar point cloud metrics for a given area over time. Pixel-wise difference vectors of the metrics are then converted from Cartesian to polar coordinates to represent the magnitude and direction of change. Finally, the change vectors are analyzed in the polar domain to automatically discriminate between the different classes of change. The method is applied to a multitemporal lidar data set of coniferous forest on Vancouver Island, British Columbia, Canada, impacted by various types of land cover change. The experimental results demonstrate that the proposed method is capable of automatically discriminating between different classes of lidar change.

Change detection is an important task in remote sensing (RS) image analysis. It is widely used in natural disaster monitoring and assessment, land resource planning, and other fields. As a pixel-to-pixel prediction task, change detection is sensitive about the utilization of the original position information. Recent change detection methods always focus on the extraction of deep change semantic feature, but ignore the importance of shallow-layer information containing high-resolution and fine-grained features, this often leads to the uncertainty of the pixels at the edge of the changed target and the determination miss of small targets. In this letter, we propose a densely connected siamese network for change detection, namely SNUNet-CD (the combination of Siamese network and NestedUNet). SNUNet-CD alleviates the loss of localization information in the deep layers of neural network through compact information transmission between encoder and decoder, and between decoder and decoder. In addition, Ensemble Channel Attention Module (ECAM) is proposed for deep supervision. Through ECAM, the most representative features of different semantic levels can be refined and used for the final classification. Experimental results show that our method improves greatly on many evaluation criteria and has a better tradeoff between accuracy and calculation amount than other state-of-the-art (SOTA) change detection methods.

Change detection is a key technology in the field of polarimetric synthetic aperture radar (PolSAR) image processing. The current research on the change detection mainly focuses on studying PolSAR images with the same angle or small angle difference, and the angle problem is not considered. However, when the angle difference occurs, especially a large angle difference, some pixels might be falsely detected because the angle difference can affect the polarimetric characteristics. In this letter, we propose a multilevel information fusion-based (MIFB) method, which is suitable for extracting change information from PolSAR images with angle difference. In particular, the proposed method first adopts data resolution correction, then applies an improved feature-based registration algorithm, and finally, incorporates weighted graph theory with the superpixel segmentation algorithm to extract and merge pixel-based and object-based change areas to eliminate false alarms. Experimental results for multitemporal and multiangle PolSAR images reveal that the MIFB method can effectively eliminate false detection caused by angle differences and improve the detection accuracy.

Change detection (CD) is one of the most important topics in the field of remote sensing. In this letter, we propose an effective satellite images CD network named DifUnet++. As the presentation of explicit difference is more conducive to extract change features, we design a differential pyramid of two input images as the input of Unet++. Considering the scale diversity of changed regions in remote sensing images, a multiply side-outs fusion strategy is adopted to predict the detection results of different scales. Furthermore, a learning upsampling method is utilized to refine the details of CD. The proposed architecture is evaluated on two public satellite image CD data sets. The experimental results show that our method performs much better than state-of-the-art methods.

Change detection (CD) of remote sensing (RS) images is one of the important problems in earth observation, which has been extensively studied in recent years. However, with the development of RS technology, the specific characteristics of remotely sensed images, including sensor characteristics, resolutions, noises, and distortions in imagery, make the CD more complex. In this article, we propose a structure consistency-based method for CD, which detects changes by comparing the structures of two images, rather than comparing the pixel values of images. Because the image structure is imaging modality-invariant and not sensitive to noise, illumination, and other interference factors, the proposed method can be applied to a variety of CD scenarios and has strong robustness. Structural comparison is realized by constructing and mapping an improved nonlocal patch-based graph (NLPG) to avoid the data leakage of two images. First, we demonstrate the effectiveness of the method in homogeneous and heterogeneous CD, which shows that the proposed method can be used as a unified CD framework. Second, we extend the method to the heterogeneous CD with multichannel synthetic aperture radar (SAR) image, which can provide a reference for future research as the heterogeneous CD with multichannel SAR is rarely studied. Third, through the decomposition and in-depth analysis of NLPG, we modify the graph construction process, structure difference calculation, and the difference image fusion to make it more robust and accurate. Experiments on six scenarios 12 data sets demonstrate the effectiveness of the proposed method.

Change detection (CD) aims to identify surface changes from bitemporal images. In recent years, deep learning (DL)-based methods have made substantial breakthroughs in the field of CD. However, CD results can be easily affected by external factors, including illumination, noise, and scale, which leads to pseudo-changes and noise in the detection map. To deal with these problems and achieve more accurate results, a deeply supervised (DS) attention metric-based network (DSAMNet) is proposed in this article. A metric module is employed in DSAMNet to learn change maps by means of deep metric learning, in which convolutional block attention modules (CBAM) are integrated to provide more discriminative features. As an auxiliary, a DS module is introduced to enhance the feature extractor's learning ability and generate more useful features. Moreover, another challenge encountered by data-driven DL algorithms is posed by the limitations in change detection datasets (CDDs). Therefore, we create a CD dataset, Sun Yat-Sen University (SYSU)-CD, for bitemporal image CD, which contains a total of 20,000 aerial image pairs of size 256 x 256. Experiments are conducted on both the CDD and the SYSU-CD dataset. Compared to other state-of-the-art methods, our network achieves the highest accuracy on both datasets, with an F1 of 93.69% on the CDD dataset and 78.18% on the SYSU-CD dataset.

Synthetic aperture radar (SAR) image change detection (CD) is an important application in the field of remote sensing. Due to the lack of labeled data especially in the pixelwise task, it is urgent to develop unsupervised techniques to effectively detect changes. In this article, we propose a novel unsupervised representation learning framework for CD in SAR images, called multiscale self-attention (SA) deep clustering based on octave convolution. The main motivation is that a convolutional neural network (CNN) has the ability to extract significant feature hidden in input images, but it relies heavily on annotated data. Clustering is typically free from supervision; however, SAR images always suffer from speckle noise, which is unfriendly for clustering. Thus, we integrate unsupervised clustering with CNN to learn clustering-friendly feature representations. In the unified framework, CNN feature learning and clustering can be optimized end-to-end without supervision. To better suppress speckle noise and boost the joint optimization for distinguishing changes and unchanges, we use the K-means++ algorithm that is robust to noise as the clustering algorithm. In the meanwhile, we introduce the octave convolution and SA mechanism into the network to fully mine important spatial structure information for enhancing noise resistance of the network. Moreover, multiscale fusion modules are proposed to fuse multiscale input into a complementary feature representation that contains more context and semantic information around each pixel so that it refines the difference feature extraction while reducing speckle noise. Experiments on challenging SAR data sets demonstrate the effectiveness and potential of the proposed model compared with the current state-of-the-art algorithms.

Currently, most of the supervised change detection approaches require a training data set that contains samples from both the changed and the unchanged data. However, under certain condition, such as natural disaster and military attack, the changed data samples are very few or even not available but the unchanged data are abundant. In this letter, we develop a generative adversarial networks (GANs)-based one-class classification (OCC) technique for time series remote-sensing image change detection. The proposed method is only trained with the unchanged data instead of both the changed and unchanged data. To achieve this purpose, first, spatial-spectral features are extracted from the time series remote-sensing images. Second, a GAN model is trained to detect the changes only with the extracted features of unchanged data. Remarkably, to offset the outlier errors caused by the incomplete supervision information provided by unchanged data alone, changed data, instead of unchanged data, are generated to improve power of discriminator. Finally, testing data are classified by the trained discriminator of GAN to produce a binary change map. Experimental results obtained on two optical time series remote-sensing data sets confirmed the effectiveness of our proposed method.

Semantic segmentation of small-scale objects in very high resolution (VHR) remote sensing images plays an important role in some special tasks, such as change detection and mapping of land cover. However, due to small size, small-scale objects are more likely to be completely obscured by shadows than large-scale objects, which make it difficult for the traditional convolutional neural network (CNN) to distinguish small-scale objects from shadows. Furthermore, even if small-scale objects are distinguished, their boundaries are still difficult to refine. To solve the above problems, a novel context union edge network (CEN) for small-scale objects semantic segmentation is proposed by comprehensively considering both the contextual and edge information. In CEN, a plug-and-play context-based feature enhancement module (CFEM) is designed to enhance the ability of CNNs to distinguish small-scale objects. Then, an information exchange mechanism (IEM) is proposed based on the dual-stream (semantic and edge stream) network to refine the boundaries of small-scale objects. Finally, some experiments based on the ISPRS Vaihingen data set are conducted in terms of both overall accuracy (OA) and F1-score. The proposed CEN achieves 89.9% of F1-score for small-scale objects (cars) and 90.9% of OA, harvesting new state-of-the-art results.

The superpixel generation is a key step for object-based classification and change detection. For the time-series PolSAR superpixel generation, the traditional polarimetric similarity measure based on the joint covariance matrix has limitations in discriminating different time-series similarity sequences with different fluctuations. Besides, in the traditional time-series PolSAR superpixel generation methods, it is difficult to determine the tradeoff factor between polarimetric and spatial similarity. In this paper, an adaptive time-series PolSAR superpixel generation method based on the simple local iterative clustering (SLIC) is proposed, named as TSPol-ASLIC. There are three main improvements. Firstly, a novel time-series polarimetric similarity measure based on the root mean square (RMS) is proposed. Multi-temporal polarimetric statistical information are combined to describe the polarimetric proximity between pixels, referring to the RMS of the multi-temporal proximities. Secondly, an edge detection method based on the stacked two-dimensional Gaussian-shaped (s2-D GS) window is proposed to initialize the central seeds for superpixel generation. Thirdly, an improved SLIC clustering similarity combined with the time-series polarimetric, time-series power and spatial similarities is proposed. Meanwhile, a homogeneity factor is applied to adaptively balance the relative weights of various similarities. We use 8 Radarsat-2 quad-polarization SAR images and 14 Sentinel-1 dual-polarization SAR images to evaluate the effectiveness. The results show our similarity measure and superpixel generation results are superior to those of the traditional methods. For example, as for the Radarsat-2 data, the improvement of the boundary recall by the proposed similarity measure and homogeneity factor is about 4% and 10%, respectively

Change detection of heterogeneous remote sensing images is an important and challenging topic in remote sensing for emergency situation resulting from nature disaster. Due to the different imaging mechanisms of heterogeneous sensors, it is difficult to directly compare the images. To address this challenge, we explore an unsupervised change detection method based on adaptive local structure consistency (ALSC) between heterogeneous images in this letter, which constructs an adaptive graph representing the local structure for each patch in one image domain and then projects this graph to the other image domain to measure the change level. This local structure consistency exploits the fact that the heterogeneous images share the same structure information for the same ground object, which is imaging modality-invariant. To avoid the leakage of heterogeneous data, the pixelwise change image is calculated in the same image domain by graph projection. Experiment results demonstrate the effectiveness of the proposed ALSC based change detection method by comparing with some state-of-the-art methods.

Change detection is a research hotspot in the remote sensing field. In this letter, an unsupervised change detection method was proposed by optimizing two critical steps, i.e., the generation and analysis of difference image. First, the difference vectors of features are calculated using the simple differencing method. Some changed and unchanged pixels are generated by the majority voting on the results produced by clustering the difference vectors and then are used for the weight calculation of difference vectors. The weights are calculated by means of F-Score and considered in the weighted change vector analysis to produce a discriminative difference image. Finally, the change map is obtained by the improved Markov random field which takes the difference in the neighborhood pixel values into account. Experimental results on three data sets demonstrated that the proposed method outperformed six unsupervised change detection methods in terms of overall accuracy.

Change detection, as an essential part of synthetic aperture radar (SAR) automatic target recognition (ATR) systems, remains a challenging problem. The lack of labeled data seriously impedes the development of deep learning-based methods in SAR applications. In this letter, we propose a patch-based semisupervised method to detect changed pixels from limited training data in the field of SAR. The complete approach includes the unsupervised pretraining stage and the iterative discrimination stage. The states of pixels are determined by comparing the corresponding image patches. First, to reduce the impact of insufficient data, we train a trapezium U-Net-like structure to extract representative and generalized features by unsupervised training on all pixels. Feature maps contain detailed and semantic information due to repetitive feature fusions. A designed feature activation module is utilized to recalibrate fused features. Finally, the discrimination is finished by a simple classification convolutional neural network (CNN) following a two-step training strategy. Ablation studies indicate the function provided by the proposed modifications. Experiments on real SAR images demonstrate that the proposed method can improve the detection accuracy by more than 1.2% compared with other state-of-the-art deep learning-based methods.

With the introduction of artificial intelligence (AI), current deep learning-driven change detection methods generally regard changes as a type of specific land cover information and try to detect them simply by using existing semantic labeling models. In practice, the changes that occur on different land cover categories may appear completely different for remote sensing images, making it difficult to detect multiple categories of changes with an end-to-end model. In addition, training such networks requires a large amount of prelabeled references, which are labor-intensive and time-consuming. Motivated by this observation, we integrate dual learning algorithm and disentangled representation theory to develop a novel approach, named content-invariant dual learning (CiDL), for either supervised or unsupervised change detection in remote sensing images. In our framework, two opposite Y-shaped networks, each of which consists of two encoders and one decoder, are introduced to translate bitemporal images from their original domains to each others, where their intrinsic content features are retained, while their style features are consistent. By training our hybrid framework, even without references, this method learns a category-wise cross-domain translation to suppress the discrepancies in paired unchanged regions, and meanwhile highlight those in paired changed regions. The experimental results on two typical change detection data sets and the comparison with other state-of-the-art deep learning-driven methods verify the effectiveness and competitiveness of our proposed CiDL.

Landslide inventory mapping (LIM) plays an important role in landslide susceptibility analysis. Many LIM approaches based on change detection techniques have been proposed, but with various drawbacks. For example, existing approaches have limited capability to capture the objects of varying shapes/sizes present in an area impacted by landslide. Many existing approaches are supervised and require parameter tuning. Moreover, some methods are prone to salt-and-pepper noise. To overcome these limitations, in this letter, an algorithm based on automatic adaptive region extension using very-high-resolution remote sensing images is developed. First, a simple yet effective k-means clustering method is used to generate training samples for landslide and nonlandslide classes, which refer to changed and unchanged areas, respectively. Second, an automatic adaptive region extension algorithm is developed and applied to each pixel of the postevent image, and the label of an extended region around a pixel is determined by the nearest distance between the central pixel and the changed or unchanged samples. Finally, the labels of a pixel are recorded because a pixel in different adaptive regions may be reassigned dissimilar labels, and the final label of the pixel is consistent with its maximum assigned label. To verify the performance of the proposed approach, we conducted experiments on two different landslide sites with VHR remote sensing images in Lantau Island, Hong Kong, China. Experimental results clearly demonstrate that the proposed approach has several advantages in improving the performance of LIM with VHR remote sensing images.

Image-based fusion is a state-of-art process to extract vital information by combining the two or more images acquired from different satellite sensors. Recently launched (26th September 2016) ISRO’s (Indian Space Research Organization) Ku-band (13.5 GHz) based Scatterometer Satellite (SCATSAT-1) as an active microwave sensor can offer the day-night, all-weather monitoring services, which are not possible with the optical-based visible and infrared remote sensing satellites. Therefore, the fusion of optical and microwave data offers the cloud-free detection of earth surface transitions and helps in emergency response to natural hazards, security, and defence. The objectives of the proposed framework are (a) nearest-neighbour based fusion (NNF) of ISRO’s SCATSAT-1 and NASA’s (National Aeronautics and Space Administration) moderate resolution imaging spectroradiometer (MODIS) optical data, (b) generation of thematic maps using artificial neural network (ANN) based classification of the fused data, (c) detection of spatiotemporal variations via post-classification comparison (PCC) based change detection, (d) cross-referencing with well-defined fusion methods, i.e. Gram-Schmidt (GS), Brovey Transformation (BT) and Ehlers, and (e) Impact analysis of clouds on the input dataset and fusion methods. This study has been conducted over the Western Himalayas to estimate the snow cover changes under cloudy conditions with two datasets i.e., winter and monsoon. The experimental outcomes confirm the efficacy of the proposed framework in the effective removal of clouds, generation of classified maps, and change maps. The present study includes an exhaustive list of applicative situations for cloud-free monitoring using freely and daily based SCATSAT-1 and MODIS datasets.

Change detection (CD) aims to identify the differences between multitemporal images acquired over the same geographical area at different times. With the advantages of requiring no cumbersome labeled change information, unsupervised CD has attracted extensive attention of researchers. Multitemporal images tend to have different resolutions as they are usually captured at different times with different sensor properties. It is difficult to directly obtain one pixelwise change map for two images with different resolutions, so current methods usually resize multitemporal images to a unified size. However, resizing operations change the original information of pixels, which limits the final CD performance. This article aims to detect changes from multitemporal images in the originally different resolutions without resizing operations. To achieve this, a cross-resolution difference learning method is proposed. Specifically, two cross-resolution pixelwise difference maps are generated for the two different resolution images and fused to produce the final change map. First, the two input images are segmented into individual homogeneous regions separately due to different resolutions. Second, each pixelwise difference map is produced according to two measure distances, the mutual information distance and the deep feature distance, between image regions in which the pixel lies. Third, the final binary change map is generated by fusing and binarizing the two cross-resolution difference maps. Extensive experiments on four datasets demonstrate the effectiveness of the proposed method for detecting changes from different resolution images.

This article presents a probabilistic model based on a bipartite convolutional architecture for unsupervised change detection. We aim to develop a robust change detection method that can adapt to different types of data and scenarios for multitemporal coregistered remote sensing images of the same spatial resolution. On the premise of coregistration, unsupervised change detection usually suffers from the distinct appearances (different intensities or data structures) of the same object in multitemporal images, such as images obtained in different climatic conditions (season, illumination, and so on), and by different and even heterogeneous sensors. Since change detection in heterogeneous images can also adapt to other scenarios, many methods have been proposed recently focusing on such data, but most of them are limited by the need for labeled data or by specific assumptions. With the excellent and flexible feature learning capability of neural networks, we model the change detection into a Gibbs probabilistic model based on a bipartite neural network. The model is driven by an energy function defined as the squared feature distance, which is the core of change detection. Via optimizing the model, the difference degree of each pixel is automatically obtained for further identification. The probabilistic model learns to capture the distribution in an unsupervised way. Therefore, the proposed method can adapt to various scenarios without being trained by labeled data. Experiments on different types of data and scenarios demonstrate the superiority of the proposed method.

Change detection of heterogeneous multitemporal satellite images is an important and challenging topic in remote sensing. Since the imaging mechanisms of heterogeneous sensors are different, it is not possible to directly compare heterogeneous images to detect changes as in the homogeneous images. To address this challenge, we propose an unsupervised image regression-based change detection method based on the structure consistency. The proposed method first adaptively constructs a similarity graph to represent the structure of a pre-event image, then uses the graph to translate the pre-event image to the domain of the post-event image, and then computes the difference image. Finally, a superpixel-based Markovian segmentation model is designed to segment the difference image into changed and unchanged classes. The proposed adaptive structure consistency-based image regression model can not only alleviate the impact of noise and changed pixels on the regression process by using the structure-based transformation, but also easily distinguish between changed and unchanged classes in the difference image by using the prior sparse knowledge of changes. Experimental results on six different datasets demonstrate the effectiveness of the proposed method by comparing with some state-of-the-art methods.

In recent years, with the development of high-resolution remote sensing (RS) images and deep learning technology, high-quality source data and state-of-the-art methods have become increasingly available, and great progress has been made in change detection (CD) in RS fields. However, existing methods still suffer from weak network feature representation and poor CD performance. To address these problems, we propose a novel CD network, called dual-pathway CD network (DP-CD-Net), which can help enhance feature representation and achieve a more accurate difference map. The proposed method contains a dual-pathway feature difference network (FDN), an adaptive fusion module (AFM), and an auxiliary supervision strategy. Dual-pathway FDNs can effectively enhance feature representation by supplementing the detailed information from the encoding layers. Then, we use the AFM method to fuse the difference maps. To solve the problem of training difficulty, we use the auxiliary supervision strategy to improve the performance of DP-CD-Net. We conduct extensive experiments to validate the performance of the proposed method on the LEVIR-CD dataset. The results demonstrate that the proposed method performs better than existing methods.

In this letter, we propose a new unsupervised change detection method based on low-rank prior for multispectral images. It is assumed that the changed and unchanged pixels are from different subspaces due to different appearance and statistical properties. So, low-rank representation (LRR) is employed to find informative pixels from the superpixels of the difference image (DI). Besides, taking the sparsity of changed pixels in the observed scenes into consideration, the selection rule is designed to distinguish these pixels. Then, principal component analysis (PCA) is used for the training of changed and unchanged dictionaries from these pixels. Finally, the change map is estimated by comparing the reconstruction error of each pixel in DI on changed and unchanged dictionaries. By LRR, more representative pixels are found for subsequent dictionary learning, which can efficiently improve the performance of the proposed method. Experiments on multitemporal images from the Landsat satellite demonstrate the effectiveness of the proposed method.

Today, remote sensing (RS) data are already regarded as ``big data.'' Developments in computer science have made it possible to explore the potential treasure within remote sensing big data, but only limited remote sensing research has made use of big data technology due to gaps in techniques between big data and remote sensing. In this research, we analyzed the full processing flow of remote sensing big data from the perspective of both computer science and remote sensing science and proposed a modular framework. Computation ready data (CRD), a dynamic data type for computation based on analysis ready data (ARD), is proposed to connect the two main modules of the framework, the data module and computation module. Compared with existing research, the proposed framework classifies and abstracts the key technical and research points of the processing of remote sensing big data as replaceable modules and bridges them through an open organization. Subsequently, we built a prototype platform with open-source technologies and carried out three experiments to validate the feasibility and advantages of the framework, namely normalized difference vegetation index (NDVI) production, water body change detection, and land use classification. Results indicate that this framework can greatly reduce experimental costs for remote sensing researchers. While the proposed framework has proven flexible and practical, further research is needed for the technical implementation of certain modules to achieve the original intention of the framework.

High spatial resolution (HSR) remote sensing images can reflect more subtle changes and more specific types of land use and land cover (LULC) due to the abundant spatial geometric information. In this article, a class-prior object-oriented conditional random field (COCRF) framework consisting of a binary change detection (CD) task and a multiclass CD task is proposed to fill the application gap. In the proposed framework, the class-prior knowledge is used to improve the construction of the unary potential in both the binary and multiclass CD tasks, to reduce the influence of spectral variability. The binary CD result provides a constraint to the multiclass CD result. As a result, both parts have effective interaction. The class posterior probability images of two dates can be obtained automatically with the class-prior knowledge by sample migration. Furthermore, an object constraint described by the class dispersion within the objects is added to improve the smoothness in local objects, while the pairwise potential improves the smoothness of the whole area by using the eight-neighborhood spectral information of the center pixel. By integrating the above approaches, the problems of error accumulation and the manual intervention required in the traditional multiclass CD methods can be relieved. An adaptive parameter estimation strategy is also adopted in the proposed framework, to save the time required for manual parameter setting. The proposed COCRF framework was validated on two HSR remote sensing image data sets, where it achieved a better performance than the other state-of-the-art CD methods.

With the wide application of deep learning (DL), change detection (CD) for remote sensing images (RSIs) has realized the leap from the traditional to the intelligent methods. However, many existing methods still need further improvement in practical applications, especially in increasing the effectiveness of feature extraction and reducing model computational cost. In this paper, we propose a novel deep multiscale Siamese network with parallel convolutional structure (PCS) and self-attention (SA) (MSPSNet), which has excellent capabilities of feature extraction and feature integration under an acceptable consumption. It mainly contains three subnetworks: deep multiscale feature extraction, feature integration by the PCS, and feature refinement based on the SA. In the first subnetwork, a deep multiscale Siamese network based on convolutional block is designed to depict image features at different scales for different temporal images. In the subsequent subnetworks, a PCS model is proposed to integrate multiscale features of different temporal images, and then, a SA model is constructed to further enhance the representation of image information. Experiments are conducted on two public RSIs datasets, indicating that the proposed framework performs well in detecting changes.

Building change detection from very high-spatial-resolution (VHR) remote sensing images has gained increasing popularity in a variety of applications, such as urban planning and damage assessment. Detecting fine-grained ``from-to'' changes (change transition from one land cover type to another) of buildings from the VHR images is still challenging as multitemporal representation is complicated. Recently, fully convolutional neural networks (FCNs) have been proven to be capable of feature extraction and semantic segmentation of VHR images, but its ability in change detection is untested and unknown. In this letter, we leverage the semantic segmentation of buildings as an auxiliary source of information for the fine-grained ``from-to'' change detection. A deep multitask learning framework for change detection (MTL-CD) is proposed for detecting building changes from the VHR images. MTL-CD adopts the encoder-decoder architecture and solves the main task of change detection and the auxiliary tasks of semantic segmentation simultaneously. Accordingly, the change detection loss function is constrained by the auxiliary semantic segmentation tasks and enables the back-propagation of the building footprints' detection errors for the improvement of change detection. A building change detection data set named the Guangzhou data set is also developed for model evaluation, in which the bitemporal R-G-B images were collected by airplane (2009) and unmanned aerial vehicle (UAV, 2019) with different flight heights. Experiments on the Guangzhou data set demonstrate that the MTL-CD method effectively detects fine-grained ``from-to'' changes and outperforms the postclassification methods and the direct change detection methods.

Facing the challenge of small open labeled data sets in remote sensing change detection, this letter proposes a novel supervised change detection method by taking advantages of capsule network which can reach the same performance as traditional convolutional neural networks (CNNs) but with less training data. To achieve this aim, we propose a pseudo-Siamese capsule network which takes both rotational invariance and spatial hierarchies between features into account for aerial images change detection. First, the features of image pairs are extracted by two identical nonshared weights convolutional capsule networks. Second, the extracted features are directly concatenated and sent to another convolutional capsule layer. The change probability map is obtained by calculating the length of the capsule vectors in the final layer. Additionally, to reduce the influence of imbalance samples when we optimize our network, we design a margin-focal loss function to pay more attention to the misclassified samples. Finally, binary change map can be produced by a simple threshold. Experimental results carried out on the SZTAKI AirChange Benchmark Set show that the proposed method achieves comparable and even better results with existing state-of-the-art methods in terms of F-measure.

With the ability to locate subtle trace objects in the large-scale region, coherent change detection (CCD) has been vital research for a synthetic aperture radar (SAR) system. Finding the difference between repeat-pass repeat-geometry SAR image pair and extracting impressive trace pixels from difference image, the SAR CCD methods consist of a difference generation module and a difference analysis module. The previous CCD methods mainly pay attention to devising a sophisticated working system or an appropriate statistic model to generalize a well difference image. In this article, we introduce the deep learning method into the CCD algorithm and propose a novel trace detection paradigm, which works by hierarchically fusing the unsupervised coherent statistics model and supervised deep learning model. To be specific, the complex reflectance change detection estimator is introduced to generate a difference image and reduce the false alarm in the low clutter-to-noise region. Since the low correlation in a difference image caused by the natural factors severely affects the detection performance, the multiple statistics based on intensity summation and intensity difference are, respectively, proposed to extract water region and vegetation region and suppress the corresponding false alarm. Then the construction of the coarse-to-fine image makes use of land cover information and trace features while the compressed Unet improves the utilization efficiency of trace samples. Meanwhile, the inductive transfer learning based on unsupervised pretraining and few labeled trace samples helps to train a well detection model. Experiments on measured SAR data demonstrate the effectiveness of proposed methods.

Landslide inventory mapping (LIM) on the basis of change detection techniques has potential significance for landslide disaster analysis. In this letter, a novel LIM approach based on the adaptive histogram-mean distance (AHMD) is proposed, which adaptively considers spatial contextual information of different landslide regions to improve the detection performance. First, to adapt the shape, size, and distribution of various landslides, an adaptive region around a pixel is extracted by a novel adaptive region extension algorithm without parameter setting. Second, the pixels within the adaptive region are taken to construct the spectral frequency histograms, and then, the adaptive histogram mean (AHM) is developed as the feature of a histogram. Third, the AHMD is defined based on the bin-to-bin (B2B) distance to measure change magnitude between the pairwise AHMs. Finally, LIM can be obtained by a supervised threshold method called double-window flexible pace search (DFPS). Experimental results tested on two real datasets with a very high spatial resolution (VHR) demonstrate the outperformance of the proposed AHMD approach with seven comparative methods.

Due to interference with remote imaging by some natural factors, the multitemporal analysis ability is limited by the spectral drift between images. In this article, a new approach to optimize the existing multitemporal analysis system is proposed: multitemporal intrinsic image decomposition (MIID). The MIID method is designed to extract common spectral reflectance from multitemporal images. With MIID, multitemporal classification, changing detection, and index extracting will become extremely easy and more accurate. Firstly, without considering land cover change, the general MIID framework is proposed by adding local temporal-spatial energy constraints in traditional intrinsic images decomposition. On this basis, an improved MIID method with change detection (CD) (CD-MIID) capability is proposed to make the model adapt to the land cover change situation. Finally, specific steps of how to use MIID methods in the multitemporal analysis are given. Multitemporal multispectral/hyperspectral remote sensing images from GF-1, GF-2, GF-5, Landsat TM, and two groups of captured datasets with reflectance truth map are used to evaluate the performance. The experimental results show the following two points: first, the MIID methods achieve better extraction results of spectral reflectance. Second, the proposed MIID methods have better performance both on multitemporal classification and CD.

Change detection in heterogeneous remote sensing images is crucial for emergencies, such as disaster assessment. Existing methods based on homogeneous transformation suffer from the high computational cost that makes the change detection tasks time-consuming. To solve this problem, this article presents a new semisupervised Siamese network (S³N) based on transfer learning. In the proposed S³N, the low- and deep-level features are separated and treated differently for transfer learning. By incorporating two identical subnetworks that are both pretrained on natural images, the proposed S³N eliminates the computational cost for learning the low-level features that are universal for both remote sensing images and natural images. As the deep-level features contain different semantics between remote sensing images and natural images, a novel transfer learning strategy is presented to train only the weights of the layers for deep-level features in the proposed S³N. The decrease in the number of network parameters to be trained reduces the demand for training samples, leading to a significant decrease in computational cost. Afterward, the thresholding method, Otsu, is applied to the difference map derived by the proposed S³N to obtain the final binary map of change detection. Three data sets including different types of heterogeneous remote sensing images are employed to evaluate the performance of the proposed S³N. The experimental results demonstrate that the proposed S³N can achieve a comparable detection performance with much lower computational cost, compared with state-of-the-art change detection algorithms.

Relative radiometric normalization (RRN) is widely used for radiometric calibration of bitemporal multispectral images prior to any temporal analysis such as change detection. However, standard RRN methods are not robust against anomalous (or changed) pixels, which warp the calibration and decrease the spectral similarity of processed images. This letter proposes a novel random sample consensus-based RRN method, which only uses small pixel subsets to implement the linear mapping relationship for RRN, and does not require the calibration of its parameters. The experimental results show that the proposed method performs favorably against the widely used RRN methods in all metrics considered in this letter.

Deep learning-based unsupervised change detection (CD) methods compare a prechange and a postchange image in deep feature space and require precise knowledge of the event date for selecting proper pre-/post-change images. However, in many applications changes may occur gradually over a span of time making pre-/post-dates difficult to establish or prior knowledge of event date is unknown. On the other hand, deep learning-based time-series analysis methods are generally supervised. Considering such scenarios, we propose a novel unsupervised deep learning-based method to detect changes in an image time-series. The method does not make any assumption on the date of the occurrence of the change event. It treats CD as an anomaly detection problem by exploiting multilayer long short term memory (LSTM) network to learn a representation of the time series. The proposed method ingests a shuffled time series and uses an encoder-decoder LSTM model to rearrange the input sequence in correct order. While the model fails to rearrange the changed pixels, unchanged data can be rearranged in the correct order. This enables the identification of the changed pixels. To show the effectiveness of the proposed method, we tested it on two multitemporal Sentinel-1 data sets over Brumadinho, Brazil, and Bhavanisagar, India.

Anomaly detection (AD) is a field of intense research in remote sensing (RS) image processing. Identifying low probability events in RS images is a challenging problem given the high dimensionality of the data, especially when no (or little) information about the anomaly is available a priori. While a plenty of methods are available, the vast majority of them do not scale well to large datasets and require the choice of some (very often critical) hyperparameters. Therefore, unsupervised and computationally efficient detection methods become strictly necessary, especially now with the data deluge problem. In this article, we propose an unsupervised method for detecting anomalies and changes in RS images by means of a multivariate Gaussianization methodology that allows to estimate multivariate densities accurately, a long-standing problem in statistics, and machine learning. The methodology transforms arbitrarily complex multivariate data into a multivariate Gaussian distribution. Since the transformation is differentiable, by applying the change of variables formula, one can estimate the probability at any point of the original domain. The assumption is straightforward: pixels with low estimated probability are considered anomalies. Our method can describe any multivariate distribution, makes an efficient use of memory and computational resources, and is parameter-free. We show the efficiency of the method in experiments involving both AD and change detection (CD) in different RS image sets. For AD, we propose two approaches. The first is using directly the Gaussianization transform and the second is using a hybrid model that combines Gaussianization and the Reed-Xiaoli (RX) method typically used in AD. For CD, we take advantage of the Gaussianization transform and attribute the change to pixels with low probability compared to the first image, instead of those with high difference value typically employed in RS. Results show that our approach outperforms other linear and nonlinear methods in terms of detection power in both anomaly and CD scenarios, showing robustness and scalability to dimensionality and sample sizes.

Multi-temporal high spatial resolution earth observation makes it possible to detect complex urban land surface changes, which is a significant and challenging task in remote sensing communities. Previous works mainly focus on binary change detection (BCD) based on modern technologies, e.g., deep fully convolutional network (FCN), whereas the deep network architecture for semantic change detection (SCD) is insufficiently explored in current literature. In this paper, we propose a deep multi-task encoder-transformer-decoder architecture (ChangeMask) designed by exploring two important inductive biases: sematic-change causal relationship and temporal symmetry. ChangeMask decouples the SCD into a temporal-wise semantic segmentation and a BCD, and then integrates these two tasks into a general encoder-transformer-decoder framework. In the encoder part, we design a semantic-aware encoder to model the semantic-change causal relationship. This encoder is only used to learn semantic representation and then learn change representation from semantic representation via a later transformer module. In this way, change representation can constrain semantic representation during training, which introduces a regularization to reduce the risk of overfitting. To learn a robust change representation from semantic representation, we propose a temporal-symmetric transformer (TST) to guarantee temporal symmetry for change representation and keep it discriminative. Based on the above semantic representation and change representation, we adopt simple multi-task decoders to output semantic change map. Benefiting from the differentiable building blocks, ChangeMask can be trained by a multi-task loss function, which significantly simplifies the whole pipeline of applying ChangeMask. The comprehensive experimental results on two large-scale SCD datasets confirm the effectiveness and superiority of ChangeMask in SCD. Besides, to demonstrate the potential value in real-world applications, e.g., automatic urban analysis and decision-making, we deploy the ChangeMask to map a large geographic area covering 30 km2 with 300 million pixels. Code will be made available.

Change detection for multitemporal hyperspectral images (HSIs) has always been a research hotspot of remote sensing. However, most current detection methods only use spectral information or spatial information separately, and there are many false detection areas in the detection results. Besides, the feature extraction method based on neural networks needs a huge amount of training samples, but collecting labeled training samples for change detection tasks is difficult. Therefore, this letter proposes a hyperspectral change detection method based on a simplified 3-D convolutional autoencoder (S3DCAECD). First, the framework is based on deep unsupervised autoencoder (AE), which can extract deep spectral-spatial features from bitemporal images without the need for prior information. Second, by adding a 3-D convolution kernel and eliminating the pooling layer, the structure of 3-D convolutional AE is simplified, which can reduce spectral redundancy and improve data processing speed. Finally, a softmax classifier with a 2-D convolutional layer added is used to obtain the detection result, and only a few label samples are needed to train the classifier. Three HSIs' experimental results indicate that the accuracy of the S3DCAECD is more than 95% on three experimental datasets and it has better detection results than several commonly used methods.

Change detection of high-resolution remote sensing images is an important task in earth observation and was extensively investigated. Recently, deep learning has shown to be very successful in plenty of remote sensing tasks. The current deep learning-based change detection method is mainly based on conventional long short-term memory (Conv-LSTM), which does not have spatial characteristics. Since change detection is a process with both spatiality and temporality, it is necessary to propose an end-to-end spatiotemporal network. To achieve this, Conv-LSTM, an extension of the Conv-LSTM structure, is introduced. Since it shares similar spatial characteristics with the convolutional layer, L-UNet, which substitutes partial convolution layers of UNet-to-Conv-LSTM and Atrous L-UNet (AL-UNet), which further using Atrous structure to multiscale spatial information is proposed. Experiments on two data sets are conducted and the proposed methods show the advantages both in quantity and quality when compared with some other methods.

It is quite an important and challenging problem for change detection (CD) from heterogeneous remote sensing images. The images obtained from different sensors (i.e., synthetic aperture radar (SAR) & optical camera) characterize the distinct properties of objects. Thus, it is impossible to detect changes by direct comparison of heterogeneous images. In this article, a new unsupervised change detection (USCD) method is proposed based on image translation. The cycle-consistent adversarial networks (CycleGANs) are employed to learn the subimage to subimage mapping relation using the given pair (i.e., before and after the event) of heterogeneous images from which the changes will be detected. Then, we can translate one image (e.g., SAR) from its original feature space (e.g., SAR) to another space (e.g., optical). By doing this, the pair of images can be represented in a common feature space (e.g., optical). The pixels with close pattern values in the before-event image may have quite different values in the after-event image if the change happens on some ones. Thus, we can generate the difference map between the translated before-event image and the original after-event image. Then, the difference map is divided into changed and unchanged parts. However, these detection results are not very reliable. We will select some significantly changed and unchanged pixel pairs from the two parts with the clustering technique (i.e., K-means). These selected pixel pairs are used to learn a binary classifier, and the other pixel pairs will be classified by this classifier to obtain the final CD results. Experimental results on different real datasets demonstrate the effectiveness of the proposed USCD method compared with several other related methods.