Change Detection Dataset Research Articles

Building Change Detection with Deep Learning by Fusing Spectral and Texture Features of Multisource Remote Sensing Images: A GF-1 and Sentinel 2B Data Case

Building change detection is an important task in the remote sensing field, and the powerful feature extraction ability of the deep neural network model shows strong advantages in this task. However, the datasets used for this study are mostly three-band high-resolution remote sensing images from a single data source, and few spectral features limit the development of building change detection from multisource remote sensing images. To investigate the influence of spectral and texture features on the effect of building change detection based on deep learning, a multisource building change detection dataset (MS-HS BCD dataset) is produced in this paper using GF-1 high-resolution remote sensing images and Sentinel-2B multispectral remote sensing images. According to the different resolutions of each Sentinel-2B band, eight different multisource spectral data combinations are designed, and six advanced network models are selected for the experiments. After adding multisource spectral and texture feature data, the results show that the detection effects of the six networks improve to different degrees. Taking the MSF-Net network as an example, the F1-score and IOU improved by 0.67% and 1.09%, respectively, compared with high-resolution images, and by 7.57% and 6.21% compared with multispectral images.

Mapping inundation extents in Poyang Lake area using Sentinel-1 data and transformer-based change detection method

Accurate and timely mapping of inundation extents during flood periods is essential for disaster evaluation and development of rescue strategies. With unique advantages over the optical sensors (e.g., little effect of clouds, and observations at day and night), Synthetic aperture radar (SAR) sensors provide an important data source for mapping inundation, particularly during flood periods. Freely available SAR images from Sentinel-1 have been increasingly used for many applications. This study applied an efficient transformer-based change detection method, bitemporal image transformer (BiT) with bitemporal Sentniel-1 images, to map inundation extents and evolution in Poyang Lake area in 2020. The transformer-based change detection method firstly adopted ResNet for high-level semantic features extraction, and applied a transformer mechanism to refine these features pixel-wise, followed by employing a FCN as the prediction head for generating the results of change detection. Besides, we constructed a water change detection dataset with spatial-and-temporal generalization from bitemporal Sentinel-1 images; this dataset consists of the seasonal variation water samples of Poyang Lake for years. We compared the results from the BiT method with other convolutional neural network (CNN) based methods (STANets and SNUNet). Mapped inundation extents were evaluated with the ground truth visually derived from high spatial resolution images. The evaluation showed the BiT method generated high accurate mapped inundation extents with the F1-score of 95.5%. The BiT model has proven its superior performance in detecting increased water. Based on the results of the BiT method, the variation of inundation extents in Poyang Lake during May-November 2020 was further analyzed. It was found that the water surface coverage of Poyang Lake is the smallest in late May; it gradually increased to the maximum on 14th July, and then began to stabilize and show a significant downward trend before November. The flood distribution map shows that cultivated land has been inundated with the largest area of approximately 600 km2.

A Novel End-to-End Unsupervised Change Detection Method with Self-Adaptive Superpixel Segmentation for SAR Images

Change detection (CD) methods using synthetic aperture radar (SAR) data have received significant attention in the field of remote sensing Earth observation, which mainly involves knowledge-driven and data-driven approaches. Knowledge-driven CD methods are based on the physical theoretical models with strong interpretability, but they lack the robust features of being deeply mined. In contrast, data-driven CD methods can extract deep features, but require abundant training samples, which are difficult to obtain for SAR data. To address these limitations, an end-to-end unsupervised CD network based on self-adaptive superpixel segmentation is proposed. Firstly, reliable training samples were selected using an unsupervised pre-task. Then, the superpixel generation and Siamese CD network were integrated into the unified framework to train them end-to-end until the global optimal parameters were obtained. Moreover, the backpropagation of the joint loss function promoted the adaptive adjustment of the superpixel. Finally, the binary change map was obtained. Several public SAR CD datasets were used to verify the effectiveness of the proposed method. The transfer learning experiment was implemented to further explore the ability to detect the changes and generalization performance of our network. The experimental results demonstrate that our proposed method achieved the most competitive results, outperforming seven other advanced deep-learning-based CD methods. Specifically, our method achieved the highest accuracy in OA, F1-score, and Kappa, and also showed superiority in suppressing speckle noise, refining change boundaries, and improving detection accuracy in a small area change.

Prior Semantic Information Guided Change Detection Method for Bi-temporal High-Resolution Remote Sensing Images

High-resolution remote sensing image change detection technology compares and analyzes bi-temporal or multitemporal high-resolution remote sensing images to determine the change areas. It plays an important role in land cover/use monitoring, natural disaster monitoring, illegal building investigation, military target strike effect analysis, and land and resource investigation. The change detection of high-resolution remote sensing images has developed rapidly from data accumulation to algorithm models because of the rapid development of technologies such as deep learning and earth observation in recent years. However, the current deep learning-based change detection methods are strongly dependent on large sample data, and the training model has insufficient cross-domain generalization ability. As a result, a prior semantic information-guided change detection framework (PSI-CD), which alleviates the change detection model’s dependence on datasets by making full use of prior semantic information, is proposed in this paper. The proposed method mainly includes two parts: one is a prior semantic information generation network that uses the semantic segmentation dataset to extract robust and reliable prior semantic information; the other is the prior semantic information guided change detection network that makes full use of prior semantic information to reduce the sample size of the change detection. To verify the effectiveness of the proposed method, we produced pixel-level semantic labels for the bi-temporal images of the public change detection dataset (LEVIR-CD). Then, we performed extensive experiments on the WHU and LEVIR-CD datasets, including comparisons with existing methods, experiments with different amounts of data, and ablation study, to show the effectiveness of the proposed method. Compared with other existing methods, our method has the highest IoU for all training samples and different amounts of training samples on WHU and LEVIR-CD, reaching a maximum of 83.25% and 83.80%, respectively.

Optimized Deep Belief Neural Network for Semantic Change Detection in Multi-Temporal Image

Nowadays, a massive quantity of remote sensing images is utilized from tremendous earth observation platforms. For processing a wide range of remote sensing data to be transferred based on knowledge and information of them. Therefore, the necessity for providing the automated technologies to deal with multi-spectral image is done in terms of change detection. Multi-spectral images are associated with plenty of corrupted data like noise and illumination. In order to deal with such issues several techniques are utilized but they are not effective for sensitive noise and feature correlation may be missed. Several machine learning-based techniques are introduced to change detection but it is not effective for obtaining the relevant features. In other hand, the only limited datasets are available in open-source platform; therefore, the development of new proposed model is becoming difficult. In this work, an optimized deep belief neural network model is introduced based on semantic modification finding for multi-spectral images. Initially, input images with noise destruction and contrast normalization approaches are applied. Then to notice the semantic changes present in the image, the Semantic Change Detection Deep Belief Neural Network (SCD-DBN) is introduced. This research focusing on providing a change map based on balancing noise suppression and managing the edge of regions in an appropriate way. The new change detection method can automatically create features for different images and improve search results for changed regions. The projected technique shows a lower missed finding rate in the Semantic Change Detection dataset and a more ideal rate than other approaches.

STCD-EffV2T Unet: Semi Transfer Learning EfficientNetV2 T-Unet Network for Urban/Land Cover Change Detection Using Sentinel-2 Satellite Images

Change detection in urban areas can be helpful for urban resource management and smart city planning. The effects of human activities on the environment and ground have gained momentum over the past decades, causing remote sensing data sources analysis (such as satellite images) to become an option for swift change detection in the environment and urban areas. We proposed a semi-transfer learning method of EfficientNetV2 T-Unet (EffV2 T-Unet) that combines the effectiveness of composite scaled EfficientNetV2 T as the first path or encoder for feature extraction and convolutional layers of Unet as the second path or decoder for reconstructing the binary change map. In the encoder path, we use EfficientNetV2 T, which was trained by the ImageNet dataset. In this research, we employ two datasets to evaluate the performance of our proposed method for binary change detection. The first dataset is Sentinel-2 satellite images which were captured in 2017 and 2021 in urban areas of northern Iran. The second one is the Onera Satellite Change Detection dataset (OSCD). The performance of the proposed method is compared with YoloX-Unet families, ResNest-Unet families, and other well-known methods. The results demonstrated our proposed method’s effectiveness compared to other methods. The final change map reached an overall accuracy of 97.66%.

CA-BIT: A Change Detection Method of Land Use in Natural Reserves

Natural reserves play a leading role in safeguarding national ecological security. Remote sensing change detection (CD) technology can identify the dynamic changes of land use and warn of ecological risks in natural reserves in a timely manner, which can provide technical support for the management of natural reserves. We propose a CD method (CA-BIT) based on the improved bitemporal image transformer (BIT) model to realize the change detection of remote sensing data of Anhui Natural Reserves in 2018 and 2021. Resnet34-CA is constructed through the combination of Resnet34 and a coordinate attention mechanism to effectively extract high-level semantic features. The BIT module is also used to efficiently enhance the original semantic features. Compared with the overall accuracy of the existing deep learning-based CD methods, that of CA-BIT is 98.34% on the natural protected area CD datasets and 99.05% on LEVIR_CD. Our method can effectively satisfy the need of CD of different land categories such as construction land, farmland, and forest land.

TChange: A Hybrid Transformer-CNN Change Detection Network

Change detection is employed to identify regions of change between two different time phases. Presently, the CNN-based change detection algorithm is the mainstream direction of change detection. However, there are two challenges in current change detection methods: (1) the intrascale problem: CNN-based change detection algorithms, due to the local receptive field limitation, can only fuse pairwise characteristics in a local range within a single scale, causing incomplete detection of large-scale targets. (2) The interscale problem: Current algorithms generally fuse layer by layer for interscale communication, with one-way flow of information and long propagation links, which are prone to information loss, making it difficult to take into account both large targets and small targets. To address the above issues, a hybrid transformer–CNN change detection network (TChange) for very-high-spatial-resolution (VHR) remote sensing images is proposed. (1) Change multihead self-attention (Change MSA) is built for global intrascale information exchange of spatial features and channel characteristics. (2) An interscale transformer module (ISTM) is proposed to perform direct interscale information exchange. To address the problem that the transformer tends to lose high-frequency features, the use of deep edge supervision is proposed to replace the commonly utilized depth supervision. TChange achieves state-of-the-art scores on the WUH-CD and LEVIR-CD open-source datasets. Furthermore, to validate the effectiveness of Change MSA and the ISTM proposed by TChange, we construct a change detection dataset, TZ-CD, that covers an area of 900 km2 and contains numerous large targets and weak change targets.

Bilateral Attention U-Net with Dissimilarity Attention Gate for Change Detection on Remote Sensing Imageries

This study proposes a bilateral attention U-Net with a dissimilarity attention gate (DAG) for change detection on remote sensing imageries. The proposed network is designed with a bilateral dissimilarity encoding for the DAG calculation to handle reversible input images, resulting in high detection rates regardless of the order of the two input images for change detection. The DAG exploits all the combinations of joint features to avoid spectral information loss fed into an attention gate on the decoder side. The effectiveness of the proposed method was evaluated on the KOMPSAT-3 satellite images dataset and the aerial change detection dataset (CDD). Its performance was better than that of conventional methods (specifically, U-Net, ATTUNet, and Modified-UNet++) as it achieved average F1-score and kappa coefficient (KC) values of 0.68 and 66.93, respectively, for the KOMPSAT-3 dataset. For CDD, it achieved F1-score and KC values of 0.70 and 68.74, respectively, which are also better values than those achieved by conventional methods. In addition, we found that the proposed bilateral attention U-Net can provide the same changed map regardless of whether the image order is reversed.

V-BANet: Land cover change detection using effective deep learning technique

Urban development alters landscapes, frequently degrading environmental services and quality of life. High-resolution remote sensing images provide a chance to detect subtle changes in land cover and can capture the features of a ground object. However, traditional approaches usually experience difficulties when processing large and quickly expanding datasets, low levels of automation, limited computational efficiency, and inconsistent identification accuracies and standards brought on by inconsistent operators. Conducting change detection in a more accurate, automated, and standardized manner has become crucial and increasingly difficult due to the quick collection of remote sensing data. Therefore, in this paper, V-Net and Bilateral Attention Network (V-BANet) based deep learning is implemented to segment the landscapes and extract the features from the images. Initially, the bi-temporal images are segmented using V-Net to independently identify the objects in each image. Then spatial and channel attention blocks are employed in Bilateral Attention Network to learn more discriminative features from the images. Finally, the features' relationships are discovered by contrasting the original feature map in one image with the updated feature map in the other. Objective and subjective experiments are performed on a public bi-temporal high-resolution ONERA Satellite Change Detection (OSCD) dataset and the LEVIR-CD dataset. Moreover, the proposed approach reached an accuracy of 99.29% and IoU of 98.31% with the OSCD Dataset and 99.42% accuracy and 98.83% IoU with the LEVIR-CD Dataset. The experimental outcomes with each specified dataset demonstrated that the suggested methodology outperformed several state-of-the-art techniques and produced superior results.

HMLNet: a hierarchical metric learning network with dual attention for change detection in high-resolution remote sensing images

ABSTRACT Change detection (CD) in high-resolution remote sensing images (RSIs) can be regarded as a binary visual recognition problem. Metric learning (ML) is a reliable method to determine pixel class attributes based on discriminative distance function between learnable image features. However, most related works learn discriminative distance functions in single-scale feature pairs, which suffer from slow convergence and poor local optima, partially due to that the loss function employs only large-scale feature samples while not interacting with the other scale features. Furthermore, more effective features are a prerequisite for improving the performance of ML-based CD. Hence, we propose a novel hierarchical metric learning network (HMLNet) with dual attention for CD in RSIs, where the key point is that hierarchical metric learning is performed in an ensemble manner to improve detection accuracy and accelerate model convergence. Specifically, based on the features extracted from the encoder-decoder backbone, we construct a feature pyramid to handle the complex details of objects at various scales in RSIs, and then perform metric learning between the paired pyramid features at the same scale. In addition, the dual-attention module is proposed to enhance the internal consistency of changed objects and effectively obtain more detailed information by acting on multi-scale pyramid features. Extensive experiments on the two public RSIs CD datasets, and the results demonstrate that the proposed HMLNet can accurately locate changed objects, which consistently outperforms the state-of-the-art CD competitors.

TSCNet: Topological Structure Coupling Network for Change Detection of Heterogeneous Remote Sensing Images

With the development of deep learning, convolutional neural networks (CNNs) have been successfully applied in the field of change detection in heterogeneous remote sensing (RS) images and achieved remarkable results. However, most of the existing methods of heterogeneous RS image change detection only extract deep features to realize the whole image transformation and ignore the description of the topological structure composed of the image texture, edge, and direction information. The occurrence of change often means that the topological structure of the ground object has changed. As a result, these algorithms severely limit the performance of change detection. To solve these problems, this paper proposes a new topology-coupling-based heterogeneous RS image change detection network (TSCNet). TSCNet transforms the feature space of heterogeneous images using an encoder–decoder structure and introduces wavelet transform, channel, and spatial attention mechanisms. The wavelet transform can obtain the details of each direction of the image and effectively capture the image’s texture features. Unnecessary features are suppressed by allocating more weight to areas of interest via channels and spatial attention mechanisms. As a result of the organic combination of a wavelet, channel attention mechanism, and spatial attention mechanism, the network can focus on the texture information of interest while suppressing the difference of images from different domains. On this basis, a bitemporal heterogeneous RS image change detection method based on the TSCNet framework is proposed. The experimental results on three public heterogeneous RS image change detection datasets demonstrate that the proposed change detection framework achieves significant improvements over the state-of-the-art methods.

STCD: efficient Siamese transformers-based change detection method for remote sensing images

ABSTRACT Remote sensing Change Detection (CD) involves identifying changing regions of interest in bi-temporal remote sensing images. CD technology has rapidly developed in recent years through the powerful learning ability of Convolutional Neural Networks (CNN), affording complex feature extraction. However, the local receptive fields in the CNN limit modeling long-range contextual relationships in semantic changes. Therefore, this work explores the great potential of Siamese Transformers in CD tasks and proposes a general CD model entitled STCD that relies on Swin Transformers. In the encoding process, pure Transformers without CNN are used to model the long-range context of semantic tokens, reducing computational overhead and improving model efficiency compared to current methods. During the decoding process, the 3D convolution block obtains the changing features in the time series and generates the predicted change map in the deconvolution layer with axial attention. Extensive experiments on three binary CD datasets and one semantic CD dataset demonstrate that the proposed STCD model outperforms several popular benchmark methods considering performance and the required parameters. Among the STCD variants, the F1-Score of the Base-STCD on the three binary CD datasets LEVIR, DSIFN, and SVCD reached 89.85%, 54.72%, and 93.75%, respectively, and the mF1-Score and mIoU on the semantic CD dataset SECOND were 75.60% and 66.19%.

Multi-Task Learning for Building Extraction and Change Detection from Remote Sensing Images

Building extraction (BE) and change detection (CD) from remote sensing (RS) imagery are significant yet highly challenging tasks with substantial application potential in urban management. Learning representative multi-scale features from RS images is a crucial step toward practical BE and CD solutions, as in other DL-based applications. To better exploit the available labeled training data for representation learning, we propose a multi-task learning (MTL) network for simultaneous BE and CD, comprising the state-of-the-art (SOTA) powerful Swin transformer as a shared backbone network and multiple heads for predicting building labels and changes. Using the popular CD dataset the Wuhan University building change detection dataset (WHU-CD), we benchmarked detailed designs of the MTL network, including backbone and pre-training choices. With a selected optimal setting, the intersection over union (IoU) score was improved from 70 to 81 for the WHU-CD. The experimental results of different settings demonstrated the effectiveness of the proposed MTL method. In particular, we achieved top scores in BE and CD from optical images in the 2021 Gaofen Challenge. Our method also shows transferable performance on an unseen CD dataset, indicating high label efficiency.

Mining Joint Intraimage and Interimage Context for Remote Sensing Change Detection

Recent deep learning methods for change detection focus on excavating more discriminative context within individual images. However, due to seasonal change, noise, and so on, the appearance of objects tends to be more heterogeneous among various scenes. Consequently, the above intra-image context is inadequate to represent specific-category objects and pseudo changes would be inevitable in detection results. To deal with this issue, we propose a context aggregation network (CANet) to mine inter-image context over all training images for further enhancing intra-image context. Specifically, a Siamese network attached with temporal attention modules is served as a feature encoder to extract multi-scale temporal features from bitemporal images. Then, a context extraction module is devised to capture long-range spatial-channel context within individual images. Meanwhile, context representations of underlying categories in the scene are inferred using all training images in an unsupervised manner. Finally, these two kinds of contextual information are aggregated to one which is subsequently fed into a multi-scale fusion module to produce the detection map. CANet is compared with several state-of-the-art methods on three benchmark datasets, including the season-varying change detection (SVCD) dataset, the Sun Yat-sen University change detection (SYSU-CD) dataset, and the Learning Vision and Remote Sensing Laboratory building change detection (LEVIR-CD) dataset. It is demonstrated that our method outperforms all comparison methods in terms of F1, overall accuracy (OA), and Intersection-of-Union (IoU). The results of CANet on three datasets are available at https://github.com/NuistZF/CANet-for-change-detection and codes will be public soon.

Change Detection on Remote Sensing Images Using Dual-Branch Multilevel Intertemporal Network

Change detection (CD) of remote sensing (RS) images is mushrooming up accompanied by the on-going innovation of convolutional neural networks (CNNs). Yet with the high-speed technology upgrade, the obstacle that identifies unbalanced variations in foreground–background categories still lies on the table, especially in cases with limited samples and massive interference such as seasonal turnover, illumination intensity, and building reformation. Moreover, to date, neither of the off-the-shelf methods probes the feasibility of direct interaction between bitemporal images before accessing difference features. In this article, we propose a dual-branch multilevel intertemporal network (DMINet) to efficiently and effectively derive the change representations. Specifically, by unifying self-attention (SelfAtt) and cross-attention (CrossAtt) in a single module, we present an intertemporal joint-attention (JointAtt) block to steer the global feature distribution of each input, motivating information coupling between intralevel representations and meanwhile suppressing the task-irrelevant interferences. In addition, centering more on the detection of difference features, a reliable architecture is designed by spotlighting two concerns, i.e., the difference acquisition using subtraction and concatenation as well as the multilevel difference aggregation using incremental feature alignment. Based on a naive backbone without sophisticated structures, i.e., ResNet18, our model outperforms other state-of-the-art (SOTA) methods on four CD datasets, especially in cases with rarely samples. Moreover, the achievement is attained with light overheads.

A Triple-Stream Network With Cross-Stage Feature Fusion for High-Resolution Image Change Detection

Change detection (CD) based on high-resolution remote sensing images can be used to monitor land cover changes, which is an important and challenging topic in the remote sensing field. In recent years, with the development of deep learning, CD methods based on deep learning have achieved good results in the field of CD. However, most current CD methods use single- or dual-stream networks to extract change features, which is insufficient to extract and learn bitemporal change information thoroughly. This article proposes a triple-stream network (TSNet) with cross-stage feature fusion for CD in high-resolution bitemporal remote sensing images. First, to obtain highly representative deep features in the original image, we perform feature extraction on bitemporal remote sensing images and their concatenated image with a dual-stream encoder and a single-stream encoder, respectively. Then, the bitemporal multiscale features extracted by the dual-stream encoder are input into a multistage bidirectional convolutional gated recurrent unit (MSBC_GRU) feature fusion module, allowing the network to learn the change information in a cross-stage manner. In addition, we use a dual-channel attention module to fuse the features extracted by dual- and single-stream encoders, improving the network’s ability to discriminate changed features. The effectiveness of TSNet is demonstrated with three publicly available CD datasets. The extensive experimental results demonstrate that the proposed method achieves the state-of-the-art CD performance on the above three datasets.

HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images

Benefiting from the developments in deep learning technology, deep learning-based algorithms employing automatic feature extraction have achieved remarkable performance on the change detection (CD) task. However, the performance of existing deep learning-based CD methods is hindered by the imbalance between changed and unchanged pixels. To tackle this problem, a progressive foreground-balanced sampling (PFBS) strategy on the basis of not adding change information is proposed to help the model accurately learn the features of the changed pixels during the early training process and thereby improve detection performance. Furthermore, we design a discriminative Siamese network, Hierarchical Attention Network (HANet), which can integrate multi-scale features and refine detailed features. The main part of HANet is the HAN module, which is a lightweight and effective self-attention mechanism. Extensive experiments and ablation studies on two CD datasets with extremely unbalanced labels validate the effectiveness and efficiency of the proposed method. Our model is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ChengxiHAN/HANet-CD</uri> .

Change Detection of Open-Pit Mine Based on Siamese Multiscale Network

Automatic change detection of open-pit mines from high-resolution remote sensing images is of great significance for the mining and management of mineral resources. For this purpose, we propose a siamese multiscale change detection network (SMCDNet) with an encoder-decoder structure. First, the multiscale low-level and high-level features of the bi-temporal image are extracted by a siamese network. Second, a multilevel feature absolute difference (MFAD) module is proposed to fuse the low-level and high-level change features. Finally, convolution and up-sampling operations are used to recover the details of the changed areas. A self-made open-pit mine change detection (OMCD) dataset is employed to conduct experiments. Experimental results have demonstrated that the proposed method is superior to the comparison networks. <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F1$ </tex-math></inline-formula> - score of 88.13% is achieved by the proposed SMCDNet. The OMCD dataset produced in this study has been made public at the following link: <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://figshare.com/s/ae4e8c808b67543d41e9</uri> .

SSCFNet: A Spatial-Spectral Cross Fusion Network for Remote Sensing Change Detection

Convolutional Neural Networks(CNNs) are data-driven methods that automatically extract the rich information embedded in remote sensing images. However, most current deep learning-based remote sensing image change detection methods prioritize high-level semantic features, while not enough attention is given to low-level semantic features, resulting in the loss of edges and details of the change region. To address this problem, this paper constructs a spatial-spectral cross fusion network SSCFNet, divided into three modules: a feature extractor network module, a combined enhancement module, and a semantic cross-fusion module. A new combined enhancement strategy is proposed to construct several semantic feature blocks in the combined enhancement module. Different convolution operations are applied to the newly constructed semantic feature blocks in the semantic cross fusion module, and the obtained semantic features at various levels are cross-fused. Experiments show that the proposed SSCFNet outperforms the other six state-of-the-art methods on four publicly available remote sensing image change detection datasets.