Image Change Detection Research Articles

An Improved Method for Human Activity Detection with High-Resolution Images by Fusing Pooling Enhancement and Multi-Task Learning

Deep learning has garnered increasing attention in human activity detection due to its advantages, such as not relying on expert knowledge and automatic feature extraction. However, the existing deep learning-based approaches are primarily confined to recognizing specific types of human activities, which hinders scientific decision-making and comprehensive environmental protection. Therefore, there is an urgent need to develop a deep learning model to address multiple-type human activity detection with finer-resolution images. In this study, we proposed a new multi-task learning model (named PE-MLNet) to simultaneously achieve change detection and land use classification in GF-6 bitemporal images. Meanwhile, we also designed a pooling enhancement module (PEM) to accurately capture multi-scale change details from the bitemporal feature maps through combining differencing and concatenating branches. An independent annotated dataset at Yellow River Delta was taken to examine the effectiveness of PE-MLNet. The results showed that PE-MLNet exhibited obvious improvements in both detection accuracy and detail handling compared with other existing methods. Further analysis uncovered that the areas of buildings, roads, and oil depots has obviously increased, while the farmland and wetland areas largely decreased over the five years, indicating an expansion of human activities and their increased impacts on natural environments.

Spatial-spectral and channel-spectral differences integration network for remote sensing image change detection

Spatial-spectral and channel-spectral differences integration network for remote sensing image change detection

Remote Sensing Image Change Detection Based on Lightweight Transformer and Multi-Scale Feature Fusion

Remote Sensing Image Change Detection Based on Lightweight Transformer and Multi-Scale Feature Fusion

Hypergraph Self-Supervised Learning-Based Joint Spectral-Spatial-Temporal Feature Representation for Hyperspectral Image Change Detection

Hypergraph Self-Supervised Learning-Based Joint Spectral-Spatial-Temporal Feature Representation for Hyperspectral Image Change Detection

Remote sensing image change detection based on swin transformer and cross-attention mechanism

Remote sensing image change detection based on swin transformer and cross-attention mechanism

An UNet3+ Network based on global pyramid aggregation for change detection in optical remote-sensing images

Change detection (CD) is a meaningful and challenging task for remote sensing (RS) image analysis. Deep learning (DL) based methods have shown great potential in change detection tasks, there are still two problems with existing deep learning methods such as CNN and Transformer: (1) They do not target different depths to extract global semantics in the network; (2) The increase in network depth will lead to uncertainty in the edge pixels of changing targets and the absence of small targets. First, to address this challenge and address these issues, this work proposes a global pyramid aggregation UNet3+ (GPA-UNet3+) change detection model, that uses UNet3+ as the backbone network and connects the encoder and decoder with a pyramid structure. Secondly, a Global Atrous Spatial Pooling Pyramid Module (GASPPM) is proposed. Refined features at different depths and aggregated them to enhance the network’s ability to extract global semantics. Finally, the Edge Enhancement Channel Attention Module (EECAM) is specifically proposed to alleviate the edge pixel uncertainty and spatial position information loss caused by the increase in network depth. Multiple experiments are conducted on two common change detection datasets and a real dataset. Extensive experimental results show that the proposed method outperforms other state-of-the-art methods, achieving the highest F1-score of 90.95%, 95.31%, and 88.32% on the LEVIR-CD dataset, SVCD dataset and Shizuishan Mining Area dataset, respectively.

HFNet: Semantic and Differential Heterogenous Fusion Network for Remote Sensing Image Change Detection

HFNet: Semantic and Differential Heterogenous Fusion Network for Remote Sensing Image Change Detection

DEST: Difference enhanced-Swin Transformer for remote sensing change detection

ABSTRACT Remote sensing (RS) change detection (CD) has recently achieved remarkable success thanks to convolutional neural networks (CNNs). However, due to the limited receptive fields of CNN models, existing methods are prone to generating pseudo detections or missed detections. In this letter, we propose a difference enhanced-Swin Transformer network (DEST) for accurate and robust change detection in RS images. First, we design a difference enhancement module (DEM) in the feature extraction stage to boost the feature learning of differences for dual-temporal images at each level. Second, to enlarge the receptive fields of networks and capture more changed details, we apply a Swin Transformer module to the difference features to model the global contextual information. Third, to avoid the semantic loss and simultaneously solve the problem of uneven contributions of features at different levels, we design a feature weight fusion module (FWFM) to effectively aggregate multi-level feature difference maps. Extensive experimental results on two publicly available benchmarks demonstrate that the proposed method is superior to some state-of-the-art change detection models.

A GAN-based cyclic iterative unsupervised change detection network

ABSTRACT Remote sensing image change detection has significant applications across various fields. In recent years, the powerful feature extraction capability of deep learning technology has introduced innovative approaches to change detection methodologies. However, the accuracy of convolutional neural network algorithms hinges heavily on labelled data, necessitating substantial manpower and resources to generate labelled samples. Therefore, this paper proposes an unsupervised change detection model called CIUCD. This model operates on the fundamental premise of unsupervised change detection, employing a generator and a segmenter for iterative training. During each iteration, the generator and segmenter update and optimize their parameters, with the segmenter leveraging the generated change images as labels for training purposes. This iterative labelling process circumvents the need for manually labelled data, thereby mitigating the difficulty of obtaining change detection labels for actual remote sensing images. To validate the efficacy of the proposed model, we conducted experiments using actual remotely sensed images from the 2023 Turkey earthquake and the 2022 Afghanistan earthquake events. The results show that our method enhances the F1, Pr, Re and OA by 5.98%, 2.05%, 11.82% and 8.50% (Turkey earthquake), and by 9.54%, 5.87%, 4.52% and 11.34% (Afghanistan earthquake), respectively, when compared to the unsupervised change detection algorithm KPCA-Mnet. Experiments on real remote sensing images of 1000 × 1000 pixels showed that the CIUCD algorithm not only accurately detect larger change areas but is also capable of identifying changes in subtle objects such as solar panels. Additionally, the CIUCD algorithm is resilient to natural environmental factors like the angle of illumination, enabling precise predictions of changes in the actual remote sensing images and yielding clearer detection results. The performance of the CIUCD algorithm remains outstanding even when applied to larger images with a resolution of 3000 × 3000 pixels.

Bidirectional-enhanced transformer network with channel weighting feature fusion for remote sensing image change detection

Bidirectional-enhanced transformer network with channel weighting feature fusion for remote sensing image change detection

Self-supervised image change detection method based on lightweight capsule network

In response to the significant impact of speckle noise on the accuracy of SAR image change detection, the high complexity of existing capsule network based image change detection methods, and the loss of a large amount of original image information in training samples, this paper proposes a self supervised image change detection method based on the Light Capsule Network (SCapsNet). First, the log ratio operator difference graph is generated, and the "pseudo label" of training samples with high confidence is obtained through the maximum inter class variance method and fuzzy C-means clustering method, which lays the foundation for self-supervised learning; Secondly, construct a three channel training sample based on the difference map of two temporal SAR images and logarithmic ratio operators to maximize the preservation of sample information; Then, SCapsNet is designed to extract training sample features through single scale convolution, and a single scale capsule network is used to mine spatial relationships between features; Finally, comparative experiments and ablation experiments were set up and tested on 5 real SAR Datasets. The experimental results show that the The advantage of this method is to improve the operational efficiency of the method while reducing model complexity, obtain stronger robust features, suppress the adverse impact of speckle noise on change detection performance, and improve change detection performance.

Detection of Floating Algae Blooms on Water Bodies Using PlanetScope Images and Shifted Windows Transformer Model

The increasing water temperature due to climate change has led to more frequent algae blooms and deteriorating water quality in coastal areas and rivers worldwide. To address this, we developed a deep learning-based model for identifying floating algae blooms using PlanetScope optical images and the Shifted Windows (Swin) Transformer architecture. We created 1,998 datasets from 105 scenes of PlanetScope imagery collected between 2018 and 2023, covering 14 water bodies known for frequent algae blooms. The methodology included data pre-processing, dataset generation, deep learning modeling, and inference result generation. The input images contained six bands, including vegetation indices such as the Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI), enhancing the model’s responsiveness to algae blooms. Evaluations were conducted using both single-period and multi-period datasets. The single-period model achieved a mean Intersection over Union (mIoU) between 72.18% and 76.47%, while the multi-period model significantly improved performance, with an mIoU of 91.72%. This demonstrates the potential of our model and highlights the importance of change detection in multi-temporal images for algae bloom monitoring. Additionally, the padding technique proposed in this study resolved the border issue that arises when mosaicking inference results from individual patches, providing a seamless view of the satellite scene.

MATNet: Multilevel attention-based transformers for change detection in remote sensing images

Remote sensing image change detection is crucial for natural disaster monitoring and land use change. As the resolution increases, the scenes covered by remote sensing images become more complex, and traditional methods have difficulties in extracting detailed information. With the development of deep learning, the field of change detection has new opportunities. However, existing algorithms mainly focus on the difference analysis between bi-temporal images, while ignoring the semantic information between images, resulting in the global and local information not being able to interact effectively. In this paper, we introduce a new transformer-based multilevel attention network (MATNet), which is capable of extracting multilevel features of global and local information, enabling information interaction and fusion, and thus modeling the global context more effectively. Specifically, we extract multilevel semantic features through the Transformer encoder, and utilize the Feature Enhancement Module (FEM) to perform feature summing and differencing on the multilevel features in order to better extract the local detail information, and thus better detect the changes in small regions. In addition, we employ a multilevel attention decoder (MAD) to obtain information in spatial and spectral dimensions, which can effectively fuse global and local information. In experiments, our method performs excellently on CDD, DSIFN-CD, LEVIR-CD, and SYSU-CD datasets, with F1 scores and OA reaching 95.67%∕87.75%∕90.94%∕86.82% and 98.95%∕95.93%∕99.11%∕90.53% respectively.

Siamese InternImage for Change Detection

For some time, CNN was the de facto state-of-the-art method in remote sensing image change detection. Although transformer-based models have surpassed CNN-based models due to their larger receptive fields, CNNs still retain their value for their efficiency and ability to extract precise local features. To overcome the limitations of the restricted receptive fields in standard CNNs, deformable convolution allows for dynamic adjustment of sampling locations in convolutional kernels, improving the network’s ability to model global contexts. InternImage is an architecture built upon deformable convolution as its foundational operation. Motivated by InternImage, in this paper, a CNN-based change detection vision foundation model is proposed. By introducing deformable convolution into Siamese InternImage architecture, the proposed CNN-based change detection vision foundation model is capable of capturing long-range dependencies and global information. A refinement block is utilized to merge local detail, where channel attention is incorporated. The proposed approach achieved excellent performance on the LEVIR-CD and WHU-CD datasets.

Fine-Grained High-Resolution Remote Sensing Image Change Detection by SAM-UNet Change Detection Model

Remote sensing image change detection is crucial for urban planning, environmental monitoring, and disaster assessment, as it identifies temporal variations of specific targets, such as surface buildings, by analyzing differences between images from different time periods. Current research faces challenges, including the accurate extraction of change features and the handling of complex and varied image contexts. To address these issues, this study proposes an innovative model named the Segment Anything Model-UNet Change Detection Model (SCDM), which incorporates the proposed center expansion and reduction method (CERM), Segment Anything Model (SAM), UNet, and fine-grained loss function. The global feature map of the environment is extracted, the difference measurement features are extracted, and then the global feature map and the difference measurement features are fused. Finally, a global decoder is constructed to predict the changes of the same region in different periods. Detailed ablation experiments and comparative experiments are conducted on the WHU-CD and LEVIR-CD public datasets to evaluate the performance of the proposed method. At the same time, validation on more complex DTX datasets for scenarios is supplemented. The experimental results demonstrate that compared to traditional fixed-size partitioning methods, the CERM proposed in this study significantly improves the accuracy of SOTA models, including ChangeFormer, ChangerEx, Tiny-CD, BIT, DTCDSCN, and STANet. Additionally, compared with other methods, the SCDM demonstrates superior performance and generalization, showcasing its effectiveness in overcoming the limitations of existing methods.

Frequency-driven transformer network for remote sensing image change detection

Frequency-driven transformer network for remote sensing image change detection

Damage Scene Change Detection Based on Infrared Polarization Imaging and Fast-PCANet

Change detection based on optical image processing plays a crucial role in the field of damage assessment. Although existing damage scene change detection methods have achieved some good results, they are faced with challenges, such as low accuracy and slow speed in optical image change detection. To solve these problems, an image change detection approach that combines infrared polarization imaging with a fast principal component analysis network (Fast-PCANet) is proposed. Firstly, the acquired infrared polarization images are analyzed, and pixel image blocks are extracted and filtered to obtain the candidate change points. Then, the Fast-PCANet network framework is established, and the candidate pixel image blocks are sent to the network to detect the change pixel points. Finally, the false-detection points predicted by the Fast-PCANet are further corrected by region filling and filtering to obtain the final binary change map of the damage scene. Comparisons with typical PCANet-based change detection algorithms are made on a dataset of infrared-polarized images. The experimental results show that the proposed Fast-PCANet method improves the PCC and the Kappa coefficient of infrared polarization images over infrared intensity images by 6.77% and 13.67%, respectively. Meanwhile, the inference speed can be more than seven times faster. The results verify that the proposed approach is effective and efficient for the change detection task with infrared polarization imaging. The study can be applied to the damage assessment field and has great potential for object recognition, material classification, and polarization remote sensing.

Feature-Selection-Based Unsupervised Transfer Learning for Change Detection from VHR Optical Images

Accurate understanding of urban land use change information is of great significance for urban planning, urban monitoring, and disaster assessment. The use of Very-High-Resolution (VHR) remote sensing images for change detection on urban land features has gradually become mainstream. However, most existing transfer learning-based change detection models compute multiple deep image features, leading to feature redundancy. Therefore, we propose a Transfer Learning Change Detection Model Based on Change Feature Selection (TL-FS). The proposed method involves using a pretrained transfer learning model framework to compute deep features from multitemporal remote sensing images. A change feature selection algorithm is then designed to filter relevant change information. Subsequently, these change features are combined into a vector. The Change Vector Analysis (CVA) is employed to calculate the magnitude of change in the vector. Finally, the Fuzzy C-Means (FCM) classification is utilized to obtain binary change detection results. In this study, we selected four VHR optical image datasets from Beijing-2 for the experiment. Compared with the Change Vector Analysis and Spectral Gradient Difference, the TL-FS method had maximum increases of 26.41% in the F1-score, 38.04% in precision, 29.88% in recall, and 26.15% in the overall accuracy. The results of the ablation experiments also indicate that TL-FS could provide clearer texture and shape detections for dual-temporal VHR image changes. It can effectively detect complex features in urban scenes.

Nighttime large-field video image change detection based on adaptive superpixel reconstruction and multi-scale singular value decomposition fusion

With the development of technology and the needs of social governance, surveillance equipment has been widely used. It is very mature to detect the change of surveillance video images in conventional scenes through video image change detection algorithms. However, in the large field of view environment at night, there are complex random noise and low signal-to-noise ratio in surveillance video images, which makes it difficult for people to find small moving targets. To this end, we propose a new method for nighttime large-field surveillance video image change detection based on adaptive superpixel reconstruction and multi-scale singular value decomposition fusion. The proposed method consists of two parts. On the one hand, an adaptive superpixel reconstruction method is used to reconstruct the two denoised difference images by selecting different segmentation parameters, and the edge information of the two reconstructed difference images is significantly enhanced. On the other hand, a multi-scale singular value decomposition fusion method is used to fuse the two difference images. The multi-scale singular value decomposition fusion obtains a robust difference image by selecting fusion rules at different scales and using the complementary information of different difference images, and the Fuzzy c-means (FCM) clustering algorithm is used to obtain the final changed image. Experimental results on a self-built nighttime large-field video image dataset with two resolutions show that the proposed method is superior to other algorithms in terms of detection accuracy and robustness.

Flood inundation monitoring using multi-source satellite imagery: a knowledge transfer strategy for heterogeneous image change detection

Flood emergency mapping is essential for flood management, often requiring near real-time extraction of large-scale flood extents by combining pre- and post-event multi-source remote sensing images. Pre-event optical imagery delineates the normal water extent, providing a benchmark for estimation of post-flood changes. Synthetic aperture radar (SAR) imagery provides rapid and accurate interpretation of flood inundation extent during the rainy period. Post-classification comparison is one of the fundamental methods for flood mapping of multi-source imagery, as the image characteristics of SAR and optical imagery are inherently different. However, the accuracy of flood mapping depends on the accuracy of water body delineation from single temporal imagery, which can lead to error propagation in flood extent determination. Change detection methods can extract flood extent directly from pre- and post-event imagery, but the models need to learn a consistent flood feature description between optical and SAR imagery from a limited flood dataset. Here, we propose an automatic method for flood inundation extent extraction using pre- and post-event multi-source imagery that requires only a small number of pseudo-change labels. The methodology adopts a pseudo-Siamese network framework as a Heterogeneous - Flood Inundation Extraction Network (H-FIENet), to detect flood extent between the pre‐ and post-event heterogeneous images. Spatially inconsistent multi-source pre- and post-event imagery was used to create a pseudo flood dataset, and this dataset was used to transfer water body feature knowledge from the pre-trained model to the flood extraction model using a cross-task knowledge transfer strategy. Pre- and post-event images from different satellite sources and different flood scenarios were used to evaluate the performance of H-FIENet. We found that: (1) The methodology produced an overall accuracy of over 0.94 for flood inundation extraction from multi-source heterogeneous pre- and post-event imagery. (2) H-FIENet can detect both expansion and recession of the flood extent using any dual-temporal imagery. Our work makes it possible to automate time-series flood monitoring from multi-source remote sensing imagery.