Remote Sensing Change Detection Research Articles

Cross attention is all you need: relational remote sensing change detection with transformer

ABSTRACT Deep-learning-based change detection methods have received wide attention, thanks to their strong capability in obtaining rich features from images. However, existing AI-based change detection (CD) methods largely rely on three functionality-enhancing modules, that is, semantic enhancement, attention mechanisms, and correspondence enhancement. The stacking of these modules leads to great model complexity. To unify these three modules into a simple pipeline, we introduce relational change detection transformer (RCDT), a novel and simple framework for remote sensing change detection tasks. The proposed RCDT consists of three major components, a weight-sharing Siamese Backbone to obtain bi-temporal features, a relational cross attention module (RCAM) that implements offset cross attention to obtain bi-temporal relation-aware features, and a features constrain module (FCM) to achieve the final refined predictions with high-resolution constraints. Extensive experiments on four different publicly available datasets suggest that our proposed RCDT exhibits superior change detection performance and great trade-off between performance and complexity compared with other competing methods. The theoretical, methodological, and experimental knowledge of this study is expected to benefit future change detection efforts that involve the cross attention mechanism.

SUPERVISED IMAGE CLASSIFICATION MODEL FOR CORAL BLEACHING DETECTION USING A BI-TEMPORAL SENTINEL-2 IMAGE STACK

Abstract. Coral reefs are among the most vulnerable ecosystems to coastal and land-based anthropogenic factors. Aside from sudden increase in sea temperatures, external factors such as local and regional disturbances are found to influence coral reef environments which often lead to bleaching events. According to the Status of Coral Reefs of the World: 2020 report, from 2009 to 2018, there has been a progressive loss of live corals at the global level which may be attributed to the increasing anthropogenic activities (Souter et al., 2021). Due to coral’s sensitivity to environmental stressors, it is significantly considered as an indicator for global climate conditions. In this regard, this study developed a remote sensing change detection technique to segment coral bleaching from satellite images. Using a bi-temporal image stack composed of Sentinel-2 images showing pre and post bleaching, a machine learning classification model was developed to capture typologies of changes visible between the two images which included bleaching. Random Forest (RF) algorithm was employed to classify changes. This model obtained overall accuracies and kappa statistics of 0.97 and 0.94 respectively with minimum consumer and producer accuracy of 0.91. Moreover, the identified changes showed 78% agreement with the in-situ data composed of 31 monitoring stations distributed around Sekisei Lagoon, Okinawa, Japan. This study demonstrated a promising potential of machine learning for change detection for coral bleaching monitoring.

Enhancing Adversarial Learning-Based Change Detection in Imbalanced Datasets Using Artificial Image Generation and Attention Mechanism

Deep Learning (DL) has become a popular method for Remote Sensing (RS) Change Detection (CD) due to its superior performance compared to traditional methods. However, generating extensive labeled datasets for DL models is time-consuming and labor-intensive. Additionally, the imbalance between changed and unchanged areas in object CD datasets, such as buildings, poses a critical issue affecting DL model efficacy. To address this issue, this paper proposes a change detection enhancement method using artificial image generation and attention mechanism. Firstly, the content of the imbalanced CD dataset is enhanced using a data augmentation strategy that synthesizes effective building CD samples using artificial RS image generation and building label creation. The created building labels, which serve as new change maps, are fed into a generator model based on a conditional Generative Adversarial Network (c-GAN) to generate high-resolution RS images featuring building changes. The generated images with their corresponding change maps are then added to the CD dataset to create the balance between changed and unchanged samples. Secondly, a channel attention mechanism is added to the proposed Adversarial Change Detection Network (Adv-CDNet) to boost its performance when training on the imbalanced dataset. The study evaluates the Adv-CDNet using WHU-CD and LEVIR-CD datasets, with WHU-CD exhibiting a higher degree of sample imbalance compared to LEVIR-CD. Training the Adv-CDNet on the augmented dataset results in a significant 16.5% F1-Score improvement for the highly imbalanced WHU-CD. Moreover, comparative analysis showcases the superior performance of the Adv-CDNet when complemented with the attention module, achieving a 6.85% F1-Score enhancement.

Multilevel feature aggregation and enhancement network for remote sensing change detection

Multilevel feature aggregation and enhancement network for remote sensing change detection

Wetness severity increases abrupt shifts in ecosystem functioning in arid savannas.

The accelerating pace of climate change has led to unprecedented shifts in surface temperature and precipitation patterns worldwide, with African savannas being among the most vulnerable regions. Understanding the impacts of these extreme changes on ecosystem health, functioning and stability is crucial. This paper focuses on the detection of breakpoints, indicative of shifts in ecosystem functioning, while also determining relevant ecosystem characteristics and climatic drivers that increase susceptibility to these shifts within the semi-arid to arid savanna biome. Utilising a remote sensing change detection approach and rain use efficiency (RaUE) as a proxy for ecosystem functioning, spatial and temporal patterns of breakpoints in the savanna biome were identified. We then employed a novel combination of survival analysis and remote sensing time series analysis to compare ecosystem characteristics and climatic drivers in areas experiencing breakpoints versus areas with stable ecosystem functioning. Key ecosystem factors increasing savanna breakpoint susceptibility were identified, namely higher soil sand content, flatter terrain and a cooler long-term mean temperature during the wet summer season. Moreover, the primary driver of changes in ecosystem functioning in arid savannas, as opposed to wetter tropical savannas, was found to be the increased frequency and severity of rainfall events, rather than drought pressures. This research highlights the importance of incorporating wetness severity metrics alongside drought metrics to comprehensively understand climate-ecosystem interactions leading to abrupt shifts in ecosystem functioning in arid biomes. The findings also emphasise the need to consider the underlying ecosystem characteristics, including soil, topography and vegetation composition, in assessing ecosystem responses to climate change. While this research primarily concentrated on the southern African savanna as a case study, the methodological robustness of this approach enables its application to diverse arid and semi-arid biomes for the assessment of climate-ecosystem interactions that contribute to abrupt shifts.

DTT-CGINet: A Dual Temporal Transformer Network with Multi-Scale Contour-Guided Graph Interaction for Change Detection

Deep learning has dramatically enhanced remote sensing change detection. However, existing neural network models often face challenges like false positives and missed detections due to factors like lighting changes, scale differences, and noise interruptions. Additionally, change detection results often fail to capture target contours accurately. To address these issues, we propose a novel transformer-based hybrid network. In this study, we analyze the structural relationship in bi-temporal images and introduce a cross-attention-based transformer to model this relationship. First, we use a tokenizer to express the high-level features of the bi-temporal image into several semantic tokens. Then, we use a dual temporal transformer (DTT) encoder to capture dense spatiotemporal contextual relationships among the tokens. The features extracted at the coarse scale are refined into finer details through the DTT decoder. Concurrently, we input the backbone’s low-level features into a contour-guided graph interaction module (CGIM) that utilizes joint attention to capture semantic relationships between object regions and the contour. Then, we use the feature pyramid decoder to integrate the multi-scale outputs of the CGIM. The convolutional block attention modules (CBAMs) employ channel and spatial attention to reweight feature maps. Finally, the classifier discriminates change pixels and generates the final change map of the difference feature map. Several experiments have demonstrated that our model shows significant advantages over other methods in terms of efficiency, accuracy, and visual effects.

CD-GAN: A robust fusion-based generative adversarial network for unsupervised remote sensing change detection with heterogeneous sensors

In the context of Earth observation, change detection boils down to comparing images acquired at different times by sensors of possibly different spatial and/or spectral resolutions or different modalities (e.g., optical or radar). Even when considering only optical images, this task has proven to be challenging as soon as the sensors differ by their spatial and/or spectral resolutions. This paper proposes a novel unsupervised change detection method dedicated to images acquired by such so-called heterogeneous optical sensors. It capitalizes on recent advances which formulate the change detection task into a robust fusion framework. Adopting this formulation, the work reported in this paper shows that any off-the-shelf network trained beforehand to fuse optical images of different spatial and/or spectral resolutions can be easily complemented with a network of the same architecture and embedded into an adversarial framework to perform change detection. A comparison with state-of-the-art change detection methods demonstrates the versatility and the effectiveness of the proposed approach.

A hybrid U‐shaped and transformer network for change detection in high‐resolution remote sensing images

AbstractDeep convolutional neural networks based remote sensing change detection has recently shown significant performance improvement. However, small region changes and global‐local features in high‐resolution remote sensing images are not fully explored. This paper introduces a hybrid U‐shaped and transformer network for change detection in high‐resolution remote sensing images. Specifically, a UNet++‐based backbone to facilitate feature learning across different scales. In addition, we introduce a transformer‐based feature fusion module for extracting long‐range dependencies, which can enhance the representation ability of the network. Furthermore, the introduced efficient channel attention mechanism can efficiently calibrate the feature representation and concentrate on more important feature information. Thanks to the above designs, the proposed method enjoys a strong ability to extract local and global features for remote sensing change detection. Extensive experimental results on different remote sensing images show that our method can achieve superior performance in comparison with state‐of‐the‐art change detection methods.

ChangeCLIP: Remote sensing change detection with multimodal vision-language representation learning

Remote sensing change detection (RSCD), which aims to identify surface changes from bitemporal images, is significant for many applications, such as environmental protection and disaster monitoring. In the last decade, driven by the wave of artificial intelligence, many change detection methods based on deep learning emerged and have achieved essential breakthroughs. However, these methods pay more attention to visual representation learning while ignoring the potential of multimodal data. Recently, the foundation vision-language model, i.e. CLIP, has provided a new paradigm for multimodal AI, demonstrating impressive performance on downstream tasks. Following this trend, in this study, we introduce ChangeCLIP, a novel framework that leverages robust semantic information from image-text pairs, specifically tailored for Remote Sensing Change Detection (RSCD). Specifically, we reconstruct the original CLIP to extract bitemporal features and propose a novel differential features compensation module to capture the detailed semantic changes between them. Besides, we proposed a vision-language-driven decoder by combining the results of image-text encoding with the visual features of the decoding stage, thereby enhancing the image semantics. The proposed ChangeCLIP achieved state-of-the-art IoU on 5 well-known change detection datasets, LEVIR-CD (85.20%), LEVIR-CD+ (75.63%), WHUCD (90.15%), CDD (95.87%) and SYSU-CD (71.41%). The code and the pretrained models of ChangeCLIP will be publicly available on https://github.com/dyzy41/ChangeCLIP.

Remote Sensing Change Detection With Bitemporal and Differential Feature Interactive Perception.

Recently, the transformer has achieved notable success in remote sensing (RS) change detection (CD). Its outstanding long-distance modeling ability can effectively recognize the change of interest (CoI). However, in order to obtain the precise pixel-level change regions, many methods directly integrate the stacked transformer blocks into the UNet-style structure, which causes the high computation costs. Besides, the existing methods generally consider bitemporal or differential features separately, which makes the utilization of ground semantic information still insufficient. In this paper, we propose the multiscale dual-space interactive perception network (MDIPNet) to fill these two gaps. On the one hand, we simplify the stacked multi-head transformer blocks into the single-layer single-head attention module and further introduce the lightweight parallel fusion module (LPFM) to perform the efficient information integration. On the other hand, based on the simplified attention mechanism, we propose the cross-space perception module (CSPM) to connect the bitemporal and differential feature spaces, which can help our model suppress the pseudo changes and mine the more abundant semantic consistency of CoI. Extensive experiment results on three challenging datasets and one urban expansion scene indicate that compared with the mainstream CD methods, our MDIPNet obtains the state-of-the-art (SOTA) performance while further controlling the computation costs.

Remote Sensing Change Detection With Transformers Trained From Scratch

Remote Sensing Change Detection With Transformers Trained From Scratch

A New Learning Paradigm for Foundation Model-Based Remote-Sensing Change Detection

A New Learning Paradigm for Foundation Model-Based Remote-Sensing Change Detection

Point Label Meets Remote Sensing Change Detection: A Consistency-Aligned Regional Growth Network

Point Label Meets Remote Sensing Change Detection: A Consistency-Aligned Regional Growth Network

MFDS-Net: Multi-Scale Feature Depth-Supervised Network for Remote Sensing Change Detection with Global Semantic and Detail Information

MFDS-Net: Multi-Scale Feature Depth-Supervised Network for Remote Sensing Change Detection with Global Semantic and Detail Information

Remote Sensing Change Detection Method Based on Dynamic Adaptive Focal Loss

Remote Sensing Change Detection Method Based on Dynamic Adaptive Focal Loss

3D Neighborhood Cross Differencing: A New Paradigm Serves Remote Sensing Change Detection

3D Neighborhood Cross Differencing: A New Paradigm Serves Remote Sensing Change Detection

LFHNet: Lightweight Full-Scale Hybrid Network for Remote Sensing Change Detection

LFHNet: Lightweight Full-Scale Hybrid Network for Remote Sensing Change Detection

Candidate-Aware and Change-Guided Learning for Remote Sensing Change Detection

Candidate-Aware and Change-Guided Learning for Remote Sensing Change Detection

UNet-Like Remote Sensing Change Detection: A review of current models and research directions

UNet-Like Remote Sensing Change Detection: A review of current models and research directions

Leveraging Diffusion Modeling for Remote Sensing Change Detection in Built-Up Urban Areas

Leveraging Diffusion Modeling for Remote Sensing Change Detection in Built-Up Urban Areas