Deep learning has achieved significant success in hyperspectral image super-resolution (HSISR) by leveraging advanced feature extraction techniques to reconstruct high-resolution images from low-resolution counterparts. However, existing methods predominantly utilize 2D/3D convolutions or Transformer architectures, which are often hindered by limited receptive fields, quadratic computational complexity, and inadequate fusion of spatial-spectral dependencies. To address these challenges, this paper proposes RWKVSR, a novel lightweight network that integrates a Receptance Weighted Key-Value (RWKV) architecture for efficient HSISR. The proposed RWKVSR comprises of three key components: (1) A linear-complexity RWKV module replacing quadratic self-attention, enabling efficient global spectral-spatial modeling; (2) A Spectral-Spatial Residual Module (SSRM) employing anisotropic, direction-separable 3D convolutions to hierarchically extract multi-scale features while enhancing local-global interactions; and (3) A Hyperspectral Frequency Loss (HFL) optimizing spectral consistency by prioritizing high-frequency structural alignment between reconstructed and ground-truth images in the frequency domain. Extensive experiments conducted on the CAVE and Harvard datasets demonstrate that RWKVSR outperforms the existing state-of-the-art methods, effectively balancing accuracy and efficiency, and providing a practical solution for high-quality HSI reconstruction. Our paper code is publicly available at https://github.com/backy-1/RWKVSR.git.

Urbanization advances at unprecedented rates, leading to negative environmental and societal impacts. Remote sensing can help mitigate these effects by supporting sustainable development strategies with accurate information on urban growth. Deep learning-based methods have achieved promising urban change detection results from optical satellite image pairs using convolutional neural networks (ConvNets), transformers, and a multi-task learning setup. However, bi-temporal methods are limited for continuous urban change detection, i.e., the detection of changes in consecutive image pairs of satellite image time series (SITS), as they fail to fully exploit multi-temporal data (> 2 images). Existing multi-temporal change detection methods, on the other hand, collapse the temporal dimension, restricting their ability to capture continuous urban changes. Additionally, multi-task learning methods lack integration approaches that combine change and segmentation outputs. To address these challenges, we propose a continuous urban change detection framework incorporating two key modules. The temporal feature refinement (TFR) module employs self-attention to improve ConvNet-based multi-temporal building representations. The temporal dimension is preserved in the TFR module, enabling the detection of continuous changes. The multi-task integration (MTI) module utilizes Markov networks to find an optimal building map time series based on segmentation and dense change outputs. The proposed framework effectively identifies urban changes based on high-resolution SITS acquired by the PlanetScope constellation (F1 score 0.551), Gaofen-2 (F1 score 0.440), and WorldView-2 (F1 score 0.543). Moreover, our experiments on three challenging datasets demonstrate the effectiveness of the proposed framework compared to bi-temporal and multi-temporal urban change detection and segmentation methods. Code is available on GitHub: https://github.com/SebastianHafner/ContUrbanCD.

Cloud mask underpins accurate precipitation nowcasting, which in turn is vital for understanding the hydrological cycle, supporting disaster prevention, solar energy forecasting and transportation. However, cloud mask nowcasting remains challenging because meteorological data exhibit irregular temporal and spatial variations, including fine-scale structures, and often suffer from highly skewed precipitation intensity distributions. Existing methods struggle to capture complex spatiotemporal dynamics and preserve fine-scale structures due to limitations in handling sparse data from numerical weather prediction (NWP) model. To address these issues, we propose an asymmetric dual-branch non-causal mamba U-Net (ADNM-UNet) featuring three key components: (1) The Asymmetric Dual-branch Non-causal Mamba (ADNM) implements a novel asymmetric bidirectional modeling framework that resolves directional bias in conventional Mamba architectures. This design preserves precise cloud boundary delineation while capturing long-range spatiotemporal dependencies in sparse data from NWP. (2) The Multi-scale Attention Enhancement Module (MAEM) enhances discriminative feature representation and suppresses spectral redundancy through anisotropic convolution kernels and hybrid pooling. This mechanism significantly improves edge retention in precipitation systems while attenuating atmospheric noise interference. (3) Complementing these advancements, the Wavelet Decomposition and Fusion Module (WDFM) maintains cloud contour integrity across scales through multiresolution decomposition. Extensive experiments demonstrate that ADNM-UNet outperforms existing methods across all metrics, achieving 27.96% improvement in CSI and 22.89% in HSS for metrics over the best performing baseline models at high intensity scenarios. Our project is open source and available on GitHub at: https://github.com/kanyu369/ADNM-UNet.

Precipitation nowcasting is a challenging task in the context of global climate variability. However, existing radar echo or numerical weather prediction data methods lack deep modeling between echograms at different time points and have difficulty in accurately capturing irregular variations and small-scale features of precipitable clouds. To address these challenges, we propose for the first time a U-Net short-term precipitation prediction network based on vision Mamba technology for the precipitation nowcasting mission, named Mamba-UNet. Specifically, Mamba-UNet includes two core modules: the dual-branch Mamba fusion module and the multiscale spatiotemporal attention module. Finally, we propose a loss function namely dynamic quantile weighted loss to address the problem of imbalanced precipitation intensity distribution. To validate the capacity of the proposed method, the experiments were conducted on an analysis dataset of the local analysis and prediction system model in a specific region of East China. The experimental results show that our proposed Mamba-UNet has the best overall performance.

This study presents a Conditional Denoising Diffusion Probabilistic Model (CDDPM) for Synthetic Aperture Radar (SAR) to Optical image translation, specifically focusing on areas affected by wildfires. Given the escalating wildfire incidences due to climate change, satellite monitoring is an essential tool for firefighting efforts. Although Sentinel-2 imagery provides accurate data for burned area mapping, its effectiveness is strongly influenced by cloud cover. While this obstacle is mitigated by Sentinel-1, which can conduct surface measurements even during sub-optimal visibility conditions, its inherent noise instead makes segmentation difficult. Our pro-posed model utilizes a multi-image, multi-temporal approach that integrates prior Sentinel-1/2 data as well as current Sentinel-1 data for context-aware output. After translation, a U-Net is trained to determine the burned area. For enhancing the efficacy of the burned area prediction, our diffusion model simultaneously learns mask generation and translation tasks. The model, trained on a dataset including 541 wildfire events in Canada from 2017 to 2021, significantly outperforms existing methods in segmentation metrics.

Floods are one of the most destructive disasters worldwide and although they largely happen in rural, ruther than in urban areas, it is in the urban areas that substantial destruction of infrastructures is observed. Thus, cost effective methods to monitor flood damage and extent are required. In this paper, we investigate the implementation of U-Net on satellite and drone image dataset such as xBD and EDDA for building damage assessment in Mozambique. The recently published dataset EDDA was created by the National Institute for Disaster Management (INGD) and comprises drone imagery of Beira, in Mozambique. Using them, we obtained a dice score of 0.76 on building localization (BL) and mean intersection over the union (mIoU) of 0.54 on damage classification (DC). These are promising results considering that many datasets lack detailed information on African buildings. We also use some pre-trained models models such as ResNet for BL and DC.

Monitoring wildfires has become increasingly critical due to the sharp rise in wildfire incidents in recent years. Optical satellites like Sentinel-2 and Landsat are extensively utilized for mapping burned areas. However, the effectiveness of optical sensors is compromised by clouds and smoke, which obstruct the detection of burned areas. As a result, there is growing interest in satellites equipped with Synthetic Aperture Radar (SAR), which can penetrate clouds and smoke. Previous studies have investigated the potential of Sentinel-1 and RADARSAT-1/-2 C-band SAR for burned area mapping. However, to the best of our knowledge, no published research is found using RADARSAT Constellation Mission (RCM) SAR data for this purpose. The objective of this study is to investigate RCM SAR data for burned area mapping using deep learning. We propose a deep-learning-based processing pipeline specifically for RCM data. The deep learningbased pipeline utilizes the U-Net as the segmentation model. The training samples are preprocessed to generate log-ratio images based on the same beam mode. The training labels are generated from binarized log-ratio images and Sentinel2 polygons. Our results demonstrate that RCM data can effectively detect burned areas in the 2023 Canadian Wildfires, achieving an F1 Score of 0.765 and an IoU Score of 0.620 for the study area in Alberta, and an F1 Score of 0.655 and an IoU Score of 0.487 for the study area in Quebec. These results indicate the promising potential of RCM data in wildfire monitoring.

Cross-modal hashing plays a pivotal role in large-scale remote sensing (RS) ship image retrieval. RS ship images often exhibit similar overall appearance with subtle differences. Existing hashing methods typically employ feature non-interaction strategies to generate common hash codes, which may not effectively capture the correlations between cross-modal ship images to reduce intermodality discrepancies. To address this issue, we propose a novel cross-modal hashing approach based on feature semi-interaction and semantic ranking (FSISR) for RS ship image retrieval. Our FSISR approach not only captures intricate correlations between different ship image modalities, but also enables the construction of hash tables for large-scale retrieval. FSISR comprises a feature semi-interaction module and a semantic ranking objective function. The semi-interaction module utilizes clustering centers from one modality to learn the correlations between two modalities and generate robust shared representations. The objective function optimizes these representations in a common Hamming space, consisting of a shared semantic alignment loss and a margin-free ranking loss. The alignment loss employs a shared semantic layer to preserve label-level similarity, while the ranking loss incorporates hard examples to establish a margin-free loss that captures similarity ranking relationships. We evaluate the performance of our method on benchmark datasets and demonstrate its effectiveness for cross-modal RS ship image retrieval.https://github.com/sunyuxi/FSISR.

Hyperspectral image (HSI) classification is an essential task in remote sensing with substantial practical significance. However, most existing convolutional neural network (CNN)-based classification methods focus only on local spatial features while neglecting global spectral dependencies. Meanwhile, Transformer-based methods exhibit robust capabilities for global spectral feature modeling but struggle to extract local spatial features effectively. To fully exploit the local spatial feature extraction capabilities of CNN-based networks and the global spectral feature extraction capabilities of Transformer-based networks, this paper proposes a dual-branch convolutional Transformer method with efficient interactive self-attention for hyperspectral image classification, namely the dual-branch convolutional Transformer network (DCTN), which can aggregate local and global spatial-spectral features fully. Specifically, DCTN includes two core modules: the spatial-spectral fusion projection module and the efficient interactive self-attention module. The former utilizes 3D convolution with adaptive pooling and 2D group convolution with residual connection to parallel extract fused and grouped spatial-spectral features, respectively. The latter performs efficient interactive self-attention across height, width and spectral dimensions, enabling deep fusion of spatial-spectral features. Extensive experiments on three real HSI datasets demonstrate that the proposed DCTN method outperforms existing classification methods, yielding state-of-the-art classification performance. The code is available at https://github.com/AllFever/DeepHyperX-DCTN for reproducibility.

Deep learning plays a crucial role in hyperspectral image (HSI) classification, with the Transformer being highly favored by researchers due to its exceptional ability to model long-range dependencies. However, the Transformer necessitates a substantial amount of labeled training samples to train its numerous parameters, exacerbating the challenge of training an effective HSI classification Transformer model, particularly given the inherent scarcity of HSI data. Therefore, we propose a novel method for HSI classification, termed multiscale spatial-spectral masked Transformer with local contrastive learning (MSMT-LCL). This method consists of two stages: self-supervised pretraining and supervised fine-tuning. Initially, we utilize the multiscale augmented feature mapping module (MAFM) to project original HSI data into two mixed-scale feature maps, which are then separately fed into two masked Transformer branches for reconstruction. To facilitate the model in learning the dependency relationships between central pixel land-cover information and neighboring land cover, we introduce a novel mask strategy based on center-patch. Furthermore, in the pretraining stage, we integrate local contrastive learning (LCL) to enable the model to focus on local center information at varying scales. Upon completion of pretraining, the network undergoes fine-tuning to obtain feature maps at two different scales. Subsequently, we devise a novel adaptive multiscale feature fusion module (AMFM) to adaptively aggregate these two features and produce the final classification results. Extensive experiments on three real datasets demonstrate the superiority of our proposed MSMT-LCL method over several state-of-the-art HSI classification methods.

This paper proposes a novel multi-temporal urban mapping approach using multi-modal satellite data from the Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 MultiSpectral Instrument (MSI) missions. In particular, it focuses on the problem of a partly missing optical modality due to clouds. The proposed model utilizes two networks to extract features from each modality separately. In addition, a reconstruction network is utilized to approximate the optical features based on the SAR data in case of a missing optical modality. Our experiments on a multi-temporal urban mapping dataset with Sentinel-1 SAR and Sentinel-2 MSI data demonstrate that the proposed method outperforms a multi-modal approach that uses zero values as a replacement for missing optical data, as well as a uni-modal SAR-based approach. Therefore, the proposed method is effective in exploiting multi-modal data, if available, but it also retains its effectiveness in case the optical modality is missing.

Accurate estimation of building heights is essential for urban planning, infrastructure management, and environmental analysis. In this study, we propose a supervised Multimodal Building Height Regression Network (MBHR-Net) for estimating building heights at 10m spatial resolution using Sentinel-1 (S1) and Sentinel-2 (S2) satellite time series. S1 provides Synthetic Aperture Radar (SAR) data that offers valuable information on building structures, while S2 provides multispectral data that is sensitive to different land cover types, vegetation phenology, and building shadows. Our MBHR-Net aims to extract meaningful features from the S1 and S2 images to learn complex spatio-temporal relationships between image patterns and building heights. The model is trained and tested in 10 cities in the Netherlands. Root Mean Squared Error (RMSE), Intersection over Union (IOU), and R-squared (R2) score metrics are used to evaluate the performance of the model. The preliminary results (3.73m RMSE, 0.95 IoU, 0.61 R2) demonstrate the effectiveness of our deep learning model in accurately estimating building heights, showcasing its potential for urban planning, environmental impact analysis, and other related applications.

Change detection using earth observation data plays a vital role in quantifying the impact of disasters in affected areas. While data sources like Sentinel-2 provide rich optical information, they are often hindered by cloud cover, limiting their usage in disaster scenarios. However, leveraging pre-disaster optical data can offer valuable contextual information about the area such as landcover type, vegetation cover, soil types, enabling a better understanding of the disaster’s impact. In this study, we develop a model to assess the contribution of pre-disaster Sentinel-2 data in change detection tasks, focusing on disaster-affected areas. The proposed Context-Aware Change Detection Network (CACDN) utilizes a combination of pre-disaster Sentinel-2 data, pre and post-disaster Sentinel-1 data and ancillary Digital Elevation Models (DEMs) data. The model is validated on flood and landslide detection and evaluated using three metrics: Area Under the Precision-Recall Curve (AUPRC), Intersection over Union (IoU), and mean IoU. The preliminary results show significant improvement (4%, AUPRC, 3-7% IoU, 3-6% mean IoU) in model’s change detection capabilities when incorporated with pre-disaster optical data reflecting the effectiveness of using contextual information for accurate flood and landslide detection.

Satellite remote sensing provides a cost-effective way for monitoring wildfires on a large scale, and the continuous observations and measurements have made remote sensing a primary source of unlabelled big data. Supervised deep learning has shown great success in various remote sensing applications, but it heavily relies on high-quality labels. However, burned area labels are only available for a small part of the world, supervised deep learning from limited labelled data has poor generalization performance across geographical regions and climate zones. Different satellite sensors represent the same physical objects in various ways, while multi-source satellite data often exhibits a combination of common and complementary information, such as optical and radar data. The common information makes it possible to exploit huge amounts of unlabelled multi-source data in model training through consistency regularization between multi-source predictions. In this work, we adopted an unsupervised geospatial domain adaptation (GDA) framework based Dual Stream U-Net model, which combines the supervised loss and unsupervised multi-modal consistency regularization to exploit both labelled and unlabelled multi-model data for model training in a semi-supervised learning manner. The experimental results demonstrate that unsupervised GDA has better generalization performance across geographical regions than fully supervised learning.

The Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-orbiting Partnership (S-NPP) satellite has been used for the early detection and daily monitoring of active wildfires. How to effectively segment the active fire pixels from VIIRS image time-series in a reliable manner remains a challenge because of the low precision associated with high recall using automatic methods. For active fire detection, multi-criteria thresholding is often applied to both low-resolution and mid-resolution Earth observation images. Deep learning approaches based on Convolutional Neural Networks are also well-studied on mid-resolution images. However, ConvNet-based approaches have poor performance on low-resolution images because of the coarse spatial features. On the other hand, the high temporal resolution of VIIRS images highlights the potential of using sequential models for active fire detection. Transformer networks, a recent deep learning architecture based on self-attention, offer hope as they have shown strong performance on image segmentation and sequential modelling tasks within computer vision. In this research, we propose a Transformer-based solution to segment active fire pixels from the VIIRS time-series. The solution feeds a time-series of tokenized pixels into a Transformer network to identify active fire pixels at each timestamp and achieves a significantly higher F1-Score than prior approaches for active fires within the study areas in California, New Mexico, and Oregon in the US, and in British Columbia and Alberta in Canada, as well as in Australia and Sweden.

In this study, a Semi-Supervised Learning (SSL) method for improved urban change detection from bi-temporal image pairs is presented. The proposed method employs a Dual-Task Siamese Difference network that not only predicts changes with the difference decoder, but also segments buildings for both images with a semantic decoder. First, the architecture was modified to produce a second change prediction derived from the semantic predictions. Second, SSL was used to improve supervised change detection. For unlabeled data, we designed a loss that encourages the network to predict consistent changes across the two change outputs. The proposed method was tested on urban change detection using the SpaceNet7 dataset. SSL achieved improved results compared to three fully supervised benchmarks. Code for the paper is available at https://github.com/SebastianHafner/SiameseSSL.git.

Climate change by anthropogenic warming leads to increases in dry fuels and promotes forest fires. Multispectral images' quality is easily affected by poor atmospheric conditions. SAR satellite sensors can penetrate through clouds and image day and night. However, the burned area mapping methods widely used for optical data are not feasible to be applied for SAR data owing to the differences in imaging mechanisms. Recent advances in deep image translation can fill this gap by using Generative Adversarial Networks (GAN). In this research, we apply a GAN-based model for SAR to optical image translation over fire-disturbed regions. Specifically, Sentinel-1 SAR images are translated into Sentinel-2 images using the ResNet-based Pix2Pix model, which is trained on 281 large fire events and tested on the other 23 events in Canada. The generated images preserve the spectral characteristics well and show high similarity to the real images with Structure Similarity Index Measure (SSIM) over 0.59.

Due to climate and land-use change, natural disasters such as flooding have been increasing in recent years. Timely and reliable flood detection and mapping can help emergency response and disaster management. In this work, we propose a flood detection network using bi-temporal SAR acquisitions. The proposed segmentation network has an encoder-decoder architecture with two Siamese encoders for pre and post-flood images. The network's feature maps are fused and enhanced using attention blocks to achieve more accurate detection of the flooded areas. Our proposed network is evaluated on publicly available Sen1Flood11 [1] benchmark dataset. The network outperformed the existing state-of-the-art (uni-temporal) flood detection method by 6% IOU. The experiments highlight that the combination of bi-temporal SAR data with an effective network architecture achieves more accurate flood detection than uni-temporal methods.

Wildfires vary across space and time, precisely and timely mapping on the wildfire affected areas is critical for wildfire management, population and property protection, and environmental impact assessment. In this study, we established a large-scale annotated wildfire burned area dataset based on freely available Sentinel-1 SAR and Sentinel-2 multispectral instrument (MSI) data and Canada Wildfire Burned Area Database. This dataset includes bi-temporal Sentinel-1 and Sentinel-2 images, which allows users to exploit remotely sensed data acquired in both optical and microwave domains. On the proposed dataset, we achieved the highest IoU score of 0.86 on the Sentinel-2 data with Siamese U-Net, and the highest IoU score of 0.80 on the Sentinel-1 data using U-Net with early fusion. The combined use of Sentinel-1 and Sentinel-2 failed to bring significant improvement compared to Sentinel-2 based results, but this dataset may have the potential to boost Sentinel-1 based results with Sentinel-2 data for near real-time wildfire progression mapping.

Burned area mapping is an essential task for assessing the damages caused by the wildfires. Optical satellite data have often been used for burned area mapping. However, due to cloud cover and smoke, it is sometimes difficult to use optical data for accurate burned area mapping at global scale. The objective of this research is to evaluate the PALSAR- 2 instrument onboard Advanced Land Observation Satellite-2 (ALOS-2) for burned area mapping at several sites around the world. In this study, a global scale bi-temporal dataset using the L-band PALSAR-2 instrument was created for the research of burned area mapping. Then a U-Net segmentation model was adopted to segment the burned area from the bi-temporal dataset. The results showed that L-Band SAR images can effectively map burned area using the segmentation model. Moreover, ablation study on the impact of different backbones revealed that the average U-Net yielded the best performance while U-Net with Resnext101 as the backbone outperforms U-Net for Grassland and Broadleaf Forest.

Urbanization is progressing rapidly around the world. With sub-weekly revisits at global scale, Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 multispectral imager (MSI) data can play an important role for monitoring urban sprawl to support sustainable development. In this letter, we proposed an urban change detection (CD) approach featuring a new network architecture for the fusion of SAR and optical data. Specifically, a dual stream concept was introduced to process different data modalities separately, before combining extracted features at a later decision stage. The individual streams are based on U-Net architecture that is one of the most popular fully convolutional networks used for semantic segmentation. The effectiveness of the proposed approach was demonstrated using the Onera Satellite CD (OSCD) dataset. The proposed strategy outperformed other U-Net-based approaches in combination with unimodal data and multimodal data with feature level fusion. Furthermore, our approach achieved state-of-the-art performance on the urban CD problem posed by the OSCD dataset. Our Sentinel-1 SAR data and code are available onhttps://github.com/SebastianHafner/DS_UNet.

Unsupervised hashing for remote sensing (RS) image retrieval first extracts image features and then use these features to construct supervised information (e.g., pseudo-labels) to train hashing networks. Existing methods usually regard RS images as natural images to extract unisource features. However, these features only contain partial information about ground objects and cannot produce reliable pseudo-labels. In addition, existing methods only generate a pseudo single-label to annotate each RS image, which cannot accurately represent multiple scenes in a RS image. To address these drawbacks, this paper proposes a new Multisource data reconstruction-based deep unsupervised Hashing method, called MrHash, which explores the characteristics of RS images to construct reliable pseudo-labels. In particular, we first use geographic coordinates to obtain different satellite images and develop a novel autoencoder network to extract multisource features from these images. Then pseudo multi-labels are designed to deal with the coexistence of multiple scenes in a single image. These labels are generated by a custom probability function with extracted multisource features. Finally, we propose a novel multi-semantic hash loss by using the Kull-back–Leibler (KL) divergence to preserve the semantic similarity of these pseudo multi-labels in Hamming space. Our newly developed MrHash only uses multisource images to construct supervised information, and hash code generation still relies on a unisource input image. Experiments on benchmark datasets clearly show the superiority of the proposed method over state-of-the-art baselines. https://github.com/sunyuxi/MrHash.

This research explores the potential of combining Sentinel-1 C-band Synthetic Aperture Radar (SAR) and Sentinel-2 MultiSpectral Instrument (MSI) data for Built-Up Area (BUA) mapping using deep learning. A lightweight U-Net model is trained using openly available building footprint reference data in North America and tested in four cities across three additional continents. The best test performance in terms of F1 score was achieved by the joint use of SAR and multispectral data (0.676), followed by multi-spectral (0.611) and SAR data (0.601). The developed fusion approach is particularly promising to distinguish BUA in low-density residential neighborhoods. Furthermore, our fusion approach compares favorably to the state-of-the-art in BUA mapping in the selected cities. However, associated with the diverse characteristics of human settlements around the world, considerable differences in accuracy among the test cities were observed. This indicates the need for more sophisticated fusion techniques to improve CNN model generalization and for adding more diverse training data.

In recent years, wildfires have become major devastating hazards that affect both public safety and the environment. Thus, agile detection of the wildfires is desirable to suppress wildfires in the early stage. Owing to the high temporal resolution, GOES-R satellites offer capabilities to obtain images every 15 minutes enabling a near real-time monitoring of wildfires. In this research, a time-series-based deep learning framework, composed of Gated Recurrent Units (GRU), is proposed to capture the emerging of the wildfire at early stage. By feeding the embedding of the coarse satellite imagery to Deep GRU network, the active fires are segmented out from the remote sensing imagery. The preliminary results show that proposed network can detect the wildfires earlier than the state-of-the-art fire product for 2020 wildfires in California and British Columbia, at the same time provide sufficiently high accuracy on the burned areas.

Sea surface and ship have different backscattering mechanisms, in which surface scattering is predominant for sea surface in the low sea state case. Based on this fact, many ship detectors have been developed by suppressing the surface scattering resulted from sea surface. Actually, small ship may also have strong surface scattering sometimes. In such a case, the methods of avoiding using surface scattering features may easily miss the detection of small ships. To verify this point, in this paper, we first analyze the shortcomings of An's method which is based on surface scattering similarity and the power maximization synthesis detector (PMS), and then improve it for detecting small ships more effectively. In order to demonstrate the performance of the proposed method, AIRSAR L-Band Polarimetric SAR dataset is exploited. Comparing to other methods, the new method shows a better ship detection performance.

With the rapid increase of remote sensing images in temporal, spectral, and spatial resolutions, it is urgent to develop effective techniques for joint interpretation of spatial-temporal images. Multitype change detection (CD) is a significant research topic in multitemporal remote sensing image analysis, and its core is to effectively measure the difference degree and represent the difference among the multitemporal images. In this paper, we propose a novel difference representation learning (DRL) network and present an unsupervised learning framework for multitype CD task. Deep neural networks work well in representation learning but rely too much on labeled data, while clustering is a widely used classification technique free from supervision. However, the distribution of real remote sensing data is often not very friendly for clustering. To better highlight the changes and distinguish different types of changes, we combine difference measurement, DRL, and unsupervised clustering into a unified model, which can be driven to learn Gaussian-distributed and discriminative difference representations for nonchange and different types of changes. Furthermore, the proposed model is extended into an iterative framework to imitate the bottom-up aggregative clustering procedure, in which similar change types are gradually merged into the same classes. At the same time, the training samples are updated and reused to ensure that it converges to a stable solution. The experimental studies on four pairs of multispectral data sets demonstrate the effectiveness and superiority of the proposed model on multitype CD.

Polarimetric Synthetic Aperture Radar data has been widely used for ship detection. In our earlier study, based on the differences between ship pixels and their surrounding background pixels, we designed a polarimetric covariance difference matrix (PCDM) to detect ships. Inadequately, the phase information of scattering differences is not included in PCD-M. Aiming at this deficiency, here, we present an improved PCDM matrix (IPCDM). Then an IPCDM-based ship detector is further proposed. To demonstrate the effectiveness of the method, two full polarimetric datasets are adopted. In comparing with other methods, we find that the result of our method is better.

It is well known that SAR imagery is affected by SAR geometric distortions due to the SAR imaging process (i.e. Layover, Foreshortening and Shadows). Specially in mountainous areas these distortions affect large portions of the images and in some applications, these areas shouldn't be included in analysis. Using a foreshortening mask is a suitable solution, but finding the mask is challenging. The aim of this research is to exploit the fusion of Sentinel-1 multi-temporal images and SRTM DEM to produce a quasi-global foreshortening mask using the Google Earth Engine (GEE), cloud-based platform. The mean value of multi-temporal Sentinel-1 images is calculated. Then a local minimum algorithm finds probable foreshortening area. Aspect and slope information from SRTM DEM are used to refine Sentinel-1 derived foreshortening mask. The proposed method is tested in British Columbia (Canada), Everest Mountain (Nepal), and Mazandaran (Iran). The results demonstrate the reliability of proposed method to detect the foreshortening area.

In this paper, a superpixel-based segmentation method is proposed for PolSAR images by utilizing hierarchical region merging and segment refinement. The loss of the energy function, which determines the consistency of two adjacent regions from the statistical aspect, is applied to guide the merging procedure. In addition to the edge penalty term, the homogeneity measurement is also employed to prevent merging the regions that are from different land covers or objects. Based on the merged segments, the segment refinement is applied to further improve the segmentation accuracy by iteratively relabeling the edge pixels. It uses a maximum a posterior (MAP) criterion using the statistical distribution of the pixels and the Markov random field (MRF) model. The performance of the proposed method is validated on an experimental PolSAR dataset from the ESAR system.

Simple linear iterative clustering (SLIC) algorithm was proposed for superpixel generation on optical images and showed promising performance. Several studies have been proposed to modify SLIC to make it applicable for polarimetric synthetic aperture radar (PolSAR) images, where the Wishart distance is adopted as the similarity measure. However, the superpixel segmentation results of these methods were not satisfactory in heterogeneous urban areas. Further, it is difficult to determine the tradeoff factor which controls the relative weight between polarimetric similarity and spatial proximity. In this research, an adaptive polarimetric SLIC (Pol-ASLIC) superpixel generation method is proposed to overcome these limitations. First, the spherically invariant random vector (SIRV) product model is adopted to estimate the normalized covariance matrix and texture for each pixel. A new edge detector is then utilized to extract PolSAR image edges for the initialization of central seeds. In the local iterative clustering, multiple cues including polarimetric, texture, and spatial information are considered to define the similarity measure. Moreover, a polarimetric homogeneity measurement is used to automatically determine the tradeoff factor, which can vary from homogeneous areas to heterogeneous areas. Finally, the SLIC superpixel generation scheme is applied to the airborne Experimental SAR and PiSAR L-band PolSAR data to demonstrate the effectiveness of this proposed superpixel generation approach. This proposed algorithm produces compact superpixels which can well adhere to image boundaries in both natural and urban areas. The detail information in heterogeneous areas can be well preserved.

The classic constant false alarm rate edge detector with a rectangle-shaped filter has been proven to be effective and widely used in polarimetric synthetic aperture radar (PolSAR) images. However, in practical use, the assumption of complex Wishart distribution is often not respected, particularly in heterogeneous urban areas. In addition, as a simple smoothing filter, the rectangle-shaped window is often shown to be easy to incur false edge pixels near true edges. Therefore, its performance is limited. To overcome this restriction, we propose a new edge detector for PolSAR images, which utilizes the spherically invariant random vector product model to estimate the normalized covariance matrix for each pixel, and then replace the rectangle-shaped filter with a Gauss-shaped filter. The performance of our proposed methodology is presented and analyzed on two real PolSAR data sets, and the results show that the new edge detector attains better performance than the classic one, particularly for urban areas.

In this paper, Sentinel-1A SAR data were evaluated for urban extent extraction using the KTH-Pavia Urban Extractor. The methodology is based on texture measures and spatial statistics as well as decision level fusion. Sentinel-1A data in Stripmap mode (SM) or Interferometric Wide Swath mode (IW) were acquired in five cities around the world. For two European cities Milan, Italy and Stockholm, Sweden, accuracy assessments were performed by comparing the extracted urban areas with the Urban Atlas in 2010. The preliminary results show that the Sentinel-1A Stripmap mode is very suitable for urban extraction, reaching an agreement of more than 83%. The Interferometric Wideswath mode shows potential as well reaching an agreement of 77%, but urban extraction over Stockholm had high omission errors in low density built up areas.

Human mobility patterns can provide valuable information in understanding the impact of human behavioral regularities in urban systems, usually with a specific focus on traffic prediction, public health or urban planning. While existing studies on human movement have placed huge emphasis on spatial location to predict where people go next, the time dimension component is usually being treated with oversimplification or even being neglected. Time dimension is crucial to understanding and detecting human activity changes, which play a negative role in prediction and thus may affect the predictive accuracy. This study aims to predict human movement from a spatio-temporal perspective by taking into account the impact of activity changes. We analyze and define changes of human activity and propose an algorithm to detect such changes, based on which a Markov chain model is used to predict human movement. The Microsoft GeoLife dataset is used to test our methodology, and the data of two selected users is used to evaluate the performance of the prediction. We compare the predictive accuracy (R2) derived from the data with and without implementing the activity change detection. The results show that the R2 is improved from 0.295 to 0.762 for the user with obvious activity changes and from 0.965 to 0.971 for the user without obvious activity changes. The method proposed by this study improves the accuracy in analyzing and predicting human movement and lays the foundation for related urban studies.

Cross-polarized scattering (HV) is not only caused by vegetation but also by rotated dihedrals. In this letter, we use rotated dihedral corner reflectors to form a cross scattering matrix and propose an extended model-based decomposition method for polarimetric synthetic aperture radar (PolSAR) data over urban areas. Unlike other urban decomposition techniques which need to discriminate between urban and natural areas before decomposition, this proposed method is applied directly on the PolSAR image. The building orientation angle is considered in this scattering matrix, making it flexible and adaptive in the decomposition process. This enables the separation of the cross scattering of urban areas from the overall HV component. The cross and helix scattering components are also compared in this study. RADARSAT-2 quad-pol C band and AIRSAR L band data are used to validate the performance of the proposed method. The cross scattering power of oriented buildings is generated, leading to a better decomposition result for urban areas with respect to other urban decomposition techniques.

TerraSAR X data has been analyzed for its suitability of urban land cover mapping using our recently developed object based image analysis tool KTH-SEG, which is based on an edge aware region growing and merging algorithm and a support vector machine classifier. Classification results over the Shanghai International Airport area using 8 classes, Water, Grass, Roads, Buildings, Crops, Forest, Bare Crops and Green Houses have proven with an overall accuracy just shy of 84% that this is very well the case. It has further been investigated which segment sizes and image configuration yield the best results.

This paper examines the relationship between different street centralities and land-use types in Stockholm. Major centrality measures of closeness, betweenness, and straightness are calculated at both global and local levels in both the primary and dual representations of the urban street network. Adaptive kernel density estimation is adopted to transform all unevenly distributed datasets to one continuous raster framework for further analysis. After computing statistical and spatial distribution of each centrality and land-use density map, we find that the density of each street centrality is highly correlated with one type of land use. Results imply that various centralities representing street properties from different aspects can capture the land development patterns of different land-use types by reflecting human activities, and are consequently important indicators to describe urban structure.

This letter presents a pixel-based contextual classification algorithm by integrating a multiscale modified Pappas adaptive clustering (mMPAC) and an adaptive Markov random field (AMRF) into the stochastic expectation-maximization process for urban land cover mapping using multitemporal polarimetric synthetic aperture radar (PolSAR) data. This algorithm can effectively explore spatiotemporal contextual information to improve classification accuracy. Using the mMPAC, the problem caused by the class feature variation could be mitigated. Using the AMRF, shape details could be preserved from overaveraging that often occurs in many nonadaptive contextual approaches. Six-date RADARSAT-2 PolSAR data over the Greater Toronto Area were used for evaluation. The results show that this algorithm outperformed the support vector machine in producing homogeneous and detailed land cover classification in a complex urban environment with high accuracy.

The objective of this paper is to develop a new effective method for hierarchical segmentation of multitemporal ultrafine-beam synthetic aperture radar (SAR) data in urban areas. Multitemporal RADARSAT-2 ultrafine-beam highresolution horizontal transmit and horizontal receive-Synthetic Aperture Radar (HH-SAR) images acquired in the rural-urban fringe of the Greater Toronto Area during the summer of 2008 are selected for this research. Stationary wavelet transform (SWT) and algebraic multigrid (AMG) method are proposed for segmentation of SAR data. SWT is applied for decomposition of multitemporal SAR images in image preprocessing. The hierarchical and matrix-based AMG method is applied for segmentation. A pyramid of fine-to-coarse grids is constructed by iteration of selecting representative pixels and calculating the interpolation matrix between a fine-level grid and a coarse-level grid. When the pyramid is completed, segments are determined by a top-down scanning based on the interpolation matrices. The AMG techniques provide a complete hierarchical segmentation of SAR data. The experimental results show that our method produces higher accuracy than eCognition.

The objectives of this research are to develop robust methods for segmentation of multitemporal synthetic aperture radar (SAR) and optical data and to investigate the fusion of multitemporal ENVISAT advanced synthetic aperture radar (ASAR) and Chinese HJ-1B multispectral data for detailed urban land-cover mapping. Eight-date multiangle ENVISAT ASAR images and one-date HJ-1B charge-coupled device image acquired over Beijing in 2009 are selected for this research. The edge-aware region growing and merging (EARGM) algorithm is developed for segmentation of SAR and optical data. Edge detection using a Sobel filter is applied on SAR and optical data individually, and a majority voting approach is used to integrate all edge images. The edges are then used in a segmentation process to ensure that segments do not grow over edges. The segmentation is influenced by minimum and maximum segment sizes as well as the two homogeneity criteria, namely, a measure of color and a measure of texture. The classification is performed using support vector machines. The results show that our EARGM algorithm produces better segmentation than eCognition, particularly for built-up classes and linear features. The best classification result (80%) is achieved using the fusion of eight-date ENVISAT ASAR and HJ-1B data. This represents 5%, 11%, and 14% improvements over eCognition, HJ-1B, and ASAR classifications, respectively. The second best classification is achieved using fusion of four-date ENVISAT ASAR and HJ-1B data (78%). The result indicates that fewer multitemporal SAR images can achieve similar classification accuracy if multitemporal multiangle dual-look-direction SAR data are carefully selected.

Multitemporal synthetic aperture radar (SAR) images have been increasingly used in change detection studies. However, the presence of speckle is the main disadvantage of this type of data. To reduce speckle, many local adaptive filters have been developed. Although these filters are effective in reducing speckle in homogeneous areas, their use is often accompanied with the degradation of spatial details and fine structures. In this paper, we investigate a nonlocal means (NLM) denoising algorithm that combines local structures with a global averaging scheme in the context of change detection using multitemporal SAR images. First, the ratio image is logarithmically scaled to convert the multiplicative noise model to an additive model. A multidimensional change image is then constructed using image neighborhood feature vectors. Principle component analysis is then used to reduce the dimensionality of the neighborhood feature vectors. Recursive linear regression combined with fitting-accuracy assessment strategy is developed to determine the number of significant PC components to be retained for similarity weight computation. An intuitive method to estimate the unknown noise variance (necessary to run the NLM algorithm) based on the discarded PC components is also proposed. The efficiency of the method has been assessed using two different bitemporal SAR datasets acquired in Beijing and Shanghai, respectively. For comparison purposes, the algorithm is also tested against some of the most commonly used local adaptive filters. Qualitative and quantitative analyses of the algorithm have demonstrated the efficiency of the algorithm in recovering the noise-free change image while preserving the complex structures in urban areas.

This paper presents a contextual classification algorithm which employs the multiscale modified Pappas adaptive clustering (MPAC) approach and the Semisupervised Expectation-Maximization (SEM) procedure for urban land cover mapping using multitemporal polarimetric SAR (PolSAR) data. The proposed pixel-based algorithm explores spatio-temporal contextual information and thus could effectively improve the classification accuracy while simultaneously avoids the pepper-salt results which often occurs on the SAR images. Moreover, owing to the multiscale analysis, MPAC could adaptively preserve the detailed features comparing with other non-adaptive contextual methods. The proposed algorithm is computationally efficient and requires less parameter to be estimated. Properties of the proposed algorithm including the MRF impact, multiscale efficiency, computational performance and the initialization influence were investigated. Six-date RADARSAT-2 polarimetric SAR data over the Greater Toronto Area were used for validation. The results show that this algorithm could generate homogenous and detailed mapping results with fair accuracy for complex urban land cover classification.

This letter introduces a new approach for light detection and ranging (LiDAR) waveform decomposition. First, inflection points are identified by the Ramer-Douglas-Peucker curve-fitting algorithm, and each inflection point has a corresponding baseline during curve fitting. Second, according to the spatial relation between the baseline and the inflection point, peaks are selected from the inflection points. The distance between each peak and its baseline and the maximum number of peaks are employed as a criterion to select a “significant” peak. Initial parameters such as width and boundaries of peaks provide restraints for the decomposition; right and left boundaries are estimated via a conditional search. Each peak is fitted by a Gaussian function separately, and other parts of the waveform are fitted as line segments. Experiments are implemented on waveforms acquired by both small-footprint LiDAR system LMS-Q560 and large-footprint LiDAR system Laser Vegetation Imaging Sensor. The results indicate that the algorithm could provide an optimal solution for LiDAR waveform decomposition.