Very High Resolution Remote Sensing Research Articles

Contextual Learning in Fourier Complex Field for VHR Remote Sensing Images.

Very high-resolution (VHR) remote sensing (RS) image classification is the fundamental task for RS image analysis and understanding. Recently, Transformer-based models demonstrated outstanding potential for learning high-order contextual relationships from natural images with general resolution ( ≈ 224 × 224 pixels) and achieved remarkable results on general image classification tasks. However, the complexity of the naive Transformer grows quadratically with the increase in image size, which prevents Transformer-based models from VHR RS image ( ≥ 500 × 500 pixels) classification and other computationally expensive downstream tasks. To this end, we propose to decompose the expensive self-attention (SA) into real and imaginary parts via discrete Fourier transform (DFT) and, therefore, propose an efficient complex SA (CSA) mechanism. Benefiting from the conjugated symmetric property of DFT, CSA is capable to model the high-order contextual information with less than half computations of naive SA. To overcome the gradient explosion in Fourier complex field, we replace the Softmax function with the carefully designed Logmax function to normalize the attention map of CSA and stabilize the gradient propagation. By stacking various layers of CSA blocks, we propose the Fourier complex Transformer (FCT) model to learn global contextual information from VHR aerial images following the hierarchical manners. Universal experiments conducted on commonly used RS classification datasets demonstrate the effectiveness and efficiency of FCT, especially on VHR RS images. The source code of FCT will be available at https://github.com/Gao-xiyuan/FCT.

Learning to Holistically Detect Bridges From Large-Size VHR Remote Sensing Imagery.

Bridge detection in remote sensing images (RSIs) plays a crucial role in various applications, but it poses unique challenges compared to the detection of other objects. In RSIs, bridges exhibit considerable variations in terms of their spatial scales and aspect ratios. Therefore, to ensure the visibility and integrity of bridges, it is essential to perform holistic bridge detection in large-size very-high-resolution (VHR) RSIs. However, the lack of datasets with large-size VHR RSIs limits the deep learning algorithms' performance on bridge detection. Due to the limitation of GPU memory in tackling large-size images, deep learning-based object detection methods commonly adopt the cropping strategy, which inevitably results in label fragmentation and discontinuous prediction. To ameliorate the scarcity of datasets, this paper proposes a large-scale dataset named GLH-Bridge comprising 6,000 VHR RSIs sampled from diverse geographic locations across the globe. These images encompass a wide range of sizes, varying from 2,048 × 2,048 to 16,384 × 16,384pixels, and collectively feature 59,737 bridges. These bridges span diverse backgrounds, and each of them has been manually annotated, using both an oriented bounding box (OBB) and a horizontal bounding box (HBB). Furthermore, we present an efficient network for holistic bridge detection (HBD-Net) in large-size RSIs. The HBD-Net presents a separate detector-based feature fusion (SDFF) architecture and is optimized via a shape-sensitive sample re-weighting (SSRW) strategy. The SDFF architecture performs inter-layer feature fusion (IFF) to incorporate multi-scale context in the dynamic image pyramid (DIP) of the large-size image, and the SSRW strategy is employed to ensure an equitable balance in the regression weight of bridges with various aspect ratios. Based on the proposed GLH-Bridge dataset, we establish a bridge detection benchmark including the OBB and HBB tasks, and validate the effectiveness of the proposed HBD-Net. Additionally, cross-dataset generalization experiments on two publicly available datasets illustrate the strong generalization capability of the GLH-Bridge dataset. The dataset and source code will be released at https://luo-z13.github.io/GLH-Bridge-page/.

Multi-Level Difference Network for Change Detection from Very High-Resolution Remote Sensing Images: A Case Study in Open-Pit Mines

Automatic change detection based on remote sensing is playing an increasingly important role in the national economy construction. To address the problem of limited change detection accuracy in existing single-level difference networks, this study proposes the Multi-level Difference Network (MDNet) for automatic change detection of ground targets from very high-resolution (VHR) remote sensing images. An early-difference network and a late-difference network are combined by MDNet to extract multi-level change features. The early-difference network can focus on change information throughout to reduce the spurious changes in the change detection results, and the late-difference network can provide deep features of a single image for reducing rough boundaries and scattered holes in the change detection results, thus improving the accuracy. However, not all high-level features extracted by MDNet contribute to the recognition of image differences, and the multi-level change features suffer from cross-channel heterogeneity. Stacking them directly on channels does not make effective use of change information, thus limiting the performance of MDNet. Therefore, the Multi-level Change Features Fusion Module (MCFFM) is proposed in this study for the effective fusion of multi-level change features. In the experiments, the publicly available open-pit mine change detection (OMCD) dataset was used first to achieve a change detection of open-pit mines over a large area, with an F1-score of 89.2%, increasing by 1.3% to 5.9% compared to the benchmark methods. Then, a self-made OMCD dataset was used to achieve an F1-score of 92.8% for the localized and fine-scale change detection in open-pit mines, which is an improvement of 0.7% to 5.4% compared to the benchmark methods. Finally, the Season-varying Change Detection Dataset is used to verify that the MDNet proposed can detect changes in other scenarios very well. The experimental results show that the proposed MDNet has significantly improved the performance of change detection on the three datasets compared with six advanced deep learning models, which will contribute to the development of change detection with VHR remote sensing images.

Building Extraction From Very High-Resolution Remote Sensing Images Using Refine-UNet

Accurate building extraction from very high-resolution (VHR) remote sensing images plays an important role in urban dynamic monitoring, planning, and management. However, it is still a challenging task to achieve building extraction with high accuracy and integrity due to diverse building appearances and more complex ground background in VHR remote sensing images. Recently, Unity Networking (UNet) has been proven to be capable of feature extraction and semantic segmentation of remote sensing images. However, UNet cannot achieve sufficient multi-scale and multi-level features with larger receptive fields. To address these problems, an improved network based on UNet structure (Refine-UNet) is proposed for extracting buildings from the VHR images. The proposed Refine-UNet mainly consists of encoder module, decoder module, and refine skip connection scheme. The refine skip connection scheme is composed of an atrous spatial convolutional pyramid pooling (ASPP) module and several improved depthwise separable convolution (IDSC) modules. Experimental results on the Jilin-1 VHR datasets with a spatial resolution of 0.75 m demonstrate that compared with UNet, PSPNet, DeepLabV3+, and SegNet, the proposed Refine-UNet can obtain more accurate building extraction results and achieve the best Precision of 95.1% and intersection over union (IoU) of 87.0%, respectively, indicating the great practical potential.

Unsupervised Domain Adaptation Augmented by Mutually Boosted Attention for Semantic Segmentation of VHR Remote Sensing Images

This work investigates unsupervised domain adaptation (UDA)-based semantic segmentation of very high-resolution (VHR) remote sensing (RS) images from different domains. Most existing UDA methods resort to generative adversarial networks (GANs) to cope with the domain shift problem caused by the discrepancies across different domains. However, these GAN-based UDA methods directly align two domains in the appearance, latent, or output space based on convolutional neural networks (CNNs), making them ineffective in exploiting long-range dependencies across the high-level feature maps derived from different domains. Unfortunately, such high-level features play an essential role in characterizing RS images with complex content. To circumvent this obstacle, a mutually boosted attention transformer (MBATrans) is proposed to capture cross-domain dependencies of semantic feature representations in this work. Compared with conventional UDA methods, MBATrans can significantly reduce domain discrepancies by capturing transferable features using global attention. More specifically, MBATrans utilizes a novel mutually boosted attention (MBA) module to align cross-domain feature maps while enhancing domain-general features. Furthermore, a novel GAN-based network with improved discriminative capability is devised by integrating an additional discriminator to learn domain-specific features. Extensive experiments on two large-scale VHR RS datasets, namely, International Society for Photogrammetry and Remote Sensing (ISPRS) Potsdam and Vaihingen, confirm the superior performance of the proposed MBATrans-augmented GAN (MBATA-GAN) architecture. The source code in this work is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/sstary/SSRS</uri> .

Transformer-Based Model with Dynamic Attention Pyramid Head for Semantic Segmentation of VHR Remote Sensing Imagery.

Convolutional neural networks have long dominated semantic segmentation of very-high-resolution (VHR) remote sensing (RS) images. However, restricted by the fixed receptive field of convolution operation, convolution-based models cannot directly obtain contextual information. Meanwhile, Swin Transformer possesses great potential in modeling long-range dependencies. Nevertheless, Swin Transformer breaks images into patches that are single-dimension sequences without considering the position loss problem inside patches. Therefore, Inspired by Swin Transformer and Unet, we propose SUD-Net (Swin transformer-based Unet-like with Dynamic attention pyramid head Network), a new U-shaped architecture composed of Swin Transformer blocks and convolution layers simultaneously through a dual encoder and an upsampling decoder with a Dynamic Attention Pyramid Head (DAPH) attached to the backbone. First, we propose a dual encoder structure combining Swin Transformer blocks and reslayers in reverse order to complement global semantics with detailed representations. Second, aiming at the spatial loss problem inside each patch, we design a Multi-Path Fusion Model (MPFM) with specially devised Patch Attention (PA) to encode position information of patches and adaptively fuse features of different scales through attention mechanisms. Third, a Dynamic Attention Pyramid Head is constructed with deformable convolution to dynamically aggregate effective and important semantic information. SUD-Net achieves exceptional results on ISPRS Potsdam and Vaihingen datasets with 92.51%mF1, 86.4%mIoU, 92.98%OA, 89.49%mF1, 81.26%mIoU, and 90.95%OA, respectively.

BUILDING FOOTPRINT EXTRACTION FROM SPACE-BORNE IMAGERY USING DEEP NEURAL NETWORKS

Abstract. One of the important and high-level detailing contained within basemaps is the ‘building feature’. Though pre-trained Deep Learning (DL) models are available for Building Feature Extraction (BFE), they are not efficient in predicting the buildings in other locations. This study explores the need and the major issue of implementing DL models for BFE from Very High Resolution Remote Sensing (VHRS) satellite data for any given area. Though advanced DL models are invented, in order to implement them, huge amount of potential training data is demanded for feed in. the building typologies are highly subjected to the context of study area including soil characteristics, culture/lifestyle/economy, architectural style and the building byelaws. The study believes that availability of enough training data of contextual buildings as one of the concern for effective model training. The study aims to extract the buildings present in the study area from Pleiades 1A (2019) RGB VHRS data using simple Mask R-CNN instance segmentation model which is training on the native contextual buildings. Here, an automated method of generating the location-specific training data for a given area is followed using Google Maps API (2021). The generated training data when trained on a deep learning architecture and predicted by the input data yielded promising results. The prediction accuracy of about 98.41% specificity, 96.20% predictive accuracy and 0.89 F1 score are achieved. The methods adopted assist the planning/governing bodies to accelerate the qualitative urban map preparation.

Feature-Selection High-Resolution Network With Hypersphere Embedding for Semantic Segmentation of VHR Remote Sensing Images

Very high resolution (VHR) remote sensing images contain various multi-scale objects, such as large-scale buildings and small-scale cars. However, these multi-scale objects cannot be considered simultaneously in the widely used backbones with large downsampling factor (e.g. VGG-like and ResNet-like), resulting in the appearance of various context aggregation approaches such as fusing low-level features and attention-based modules. To alleviate this problem caused by backbones with large downsampling factor, we propose a feature-selection high-resolution network (FSHRNet) based on an observation: if the features maintain high resolution throughout the network, a high precision segmentation result can be obtained by only using a 1&#x00D7;1 convolution layer with no need for complex context aggregation modules. Specifically, the backbone of FSHRNet is a multi-branch structure similar to HRNet where the high-resolution branch is the principal line. Then, a lightweight dynamic weight module, named feature-selection convolution layer (FSConv), is presented to fuse multi-resolution features, allowing adaptively feature selection based on the characteristic of objects. Finally, a specially designed 1&#x00D7;1 convolution layer derived from hypersphere embedding is used to produce the segmentation result. Experiments with other widely used methods show that the proposed FSHRNet obtains competitive performance on ISPRS Vaihingen dataset, ISPRS Potsdam dataset and iSAID dataset.

Novel Automatic Approach for Land Cover Change Detection by Using VHR Remote Sensing Images

Many land cover change detection (LCCD) approaches applied on very high resolution (VHR) remote sensing images utilize spatial information by using a regular window or strict mathematical model. However, regular shape or strict models cannot fit the various shapes and sizes of the ground targets. In this article, a novel LCCD approach without the parameter is proposed to detect land cover change with VHR remote sensing images. First, an adaptive spatial-context extraction algorithm is applied to explore contextual information around a pixel. Second, the change magnitude between pairwise pixels is quantitatively measured by computing the band-to-band distance which is defined by the pairwise adaptive regions around the corresponding pixels. Finally, after the generation of a change magnitude image (CMI), a binary threshold method called double-window flexible pace search (DFPS) is adopted to divide CMI into a binary change detection map. The performance of the proposed approach is verified by comparing it with five state-of-the-art methods with three pairs of VHR images. The comparisons demonstrated that the proposed approach achieved the improved detected results comparing with state-of-the-art LCCD methods. The code of the proposed approach is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/TongfeiLiu/ASEA-CD</uri> .

Building Outline Delineation From VHR Remote Sensing Images Using the Convolutional Recurrent Neural Network Embedded With Line Segment Information

Recently, several recurrent neural network (RNN)-based models have been proposed to delineate the outlines of buildings from very high resolution (VHR) remote sensing images. These models first use convolutional neural networks (CNNs) to recognize the boundary fragments by learning probability maps of both edges and corners and then feed them into RNN to find and link a set of sequent corners into external boundaries of buildings. However, caused by the category imbalance of edges and corners, the local ambiguity of edge detection is very serious, which significantly affects the accuracy of predicted outline corners. To tackle this challenge, this article introduces a convolutional RNN embedded with line segment information (LSI-RNN), a novel network that aims to directly detect line segment instead of edges. To achieve this, LSI-RNN utilizes an additional cotraining branch to generate an attraction field map (AFM) by neural discriminative dimensionality reduction (NDDR) layer. Consequently, the conventional classification problem of edges is converted to a regression problem of line segments, thus solving the aforementioned issues. Experimental results over three remote sensing datasets with different spatial resolutions show that the proposed method consistently outperforms other state-of-the-art methods.

CGSANet: A Contour-Guided and Local Structure-Aware Encoder–Decoder Network for Accurate Building Extraction From Very High-Resolution Remote Sensing Imagery

Extracting buildings accurately from very high-resolution (VHR) remote sensing imagery is challenging due to diverse building appearances, spectral variability, and complex background in VHR remote sensing images. Recent studies mainly adopt a variant of the fully convolutional network (FCN) with an encoder–decoder architecture to extract buildings, which has shown promising improvement over conventional methods. However, FCN-based encoder–decoder models still fail to fully utilize the implicit characteristics of building shapes. This adversely affects the accurate localization of building boundaries, which is particularly relevant in building mapping. A contour-guided and local structure-aware encoder–decoder network (CGSANet) is proposed to extract buildings with more accurate boundaries. CGSANet is a multitask network composed of a contour-guided (CG) and a multiregion-guided (MRG) module. The CG module is supervised by a building contour that effectively learns building contour-related spatial features to retain the shape pattern of buildings. The MRG module is deeply supervised by four building regions that further capture multiscale and contextual features of buildings. In addition, a hybrid loss function was designed to improve the structure learning ability of CGSANet. These three improvements benefit each other synergistically to produce high-quality building extraction results. Experimental results on the WHU and NZ32km2 building datasets demonstrate that compared with the tested algorithms, CGSANet can produce more accurate building extraction results and achieve the best intersection over union value 91.55% and 90.02%, respectively. Experiments on the INRIA building dataset further demonstrate the ability for generalization of the proposed framework, indicating great practical potential.

Gated Recurrent Multiattention Network for VHR Remote Sensing Image Classification

With the advances of deep learning, many recent CNN-based methods have yielded promising results for image classification. In very high-resolution (VHR) remote sensing images, the contributions of different regions to image classification can vary significantly, because informative areas are generally limited and scattered throughout the whole image. Therefore, how to pay more attention to these informative areas and better incorporate them over long distances are two main challenges to be addressed. In this article, we propose a gated recurrent multiattention neural network (GRMA-Net) to address these problems. Because informative features generally occur at multiple stages in a network (i.e., local texture features at shallow layers and global profile features at deep layers), we use multilevel attention modules to focus on informative regions to extract more discriminative features. Then, these features are arranged as spatial sequences and fed into a deep-gated recurrent unit (GRU) to capture long-range dependency and contextual relationship. We evaluate our method on the UC Merced (UCM), Aerial Image dataset (AID), NWPU-RESISC (NWPU), and Optimal-31 (Optimal) datasets. Experimental results have demonstrated the superior performance of our method as compared to other state-of-the-art methods.

Object-Based Classification Framework of Remote Sensing Images With Graph Convolutional Networks

Object-based image classification (OBIC) on very-high-resolution (VHR) remote sensing (RS) images is utilized in a wide range of applications. Nowadays, many existing OBIC methods only focus on features of each object itself, neglecting the contextual information among adjacent objects and resulting in low classification accuracy. Inspired by a spectral graph theory, we construct a graph structure from objects generated from VHR RS images and propose an OBIC framework based on truncated sparse singular value decomposition and graph convolutional network (GCN) model, aiming to make full use of relativities among objects and produce an accurate classification. Through conducting experiments on two annotated RS image data sets, our framework obtained 97.2% and 66.9% overall accuracy, respectively, in automatic and manual object segmentation circumstances, within a processing time of about 1/100 of convolutional neural network (CNN)-based methods’ training time.

Multi-Modality and Multi-Scale Attention Fusion Network for Land Cover Classification from VHR Remote Sensing Images

Land cover classification from very high-resolution (VHR) remote sensing images is a challenging task due to the complexity of geography scenes and the varying shape and size of ground targets. It is difficult to utilize the spectral data directly, or to use traditional multi-scale feature extraction methods, to improve VHR remote sensing image classification results. To address the problem, we proposed a multi-modality and multi-scale attention fusion network for land cover classification from VHR remote sensing images. First, based on the encoding-decoding network, we designed a multi-modality fusion module that can simultaneously fuse more useful features and avoid redundant features. This addresses the problem of low classification accuracy for some objects caused by the weak ability of feature representation from single modality data. Second, a novel multi-scale spatial context enhancement module was introduced to improve feature fusion, which solves the problem of a large-scale variation of objects in remote sensing images, and captures long-range spatial relationships between objects. The proposed network and comparative networks were evaluated on two public datasets—the Vaihingen and the Potsdam datasets. It was observed that the proposed network achieves better classification results, with a mean F1-score of 88.6% for the Vaihingen dataset and 92.3% for the Potsdam dataset. Experimental results show that our model is superior to the state-of-the-art network models.

A Novel Query Strategy-Based Rank Batch-Mode Active Learning Method for High-Resolution Remote Sensing Image Classification

An informative training set is necessary for ensuring the robust performance of the classification of very-high-resolution remote sensing (VHRRS) images, but labeling work is often difficult, expensive, and time-consuming. This makes active learning (AL) an important part of an image analysis framework. AL aims to efficiently build a representative and efficient library of training samples that are most informative for the underlying classification task, thereby minimizing the cost of obtaining labeled data. Based on ranked batch-mode active learning (RBMAL), this paper proposes a novel combined query strategy of spectral information divergence lowest confidence uncertainty sampling (SIDLC), called RBSIDLC. The base classifier of random forest (RF) is initialized by using a small initial training set, and each unlabeled sample is analyzed to obtain the classification uncertainty score. A spectral information divergence (SID) function is then used to calculate the similarity score, and according to the final score, the unlabeled samples are ranked in descending lists. The most “valuable” samples are selected according to ranked lists and then labeled by the analyst/expert (also called the oracle). Finally, these samples are added to the training set, and the RF is retrained for the next iteration. The whole procedure is iteratively implemented until a stopping criterion is met. The results indicate that RBSIDLC achieves high-precision extraction of urban land use information based on VHRRS; the accuracy of extraction for each land-use type is greater than 90%, and the overall accuracy (OA) is greater than 96%. After the SID replaces the Euclidean distance in the RBMAL algorithm, the RBSIDLC method greatly reduces the misclassification rate among different land types. Therefore, the similarity function based on SID performs better than that based on the Euclidean distance. In addition, the OA of RF classification is greater than 90%, suggesting that it is feasible to use RF to estimate the uncertainty score. Compared with the three single query strategies of other AL methods, sample labeling with the SIDLC combined query strategy yields a lower cost and higher quality, thus effectively reducing the misclassification rate of different land use types. For example, compared with the Batch_Based_Entropy (BBE) algorithm, RBSIDLC improves the precision of barren land extraction by 37% and that of vegetation by 14%. The 25 characteristics of different land use types screened by RF cross-validation (RFCV) combined with the permutation method exhibit an excellent separation degree, and the results provide the basis for VHRRS information extraction in urban land use settings based on RBSIDLC.

Modified Deep Reinforcement Learning with Efficient Convolution Feature for Small Target Detection in VHR Remote Sensing Imagery

Small object detection in very-high-resolution (VHR) optical remote sensing images is a fundamental but challenaging problem due to the latent complexities. To tackle this problem, the MdrlEcf model is proposed by modifying deep reinforcement learning (DRL) and extracting the efficient convolution feature. Firstly, an efficient attention network is constructed by introducing the local attention into the convolutional neural network. Combining the shallow low-level features with rich detail descriptions and high-level features with more semantic meanings effectively, efficient convolution features can be obtained. By this, the attention network can effectively enhance the ability to extract small target features and suppressing useless features. Secondly, the efficient feature map is sent to the region proposal network constructed by modified DRL. Using the modified reward function, this model can accumulate more rewards to conduct the search process, and potentially generate effective subsequent proposals and classification scores. It also can increase the effectiveness of object locations and classifications for small targets. Quantitative and qualitative experiments are conducted to verify the detection performance of different models. The results show that the proposed MdrlEcf can effectively and accurately locate and identify related small objects.

Identification and Evaluation of Urban Construction Waste with VHR Remote Sensing Using Multi-Feature Analysis and a Hierarchical Segmentation Method

With rapid urbanization, the disposal and management of urban construction waste have become the main concerns of urban management. The distribution of urban construction waste is characterized by its wide range, irregularity, and ease of confusion with the surrounding ground objects, such as bare soil, buildings, and vegetation. Therefore, it is difficult to extract and identify information related to urban construction waste by using the traditional single spectral feature analysis method due to the problem of spectral confusion between construction waste and the surrounding ground objects, especially in the context of very-high-resolution (VHR) remote sensing images. Considering the multi-feature analysis method for VHR remote sensing images, we propose an optimal method that combines morphological indexing and hierarchical segmentation to extract the information on urban construction waste in VHR images. By comparing the differences between construction waste and the surrounding ground objects in terms of the spectrum, geometry, texture, and other features, we selected an optimal feature subset to improve the separability of the construction waste and other objects; then, we established a classification model of knowledge rules to achieve the rapid and accurate extraction of construction waste information. We also chose two experimental areas of Beijing to validate our algorithm. By using construction waste separability quality evaluation indexes, the identification accuracy of construction waste in the two study areas was determined to be 96.6% and 96.2%, the separability indexes of the construction waste and buildings reached 1.000, and the separability indexes of the construction waste and vegetation reached 1.000 and 0.818. The experimental results show that our method can accurately identify the exposed construction waste and construction waste covered with a dust screen, and it can effectively solve the problem of spectral confusion between the construction waste and the bare soil, buildings, and vegetation.

A Generic FCN-Based Approach for the Road-Network Extraction From VHR Remote Sensing Images – Using OpenStreetMap as Benchmarks

As one road network is often the backbone in a geo-spatial dataset, capturing and/or updating the road networks using remote sensing imagery play an important role in traffic management, urban planning, vehicle navigation, and emergency management. Along with the progress of remote sensing launching technologies and the successful applications of deep learning in the field of computer vision, it has become more and more efficient and economical to employ deep learning methods for road-features extractions from very high-resolution (VHR) remote sensing imagery. Meanwhile, as one of the most significant and popular volunteer geographic information data sources, the OpenStreetMap (OSM) including the complete road networks in the wide world has been accumulated in the past decades. In this article, a generic and automatic approach for extracting road networks from VHR remote sensing images has been proposed based on fully convolutional neural network, in which the road centerlines from OSM have been employed to construct the labels for the model training and validation. In the conducted experiments on various VHR image datasets with two different spatial resolutions of 0.3 and 1 m, the proposed model has demonstrated quite satisfactory results – the overall completeness and correctness of the roads extraction from VHR remote sensing images exceed 94.0% and 98.0%, respectively.

A Local-Global Dual-Stream Network for Building Extraction From Very-High-Resolution Remote Sensing Images.

Buildings constitute one of the most important landscapes in remote sensing (RS) images and have been broadly analyzed in a wide range of applications from urban planning to other socioeconomic studies. As very-high-resolution (VHR) RS imagery becomes more accessible, the current building extraction methods are confronted with the challenges of the diverse appearances, various scales, and complicated structures of buildings in complex scenes. With the development of context-aware deep learning methods, it has been proven by numerous works that capturing contextual information can offer spatial relation cues for robust recognition and detection of the objects. In this article, we propose a novel local-global dual-stream network (DS-Net) that adaptively captures local and long-range information for the accurate mapping of building rooftops in VHR RS images. The local branch and the global branch of DS-Net work in a complementary manner to each other with different fields of view on the input image. Through a well-defined dual-stream architecture, DS-Net learns hierarchical representations for both the local and global branches, and a deep feature sharing strategy is further developed to enforce more collaborative integration of the two branches. Extensive experiments were carried out to verify the effectiveness of our model on three widely used VHR RS data sets: the Massachusetts buildings data set, the Inria Aerial Image Labeling data set, and the DeepGlobe Building Detection Challenge data set. Empirically, the proposed DS-Net achieves competitive or superior performance compared with the current state-of-the-art methods in terms of quantitative measures and visual evaluations.

Improved Generative Adversarial Networks for VHR Remote Sensing Image Classification

With increasing spatial resolution of remote sensing images, accurate classification of land classes depends more on the number of labeled samples. However, the acquisition of labeled samples is difficult and time-consuming. Hence, generative adversarial networks (GANs) have become a new method for collecting training samples for very-high-resolution (VHR) remote sensing image classification. A traditional GAN generates new samples with the same distribution as the labeled samples. However, the generated samples have features close to their class center, and the network cannot obtain effective discriminative ability for the samples close to the decision boundary. This letter presents an improved GAN (IGAN) for VHR remote sensing image classification. In the proposed framework, the generator aims to generate synthetic samples close to the classification boundary, and the discriminator aims to constrain the labels of the synthetic samples. The obtained synthetic samples can effectively improve the classification accuracy of the classification boundary. Experiments are conducted on two VHR remote sensing images, and the results show that the proposed method performs better than several state-of-the-art methods.