相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Engineering, Electrical & Electronic
Liangyi Cui et al.
Summary: This paper proposes an improved Swin Transformer model for segmenting dense urban buildings from remote sensing images with complex backgrounds. A convolutional block attention module is utilized to focus on significant features, and hierarchical feature maps are fused to enhance the feature extraction process. The effectiveness and superiority of the proposed method are validated through ablation experiments and comparative studies, achieving an improvement of 1.3% in mean intersection-over-union compared to the original model.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2023)
Article
Ecology
Paula J. Noble et al.
Summary: Periphyton assemblages from Lake Tahoe's west side nearshore environment were analyzed to determine their taxonomic composition and community structure across habitats and seasons. The results showed changes in species dominance and increased algal species biodiversity compared to previous monitoring efforts. The creation of a voucher flora helped provide reproducible identification and enumeration of algal species, and the data collected from November 2019 to September 2020 provide useful snapshots for future monitoring projects.
FRONTIERS IN ECOLOGY AND EVOLUTION
(2023)
Review
Environmental Sciences
Abdulaziz Amer Aleissaee et al.
Summary: Deep learning algorithms have gained popularity in remote sensing image analysis, and transformer-based architectures have been widely used in computer vision with self-attention mechanism replacing convolution operator. Inspired by this, the remote sensing community has explored vision transformers for various tasks. This survey presents a systematic review of recent transformer-based methods in remote sensing, covering different sub-areas like very high-resolution (VHR), hyperspectral (HSI), and synthetic aperture radar (SAR) imagery. The survey concludes by discussing challenges and open issues of transformers in remote sensing.
Article
Mathematics, Interdisciplinary Applications
Zhiyong Fan et al.
Summary: In this study, a river segmentation model based on composite attention network is proposed for remote sensing images. By introducing a composite attention mechanism and dynamically combining loss functions, the proposed method can accurately segment rivers in images with high evaluation indexes.
Article
Geochemistry & Geophysics
Haiwei Bai et al.
Summary: This letter introduces a hierarchical context aggregation network (HCANet) for semantic segmentation of high-resolution remote sensing images (HRRSIs), utilizing CASPP and CASPP+ modules to extract multiscale context information and hierarchical merging for segmentation, achieving outstanding performance on ISPRS datasets.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Li Chen et al.
Summary: The paper introduces an end-to-end ensemble fully convolutional network (EFCNet) with adaptive fusion module (AFM) and separable convolutional module (SCM), which can effectively enhance semantic segmentation performance of high-resolution remote sensing images and reduce model complexity.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Libo Wang et al.
Summary: The fully convolutional network (FCN) with an encoder-decoder architecture is widely used for semantic segmentation. In this paper, the authors propose using the Swin Transformer as the backbone and a novel decoder called DCFAM for better context extraction and resolution restoration. Experimental results on two remotely sensed semantic segmentation datasets demonstrate the effectiveness of the proposed scheme.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Danpei Zhao et al.
Summary: The study introduces an RSANet model based on a regional self-attention mechanism that achieves better semantic segmentation results in remote sensing images. Compared to traditional models, RSANet is more capable of combining local and global information, significantly reducing noise in feature maps and interference from redundant features. Experimental results demonstrate that RSANet outperforms baseline models by achieving a 2% higher mean intersection over union (mIoU), particularly in fine details, edge integrity, and classification accuracy.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Rui Li et al.
Summary: The study introduces a linear attention mechanism (LAM) to address the issue of increasing memory and computational costs of the dot-product attention mechanism with large-scale inputs, enhancing the flexibility and versatility of integration between attention mechanisms and deep networks.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Qi Zhao et al.
Summary: This study proposes an end-to-end attention-based semantic segmentation network SSAtNet, which includes a pyramid attention pooling module and a pooling index correction module to refine and recover fine-grained features. By designing a more effective ResNet-101 backbone and data augmentation methods, the performance of the model is enhanced, leading to state-of-the-art results on the ISPRS Vaihingen dataset.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Zhiqiang Li et al.
Summary: This article introduces the self-smoothing atrous convolution (SS-AConv) to improve the performance of convolutional neural networks in semantic segmentation of very-high-resolution images in urban areas. SS-AConv enhances sampling rates with low computational costs by adding key parameters and replaces max pooling operations in the Xception network.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Ailong Ma et al.
Summary: The FactSeg framework proposed in this article combines FA object representation and CP loss to effectively enhance the performance of small object segmentation.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Cheng Zhang et al.
Summary: This article presents a hybrid deep neural network that combines transformer and convolutional neural network (CNN) for semantic segmentation of very high resolution remote sensing imagery. The network utilizes a new universal backbone Swin transformer for feature extraction and incorporates various strategies for multiscale context modeling. It achieves improved accuracy through skip connections and an auxiliary boundary detection branch.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Guohui Deng et al.
Summary: Semantic segmentation is crucial for understanding subdecimeter aerial images. This paper proposes a novel deep network called class-constraint coarse-to-fine attentional (CCA) network, which improves the performance of fine-structured geographic entity segmentation by explicitly obtaining long-range context information. The proposed method achieved state-of-the-art performance on benchmark datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Xin He et al.
Summary: In this paper, a novel semantic segmentation framework called ST-UNet is proposed for remote sensing images. By incorporating Swin Transformer and CNN, the framework achieves improved segmentation accuracy. The introduced spatial interaction module, feature compression module, and relational aggregation module effectively utilize global context information and local features, leading to significant performance improvements.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Rui Li et al.
Summary: Semantic segmentation of remote sensing images is vital for various applications such as land resource management and urban planning. Despite the improvement in accuracy with deep convolutional neural networks, standard models have limitations like underuse of information and insufficient exploration of long-range dependencies. This article introduces a multiattention network (MANet) with efficient attention modules to address these issues and demonstrates superior performance on large-scale remote sensing datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Artificial Intelligence
Gaihua Wang et al.
Summary: The semantic segmentation of remote sensing images is a critical and challenging task. Many methods based on convolutional neural networks have been explored, but the results are not satisfactory due to the uniqueness of remote sensing images. To solve this problem, a special network is designed and tested on remote sensing datasets, showing the best results and state-of-the-art performance.
IET IMAGE PROCESSING
(2022)
Article
Computer Science, Artificial Intelligence
Priyanka et al.
Summary: This paper presents an AI-based approach for scene understanding in high-resolution aerial images. The proposed DIResUNet model combines different modules and structures to extract both local and global information, leading to improved performance in pixel-level classification.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Hai-Feng Zhong et al.
Summary: This paper proposes an automatic extraction method of lake water bodies based on semantic segmentation, using a multi-scale information enhancement network and a two-way channel attention mechanism to enhance the network's capability and accuracy, experimental results show that this method has better segmentation accuracy than others.
APPLIED INTELLIGENCE
(2022)
Article
Computer Science, Theory & Methods
Yujin Zhang et al.
Summary: This study proposes an end-to-end deep learning model for robust smooth filtering identification. By introducing Squeeze-and-Excitation block and multiple Inception-Residual blocks, it can effectively learn different filtering operations and perform well in various scenarios.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Remote Sensing
Rui Li et al.
Summary: The thriving development of earth observation technology has made it easier to obtain high-resolution remote-sensing images. However, the complexity caused by fine-resolution makes automated semantic segmentation a challenging task. To tackle this issue, researchers propose a novel framework called Attention Aggregation Feature Pyramid Network (A(2)-FPN) that uses the Feature Pyramid Network (FPN) and Attention Aggregation Module (AAM) to enhance multiscale feature learning. Extensive experiments demonstrate the effectiveness of A(2)-FPN in segmentation accuracy.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2022)
Review
Environmental Sciences
Huiwei Jiang et al.
Summary: This paper provides a review of the latest progress and challenges in deep learning-based change detection algorithms using high-resolution remote sensing images, and suggests promising directions for future research.
Article
Environmental Sciences
Yalan Zheng et al.
Summary: Semantic segmentation plays a crucial role in remote sensing interpretation. This study proposes a novel semi-supervised adversarial semantic segmentation network that utilizes a multiscale input convolution module and a Transformer module for feature extraction. The network is trained under the semi-supervised adversarial learning framework, along with a double-branch discriminator network, to enhance segmentation accuracy. Experimental results on different datasets demonstrate the effectiveness of the proposed network in improving semantic segmentation accuracy, outperforming other methods.
Review
Environmental Sciences
Zheng Li et al.
Summary: This paper reviews the development history of remote sensing object detection techniques and systematically summarizes the steps used in deep learning-based detection algorithms. It introduces a taxonomy based on various detection methods, summarizing major improvement strategies such as attention mechanisms, multi-scale feature fusion, and super-resolution. It also presents recognized open-source benchmarks and evaluation metrics for remote sensing detection. Lastly, it discusses the challenges and potential trends in the field of RSOD.
Article
Environmental Sciences
Zhiqiang Liu et al.
Summary: In this paper, a novel approach called EGCAN is proposed for semantic segmentation of remote sensing imagery. It utilizes edge guidance and minority category extraction to enhance semantic modeling. The proposed method achieves superior performance on multiple datasets.
Article
Environmental Sciences
Hong Wang et al.
Summary: This study discusses the efficient method of semantic segmentation using remote sensing images for agricultural crop classification and the challenges it faces. A novel architecture named CCTNet is proposed to address these challenges, along with two fusion modules and three effective methods aimed at improving classification accuracy and image completeness. Experimental results demonstrate that CCTNet outperforms single CNN or Transformer methods in terms of mean Intersection over Union (mIoU) scores, making it a competitive option for crop segmentation through remote sensing images.
Article
Computer Science, Information Systems
Zhongyu Sun et al.
Summary: This paper proposes a Hybrid Multi-resolution and Transformer semantic extraction Network (HMRT) that can provide a global receptive field, overcome the limitations of existing methods on high-resolution remote sensing images, and enhance scene understanding ability.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2022)
Review
Computer Science, Software Engineering
Meng-Hao Guo et al.
Summary: Attention mechanisms, inspired by the human visual system, have been successfully applied in various computer vision tasks. This survey provides a comprehensive review of different types of attention mechanisms and suggests future research directions.
COMPUTATIONAL VISUAL MEDIA
(2022)
Article
Computer Science, Artificial Intelligence
Jiaqi Zhao et al.
Summary: This paper proposes an end-to-end multisource remote sensing image semantic segmentation network (MCENet) to address the issues of intra-class inconsistency and inter-class indistinguishability in remote sensing images. Experimental results demonstrate significant performance improvements of our method on two datasets, with competitive advantages in terms of parameter quantity and inference speed.
Article
Computer Science, Hardware & Architecture
Xingjian Gu et al.
Summary: A novel Adaptive Enhanced Swin Transformer with U-Net (AESwin-UNet) model is proposed for remote sensing segmentation, which combines the advantages of CNN and Transformer and achieves good semantic segmentation performance.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Computer Science, Interdisciplinary Applications
Inuwa Mamuda Bello et al.
Summary: This study introduces an accurate and highly efficient densely multiscale segmentation network specifically for real-time segmentation of remotely sensed imagery, improving the network's representation capability by embedding its structure with dense connections, suitable for real-time remote sensing applications.
COMPUTERS & GEOSCIENCES
(2022)
Article
Environmental Sciences
Jiabao Ma et al.
Summary: The study proposed a deep-separation-guided progressive reconstruction network to address the challenges of scale variation and feature reconstruction in remote sensing image segmentation. Experimental results demonstrated that the network outperformed existing methods in accuracy and performance.
Article
Environmental Sciences
Bo Liu et al.
Summary: This article introduces a new framework called PGNet for semantic segmentation of VHR remote sensing images. It effectively improves the segmentation results through the positioning guidance module and the self-multiscale collection module. Experimental results show that PGNet achieves higher mIoU scores compared to FactSeg, with an improvement of 1.49% and 2.40% on the iSAID dataset and ISPRS Vaihingn dataset, respectively.
Article
Environmental Sciences
Xin Li et al.
Summary: This article introduces ICTNet, which aims to address the issue of contextual information in semantic segmentation of remote sensing imagery. By using an encoder-decoder architecture, ICTNet is able to learn local patterns and long-range dependencies simultaneously, improving the performance of the network.
Article
Environmental Sciences
Yiyun Luo et al.
Summary: This study proposed a semantic segmentation method based on pixel representation augmentation, which utilizes a cross-attention mechanism in the Transformer to achieve excellent performance, effectively addressing two key issues in the transfer process from natural image segmentation to land cover classification.
Article
Environmental Sciences
Weitao Li et al.
Summary: This study proposes two training strategies to enhance the performance of unsupervised domain adaptation (UDA) for remote sensing image semantic segmentation, using Transformer model and a self-training framework. Experimental results show that the proposed method achieves significant performance improvement over state-of-the-art models on two datasets.
Article
Environmental Sciences
Renan Bides de Andrade et al.
Summary: The Amazon rainforest covers more than half of the remaining tropical forest on Earth and plays a crucial role in regulating rainfall patterns in South America while also holding significant biotechnological potential. Threats such as forest fires, illegal mining, and logging pose risks to the survival of the Amazon, making the use of deep learning to detect deforestation highly effective.
Article
Physics, Multidisciplinary
Yufen Xu et al.
Summary: In this study, a novel U-shaped architecture based on Swin Transformer and Unet is proposed, achieving exceptional results in semantic segmentation of very-high-resolution remote sensing images. By combining dual encoders, a multi-path fusion model, and a dynamic attention pyramid head, the limitations of fixed receptive field and position loss are effectively addressed.
Proceedings Paper
Computer Science, Artificial Intelligence
Martina Pastorino et al.
Summary: This paper introduces a novel semantic segmentation method for very high resolution remotely sensed images, combining fully convolutional networks and feedforward neural networks to achieve accurate classification results, especially in the case of sparse ground truth data.
2022 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, ICIP
(2022)
Article
Geochemistry & Geophysics
Yan Zhang et al.
Summary: This paper proposes an efficient deformable hybrid Transformer (DHT) method, which simultaneously extracts global and local information by introducing deformable orientational self-attention (DoA) and depthwise channel self-attention (DcA) techniques. It achieves high-quality object segmentation on high-resolution aerial images while reducing the dependence on pretrained parameters.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Lingfei Ma et al.
Summary: This study proposes a saliency-guided transformer architecture (STN) for point-wise semantic segmentation of road objects using mobile laser scanning (MLS) point clouds. By constructing feature saliency maps and integrating offset attention mechanisms and edge convolutions, the model can extract high-level features and perform accurate label assignment for road objects.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Zhen Wang et al.
Summary: A novel SSS image segmentation method is proposed in this study, which improves the limitations of existing methods by extracting multiscale features, constructing adaptive receptive field mechanisms, and designing feature fusion attention mechanisms. The method achieves high accuracy in SSS image segmentation and outperforms other state-of-the-art methods in terms of speed and calculation parameters.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Engineering, Electrical & Electronic
Zhen Li et al.
Summary: This paper presents a horizontally connected residual blocks-based multiscale attention network for high-quality extraction of buildings in high spatial resolution (HSR) remote sensing images. The experiments show that this method can achieve better building extraction results.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2022)
Article
Geochemistry & Geophysics
Guanzhou Chen et al.
Summary: This article introduces an efficient unsupervised remote sensing image segmentation method based on superpixel segmentation and fully convolutional networks. The method can rapidly achieve pixel-level image segmentation without requiring manual labels or prior knowledge.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geochemistry & Geophysics
Hai-Feng Zhong et al.
Summary: This article proposes an end-to-end semantic segmentation network (NT-Net) for the automatic extraction of lake water bodies from remote sensing images. By utilizing an interference attenuation module and a multilevel transformer module, the method addresses the issues of over-segmentation and inaccurate boundary segmentation.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Dongdong Feng et al.
Summary: In this paper, a semantic segmentation method for remote sensing images based on Swin Transformer fusion with a Gabor filter is proposed. The method achieved high accuracy and improved performance in the semantic segmentation of high-precision remote sensing images.
Article
Geochemistry & Geophysics
Hanwen Xu et al.
Summary: This paper proposes a feature-selection high-resolution network (FSHRNet) that maintains high-resolution features throughout the network to achieve high-precision segmentation results. Experimental results show that FSHRNet performs competitively on multiple datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
A. Pugazhenthi et al.
Summary: This paper explores and evaluates the benefits and drawbacks of various image segmentation evaluation metrics used in remote sensing applications. Several algorithms are compared and analyzed, and the IFCM algorithm performs the best among unsupervised machine learning algorithms, while the DT algorithm performs the best among supervised machine learning algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Geochemistry & Geophysics
Xiaoliang Meng et al.
Summary: Semantic segmentation of remote sensing images is crucial in practical applications. CNN-based methods have limitations, while Vision Transformer shows great potential.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geography, Physical
Shouji Du et al.
Summary: This study proposes a semantic segmentation method for VHR images by combining a deep learning semantic segmentation model and object-based image analysis, which aims to capture precise outlines of ground objects and explore context information, achieving competitive overall accuracies for Vaihingen and Potsdam datasets.
INTERNATIONAL JOURNAL OF DIGITAL EARTH
(2021)
Article
Geochemistry & Geophysics
Jie Chen et al.
Summary: A novel semantic segmentation framework named SMAF-Net is proposed in this study, which utilizes multiscale adversarial features to improve boundary accuracy of geo-objects. Comparison experiments on the Potsdam and Vaihingen datasets demonstrate considerable improvement in HRSI semantic segmentation.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Remote Sensing
Yanheng Wang et al.
Summary: This paper presents a feature regularized mask DeepLab (FRM-DeepLab) algorithm for high-resolution change detection, which utilizes the MaskNet framework and autoencoder to alleviate overfitting issues, achieving significant performance improvements by combining middle-level feature extraction techniques.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2021)
Article
Geography, Physical
Rui Li et al.
Summary: Semantic segmentation of remotely sensed imagery is crucial in various applications, such as environmental protection and precision agriculture. However, current deep learning algorithms often come with high computational demand, hindering real-time practical applications. The proposed ABCNet balances computational efficiency and accuracy, outperforming lightweight benchmark methods in segmentation tasks.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2021)
Article
Computer Science, Information Systems
Yujin Zhang et al.
Summary: The rapid development of blockchain technology has changed people's daily lives significantly. It is necessary to identify image authenticity on the blockchain, and the proposed method of diffusion-based image inpainting via weighted least squares filtering enhancement can effectively enhance image forensics on the blockchain.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Software Engineering
Liang Tian et al.
Summary: This paper proposes a new image semantic segmentation method based on Generative Adversarial Network (GAN) and Fully Convolutional Neural Network (FCN). Experimental results demonstrate that this method can meet the high-efficiency requirements of complex image semantic segmentation.
SCIENTIFIC PROGRAMMING
(2021)
Article
Chemistry, Analytical
Sijun Dong et al.
Summary: The study proposes a multi-level feature fusion network for high-resolution remote sensing image segmentation, achieving good results. The aim of the research is to improve the recognition results of remote sensing image segmentation.
Article
Environmental Sciences
Shuting Sun et al.
Summary: The study introduces a method to reduce intra-class differences by using two orthogonal generative adversarial networks to generate backgrounds and targets separately. By connecting the two networks' discriminators with a new loss function, and drawing on the idea of fine-grained image classification during building feature extraction, feature vectors for targets are clustered and used to train semantic segmentation networks.
Article
Environmental Sciences
Yingying Kong et al.
Summary: This study proposes an encoding-decoding network based on Deeplabv3+ for semantic segmentation of SAR images and introduces a new potential energy loss function and improved attention module to enhance recognition accuracy.
Article
Computer Science, Information Systems
Hui Lu et al.
Summary: This paper introduces and analyzes the research and application progress of remote sensing image satellite data processing from the perspective of semantics, with a focus on technical advancements in the field of semantic construction, particularly deep learning technology. Furthermore, it discusses in detail the challenges and problems in semantic description, semantic classification, and semantic search, aiming to provide more directions for future exploration.
JOURNAL OF ORGANIZATIONAL AND END USER COMPUTING
(2021)
Article
Environmental Sciences
Teerapong Panboonyuen et al.
Summary: A DL model with Swin Transformer as the backbone and three decoder designs for semantic segmentation achieved state-of-the-art results in various tasks.
Article
Environmental Sciences
Xinyue Zhang et al.
Summary: This paper introduces the research status and development trend of multi-modal remote sensing image registration methods, including three theoretical frameworks: area-based, feature-based, and deep learning-based methods. It explores traditional methods and more advanced methods proposed in recent years, aiming to provide researchers in related fields with a deeper understanding for further breakthroughs and innovations.
Article
Environmental Sciences
Guanzhou Chen et al.
Summary: Semantic segmentation is a fundamental task in remote sensing image analysis, and our proposed SDFCNv2 framework shows better performance on remote sensing images compared to the SDFCNv1 framework, increasing the mIoU metric by up to 5.22% while using only about half of the parameters.
Article
Environmental Sciences
Xin Zhao et al.
Summary: The proposed memory-augmented transformer (MAT) effectively models both local and global information in semantic segmentation of remote sensing images. It utilizes memory interaction and bidirectional information flow to achieve global guidance and local feature extraction.
Article
Geochemistry & Geophysics
Haifeng Li et al.
Summary: A new end-to-end semantic segmentation network integrating lightweight spatial and channel attention modules is proposed, which can better optimize features. Experimental results demonstrate that this method can achieve better semantic segmentation results.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2021)
Article
Geochemistry & Geophysics
Danfeng Hong et al.
Summary: This article addresses the challenge of semantic segmentation in large-scale urban scenes with limited cross-modality data, introducing two novel plug-and-play units: self-generative adversarial networks (GANs) module and mutual-GANs module, as well as a patchwise progressive training strategy. Significant improvement is achieved through evaluation on two multimodal image datasets.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Pourya Shamsolmoali et al.
Summary: A new model is introduced to apply structured domain adaption for synthetic image generation and road segmentation, incorporating a feature pyramid network into generative adversarial networks to minimize the difference between the source and target domains and improve road extraction accuracy and completeness.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Xin Pan et al.
Summary: This article proposes a conditional generative adversarial network (CGAN)-based training sample set improvement model for semantic segmentation of high-resolution remote sensing images, which generates diverse sample images containing various object combinations, directions, and locations to improve the spatial information diversity of the original training sample set. This approach actively generates new sample images by extracting high-level spatial information from the original training images, leading to improved classification accuracy compared to traditional methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Environmental Sciences
Ziyi Chen et al.
Summary: This study introduces a U-Net architecture that combines self-attention and reconstruction-bias modules to enhance semantic segmentation ability, achieving high IoU scores on the WHU and Massachusetts Building datasets.
Article
Environmental Sciences
Valerio Marsocci et al.
Summary: The paper proposes a combination of a self-supervised learning algorithm and a semantic segmentation algorithm, focusing on aerial images, and achieves new encouraging results on the ISPRS Vaihingen dataset.
Article
Environmental Sciences
Abolfazl Abdollahi et al.
Summary: The study introduces two novel deep convolutional models based on the UNet family for multi-object segmentation from aerial imagery. The proposed methods leverage densely connected convolutions, bi-directional ConvLSTM, and a squeeze and excitation module to produce high-resolution segmentation maps, maintaining boundary information under complicated backgrounds. The networks outperformed other state-of-the-art deep learning-based models in multi-object segmentation tasks.
Article
Environmental Sciences
Rafik Ghali et al.
Summary: This study explores the potential of using vision Transformers for forest fire segmentation, presenting two frameworks based on Transformers that outperform current methods. Extensive evaluations showed superior performance, achieving state-of-the-art results in forest fire pixel mis-classification reduction and finer detection of fire shape.
Article
Environmental Sciences
Zhiyong Xu et al.
Summary: This study introduces a novel Efficient Transformer model to address edge classification issues in remote sensing image semantic segmentation, significantly improving accuracy while balancing computational complexity. By accelerating inference speed and introducing edge enhancement methods, improvements were achieved on the Potsdam and Vaihingen datasets.
Article
Environmental Sciences
Seonkyeong Seong et al.
Summary: This study utilized csAG-HRNet for building extraction in aerial images, incorporating HRNet-v2 with channel and spatial attention gates to efficiently learn important features and minimize false detections based on the shapes of large buildings and small nonbuilding objects compared to existing deep learning models.
Article
Environmental Sciences
Libo Wang et al.
Summary: Proposed a Bilateral Awareness Network, combining a dependency path and a texture path to capture long-range relationships and details in VFR images. Designed a feature aggregation module using linear attention mechanism to effectively fuse dependency features and texture features. Achieved significant results on large-scale urban scene image segmentation datasets.
Article
Computer Science, Information Systems
Chunhua Li et al.
Summary: This study presents a neural network model for semantic segmentation of remote-sensing imagery, which effectively enhances feature discriminability and the utilization of contextual information through self-attention and dense connection techniques. Experimental results show significant improvements compared to other methods.
Article
Engineering, Electrical & Electronic
Yun-Cheng Li et al.
Summary: The study introduces a novel dual-channel scale-aware segmentation network for effective semantic segmentation of high-resolution aerial images. By utilizing Xception branch and DSMPCF branch to process different types of image information, and incorporating position and channel attention in the proposed model, it achieves more accurate and efficient results.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Subhashree Subudhi et al.
Summary: Recent advancements in hyperspectral sensors allow for higher resolution hyperspectral images, but also present challenges. Superpixels offer a potential solution to these challenges by simplifying processing steps. Superpixels have been successfully applied in various areas of hyperspectral image processing, including classification, spectral unmixing, dimensionality reduction, band selection, active learning, denoising, and anomaly detection.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Engineering, Electrical & Electronic
Liang Gao et al.
Summary: The STransFuse model is a new method that combines Transformer and CNN for remote sensing image segmentation, utilizing an adaptive fusion module to extract features at different scales and fuse semantic information, achieving higher overall accuracy compared to the baseline.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Geochemistry & Geophysics
Lei Ding et al.
Summary: Two proposed modules, Patch Attention Module (PAM) and Attention Embedding Module (AEM), enhance feature representation in remote sensing images by bridging the gap between high-level and low-level features. Experimental results show that integrating these modules into a baseline fully convolutional network greatly improves performance and outperforms other attention-based methods.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2021)
Article
Geography, Physical
Xueliang Zhang et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2020)
Article
Computer Science, Artificial Intelligence
N. Venugopal
NEURAL PROCESSING LETTERS
(2020)
Review
Environmental Sciences
M. Weiss et al.
REMOTE SENSING OF ENVIRONMENT
(2020)
Article
Geochemistry & Geophysics
Lunhao Duan et al.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2020)
Article
Geography, Physical
Foivos Diakogiannis et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2020)
Article
Computer Science, Information Systems
Liguo Weng et al.
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION
(2020)
Article
Geochemistry & Geophysics
Lei Ding et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Article
Geography, Physical
Ye Lyu et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2020)
Correction
Geography, Physical
Li Mi et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2020)
Article
Geochemistry & Geophysics
Yao Wei et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Article
Geography, Physical
Xianwei Zheng et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2020)
Article
Environmental Sciences
Aaron E. Maxwell et al.
Article
Environmental Sciences
Yansheng Li et al.
Article
Geochemistry & Geophysics
Lichao Mou et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2020)
Article
Engineering, Electrical & Electronic
Xian Sun et al.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2020)
Article
Engineering, Electrical & Electronic
Zhenfeng Shao et al.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2020)
Article
Computer Science, Artificial Intelligence
Yi Sun et al.
Review
Computer Science, Interdisciplinary Applications
Anju Asokan et al.
EARTH SCIENCE INFORMATICS
(2019)
Article
Geochemistry & Geophysics
Yahui Liu et al.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2019)
Article
Geography, Physical
Michael Wurm et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2019)
Article
Engineering, Electrical & Electronic
Haifeng Luo et al.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2019)
Review
Chemistry, Analytical
Grigorios Tsagkatakis et al.
Article
Geography, Physical
Kai Yue et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2019)
Article
Environmental Sciences
Yansong Liu et al.
JOURNAL OF APPLIED REMOTE SENSING
(2019)
Article
Environmental Sciences
Teerapong Panboonyuen et al.
Article
Geography, Physical
Yongcheng Liu et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2018)
Article
Geochemistry & Geophysics
Kaiqiang Chen et al.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2018)
Article
Engineering, Electrical & Electronic
Antonia Creswell et al.
IEEE SIGNAL PROCESSING MAGAZINE
(2018)
Article
Computer Science, Artificial Intelligence
Liang-Chieh Chen et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2018)
Article
Geography, Physical
Ronald Kemker et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2018)
Article
Geography, Physical
D. Marmanis et al.
ISPRS JOURNAL OF PHOTOGRAMMETRY AND REMOTE SENSING
(2018)
Review
Computer Science, Artificial Intelligence
Ying Li et al.
WILEY INTERDISCIPLINARY REVIEWS-DATA MINING AND KNOWLEDGE DISCOVERY
(2018)
Article
Environmental Sciences
Sankaranarayanan Piramanayagam et al.
Article
Computer Science, Artificial Intelligence
Vijay Badrinarayanan et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Article
Computer Science, Artificial Intelligence
Evan Shelhamer et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Article
Geochemistry & Geophysics
Xiao Xiang Zhu et al.
IEEE GEOSCIENCE AND REMOTE SENSING MAGAZINE
(2017)
Article
Geochemistry & Geophysics
Qin Zou et al.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2015)
