检索结果-内蒙古大学图书馆

Efficient transformer architecture for extraction of global and local dependencies to dehaze RS satellite images

signal image AND VIDEO processing 2024年第12期18卷 8899-8909页

作者： Mallesh, Sudhamalla Haripriya, D. Anurag Univ Dept ECE Hyderabad 500088 Telangana India

Existing methods for dehazing remote sensing (RS) images using deep learning have typically relied on convolutional frameworks. However, the limitations inherent in convolution, such as local receptive fields and independent input elements, hinder the network's ability to grasp long-range dependencies and nonuniform distributions. Consequently, the network is constrained in its capacity to learn these aspects. In response to this challenge, a proficient architecture for enhancing the clarity of remote sensing images through transformation, labeled RSDformer, has been designed. The architecture is structured to tackle the non-regular formations and varied spreads of hazing commonly found inside pictures of remote sensing. Emphasizing the importance of acquiring features from both nearby and distant areas, the design incorporates a novel detail-compensated transposed attention (DCTA) mechanism. This mechanism aims to get both localized and globalized dependency throughout channel. Furthermore, for enhancing model's capability towards learning from aspects that have undergone degradation and direct processes of restoring effectively, the DFBA or dualized frequencies blocks ( adaptive) with filters of dynamic type has been developed. In the end DGBF or blocks of fusion that are dynamic has been devised to facilitate the effective fusion along with exchanging of aspects over differing levels. Through these innovations, these frameworks demonstrate robustness in their capability in capturing dependency in local regions and regions that are globalized, thereby enhancing restoration of visual information within the image. Wide-ranging experimental evaluations confirm superiorities of the proposed methodology over other competitive approaches.

关键词： DCTA RSDformers remote sensing Dehazing

来源：评论

学校读者我要写书评

暂无评论

ATTENTION ENHANCEMENT WITH PARALLEL GROUPS FOR remote sensing OBJECT DETECTION 31

ATTENTION ENHANCEMENT WITH PARALLEL GROUPS FOR REMOTE SENSIN...

引用

2024 International conference on image processing

作者： Yang, Zhigang Liu, Yiming Gao, Zehao He, Jiayue Chen, Tao Zhang, Wei Emma Harbin Engn Univ Coll Informat & Commun Engn Harbin 150001 Peoples R China Univ Adelaide Sch Comp Sci Adelaide SA 5005 Australia

ISBN: (纸本)9798350349405;9798350349399

Nowadays, remote sensing object detection has benefited a lot from the development of convolutional neural networks (CNNs). However, it is still a challenging task due to arbitrary orientation and dense distribution of objects in remote sensing images. To deal with these difficulties, we propose two effective attention mechanisms with parallel groups strategy to enhance feature representations in the detection head, named PGAE-head. Significantly, our designs can achieve competitive performance improvement by only introducing tiny parameters and computations in the model. Firstly, the features received by the PGAE-head are divided into multiple groups, which ensures the independence of each group during subsequent attention enhancement. Then, PGAE-head processes these sub-features with enhanced attention mechanisms based on spatial and channel dimensions in parallel to detect more accurate results. Experiments on DOTA and HRSC datasets show that the proposed PGAE-head achieves comparable performances with other state-of-the-art CNN-based models at minimal optimization costs, demonstrating its effectiveness.

关键词： remote sensing image object detection parallel groups attention enhancement detection head

来源：评论

学校读者我要写书评

暂无评论

Domain Generalized Object Detection for remote sensing images 31

Domain Generalized Object Detection for Remote Sensing Image...

引用

31st IEEE conference on signal processing and Communications Applications (SIU)

作者： Durakli, Efkan Aptoula, Erchan Gebze Tech Univ Dept Comp Engn Kocaeli Turkiye Sabanci Univ Fac Engn & Nat Sci Istanbul Turkiye

ISBN: (纸本)9798350343557

Building roof type detection from remotely sensed images is a crucial task for many remote sensing applications, including urban planning and disaster management. In recent years, deep learning-based object detection approaches have demonstrated outstanding performance in this field. However, most of these approaches assume that the training and testing data are sampled from the same distribution. When there are differences between the distributions of training and test data, known as domain shift, the performance significantly degrades. In this paper, we proposed a domain generalization method to address domain shift at the instance and image level for roof type detection from remote sensing images. Furthermore, we evaluated our proposed method with IEEE Data Fusion Contest 2023 dataset. The proposed approach is the first of its kind in terms of domain generalization for remote sensing object detection.

关键词： domain generalization object detection remote sensing

来源：评论

学校读者我要写书评

暂无评论

GABOR FEATURE NETWORK FOR TRANSFORMER-BASED BUILDING CHANGE DETECTION MODEL IN remote sensing 31

GABOR FEATURE NETWORK FOR TRANSFORMER-BASED BUILDING CHANGE ...

引用

2024 International conference on image processing

作者： Osa, Priscilla Indira Zerubia, Josiane Kato, Zoltan Univ Genoa DITEN Dept Genoa Italy Univ Cote Azur INRIA Nice France Univ Szeged Inst Informat Szeged Hungary J Selye Univ Komarno Slovakia

ISBN: (纸本)9798350349405;9798350349399

Detecting building change in bitemporal remote sensing (RS) imagery requires a model to highlight the changes in buildings and ignore the irrelevant changes of other objects and sensing conditions. Buildings have comparatively less diverse textures than other objects and appear as repetitive visual patterns on RS images. In this paper, we propose Gabor Feature Network (GFN) to extract the distinctive repetitive texture features of buildings. Furthermore, we also design Feature Fusion Module (FFM) to fuse the extracted multiscale features from GFN with the features from a Transformer-based encoder to pass on the texture features to different parts of the model. Using GFN and FFM, we design a Transformer-based model, called GabFormer for building change detection. Experimental results on the LEVIR-CD and WHU-CD datasets indicate that GabFormer outperforms other SOTA models and in particular show significant improvement in the generalization capability. Our code is available on https://***/Ayana-Inria/GabFormer.

关键词： Transformer Gabor feature building change detection remote sensing image analysis

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Methods for Lithology Classification and Identification in remote sensing images

引用

IEEE ACCESS 2025年 13卷 3038-3050页

作者： Zhang, Zhijun Wang, Ming Qi, Yueji Su, Xiaoqin Kong, Di China Univ Geosci Wuhan Key Lab Geol Survey & Evaluat Minist Educ Wuhan 430074 Hubei Peoples R China China Geol Survey Langfang Integrated Nat Resources Survey Ctr Langfang 065000 Hebei Peoples R China China Geol Survey Xining Ctr Integrated Nat Resources Survey Xining 810000 Qinghai Peoples R China China Geol Survey Geophys Survey Ctr Langfang 065000 Hebei Peoples R China

This study presents a deep learning model that integrates Vision Transformers (ViT) with Fourier spectral filtering for remote sensing lithology classification. The model automates the process of identifying and classifying various rock types in remote sensing images, addressing a multi-class classification challenge. It utilizes ViT for feature extraction, enhanced by pretrained weights for improved efficiency and accuracy in recognizing geographical features. Fourier spectral filtering further augments the model by leveraging frequency domain information for accurate classification. The model preprocesses images, extracts spatial features, applies spectral filtering, and employs a classification head to predict rock types. Optimization of parameters through backpropagation and gradient descent methods, coupled with regularization strategies, aims to prevent overfitting and ensure generalizability. This approach combines deep learning's capability for feature extraction with the analytical power of signal processing, offering a significant advancement for automatic rock type classification in remote sensing.

关键词： Rocks remote sensing Feature extraction Geology Accuracy Radar polarimetry Deep learning Filtering Data mining Surveys Lithography Classification algorithms Synthetic aperture radar Speckle Noise measurement remote sensing image lithology classification deep learning technology SAR image speckle noise

来源：评论

学校读者我要写书评

暂无评论

Look Twice and Closer: A Coarse-to-Fine Segmentation Network for Small Objects in remote sensing images

引用

IEEE signal processing LETTERS 2025年 32卷 826-830页

作者： Chen, Silin Wang, Qingzhong Di, Kangjian Xiong, Haoyi Zou, Ningmu Nanjing Univ Sch Integrated Circuits Suzhou 210093 Peoples R China Baidu Inc Beijing 100193 Peoples R China Nanjing Univ Interdisciplinary Res Ctr Future Intelligent Chips Suzhou 210093 Peoples R China

Convolutional neural networks (CNNs) are frequently used to analyze remote sensing images and achieve impressive progress. Limited by the receptive field size of CNNs, small objects tended to lack adequate features to obtain more accurate segmentation results. To address this problem, we introduce a novel CNN model for coarse-to-fine segmentation called C2FNet. C2FNet comprises two stages: the coarse network and the fine network. The coarse network identifies the positions and coarse segmentation outcomes of small objects in the input image. The fine network then takes a closer look at the small objects and re-segments the patches using binary segmentation. The fine network distinguishes small objects from the background to refine small object segmentation. Finally, C2FNet employs an aggregation module that merges the binary segmentation maps and coarse outcomes to obtain accurate small object segmentation. We conducted extensive experiments on three widely accepted datasets for remote sensing image segmentation, namely the ISPRS 2-D semantic labeling Potsdam, Vaihingen, and iSAID. Our approach significantly improves the performance of baseline models, achieving a 0.24%-2.83% increase in IoU per small object class on iSAID.

关键词： image segmentation remote sensing Training Accuracy Semantic segmentation Object segmentation Feature extraction Sensors Integrated circuit modeling Electronic mail Deep learning remote sensing images semantic segmentation small objects

来源：评论

学校读者我要写书评

暂无评论

Efficient High-Frequency Texture Recovery Diffusion Model for remote sensing image Super-Resolution

引用

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT 2025年 74卷

作者： Weng, Wu-Ding Zheng, Chao-Wei Su, Jian-Nan Chen, Guang-Yong Gan, Min Fuzhou Univ Coll Comp & Data Sci Fuzhou 350116 Peoples R China Minist Educ Fujian Key Lab Network Comp & Intelligent Informat Key Lab Intelligent Metro Univ Fujian Fuzhou 350108 Peoples R China Minist Educ Engn Res Ctr Big Data Intelligence Fuzhou 350108 Peoples R China Putina Univ New Engn Ind Coll Putian 351100 Fujian Peoples R China Putian Univ Putian Elect Informat Ind Technol Res Inst Putian 351100 Fujian Peoples R China Qingdao Univ Coll Comp Sci & Technol Qingdao 266071 Peoples R China

remote sensing super-resolution (SR), which aims to reconstruct high-resolution (HR) images with rich spatial details from low-resolution (LR) remote sensing images predominantly composed of low-frequency components, presents a challenging yet practical task. Existing diffusion model (DM)-based methods for remote sensing SR are inefficient, requiring extensive iterations and often failing to recover high-frequency details adequately due to a lack of targeted processing for high-frequency components. To mitigate these challenges, this article introduces an efficient DM for remote sensing image SR, termed image reconstruction representation-diffusion model for super-resolution (IRR-DiffSR). IRR-DiffSR employs a feature extraction encoder to extract the image reconstruction representation (IRR) from ground-truth (GT) images, which makes the reconstruction network focus more on recovering high-frequency textures. Unlike traditional DM-based methods that learn the direct mapping from LR to HR images, IRR-DiffSR employs a pre-trained encoder to guide the DM in extracting consistent IRR directly from LR images. This auxiliary information aids in the efficient and effective reconstruction of high-frequency textures. By serving as an implicit reconstruction prior, this enables the DM to achieve accurate estimations with fewer iterations, thus assisting IRR-DiffSR in recovering high-frequency information more efficiently and effectively. Extensive experiments on four remote sensing datasets demonstrate that IRR-DiffSR achieves state-of-the-art reconstruction results in both real and synthetic scenarios. Specifically, in real scenarios, IRR-DiffSR outperforms the next best method by 0.766 and 0.69 in the naturalness image quality evaluator (NIQE), while in synthetic scenarios, it achieves peak signal-to-noise ratio (PSNR) improvements of 1.07 and 0.51. These results highlight the effectiveness and efficiency of IRR-DiffSR in recovering high-frequency details. Our code and pre-

关键词： image reconstruction remote sensing Superresolution Diffusion models Feature extraction Training Data mining image restoration Visualization Brain modeling Diffusion model (DM) image reconstruction image super-resolution (SR) reconstruction representation remote sensing

来源：评论

学校读者我要写书评

暂无评论

remote sensing and image processing Techniques for Water Environment Monitoring: A Case Study of the Beijing-Tianjin-Hebei Region

引用

TRAITEMENT DU signal 2023年第4期40卷 1771-1779页

作者： Zhang, Yiting Lun, Haibo Hebei Univ Environm Engn Dept Environm Engn Qinhuangdao 066012 Hebei Peoples R China Hebei Key Lab Agr Ecol Secur Qinhuangdao 066012 Hebei Peoples R China Hebei Univ Environm Engn Environm Technol Res & Expt Ctr Qinhuangdao 066012 Hebei Peoples R China

With rapid economic and urban progression, water resource and environmental challenges have become increasingly evident. This research focuses on water environment monitoring in the Beijing-Tianjin-Hebei region, employing advanced remote sensing and image processing methodologies. A technique was developed to extract the spatial location features of water bodies using remote sensing image segmentation. In addition, a novel spectral feature extraction technique predicated on a double inverse Gaussian model was introduced. This innovative method adeptly captures the contours of absorption peaks, facilitating the expression and extraction of spectral characteristics inherent to the water bodies. These methodologies were primarily designed to offer both theoretical and technical insights into the spatial distribution and temporal dynamics of the water environment. The outcomes of this study are comprehensively examined, with potential enhancements and prospective trends in water environment monitoring elucidated.

关键词： remote sensing images Beijing-Tianjin-Hebei region water environment monitoring

来源：评论

学校读者我要写书评

暂无评论

Global Priors With Anchored-Stripe Attention and Multiscale Convolution for remote sensing image Compression

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND remote sensing 2024年 17卷 138-149页

作者： Zhang, Lei Hu, Xugang Pan, Tianpeng Zhang, Lili Shenyang Aerosp Univ Coll Elect & Informat Engn Shenyang 110136 Peoples R China

Compressing remote sensing images with high spatial and spectral resolution plays an important role in subsequent image processing and information acquisition. Accurate data modeling can help the entropy model to better estimate the entropy value. For better image recovery, it is necessary to make full use of the prior information contained in the latent information. To achieve global association and hierarchical modeling of latent elements, this article proposes adding additional global anchored-stripe self-attention capturing global, local, and interchannel dependencies. To enhance the feature extraction capabilities of the encoder and the decoder, the multiscale attention module of depthwise convolution is used to increase the receptive field and nonlinear conversion process, ensuring that the network can retain more useful information. We evaluate the compression performance of the proposed method in terms of rate-distortion curves and running speed. Through comparative experiments on DOTA, LoveDA, and UC-Merced datasets, it is shown that the proposed method has a faster running speed than that of the context model. It outperforms some traditional compression methods, such as BPG, WebP, JPEG2000, and state-of-the-art deep-learning-based methods, in terms of peak signal-to-noise ratio and multiscale structural similarity index measure. In terms of perceptual quality, adding perceptual loss reduces the smooth image blurring due to MSE loss, and the proposed method has better image perceptual quality under the approximate bits per pixel.

关键词： Attention mechanism multiscale convolution module object detection remote sensing image compression

来源：评论

学校读者我要写书评

暂无评论

Synthesis of complex-valued InSAR data with a multi-task convolutional neural network

引用

ISPRS JOURNAL OF PHOTOGRAMMETRY AND remote sensing 2025年 220卷 192-206页

作者： Sibler, Philipp Sica, Francescopaolo Schmitt, Michael Univ Bundeswehr Munich Dept Aerosp Engn Werner Heisenberg Weg 39 D-85577 Neubiberg Germany Hensoldt Sensors GmbH Graf Von Soden Str D-88090 Immenstaad Germany

Simulated remote sensing images bear great potential for many applications in the field of Earth observation. They can be used as controlled testbed for the development of signal and image processing algorithms or can provide a means to get an impression of the potential of new sensor concepts. With the rise of deep learning, the synthesis of artificial remote sensing images by means of deep neural networks has become a hot research topic. While the generation of optical data is relatively straightforward, as it can rely on the use of established models from the computer vision community, the generation of synthetic aperture radar (SAR) data until now is still largely restricted to intensity images since the processing of complex-valued numbers by conventional neural networks poses significant challenges. With this work, we propose to circumvent these challenges by decomposing SAR interferograms into real-valued components. These components are then simultaneously synthesized by different branches of a multi-branch encoder-decoder network architecture. In the end, these real-valued components can be combined again into the final, complex-valued interferogram. Moreover, the effect of speckle and interferometric phase noise is replicated and applied to the synthesized interferometric data. Experimental results on both medium-resolution C-band repeat-pass SAR data and high-resolution X-band single-pass SAR data, demonstrate the general feasibility of the approach.

关键词： Synthetic aperture radar (SAR) Deep learning Multitask learning image synthesis SAR interferometry (InSAR)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：