检索结果-内蒙古大学图书馆

SAR image Target recognition Using Diffusion Model and Scattering Information

IEEE GEOSCIENCE AND remote sensing LETTERS 2024年 21卷 1页

作者： Sun, Sheng-Kai He, Zi Fan, Zhen-Hong Ding, Da-Zhi Nanjing Univ Sci & Technol Dept Commun Engn Nanjing 210094 Peoples R China

The synthetic aperture radar (SAR) imaging environment, especially with limited samples, poses a serious challenge to automatic target recognition (ATR) in modern electronic reconnaissance systems. To enhance SAR image recognition performance, this study proposes a technique leveraging a diffusion model and scattering information. This method involves SAR image generation and scattering information processing to improve generalization with few-shot samples. First, the number of few-shot SAR samples was augmented using the denoising diffusion probabilistic model (DDPM). Then, the scattering information is extracted to stably calculate SAR image similarity from the scattering mechanism. Finally, the recognition task is effectively accomplished through the optimal integration of the recognition network and scattering similarity. Simulation results demonstrate that the proposed method achieves superior SAR image generation quality and recognition accuracy compared to the existing methods when the available data are extremely limited.

关键词： Radar polarimetry Scattering Target recognition image recognition Training Diffusion models Information processing Diffusion model few-shot samples synthetic aperture radar (SAR) target recognition

来源：评论

学校读者我要写书评

暂无评论

TransRefine: Transformer-augmented feature refinement for zero-shot scene classification in remote sensing images

引用

pattern recognition 2025年 162卷

作者： Damalla, Rambabu Bendre, Pratik Abhijeet Gayathri, C. Datla, Rajeshreddy Chalavadi, Vishnu Indian Inst Technol Hyderabad Dept Comp Sci & Engn Visual Learning & Intelligence VIGIL Lab Sangareddy India Mahindra Univ Dept Comp Sci & Engn Hyderabad India Adv Data Proc Res Inst ADRIN Dept Space Secunderabad India IIT Tirupathi Dept Comp Sci & Engn Chindepalle India

Zero-shot learning becomes challenging in classifying scenes of unseen classes due to the typical characteristics of remote-sensing images. The intricate variations among the scenes of remote sensing images further complicate achieving discriminative semantic knowledge. Previous studies of zero-shot scene classification have explored embedding-based and generative-based approaches as separate entities, thus underutilizing their potential in addressing these challenges. In this paper, we propose a unified framework called TransRefine that combines a semantic attribute-guided Transformer (SAGT) module, feature-generating models, and a feature refinement (FR) module for the zero-shot scene classification in remote sensing images. Firstly, we introduce the semantic attributes for four benchmark remote sensing scene classification datasets to explore the semantic knowledge in zero-shot learning. The SAGT in TransRefine helps to alleviate cross-data bias by extracting visual features based on regions with the guidance of semantic attributes. It incorporates a feature expansion encoder to enhance the transferability of visual features and a visual semantic decoder to localize the object attributes. The feature-generating models map semantic vectors to the visual features of remote-sensing images. The FR module incorporates triplet center margin loss and semantic loop consistency loss functions to capture class-related and semantically-related discriminative features for achieving intra-class closeness and interclass distinctiveness. Our extensive experiments on four benchmark remote sensing image scene classification datasets demonstrate the efficacy of TransRefine over state-of-the-art approaches. The semantic attributes and code are available at https://***/rs-scn-cls/TransRefine.

关键词： Zero-shot learning remote-sensing images Scene classification

来源：评论

学校读者我要写书评

暂无评论

A Deeper Look Into remote sensing Scene image Misclassification by CNNs

引用

IEEE ACCESS 2024年 12卷 123078-123098页

作者： Balarabe, Anas Tukur Jordanov, Ivan Univ Portsmouth Sch Comp Portsmouth PO12 UP England

As deeper and lighter variations of convolutional neural networks (CNNs) continue to break accuracy and efficiency records, their applications for solving domain-specific challenges continue to widen, particularly in computer vision and pattern recognition. The feat achieved by these end-to-end learning models can be attributed to their ability to extract local and global discriminative features for effective classification. However, in land use and land cover classification (LULC), inner-class variability and outer-class similarity could cause a classifier to confuse one image's discriminative features with another's, leading to inefficiency and poor classification. In this work, we deviate from the conventional approach of classifying high-resolution remote sensing images (HRRS) by proposing a framework for comparing and combining images of different simple classes into superclasses based on spatial, textural, and colour similarities. To achieve this, we implement the Bhattacharyya metric for colour-based similarity analysis, a combination of LBPs (Local Binary pattern), the Earth Mover's Distance, and Euclidean Distance for the texture and spatial similarity analysis in addition to the structural similarity index (SSIM). A pre-trained CNN model (Xception) is then fine-tuned to classify the superclasses and the original classes of the Aerial image (AID), the UC Merced, the Optical image Analysis and Learning (OPTIMAL-31), and NWPU-RESIS45 datasets. Results show that methodically combining overlapping classes into superclasses reduces the possibility of misclassifications and increases the efficiency of CNNs. The model evaluation further indicates that this approach can boost classifiers' robustness and significantly reduce the impact of inner-class variability and outer-class similarity on their performance.

关键词： Feature extraction Transfer learning Scene classification Task analysis remote sensing Data models Training Euclidean distance image similarity metrics local binary pattern transfer learning scene classification

来源：评论

学校读者我要写书评

暂无评论

MHFNet: An Improved HGR Multimodal Network for Informative Correlation Fusion in remote sensing image Classification

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND remote sensing 2024年 17卷 15052-15066页

作者： Zhang, Hongkang Huang, Shao-Lun Kuruoglu, Ercan Engin Tsinghua Univ Tsinghua Shenzhen Int Grad Sch Shenzhen 518055 Peoples R China

In the realm of urban development, the precise classification and identification of land types are crucial for improving land use efficiency. This article proposes a land recognition and classification method based on data sparsity and improved Soft Hirschfeld-Gebelein-R & eacute;nyi (Soft-HGR) under multimodal conditions. First, a sparse information processing module is designed to enhance information accuracy and quickly obtain data sample features. Then, to solve the problem of information independence in single mode and lack of fusion in multimodal mode, an improved SoftHGR module is developed. This module incorporates covariance and trace constraints, enhances machine learning efficiency by stabilizing output and addressing dimensionality and variance issues in HGR, and speeds up land classification by cross-fusing multimodal features to deepen the understanding of diverse information interconnections. Based on this, a multimodal MI-SoftHGR fusion network is constructed, which can achieve cross-correlation sharing and collaborative extraction of feature information, thereby realizing accurate remote sensing image recognition and classification under multimodal conditions. Finally, empirical evaluations were conducted on Berlin, Augsburg, and MUUFL datasets, and the proposed method was compared with state-of-the-art algorithms. The results fully validate the efficacy and significant superiority of the proposed method.

关键词： Feature extraction Convolutional neural networks remote sensing Correlation Laser radar Data models Synthetic aperture radar Data sparsity HGR maximal correlation multimodal fusion remote sensing image classification

来源：评论

学校读者我要写书评

暂无评论

Triplet Network with Autoencoder for remote sensing image scene recognition and classification

Triplet Network with Autoencoder for Remote sensing image sc...

引用

2024 International Conference on image, Signal processing, and pattern recognition, ISPP 2024

作者： Hu, Fangchun Dai, Yifeng Wu, Lie Anhui University Anhui China Chuzhou University Anhui China

ISBN: (纸本)9781510680425

remote sensing image scene categorization is a crucial process that involves assigning semantic labels to images based on their content,which has wide-ranging applications in a number of *** inherent potential of deep neural networks to learn attractive features has substantially sped up progress in the field, resulting in considerable breakthroughs in remote sensing and scene classification powered by deep ***, the existing literature lacks a comprehensive evaluation of research findings in deep learning for remote sensing image scene categorization, despite the notable advancements in this *** CNN has shown remarkable efficacy in extracting image features, ranging there are persistent challenges that hinder its optimal performance in the domain of categorization of images from data collected from remote *** intrinsic attributes linked to remote sensing image data, such as intraclass variability and inter-class similarities, result in a notable decrease in the classification accuracy of the ***, the discernible impact of noise and interference further exacerbates limitations in CNN performance within this specific *** response to these challenges, this study introduces an innovative classification methodology that seamlessly integrates a triplet network and ***, the paper systematically conducts a rigorous comparative assessment, evaluating the performance of diverse image classification models across various remote sensing *** holistic approach aims to contribute to the evolving landscape of remote sensing image scene classification by addressing existing gaps and advancing our understanding of effective model architectures. © 2024 SPIE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

A remote sensing image de-noising method based on wavelet packet decomposition and information entropy threshold function

A remote sensing image de-noising method based on wavelet pa...

引用

2024 International Conference on image, Signal processing, and pattern recognition, ISPP 2024

作者： Ma, Hongjin Zhao, Jiayu Zhang, Weiwei School of Science Xi'an University of Architecture and Technology Shaanxi Xi'an710055 China School of Mathematics and Statistics Northwestern Polytechnical University Shaanxi Xi'an710072 China

ISBN: (纸本)9781510680425

remote sensing images are widely used in various fields, such as geographic information systems, environmental monitoring, and agricultural management. However, remote sensing images are often corrupted by various noises during acquisition, transmission, and storage, which degrade the image quality and affect the image analysis and utilization. Therefore, de-noising remote sensing images is an important step to improve the image quality and application performance. In this paper, we propose a remote sensing image de-noising method based on wavelet packet decomposition and information entropy threshold function. The proposed method uses wavelet packet decomposition to perform multi-resolution analysis on remote sensing images, and combines information entropy threshold function to adaptively suppress noises. The experimental results show that the proposed method can effectively remove Gaussian noise and salt-and-pepper noise, and preserve the edge and detail information of remote sensing images. The proposed method outperforms the existing methods in terms of peak signal-to-noise ratio, structural similarity index, and visual quality. © 2024 SPIE.

关键词： Wavelet decomposition

来源：评论

学校读者我要写书评

暂无评论

remote sensing data processing and analysis for the identification of geological entities

引用

ACTA GEOPHYSICA 2023年第3期71卷 1565-1577页

作者： Chi, Huanzhao Sun, Jing Zhang, Cheng Miao, Changsheng Changchun Inst Technol Sch Prospecting & Surveying Engn Changchun 130021 Jilin Peoples R China Jilin Prov Key Lab Changbai Hist Culture & VR Rec Changchun 130021 Jilin Peoples R China CGS Qingdao Inst Marine Geol Qingdao 266071 Shandong Peoples R China Qingdao Natl Lab Marine Sci & Technol Lab Marine Mineral Resources Qingdao 266071 Shandong Peoples R China

As Earth observation technology has advanced, the volume of remote sensing big data has grown rapidly, offering significant obstacles to efficient and effective processing and analysis. A convolutional neural network refers to a neural network that covers convolutional calculations. It is a form of deep learning, and convolutional neural networks have characterization learning characteristics, which can classify information into different data. remote sensing Data processing from various sensors has been attracting with more information in remote sensing. remote sensing data is generally adjusted and refined through image processing. image processing techniques, such as filtering and feature detection, are ideal for dealing with the high-dimensionality of geographically distributed systems. The geological entity is a term in geological work which refers to the product of geological processes that occupy a certain space in the Earth's crust and are different from other materials. They are of different sizes and are divided into different types according to their size. It mainly focuses on improving classification accuracy and accurately describing scattering types. For geological entity recognition, this paper proposed a Deep Convolutional Neural Network Polarized Synthetic Aperture Radar (DCNN-PSAR). It is expected to use deep convolutional neural network technology and polarized SAR technology to explore new methods of geological entities and improve geological recognition capabilities. With the help of Multimodal remote sensing Data processing, it is now possible to characterize and identify the composition of the Earth's surface from orbital and aerial platforms. This paper proposes a ground object classification algorithm for polarized SAR images based on a fully convolutional network, which realizes the geological classification function and overcomes the shortcomings of too long. The evaluation of DCNN-PSAR shows that the accuracy of the water area is showing

关键词： Deep convolutional neural network Synthetic aperture radar Geological body Entity recognition remote sensing Multimodal Data processing

来源：评论

学校读者我要写书评

暂无评论

Integrated Physically Interpretable Model for SAR Target recognition: Unified Fusion of Electromagnetic and Deep Features

引用

IEEE GEOSCIENCE AND remote sensing LETTERS 2025年 22卷

作者： Liao, Leiyao Hong, Zishuo Liu, Ziwei Zhang, Gengxin Nanjing Univ Posts & Telecommun Coll Commun & Informat Engn Nanjing 210003 Peoples R China

Synthetic aperture radar (SAR) target recognition has been a prominent research topic in the field of remote sensing image processing. Traditional methods can extract physical features for SAR target recognition, but they are often time-consuming. Deep learning-based methods can learn representative features, but they often operate as black boxes and lack interpretability. This letter introduces an integrated physically interpretable model (IPIM) for SAR target recognition, which unifies electromagnetic and deep learning features. Our method is an integrative model built with an end-to-end mechanism, achieving promising performance and high time efficiency. Specifically, our method employs a deep-unfolding network to learn physical features by incorporating the generative process of complex SAR images. Additionally, a feature fusion module is designed to combine physical features, which reflect local target characteristics, with deep features that capture global information. Experimental results on a measured SAR image dataset demonstrate that our method effectively learns physical features and achieves high performance in target recognition.

关键词： Feature extraction Target recognition Synthetic aperture radar Scattering Radar polarimetry Point cloud compression Decoding Transformers image reconstruction Electromagnetics Complex networks feature fusion interpretability synthetic aperture radar (SAR) target recognition

来源：评论

学校读者我要写书评

暂无评论

Discrete diffusion models with Refined Language-image Pre-trained representations for remote sensing image captioning☆ ☆

引用

pattern recognition LETTERS 2024年 186卷 164-169页

作者： Leng, Guannan Xiong, Yu-Jie Qiu, Chunping Guo, Congzhou Shanghai Univ Engn Sci Sch Elect & Elect Engn Shanghai 201600 Peoples R China Informat Engn Univ Inst Geospatial Informat Zhengzhou 450001 Peoples R China

RS image captioning (RSIC) utilizes natural language to provide a description of image content, assisting in the comprehension of object properties and relationships. Nonetheless, RS images are characterized by variations in object scales, distributions, and quantities, which make it challenging to obtain global semantic information and object connections. To enhance the accuracy of captions produced from RS images, this paper proposes a novel method referred to as Discrete Diffusion Models with Refined Language-image Pre- trained representations (DDM-RLIP), leveraging an advanced discrete diffusion model (DDM) for nosing and denoising text tokens. DDM-RLIP is based on an advanced DDM-based method designed for natural pictures. The primary approach for refining image representations involves fine-tuning a CLIP image encoder on RS images, followed by adapting the transformer with an additional attention module to focus on crucial image regions and relevant words. Furthermore, experiments were conducted on three datasets, Sydney-Captions, UCM-Captions, and NWPU-Captions, and the results demonstrated the superior performance of the proposed method compared to conventional autoregressive models. On the NWPU-Captions dataset, the CIDEr score improved from 116.4 to 197.7, further validating the efficacy and potential of DDM-RLIP. The implementation codes for our approach DDM-RLIP are available at https://***/Leng-bingo/DDM-RLIP.

关键词： Discrete diffusion model Contrastive Language-image Pre-training Transformer remote sensing image captioning

来源：评论

学校读者我要写书评

暂无评论

Sustainable Environmental Monitoring: Multistage Fusion Algorithm for remotely Sensed Underwater Super-Resolution image Enhancement and Classification

引用

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND remote sensing 2025年 18卷 3640-3653页

作者： Ghaban, Wad Ahmad, Jawad Siddique, Ali Akbar Alshehri, Mohammad S. Saghir, Anila Saeed, Faisal Ghaleb, Baraq Rehman, Mujeeb Ur Univ Tabuk Appl Coll Tabuk 47512 Saudi Arabia Prince Mohammad bin Fahd Univ Cybersecur Ctr Al Khobar 31952 Saudi Arabia Iqra Univ Dept Comp Sci Karachi 75300 Pakistan Najran Univ Coll Comp Sci & Informat Syst Dept Comp Sci Najran 61441 Saudi Arabia Sir Syed Univ Engn & Technol Dept Telecommun Engn Karachi 75300 Pakistan Birmingham City Univ Coll Comp Birmingham B4 7XG England Edinburgh Napier Univ Sch Comp Engn & Built Environm Edinburgh EH105DT Scotland Montfort Univ Inst Artificial Intelligence Sch Comp Sci & Informat Leicester LE1 9BH England

Oceans and seas cover more than 70% of the Earth's surface. If compared with the land mass there are a lot of unexplored locations, a wealth of natural resources, and diverse ocean creatures that are inaccessible to us humans. Underwater rovers and vehicles play a vital role in discovering these resources, yet limited visibility in deep waters and technological constraints impede underwater exploration. To address these issues, advanced image super-resolution and enhancement techniques are crucial for reliable resource identification, species recognition, and underwater ecosystem study. This will ultimately bridge the current gap in environmental monitoring by facilitating resource tracking and underwater waste assessment. This article proposes a novel multistage fusion algorithm for underwater image super-resolution, designed to enhance the quality and spatial resolution of low-resolution underwater images toward a more accurate object characterization. The effectiveness of the proposed super-resolution technique is demonstrated using multiple performance metrics including accuracy, f1-score, recall, and precision. By enhancing the spatial resolution of underwater images, our approach meets the increasing demand for detailed and accurate information in underwater earth observation applications.

关键词： remote sensing Superresolution image enhancement Spatial resolution image quality image color analysis Computer science Accuracy Colored noise Classification algorithms image classification image enhancement image processing image recognition remote sensing

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：