检索结果-内蒙古大学图书馆

International Journal of Cognitive Computing in Engineering 2025年 6卷 360-369页

作者： Wang, Xin E, Na Yang, Jingbo Network Center Hulunbuir University Hulunbuir021008 China School of Law and Economic Management Hulunbuir University Hulunbuir021008 China Information Technology Section Hulunbuir Archives Hulunbuir021100 China

image restoration and enhancement techniques have found widespread applications in the field of digital image processing, spanning areas such as medical imaging, remote sensing image analysis, and historical document restoration. However, with the advancements in generative adversarial networks, existing technologies are no longer sufficient to meet the high-definition requirements of image restoration. In light of this, the experiment proposes an image restoration and enhancement technique based on generative adversarial networks and style perception. The proposed model synergistically combines the image feature capturing ability of generative adversarial networks with the feature fusion capability of a multi-scale attention mechanism. This aims to address the complexities and information loss encountered in traditional image restoration processes. The results indicated that the proposed method, when applied to the Helen Face dataset, consistently increased the average Peak Signal-to-Noise Ratio (PSNR) values across four models. At a system runtime of 0.387 s, the PSNR value for the proposed method reached 52.84 dB, while the PSNR values for the other algorithms continue to increase. On the CelebA dataset, when the proposed method achieved the maximum Structural Similarity Index (SSIM) value, the corresponding number of restored images was 360, with a continuously rising SSIM value reaching 0.968. A comparative analysis of the four methods for image restoration revealed that the proposed method exhibited the highest degree of consistency with real images, demonstrating superior performance in handling details that closely resemble those in real images. The restoration effectiveness of the proposed method surpassed the other three methods significantly. These results indicate that the proposed method yields the best results for image restoration. Furthermore, the stability and low error of the system operation greatly enhance image recognition accuracy, effectively

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Learning Many-to-Many Mapping for Unpaired Real-World image Super-Resolution and Downscaling

引用

IEEE TRANSACTIONS ON pattern ANALYSIS AND MACHINE INTELLIGENCE 2024年第12期46卷 9874-9889页

作者： Sun, Wanjie Chen, Zhenzhong Wuhan Univ Sch Remote Sensing & Informat Engn Wuhan 430072 Peoples R China

Learning based single image super-resolution (SISR) for real-world images has been an active research topic yet a challenging task, due to the lack of paired low-resolution (LR) and high-resolution (HR) training images. Most of the existing unsupervised real-world SISR methods adopt a two-stage training strategy by synthesizing realistic LR images from their HR counterparts first, then training the super-resolution (SR) models in a supervised manner. However, the training of image degradation and SR models in this strategy are separate, ignoring the inherent mutual dependency between downscaling and its inverse upscaling process. Additionally, the ill-posed nature of image degradation is not fully considered. In this paper, we propose an image downscaling and SR model dubbed as SDFlow, which simultaneously learns a bidirectional many-to-many mapping between real-world LR and HR images unsupervisedly. The main idea of SDFlow is to decouple image content and degradation information in the latent space, where content information distribution of LR and HR images is matched in a common latent space. Degradation information of the LR images and the high-frequency information of the HR images are fitted to an easy-to-sample conditional distribution. Experimental results on real-world image SR datasets indicate that SDFlow can generate diverse realistic LR and SR images both quantitatively and qualitatively.

关键词： Super-resolution downscaling normalizing flow invertible neural network unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Aerial orthoimage generation for UAV remote sensing: Review

引用

INFORMATION FUSION 2023年 89卷 91-120页

作者： Zhang, Jiguang Xu, Shilin Zhao, Yong Sun, Jiaxi Xu, Shibiao Zhang, Xiaopeng Chinese Acad Sci Inst Automat Natl Lab Pattern Recognit Beijing Peoples R China Beijing Univ Posts & Telecommun Sch Artificial Intelligence Beijing Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing Peoples R China Northwestern Polytech Univ Xian Peoples R China

With its unique advantages of high flexibility and high efficiency, UAV has become a reasonable substitute for conventional aerial measurement technology. Especially in the low altitude remote sensing image processing, the ortho-rectification and mosaic of aerial images are the key to vision-based UAV orthoimage generation. Therefore, how to select the appropriate methods to rectify and mosaic the aerial images of UAV is significance to research the automatic generation of digital orthoimages. Unfortunately, most of the existing reviews only focus on the general image mosaic techniques, and there are few special reports on the application of UAV orthoimage generation for reference. This paper presents a comprehensive survey on UAV orthoimage generation technologies. We conclude three mainstream frameworks of visual orthoimage generation, which are 2D mosaic framework based, SfM framework based and SLAM framework based methods. According to the above three specific frameworks, we first carried out a detailed description and comparative analysis of related important algorithms, and sorted out the differences, common points and inherent relationships. Considering the wide application of deep learning in UAV remote sensing, we propose some hypotheses on how to introduce deep learning technology into above three orthoimage generation frameworks. After analysis, we provide a more detailed performance quantification comparison of the two most recent potential frameworks (State-of-the-art methods based on SfM and SLAM). It is worth noting that we integrated different test data sources of UVA aerial video sequence with a general SLAM testing platform, and solve the issue that SLAM-based orthoimage generation methods are difficult to evaluate cross-platform. Finally, challenges about visual UAV orthoimage generation and future directions in addressing these challenges are also pointed out.

关键词： Orthoimage generation UAV SfM SLAM 2D mosaic Ortho-rectification

来源：评论

学校读者我要写书评

暂无评论

remote sensing image Compression Method Based on Implicit Neural Representation 12

Remote Sensing Image Compression Method Based on Implicit Ne...

引用

12th International Conference on Computing and pattern recognition, ICCPR 2023

作者： Li, Xin Sun, Baile Liao, Jixiu Zhao, Xiaofei Shandong Qingdao China

ISBN: (纸本)9798400707988

Oceanography-oriented remote sensing image is characterized by being multi-source, heterogeneous, and massive. In recent years, the scale of remote sensing data is exploding, necessitating efficient compression methods for storage. Traditional algorithms have low compression ratio, poor flexibility, and are unsuitable for storing large-scale remote sensing image data. To address this, we propose a remote sensing image lossy compression and storage method based on implicit neural representation. We used an implicit neural network to learn the mapping relationship between longitude, latitude coordinates, and values. Then, we compressed the network weights using quantization. Our method can significantly reduce storage space by approximately 80% for multi-source and heterogeneous remote sensing image data. And the reconstructed quality is capable of meeting the requirements of downstream tasks related to marine AI and visualization. © 2023 ACM.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Classifying remote sensing images using Convolutional Neural Networks

A Novel Framework for Classifying Remote Sensing Images usin...

引用

2024 International Conference on Knowledge Engineering and Communication Systems, ICKECS 2024

作者： Manoharan, Thiyagarajan Basha, Shaik Hedayath Murugan, J.Senthil Suja, G.P. Rajkumar, R. Srimathi, S. Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology India R.M.K. College of Engineering and Technology Department of Ece India Vel Tech High Tech Dr. Rangarajan Dr.Sakunthala Engineering College Department of Cse Avadi Chennai India Muslim Arts College Thiruvithancode Department of Computer Science Kanyakumari629174 India Rajarajeswari College of Engineering Computer Science and Engineering Mysore Road Bengaluru74 India Simats Saveetha School of Engineering Department of Bio Technology Tamilnadu Chennai India

ISBN: (纸本)9798350359688

The classification of Hyperspectral remote sensing images (HRSIs) using Convolutional Neural Networks (CNNs) has gained significant. Due to excessive dimensional data and a lack of sample training examples, the Hughes phenomenon is frequently seen in hyperspectral remote sensing photos. In the realm of high-dimensional information processing, it is worth noting that there is a notable consumption of time and computing power. Additionally, there is a possibility that the features extracted may not accurately represent the data, leading to suboptimal classification efficiency and accuracy. In this research, a novel framework called GCNN is proposed, which combines the concepts of global context spatial attention (GCSA) and three-dimensional convolutional neural network (3DCNN). The GCNN framework aims to enhance the performance of spatial attention and convolutional neural networks by leveraging global context information. By integrating GCSA and 3DCNN, GCNN offers a promising approach for various applications in computer vision and image analysis. The mix-up operation is a commonly employed technique in the field of remote sensing image analysis. Its primary purpose is the spatially heterogeneous data available in these photos, and improve it. This is achieved by transforming the discrete sample space into a continuous one, thereby promoting improved flatness in the local vicinity of the data space. The integration of GCSA into the network allows for the encoding of contextual information from remote sensing scene images into the local features. The findings of this study indicate that the utilization of CNN for remote sensing image recognition yields significantly higher accuracy compared to traditional image recognition models. The recognition accuracy achieved by CNN in this context is reported to be as high as 97%. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Physically Feasible Counter-Attack Method for remote sensing Imaging Point Clouds 6th

A Physically Feasible Counter-Attack Method for Remote Sensi...

引用

6th Chinese Conference on pattern recognition and Computer Vision (PRCV)

作者： Wei, Bo Wei, Huanchun Cao, Cong Huang, Teng Xiong, Huagang Lang, Aobo Zhang, Xiqiu Zhang, Haiqing Beihang Univ Sch Elect & Informat Engn Beijing Peoples R China Guangxi Univ Informat Engn Guangxi Coll Beidou Nanning Peoples R China Guangzhou Univ Inst Artificial Intelligence & Blockchain Guangzhou Peoples R China Sun Yat Sen Univ Sch Arts Guangzhou Peoples R China

ISBN: (纸本)9789819984619;9789819984626

This research introduces an innovative approach to address the vulnerability of deep learning-based point cloud target recognition systems to adversarial sample attacks. Instead of directly tampering with the spatial location information of the point cloud data, the approach focuses on modifying specific attribute information. The modified point cloud data is then associated with a simulated physical environment for comprehensive attack testing. The experimental findings demonstrate the aggressive nature of the generated counter-samples achieved through signal amplitude modulation, effectively deceiving deep learning-based target recognition systems. The experimental results highlight the effectiveness of the adversarial object samples generated by modifying the signal amplitude of the point cloud data, showcasing their strong misguiding capabilities towards the deep learning-based target recognition algorithm. This approach ensures good stealthiness and practicality, making it a viable attack method applicable in physical scenarios.

关键词： Point Cloud Target recognition Counter-sample Attacks

来源：评论

学校读者我要写书评

暂无评论

DCI-Net: remote sensing image-Based Object Detector 27th

DCI-Net: Remote Sensing Image-Based Object Detector

引用

27th International Conference on pattern recognition, ICPR 2024

作者： Cui, Quanyue Lu, Jun College of Computer Science and Technology Heilongjiang University Harbin150080 China Jiaxiang Industrial Technology Research Institute of Heilongjiang University Shandong Jining272400 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Heilongjiang University Harbin150080 China

ISBN: (纸本)9783031781124

Recently the analysis of remotely sensed images has played a vital role in various aspects of research. The current researches ignore the unique prior knowledge in remote sensing images and do not consider exploring the contextual information of the object, while the existence of multi-scale and high image resolution of objects in remote sensing images also affects the accuracy of the object detection task. Based on the above problems, this paper proposes a object detector DCI-Net (Dynamic Context-Aware IoU Network) based on remote sensing images, in which the proposed CASK (Context-Aware Selective Kernel) module can explicitly model the interdependence between the convolutional feature channels. A loss function Pi_IoU is proposed, which adaptively adjusts the penalty factor in combination with the size of the detected object. A DySample module is introduced, which is able to effectively extract and utilize the spatial structure features. The model in this paper improves the detection accuracy of complex objects in remote sensing images. On the DIOR dataset, compared with the baseline model YOLOV9, the accuracy is improved by 0.6%, the number of parameters is decreased by 4%, and the floating point operation speed is improved by 27.8%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

SARATR-X: Toward Building a Foundation Model for SAR Target recognition

引用

IEEE TRANSACTIONS ON image processing 2025年 34卷 869-884页

作者： Li, Weijie Yang, Wei Hou, Yuenan Liu, Li Liu, Yongxiang Li, Xiang Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410073 Peoples R China Shanghai AI Lab Shanghai 200000 Peoples R China

Despite the remarkable progress in synthetic aperture radar automatic target recognition (SAR ATR), recent efforts have concentrated on detecting and classifying a specific category, e.g., vehicles, ships, airplanes, or buildings. One of the fundamental limitations of the top-performing SAR ATR methods is that the learning paradigm is supervised, task-specific, limited-category, closed-world learning, which depends on massive amounts of accurately annotated samples that are expensively labeled by expert SAR analysts and have limited generalization capability and scalability. In this work, we make the first attempt towards building a foundation model for SAR ATR, termed SARATR-X. SARATR-X learns generalizable representations via self-supervised learning (SSL) and provides a cornerstone for label-efficient model adaptation to generic SAR target detection and classification tasks. Specifically, SARATR-X is trained on 0.18 M unlabelled SAR target samples, which are curated by combining contemporary benchmarks and constitute the largest publicly available dataset till now. Considering the characteristics of SAR images, a backbone tailored for SAR ATR is carefully designed, and a two-step SSL method endowed with multi-scale gradient features was applied to ensure the feature diversity and model scalability of SARATR-X. The capabilities of SARATR-X are evaluated on classification under few-shot and robustness settings and detection across various categories and scenes, and impressive performance is achieved, often competitive with or even superior to prior fully supervised, semi-supervised, or self-supervised algorithms. Our SARATR-X and the curated dataset are released at https://***/waterdisappear/SARATR-X to foster research into foundation models for SAR image interpretation.

关键词： Radar polarimetry Foundation models remote sensing Imaging Frequency modulation Buildings Object detection Noise Marine vehicles Atmospheric modeling Synthetic aperture radar target recognition object detection foundation model self-supervised learning deep learning masked image modeling

来源：评论

学校读者我要写书评

暂无评论

Tensor ring with alternative change mask for multitemporal hyperspectral image change detection

引用

pattern recognition LETTERS 2022年 164卷 46-52页

作者： Sohail, Muhammad Chen, Zhao Liu, Guohua Donghua Univ Sch Comp Sci & Technol Shanghai 201620 Peoples R China 2999 Renmin North Rd Shanghai 201620 Peoples R China

Multitemporal hyperspectral image (HSI) change detection (CD) is a prevalent topic in remote sensing im-age processing. HSI CD usually consists of change feature extraction and classification. Although the high dimensionality of HSIs provides rich spectral information, HSIs are prone to spectral-spatial variability that degrades change detection accuracy. Recently, tensor decomposition has been successfully applied to CD. However, there is still room for improvement. We propose a tensor ring-based CD model with alter-native change masks (TRACM-CD) for multitemporal HSIs. TRACM-CD extracts temporal change features using TR decomposition applied to different temporal change vectors. The alternative change masks con-strain the temporal change representation and guarantee the temporal symmetry for change features to facilitate recognition of background and changes. Experimental results on four real-world multitemporal HSI datasets confirm the effectiveness and superiority of TR-based CD. The proposed model outperforms its tensor counterparts and classic approaches for multitemporal HSIs.(c) 2022 Elsevier B.V. All rights reserved.

关键词： Multitemporal Change detection Tensor ring remote sensing

来源：评论

学校读者我要写书评

暂无评论

Attention-based U-Net for building extraction from remote sensing images

Attention-based U-Net for building extraction from remote se...

引用

2022 International Conference on image, Signal processing, and pattern recognition, ISPP 2022

作者： Zhang, Qiong College of Geomatics and Geoinformation Guilin university of technology Guangxi Guilin China

ISBN: (纸本)9781510654846

To extract ground objects from remote sensing images based on deep learning method is one of the current research hotspots, and building information has attracted much attention as an important artificial feature. Convolutional neural networks have shown great potential for building extraction tasks. In view of the current research status, this paper proposes a lightweight improved network ECAU-Net that combines semantic segmentation network U-Net and efficient channel attention mechanism, and applies it to automatic extraction of buildings from high-resolution remote sensing images. Experiments show that the extraction method proposed in this paper shows good extraction results on the Massachusetts building data set, and the accuracy, recall, precision, and F1 score are better than the original U-Net. Therefore, this method does have certain advantages. © 2022 SPIE.

关键词： 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：