检索结果-内蒙古大学图书馆

武汉大学学报（信息科学版） 2023年第6期48卷 950-959页

作者：王严刘万军谭亚丽李玉辽宁工程技术大学测绘与地理科学学院辽宁阜新123000 辽宁工程技术大学软件学院辽宁葫芦岛125000

目前基于遥感图像的城市功能区分类方法通常采用光谱特征解译、兴趣点数据辅助、评价策略优化等方式,依赖大量人工操作,并借助遥感图像外的其他信息源。为了解决以上问题,提出利用卷积神经网络进行滑窗识别,提取图像语义标签,结合语义... 详细信息

目前基于遥感图像的城市功能区分类方法通常采用光谱特征解译、兴趣点数据辅助、评价策略优化等方式,依赖大量人工操作,并借助遥感图像外的其他信息源。为了解决以上问题,提出利用卷积神经网络进行滑窗识别,提取图像语义标签,结合语义推理机制实现城市功能区分类的滑窗-推理方法。首先,建立两级城市功能区分类,以二级城市功能区为标识标注训练样本,并以此训练卷积神经网络作为识别器;然后,设计有重叠的滑窗识别模式,使用识别器辨识滑窗区域内图像块的二级城市功能区类型;最后,提出一个带权重的打分机制,作为语义推理方式,语义推理对象为全部识别结果,确定各图像块的一级城市功能区类型,实现遥感图像城市功能区分类。实验使用模拟图像和高分辨率遥感图像,两种图像的总分类精度分别可达94.50%、92.04%。滑窗-推理方法旨在通过语义推理处理滑窗识别产生的多语义标签,根据多语义标签确定对象的真实城市功能区。实验结果表明,所提方法无需辅助信息,直接利用遥感图像进行城市功能区分类是可行和有效的。

关键词：城市功能区图像分类卷积神经网络滑窗识别语义推理投票机制

来源：评论

学校读者我要写书评

暂无评论

Quantum AI: Deep Learning Optimization Using Hybrid Quantum Filters

SSRN

引用

SSRN 2024年

作者： Ganguly, Kaushik Birla Institute of Technology and Science Pilani India Cognizant Technology Solutions India Pvt. Ltd. India

Deep learning algorithms have shown promising results for different image processing tasks, particularly in remote sensing & image recognition. Till now many studies have been carried out on image processing, which brings a new paradigm of innovative capabilities under the umbrella of intelligent remote sensing and computer vision. Accordingly, quantum processing algorithms have proved to efficiently solve some issues that are undetectable to classical algorithms and processors. Keeping that in mind, a Quantum Convolutional Neural Network (QCNN) architecture along with Hybrid Quantum filters would be utilized supported by cloud computing infrastructures and data centers to provide a broad range of complex AI services and high data *** research summaries the conventional techniques of Classical and Quantum Deep Learning and it’s research progress on real-world problems in remote sensing image processing as a comparative demonstration. Last but not least, we evaluate our system by training on Street View House Numbers datasets in order to highlight the feasibility and effectiveness of using Quantum Deep Learning approach in image recognition and other similar applications. Upcoming challenges and future research areas on this spectrum are also discussed. © 2024, The Authors. All rights reserved.

关键词： image recognition

来源：评论

学校读者我要写书评

暂无评论

Interactive Segmentation and Visualization for Tiny Objects in Multi-megapixel images

Interactive Segmentation and Visualization for Tiny Objects ...

引用

IEEE/CVF Conference on Computer Vision and pattern recognition (CVPR)

作者： Xu, Chengyuan Dong, Boning Stier, Noah McCully, Curtis Howell, D. Andrew Sen, Pradeep Hollerer, Tobias Univ Calif Santa Barbara Santa Barbara CA 93106 USA Las Cumbres Observ Goleta CA USA

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

We introduce an interactive image segmentation and visualization framework for identifying, inspecting, and editing tiny objects (just a few pixels wide) in large multi-megapixel high-dynamic-range (HDR) images. Detecting cosmic rays (CRs) in astronomical observations is a cum-bersome workflow that requires multiple tools, so we developed an interactive toolkit that unifies model inference, HDR image visualization, segmentation mask inspection and editing into a single graphical user interface. The feature set, initially designed for astronomical data, makes this work a useful research-supporting tool for human-in-the-loop tiny-object segmentation in scientific areas like biomedicine, materials science, remote sensing, etc., as well as computer vision. Our interface features mouse-controlled, synchronized, dual-window visualization of the image and the segmentation mask, a critical feature for locating tiny objects in multi-megapixel images. The browser-based tool can be readily hosted on the web to provide multi-user access and GPU acceleration for any device. The toolkit can also be used as a high-precision annotation tool, or adapted as the frontend for an interactive machine learning framework. Our open-source dataset, CR detection model, and visualization toolkit are available at https://***/cy-xu/cosmic-conn.

关键词： image segmentation Computer vision Materials science and technology Computational modeling Data visualization Machine learning pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SAR image Classification Using Greedy Hierarchical Learning With Unsupervised Stacked CAEs

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND remote sensing 2021年第7期59卷 5721-5739页

作者： Sun, Zhensheng Li, Juan Liu, Peng Cao, Weijia Yu, Tao Gu, Xingfa Univ Chinese Acad Sci Sch Elect Elect & Commun Engn Aerosp Informat Res Inst Beijing 100049 Peoples R China Chinese Acad Sci Inst Remote Sensing & Digital Earth Aerosp Informat Res Inst Beijing 100101 Peoples R China

Synthetic aperture radar (SAR) can provide stable data source for earth observation due to its advantages of all day and night, all-weather, and strong penetration. SAR image classification as a fundamental procedure has been proved its great value in plenty of remote sensing applications. Conventional classification algorithms mainly rely on hand-designed features, which are susceptible to widespread coherent speckle noise and geometric distortion in high-resolution SAR images. Inspired by the recent impressive success in data mining and deep learning, a greedy hierarchical convolutional neural network (GHCNN) is developed. It aims at obtaining optimized feature representation, relieving the effect of speckle noise, and promoting the local pattern recognition of geometric distortion in single-polarized SAR image classification. First, a series of convolutional autoencoders (CAEs) is trained in the greedy layer-wise unsupervised strategy. This step provides an unbiased regularizer and a priori distribution derived from large volumes of unlabeled SAR patches. Then, to optimize multiple parameter subspaces globally, several CAEs are coupled together to form a deeper hierarchical structure in a stacked and unsupervised fashion. Afterward, a convolutional network with identical topology inherits the pretrained weights. After supervised finetuning, it realizes class prediction. Synchronously, t-distributed stochastic neighbor embedding (t-SNE) algorithm is applied to monitor the efficiency of feature representation during the training period. Experimental results demonstrate that the proposed method has competitive advantages over involved contrast methods.

关键词： Synthetic aperture radar remote sensing Feature extraction Training Convolution Speckle Machine learning Convolutional neural network (CNN) hierarchical parameter-oriented learning image classification local pattern recognition stacked convolutional autoencoders (SCAEs) synthetic aperture radar (SAR)

来源：评论

学校读者我要写书评

暂无评论

Patch-based Cross-domain Adaptation for Few-shot remote sensing Scene recognition

Patch-based Cross-domain Adaptation for Few-shot Remote Sens...

引用

Signal, Information and Data processing (ICSIDP), IEEE International Conference on

作者： Chengzhi He Yu Liu Zhizhuo Jiang Yaowen Li Chenggang Yan Bolun Zheng Shenzhen International Graduate School Tsinghua University Shenzhen China Department of Electronic Engineering Tsinghua University Beijing China Intelligent Information Processing Laboratory Hangzhou Dianzi University Hangzhou China

ISBN: (数字)9798331515669

ISBN: (纸本)9798331515676

Recognizing new classes from a few labeled remote sensing images presents a significant challenge. Existing methodologies assume that training and testing datasets come from identical domains. Collecting training datasets of remote sensing images from each domain is practically unfeasible. To tackle this challenge, we propose a strategy that leverages image patch feature embedding and cross-adaptation mechanism for cross-domain few-shot classification. Initially, the supplied image is segmented into patches of the same size. Subsequently, feature embeddings are extracted and reinforced with prototypical triplet loss to enhance robustness. A unified module then facilitates cross-adaptation between the support and query sets, producing classification features that effectively represent the relationship between them, thus better adapting to few-shot remote sensing classification challenges with domain shifts. Our proposed method’s excellence and generality are confirmed by comprehensive experiments.

关键词： Training image segmentation Adaptation models image recognition Feature extraction Data processing Robustness Labeling remote sensing Testing

来源：评论

学校读者我要写书评

暂无评论

Global Contextual Learning Network for Multisource remote sensing image Fusion

Global Contextual Learning Network for Multisource Remote Se...

引用

pattern recognition, Machine Vision and Intelligent Algorithms (PRMVIA), International Conference on

作者： Puhong Duan Zhuojun Xie Xukun Lu Xudong Kang School of Robotics Hunan University Changsha China College of Electrical and Information Engineering Hunan University Changsha China

ISBN: (数字)9798350389746

ISBN: (纸本)9798350389753

Multisource remote sensing image fusion aims to combine the complementary advantage of different modalities for fine-grained classification. Current multisource image fusion methods are based on a patch-by-patch learning paradigm, which requires high computational burden. In addition, how to combine different attributes is still a challenging issue. In this article, a global contextual learning network (GCLNet) is studied for multisource remote sensing image fusion. In GCLNet, an encoder-decoder convolutional network is proposed to draw global spectral-spatial information, which can significantly reduce the computing cost. Furthermore, a contextual attention feature fusion module is designed to connect coarse-to-fine features between encoder and decoder. Experiments on Augsburg and Yellow River datasets reveal that the proposed GCLNet obtains promising results in the light of classification result and inference speed compared to other advanced fusion methods.

关键词： Machine vision Semantics Radar Radar imaging Inference algorithms Rivers pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Development of a Verilog-Based System for pattern Detection Using Convolutional Neural Networks 2

Development of a Verilog-Based System for Pattern Detection ...

引用

2nd International Conference on Recent Trends in Microelectronics, Automation, Computing, and Communications Systems, ICMACC 2024

作者： Kandula, Bala Sindhuri Singh, Sangeeta Tata, Subhashini Manasaveena, T. Bolisetty, V Vijayasri Sadguna Kumari, V. S.R.K.R Engineering College Department of E.C.E Bhimavaram India Vardhaman College of Engineering Hyderabad Department of E.C.E Telangana India SR Gudlavalleru Engineering College Department of E.C.E Gudlavalleru India NRI Institute of Technology Department of E.C.E Vijayawada India Aditya College of Engineering and Technology Department of E.C.E Surampalem India Pydah College of Engineering Department of E.C.E Kakinada India

ISBN: (纸本)9798350366570

pattern detection is a foundational element in computer vision, crucial for advancements in autonomous driving, surveillance, and numerous other fields. Convolutional Neural Networks (CNNs) have significantly enhanced pattern detection by improving both accuracy and efficiency. This paper aims to develop a Verilog-based system for pattern detection using CNNs, focusing on detecting and counting occurrences of a specified test pattern within input images. The CNN architecture employs Convolutional Layers for feature extraction and Max Pooling Layers for spatial downsampling, both essential in image processing. Through iterative weight adjustments during training, the CNN learns to recognize patterns similar to the test pattern. After training, the system evaluates unseen images, predicting the presence and count of test pattern instances. To optimize performance, the system incorporates approximate adders to reduce area and gate count, thereby enhancing efficiency. These optimizations enable the system to achieve high performance while maintaining computational efficiency, providing detection and counting of specified patterns in images. This capability offers valuable insights and practical solutions for various real-world applications. © 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

Intelligent Satellite Design and Implementation 1st

引用

2023年

作者： Jianjun Zhang Jing Li

ISBN: (数字)9781394198986

ISBN: (纸本)9781394198955

INTELLIGENT SATELLITE DESIGN AND IMPLEMENTATION Integrate cutting-edge technology into spacecraft design with this groundbreaking work Artificial intelligence and machine learning have revolutionized virtually every area of computing and complex engineering, and the design of satellite spacecraft is no exception. Intelligent satellites are increasingly capable of human-like perception, decision-making, and operations, and their problem-solving capacities are still expanding. As AI and machine learning continue to advance, their integration into satellite manufacture will only deepen. Intelligent Satellite Design and Implementation seeks to understand the foundations of this integration and its likely directions in the coming years. Beginning from the basic principles of interaction between artificial intelligence and satellite design and mission planning, the book analyzes a series of current or potential areas of technological advancement to create a comprehensive overview of the subject. Intelligent Satellite Design and Implementation readers will also find: Background information on the introduction and development of artificial intelligence Detailed discussion of topics including autonomous satellite operation, remote sensing satellites, and many more Over 100 illustrations and tables to reinforce key concepts Intelligent Satellite Design and Implementation is ideal for graduate students and advanced undergraduates in engineering, computing, and spacecraft design programs, as well as researchers in these and related fields.

关键词： image recognition artificial intelligence machine learning satellite technology architecture NASA European Space Agency natural language processing remote sensing satellites intelligent communication satellite system OODA loop

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Mahalanobis Kernel-Based Support Vector Machine for Classification of High-Resolution remote sensing images

引用

COGNITIVE COMPUTATION 2021年第4期13卷 787-794页

作者： Sun, Genyun Rong, Xueqian Zhang, Aizhu Huang, Hui Rong, Jun Zhang, Xuming China Univ Petr East China Sch Geosci Qingdao 266580 Shandong Peoples R China Qingdao Natl Lab Marine Sci & Technol Lab Marine Mineral Resources Qingdao 266071 Peoples R China Key Lab Deep Oil & Gas Qingdao 266580 Peoples R China

Support vector machine (SVM) is a powerful cognitive and learning algorithm in the domain of pattern recognition and image classification. However, the generalization ability of SVM is limited when processing classification of high-resolution remote sensing images. One chief reason for this is that the Euclidean distance-based distance matrix in traditional SVM treats different samples equally and overlooks the global distribution of samples. To construct a more effective SVM-based classification method, this paper proposes a multi-scale Mahalanobis kernel-based SVM classifier. In this new method, we first introduce a Mahalanobis distance kernel to improve the global cognitive learning ability of SVM. Then, the Mahalanobis distance kernel is embedded to the multi-scale kernel learning (MSKL) to construct a novel multi-scale Mahalanobis kernel, in which the parameters are optimized by a bio-inspired algorithm, named differential evolution. Finally, the new method is extended to the classification of high-resolution remote sensing images based on the spatial-spectral features. The comparison experiments of five public UCI datasets and two high-resolution remote sensing images verify that the Mahalanobis distance-based method can obtain more accurate classification results than that of the Euclidean distance-based method. In addition, the proposed method produced the best classification results in all the experiments. The global cognitive learning ability of Mahalanobis distance-based method is stronger than that of the Euclidean distance-based method. In addition, this study indicates that the optimized MSKL are potential for the interpretation and understanding of complicated high-resolution remote sensing scene.

关键词： Support vector machine (SVM) Mahalanobis distance image classification High-resolution image Multi-scale kernel learning

来源：评论

学校读者我要写书评

暂无评论

AUTOMATIC ENRICHMENT OF INDOOR 3D MODELS USING A DEEP LEARNING APPROACH BASED ON SINGLE imageS WITH UNKNOWN CAMERA POSES

AUTOMATIC ENRICHMENT OF INDOOR 3D MODELS USING A DEEP LEARNI...

引用

ISPRS WG V/7 Conference on Measurement, Visualisation and processing in BIM for Design and Construction Management II

作者： Jarzabek-Rychard, M. Maas, H-G Wroclaw Univ Environm & Life Sci Inst Geodesy & Geoinformat Wroclaw Poland Tech Univ Dresden Inst Photogrammetry & Remote Sensing Dresden Germany

3D building modeling is a diverse field of research with a multitude of challenges, where data integration is an inherent component. The intensively growing market of BIM-related consumer applications requires methods and algorithms that enable efficient updates of existing 3D models without the need for cost-intensive data capturing and repetitive reconstruction processes. We propose a novel approach for semantic enrichment of existing indoor models by window objects, based on amateur camera RGB images with unknown exterior orientation parameters. The core idea of the approach is the parallel estimation of image camera poses with semantic recognition of target objects and their automatic mapping onto a 3D vector model. The presented solution goes beyond pure texture matching and links deep learning detection techniques with camera pose estimation and 3D reconstruction. To evaluate the performance of our procedure, we compare the estimated camera parameters with reference data, obtaining median values of 13.8 cm for the camera position and 1.1 degrees for its orientation. Furthermore, a quality of 3D mapping is assessed based on the comparison to the reference 3D point cloud. All the windows presented in the data source were detected successfully, with a mean distance between both point sets equal to 3.6 cm. The experimental results prove that the presented approach achieves accurate integration of objects extracted from single images with an input 3D model, allowing for an effective increase of its semantic coverage.

关键词： Building Information Model (BIM) deep learning object recognition texture mapping camera pose estimation

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：