检索结果-内蒙古大学图书馆

Panchromatic and multispectral image fusion for remote sensing and earth observation: Concepts, taxonomy, literature review, evaluation methodologies and challenges ahead

引用

INFORMATION FUSION 2023年 93卷 227-242页

作者： Zhang, Kai Zhang, Feng Wan, Wenbo Yu, Hui Sun, Jiande Del Ser, Javier Elyan, Eyad Hussain, Amir Shandong Normal Univ Sch Informat Sci & Engn Jinan Peoples R China Univ Portsmouth Sch Creat Technol Portsmouth England Basque Res & Technol Alliance BRTA TECNALIA Derio 48160 Spain Univ Basque Country UPV EHU Bilbao 48013 Spain Robert Gordon Univ Sch Comp Aberdeen Scotland Edinburgh Napier Univ Sch Comp Edinburgh Scotland

Panchromatic and multispectral image fusion, termed pan-sharpening, is to merge the spatial and spectral information of the source images into a fused one, which has a higher spatial and spectral resolution and is more reliable for downstream tasks compared with any of the source images. It has been widely applied to image interpretation and pre-processing of various applications. A large number of methods have been proposed to achieve better fusion results by considering the spatial and spectral relationships among panchromatic and multispectral images. In recent years, the fast development of artificial intelligence (AI) and deep learning (DL) has significantly enhanced the development of pan-sharpening techniques. However, this field lacks a comprehensive overview of recent advances boosted by the rise of AI and DL. This paper provides a comprehensive review of a variety of pan-sharpening methods that adopt four different paradigms, i.e., component substitution, multiresolution analysis, degradation model, and deep neural networks. As an important aspect of pan-sharpening, the evaluation of the fused image is also outlined to present various assessment methods in terms of reduced-resolution and full-resolution quality measurement. Then, we conclude this paper by discussing the existing limitations, difficulties, and challenges of pan-sharpening techniques, datasets, and quality assessment. In addition, the survey summarizes the development trends in these areas, which provide useful methodological practices for researchers and professionals. Finally, the developments in pan-sharpening are summarized in the conclusion part. The aim of the survey is to serve as a referential starting point for newcomers and a common point of agreement around the research directions to be followed in this exciting area.

关键词： image fusion Pan-sharpening image quality evaluation Multispectral image Panchromatic image

来源：评论

学校读者我要写书评

暂无评论

Synthetic aperture radar image and its despeckling using variational methods: A Review of recent trends

引用

SIGNAL processing 2023年第1期212卷

作者： Baraha, Satyakam Sahoo, Ajit Kumar Natl Inst Technol Rourkela Dept Elect & Commun Engn Rourkela Orissa India

Synthetic aperture radar (SAR) has drawn significant interest from the remote sensing community due to its ability to provide high-resolution images irrespective of weather and illumination conditions. It has numerous applications in a variety of fields, including military surveillance, geological exploration, disaster management, and mapping of natural phenomena like climate change, forest management, and volcanic eruptions. The image acquired by coherent sensors such as SAR is corrupted by granular multiplicative noise, also known as speckle. It has an adverse influence on the visual interpretation of SAR images and prevents the use of various post-processing tasks. Despeckling addresses the removal of such noise from SAR images while preserving the image details. This work provides a brief summary of the theory, applications, speckle statistics, performance measures, and recent developments in despeckling filters using variational methods for SAR images. The primary focus is given to recently proposed despeckling filters, discussing their typical usage, benefits, and drawbacks.& COPY;2023 Elsevier B.V. All rights reserved.

关键词： remote sensing SAR Speckle Inverse-imaging Regularization Convex optimization Variational methods

来源：评论

学校读者我要写书评

暂无评论

Drought Stress Segmentation on Drone captured Maize using Ensemble U-Net framework 5

Drought Stress Segmentation on Drone captured Maize using En...

引用

5th IEEE International Conference on image processing applications and Systems (IPAS)

作者： Tejasri, N. Sai, Ujwal G. Rajalakshmi, P. Naik, Balaji Desai, Uday B. IIT Hyderabad Dept AI Hyderabad Telangana India IIT Hyderabad Dept Elect Engn Hyderabad Telangana India PJTSAU Dept Agron Hyderabad Telangana India

ISBN: (纸本)9781665462198

Water is essential for any crop production. Lack of sufficient supply of water supply causes abiotic stress in crops. Accurate identification of the crops affected by drought is required for achieving sustainable agricultural yield. The image data plays a crucial role in studying the crop's response. recent developments in aerial-based imaging methods allow us to capture RGB maize data by integrating an RGB camera with the drone. In this work, we propose a pipeline to collect data rapidly, pre-process the data and apply deep learning based models to segment drought affected/stressed and unaffected/healthy RGB maize crop grown in controlled water conditions. We develop an ensemble-based framework based on U-Net and U-Net++ architectures for the drought stress segmentation task. The ensemble framework is based on the stacking approach by averaging the predictions of fine-tuned U-Net and U-Net++ models to generate the output mask. The experimental results showed that the ensemble framework performed better than individual U-Net and U-Net++ models on the test set with a mean IoU of 0.71 and a dice coefficient of 0.74.

关键词： Drought Stress Drone-based sensing image Segmentation U-Net Ensemble framework

来源：评论

学校读者我要写书评

暂无评论

Automation and Computational Intelligence for Road Maintenance and Management: Advances and applications 1

引用

2022年

作者： Hamzeh Zakeri Fereidoon Moghadas Nejad Amir H. Gandomi

ISBN: (数字)9781119800668;9781119800651

ISBN: (纸本)9781119800644

Automation and Computational Intelligence for Road Maintenance and Management A comprehensive computational intelligence toolbox for solving problems in infrastructure management In Automation and Computational Intelligence for Road Maintenance and Management, a team of accomplished researchers delivers an incisive reference that covers the latest developments in computer technology infrastructure management. The book contains an overview of foundational and emerging technologies and methods in both automation and computational intelligence, as well as detailed presentations of specific methodologies. The distinguished authors emphasize the most recent advances in the maintenance and management of infrastructure robotics, automated inspection, remote sensing, and the applications of new and emerging computing technologies, including artificial intelligence, evolutionary computing, fuzzy logic, genetic algorithms, knowledge discovery and engineering, and more. Automation and Computational Intelligence for Road Maintenance and Management explores a universal synthesis of the cutting edge in parameters and indices to evaluate models. It also includes:

Thorough introductions to management science and the latest methods of automation and the structure and framework of automation and computing intelligence
Comprehensive explorations of advanced image processing techniques, recent advances in fuzzy, and diagnosis automation
Practical discussions of segmentation and fragmentation and different types of features and feature extraction methods
In-depth examinations of methods of classification along with various developed methodologies and models of quantification, evaluation, and indexing in automation

Perfect for postgraduate students in road and transportation engineering, evaluation, and assessment, Automation and Computational Intelligence for Road Maintenance and Management will also earn a place in the libraries of researc

关键词： Systems Engineering \u0026 Management

来源：评论

学校读者我要写书评

暂无评论

Machine Learning and remote sensing for near Realtime Flood Mapping

Machine Learning and Remote Sensing for near Realtime Flood ...

引用

作者： Peng, Bo University of Wisconsin– Madison

学位级别：博士

Flooding has been the world most frequent natural disaster over the past decades. Near realtime flood mapping is critical for mitigating the devastating impacts of flooding (e. g., life/economic losses). The United Nations (UN) Sustainable Development Goal 11 (2015–2030) is calling for global efforts to monitor large-scale floods in near realtime for protecting the vulnerable communities. remote sensing (RS) has the unique capability of earth observation with applications in global disaster response. recent advances in micro-satellite constellations are offering opportunities for daily satellite image acquisition with a high spatial resolution. Such a high temporal resolution (i. e., daily) is the key to the success of RS for near realtime global flood monitoring. Moreover, the large volume of RS imagery further unleashes the vast potential of data-driven machine learning (ML) approaches for accurate flood mapping. recent developments in deep learning, a sub-field of ML, have demonstrated the superiority of ML in flood mapping given massive RS data and corresponding labels. Unfortunately, training labels are very scarce in the domain of disaster response. This dissertation explores ML models for flood mapping without massive training labels by introducing the prior knowledge in RS data including the spatial, temporal, and spectral information: First, this dissertation proposes the PSNet to model flood mapping as bitemporal change detection by leveraging the temporal information of RS data. With only a few hand labels, the model can map floods with an over 0.85 F1 score for various heterogeneous flooded areas. Second, to further accelerate flood mapping, a self-supervised bitemporal change detection model, Patch-CVA, is developed to detect changed areas without hand labels. Further post-processing removes most false alarms by introducing the spatial and spectral information of floodwaters. Third, while the Patch-CVA has achieved good performance, its underlying assum

关键词：

来源：评论

学校读者我要写书评

暂无评论

Land-cover classification with hyperspectral remote sensing image using CNN and spectral band selection

引用

remote sensing applications-SOCIETY AND ENVIRONMENT 2023年 31卷

作者： Solomon, A. Arun Agnes, S. Akila GMR Inst Technol Dept Civil Engn Razam Andhra Pradesh India GMR Inst Technol Dept Comp Sci & Engn Razam Andhra Pradesh India

recent developments in remote sensing technology have led to a significant rise in the demand for precise and reliable algorithms for analyzing hyperspectral remote sensing images. Hyper -spectral remote sensing image analysis aims to differentiate various types of landscapes on Earth's surface, which is challenging due to the high dimensionality of the data space and the abundance of spectral bands. To address these challenges, this work proposes a novel 3D CNN-based model for classifying hyperspectral images based on both spectral and spatial features. The proposed ap-proach comprises two stages: data pre-processing and classification. First, the raw hyperspectral image is processed, and the essential spectral bands are selected using HyperPCA to reduce the data's high dimensionality. Second, using fused multi-resolution spectral and spatial features, ob-tained by a 3D convolutional neural network model the landscapes of the hyperspectral remote sensing image are classified. The proposed model employs concatenation and addition operations to extract comprehensive and selective features, respectively, and uses direct max pooling to miti-gate strong activations that reduce feature maps. The proposed approach enhances hyperspectral image classification even with a small number of labeled samples by enabling the automatic ex-traction of pertinent information while maintaining the spatial and spectral features of the data. The Indian Pines and University of Pavia datasets, two existing hyperspectral images, are used in the experiments. The results demonstrate that, in terms of classification performance, the sug-gested approach is competitive with the state-of-the-art.

关键词： Land -cover classification Convolution neural network Deep learning Spectral band selection Hyperspectral remote sensing image

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different remote sensing Methods for 3D Modeling of Small Rock Outcrops

引用

SENSORS 2020年第6期20卷 1663-1663页

作者： Mikita, Tomas Balkova, Marie Bajer, Ales Cibulka, Milos Patocka, Zdenek Mendel Univ Brno Fac Forestry & Wood Technol Dept Forest Management & Appl Geoinformat Brno 61300 Czech Republic Mendel Univ Brno Fac Forestry & Wood Technol Dept Geol & Pedol Brno 61300 Czech Republic

This paper reviews the use of modern 3D image-based and Light Detection and Ranging (LiDAR) methods of surface reconstruction techniques for high fidelity surveys of small rock outcrops to highlight their potential within structural geology and landscape protection. LiDAR and Structure from Motion (SfM) software provide useful opportunities for rock outcrops mapping and 3D model creation. The accuracy of these surface reconstructions is crucial for quantitative structural analysis. However, these technologies require either a costly data acquisition device (Terrestrial LiDAR) or specialized image processing software (SfM). recent developments in augmented reality and smartphone technologies, such as increased processing capacity and higher resolution of cameras, may offer a simple and inexpensive alternative for 3D surface reconstruction. Therefore, the aim of the paper is to show the possibilities of using smartphone applications for model creation and to determine their accuracy for rock outcrop mapping.

关键词： terrestrial laser scanning ARCore Structure from Motion rock outcrops

来源：评论

学校读者我要写书评

暂无评论

Computer Vision for Smart Farming and Sustainable Agriculture

Computer Vision for Smart Farming and Sustainable Agricultur...

引用

IST-Africa Conference (IST-Africa)

作者： Tombe, Ronald Kisii Univ Dept Comp Sci Kisii Kenya

ISBN: (纸本)9781905824656

developments in satellite technology, remote sensors and drone technologies are mushrooming. These developments yield volumes of high quality scene images that require effective processing for intelligent farming applications. The recent deep learning technologies can leverage these opportunities to fuse computer vision and artificial intelligence in farming. This encompasses the big data phenomena and huge volumes of data that are captured, processed and applied for decision-making. This paper aims to give insights on the integration of computer vision for smart farming in-order to attain sustainable agriculture. Using a structured approach, this research proposes a computer vision technique for crop image feature characterization that applies in the determination of the crop's health status. To achieve this, a deep convolutional network is applied for image feature extraction and representation, and then these features are fed to the support vector-learning machine for training and subsequent image interpretation. From the experimental results, it is evident that the proposed technique generates superior visual interpretation results of scene images as compared to other methods in literature. It follows that the Global food security and agricultural sustainability can be attained through ICT enabled solutions that are integrates and works together a phenomenon referred to as smart farming.

关键词： remote sensing images drones computer vision deep learning machine learning big data processing

来源：评论

学校读者我要写书评

暂无评论

Leveraging Modern Artificial Intelligence for remote sensing and NWP: Benefits and Challenges

引用

BULLETIN OF THE AMERICAN METEOROLOGICAL SOCIETY 2019年第12期100卷 ES473-ES491页

作者： Boukabara, Sid-Ahmed Krasnopolsky, Vladimir Stewart, Jebb Q. Maddy, Eric S. Shahroudi, Narges Hoffman, Ross N. NOAA NESDIS Ctr Satellite Applicat & Res College Pk MD 20740 USA NOAA Environm Modeling Ctr College Pk MD 20740 USA Colorado State Univ NOAA Cooperat Inst Res Atmosphere Earth Syst Res Lab Boulder CO USA Riverside Technol Inc NOAA NESDIS Ctr Satellite Applicat & Res College Pk MD USA Univ Maryland NOAA Cooperat Inst Satellite Earth Syst Studies NESDISCtr Satellite Applicat & Res College Pk MD 20742 USA

Artificial intelligence (AI) techniques have had significant recent successes in multiple fields. These fields and the fields of satellite remote sensing and NWP share the same fundamental underlying needs, including signal and image processing, quality control mechanisms, pattern recognition, data fusion, forward and inverse problems, and prediction. Thus, modern AI in general and machine learning (ML) in particular can be positively disruptive and transformational change agents in the fields of satellite remote sensing and NWP by augmenting, and in some cases replacing, elements of the traditional remote sensing, assimilation, and modeling tools. And change is needed to meet the increasing challenges of Big Data, advanced models and applications, and user demands. Future developments, for example, SmallSats and the Internet of Things, will continue the explosion of new environmental data. ML models are highly efficient and in some cases more accurate because of their flexibility to accommodate nonlinearity and/or non-Gaussianity. With that efficiency, ML can help to address the demands put on environmental products for higher accuracy, for higher resolution-spatial, temporal, and vertical, for enhanced conventional medium-range forecasts, for outlooks and predictions on subseasonal to seasonal time scales, and for improvements in the process of issuing advisories and warnings. Using examples from satellite remote sensing and NWP, it is illustrated how ML can accelerate the pace of improvement in environmental data exploitation and weather prediction-first, by complementing existing systems, and second, where appropriate, as an alternative to some components of the NWP processing chain from observations to forecasts.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

Implementation of SAM and MF Algorithms with Multi-core Programming 9

Implementation of SAM and MF Algorithms with Multi-core Prog...

引用

9th International Conference on recent Advances in Space Technologies (RAST)

作者： Pekturk, Mustafa Kemal Ozuzun, Yilmaz Ozsancaktar, Oguz HAVELSAN Informat & Commun Technol Dept Ankara Turkey

ISBN: (纸本)9781538694480

In conjunction with the recent developments in remote sensing technologies, as a result of both the spatial and spectral resolution increases of the image data, the analysis operations made using this data have big difficulties in storage, transferring and processing. When the real/near real-time analysis of exponentially growing data is required online, the implementation of parallel approaches in critical applications, rather than the traditional methods that are inadequate, has become a necessity. In this paper, the Spectral Angle Mapper (SAM) and Matched Filter (MF) algorithms, which are frequently used in remote sensing applications, have been developed using OpenMP technology and have been integrated into a remote sensing application that works online. As a result of experiments, 3-4 times improvement for offline and 16-19 times improvement for online has been achieved when compared to MATLAB algorithms.

关键词： remote sensing Real-time/Near Real-time Analysis SAM MF OpenMP MPI

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：