检索结果-内蒙古大学图书馆

Editorial for the Special Issue "Machine Learning in Computer Vision and image sensing: Theory and applications"

SENSORS 2024年第9期24卷 2874页

作者： Chakraborty, Subrata Pradhan, Biswajeet Univ New England Sch Sci & Technol Armidale NSW 2351 Australia Univ Technol Sydney Fac Engn & IT Ctr Adv Modelling & Geospatial Informat Syst CAMGI Sch Civil & Environm Engn Sydney NSW 2007 Australia Griffith Univ Griffith Business Sch Nathan Qld 4111 Australia Univ Kebangsaan Malaysia Inst Climate Change Earth Observat Ctr Bangi 43600 Selangor Malaysia

Machine learning (ML) models have experienced remarkable growth in their application for multimodal data analysis over the past decade [1]. The diverse applications of ML models span domains such as medical image [2,3,4] and signal processing [5,6], remote sensing for earth observation and monitoring [7,8,9], the detection of daily human activities [10,11], and many more. ML models play a significant role in supporting computer vision and image-sensing applications, helping to unravel complex and real-world challenges. recent developments in ML empower us to better analyse image and sensor data, motivating extensive research initiatives aimed at addressing applied challenges in multiple domains, including healthcare, agriculture, defence, remote sensing, earth observation, and autonomous navigation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive analysis of ghost imaging for remote sensing (GIRS): A review

引用

OPTICS AND LASER TECHNOLOGY 2025年 189卷

作者： Iqbal, Rehmat Abbas, Ayesha Jie, Cao Shah, Syed Ali Idrees, Muhammad Ning, Yan Minist Educ Key Lab Biomimet Robots & Syst Beijing Peoples R China Beijing Inst Technol Sch Opt & Photon Beijing 100081 Peoples R China Minist Educ Biomimet Robots & Syst Beijing Peoples R China Beijing Inst Technol Yangtze Delta Reg Acad Jiaxing 314003 Peoples R China Natl Key Lab Near Surface Detect Beijing 100072 Peoples R China Beijing Inst Technol Sch Phys Beijing 100081 Peoples R China Natl Key Lab Land & Air Based Informat Percept & C Beijing Peoples R China Xian Modern Control Technol Res Inst Xian Peoples R China

Ghost imaging (GI) is an innovative technique that utilizes correlated light intensities to reconstruct images without the requirement of direct spatial resolution measurements. It offers several advantages in various applications, such as improved image resolution, robustness against noise and scattering, less computational cost, and an effective solution for low-light imaging. GI enables surveillance and target detection in remote sensing with its recent developments. With the evolving technique of GI with machine and deep learning (ML/DL), GI with LiDAR and advanced reconstruction algorithms in computational ghost imaging (CGI), GI can be applied in various domains of remote sensing. Ghost imaging in remote sensing (GIRS), is potential solution for atmospheric monitoring, target detection and classification, surveillance and underwater imaging. In this comprehensive analysis, we studied the recent advancements in GI and its modalities in remote sensing with new developments in optical components used in GIRS. However, with the challenges available in scaling the technologies for long-range sensing and real-time processing capabilities, we provide comprehensive solutions in limitations and future directions with advantages in GIRS.

关键词： Ghost imaging Single pixel imaging remote sensing GI LiDAR Object detection Deep learning Underwater imaging

来源：评论

学校读者我要写书评

暂无评论

recent advances in the application of vision transformers to remote sensing image scene classification

引用

remote sensing LETTERS 2023年第7期14卷 722-732页

作者： Kumari, Monika Kaul, Ajay Shri Mata Vaishno Devi Univ Sch Comp Sci & Engn Katra J&K India

Researchers have investigated the potential of transformer-based models in remote sensing (RS) applications, such as scene categorization, after their recent success in natural language processing and computer vision tasks. In this review article, we provide an overview of the recent developments in vision transformer (ViT)-based models for remote sensing image scene classification (RSISC). We first introduce the basic architecture of transformer models and their extensions to computer vision tasks. Then, we summarize the current state-of-the-art ViT-based models for RSISC, including their architectures, training strategies, and performance evaluation. We also discuss the challenges and limitations of the existing ViT-based models. Finally, we outline some potential future directions for developing transformer-based models for RS applications. This review article intends to give a complete analysis of the current state-of-the-art and future research prospects for ViTs in RSISC, which can be used as a reference for researchers and practitioners in this field.

关键词： Convolutional neural network Computer Vision Scene representation Scene classification Deep Learning vision transformers

来源：评论

学校读者我要写书评

暂无评论

Advancing horizons in remote sensing: a comprehensive survey of deep learning models and applications in image classification and beyond

引用

Neural Computing and applications 2024年第27期36卷 16727-16767页

作者： Paheding, Sidike Saleem, Ashraf Siddiqui, Mohammad Faridul Haque Rawashdeh, Nathir Essa, Almabrok Reyes, Abel A. Department of Computer Science and Engineering Fairfield University 1073 N Benson Rd FairfieldCT06824 United States Department of Applied Computing Michigan Technological University 1400 Townsend Dr HoughtonMI49931 United States Department of Computer Science West Texas AM University 2501 4th Ave CanyonTX79016 United States Department of Mathematics Computer Science and Data Science John Carroll University 1 John Carroll Blvd University HeightsOH44118 United States

In recent years, deep learning has significantly reshaped numerous fields and applications, fundamentally altering how we tackle a variety of challenges. Areas such as natural language processing (NLP), computer vision, healthcare, network security, wide-area surveillance, and precision agriculture have leveraged the merits of the deep learning era. Particularly, deep learning has significantly improved the analysis of remote sensing images, with a continuous increase in the number of researchers and contributions to the field. The high impact of deep learning development is complemented by rapid advancements and the availability of data from a variety of sensors, including high-resolution RGB, thermal, LiDAR, and multi-/hyperspectral cameras, as well as emerging sensing platforms such as satellites and aerial vehicles that can be captured by multi-temporal, multi-sensor, and sensing devices with a wider view. This study aims to present an extensive survey that encapsulates widely used deep learning strategies for tackling image classification challenges in remote sensing. It encompasses an exploration of remote sensing imaging platforms, sensor varieties, practical applications, and prospective developments in the field. © The Author(s) 2024.

关键词： remote sensing

来源：评论

学校读者我要写书评

暂无评论

Advances in Deep Learning applications for Plant Disease and Pest Detection: A Review

引用

remote sensing 2025年第4期17卷 698-698页

作者： Wang, Shaohua Xu, Dachuan Liang, Haojian Bai, Yongqing Li, Xiao Zhou, Junyuan Su, Cheng Wei, Wenyu Hainan Aerosp Informat Res Inst Key Lab Earth Observat Hainan Prov Sanya 572029 Peoples R China Chinese Acad Sci Aerosp Informat Res Inst State Key Lab Remote Sensing & Digital Earth Beijing 100101 Peoples R China Lanzhou Jiaotong Univ Fac Geomat Lanzhou 730070 Peoples R China Univ Chinese Acad Sci Coll Resources & Environm Beijing 100049 Peoples R China Lanzhou Jiaotong Univ Sch Architecture & Urban Planning Lanzhou 730070 Peoples R China

Traditional methods for detecting plant diseases and pests are time-consuming, labor-intensive, and require specialized skills and resources, making them insufficient to meet the demands of modern agricultural development. To address these challenges, deep learning technologies have emerged as a promising solution for the accurate and timely identification of plant diseases and pests, thereby reducing crop losses and optimizing agricultural resource allocation. By leveraging its advantages in image processing, deep learning technology has significantly enhanced the accuracy of plant disease and pest detection and identification. This review provides a comprehensive overview of recent advancements in applying deep learning algorithms to plant disease and pest detection. It begins by outlining the limitations of traditional methods in this domain, followed by a systematic discussion of the latest developments in applying various deep learning techniques-including image classification, object detection, semantic segmentation, and change detection-to plant disease and pest identification. Additionally, this study highlights the role of large-scale pre-trained models and transfer learning in improving detection accuracy and scalability across diverse crop types and environmental conditions. Key challenges, such as enhancing model generalization, addressing small lesion detection, and ensuring the availability of high-quality, diverse training datasets, are critically examined. Emerging opportunities for optimizing pest and disease monitoring through advanced algorithms are also emphasized. Deep learning technology, with its powerful capabilities in data processing and pattern recognition, has become a pivotal tool for promoting sustainable agricultural practices, enhancing productivity, and advancing precision agriculture.

关键词： deep learning disease detection plant diseases and pests image classification object detection convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Interferometric Synthetic Aperture Radar Statistical Inference in Deformation Measurement and Geophysical Inversion: A review

引用

IEEE GEOSCIENCE AND remote sensing MAGAZINE 2024年第1期12卷 8-35页

作者： Wang, Chisheng Chang, Ling Wang, Xiang-Sheng Zhang, Bochen Stein, Alfred Shenzhen Univ Minist Nat Resources MNR Key Lab Geoenvironm Monitoring Great Bay Area Shenzhen 518060 Peoples R China Shenzhen Univ Sch Architecture & Urban Planning Guangdong Key Lab Urban Informat Shenzhen 518060 Peoples R China Univ Twente Fac Geoinformat Sci & Earth Observat Microwave Remote Sensing Dept Earth Observat Sci NL-7522 NH Enschede Netherlands Univ Louisiana Lafayette Dept Math Lafayette LA 70503 USA Shenzhen Univ Coll Civil & Transportat Engn Shenzhen 518060 Peoples R China Univ Twente Fac Geoinformat Sci & Earth Observat Spatial Stat & Image Anal Dept EOS NL-7522 NH Enschede Netherlands

With the rapid advancements in synthetic aperture radar (SAR) satellites and associated processing algorithms over recent decades, interferometric SAR (InSAR) has emerged as a routine method for monitoring large-scale ground deformation and interpreting geophysical processes. Statistical inference serves as a major component in InSAR technique developments and applications. This article provides an overview of InSAR deformation measurement and InSAR-constrained geophysical inversion, using a statistical inference point of view. Its objectives are to facilitate understanding of the method by addressing its underlying mathematical challenges. We begin by introducing the concept of statistical inference and the structure of our content organization framework. Next, we investigate the distinct concerns associated with statistical inference in InSAR deformation measurement and InSAR-constrained geophysical inversion. Finally, we propose several significant directions for future research. Table 1 includes abbreviations used throughout this article. Additionally, we highlight relevant resources, such as mathematical background, open source codes, and data repositories, in an appendix, which is available as supplementary material at https://***/10.1109/MGRS.2023.3344159.

关键词： Deformation Geophysical measurements Synthetic aperture radar Maximum likelihood estimation Phase estimation Coherence Testing

来源：评论

学校读者我要写书评

暂无评论

recent Advances in Linear Polarization-Sensitive Photodetectors Based on Perovskites with Different Molecular Dimensions

引用

ADVANCED MATERIALS TECHNOLOGIES 2025年第3期10卷

作者： Wang, Xiaoting Zhang, Fengyi Xu, Rongrong Yin, Qianxi Li, Mulin Huang, Xianliang Ma, Teng Chen, Ziyi Chen, Jun Zeng, Haibo Nanjing Univ Sci & Technol Inst Optoelect & Nanomat Sch Mat Sci & Engn MIIT Key Lab Adv Display Mat & Devices Nanjing 210094 Peoples R China Nanjing Univ Sci & Technol Sch Phys Nanjing 210094 Peoples R China

The function of photodetectors is to convert optical signals into current or voltage output. Polarization-sensitive perovskite photodetectors have attracted significant interest because of their potential applications in imaging and remote sensing technologies. This study provides an overview of the advancements in research on halide perovskite photodetectors, particularly focusing on their capability for linear polarization-sensitive detection. First, there is a brief description of the background and strengths of linear polarization-sensitive photodetectors. Then, the core parameters of linear polarization-sensitive photodetectors are introduced briefly. Third, according to the classification of active layer materials, linear polarization-sensitive photodetectors are divided into 3D perovskites and low-dimensional perovskites. The research on linear polarization-sensitive perovskite detectors are reviewed. Finally, the developments and challenges faced by linear polarization-sensitive perovskite photodetectors are analyzed. Photodetector is a core component of optoelectronic devices. Halide perovskites are popular materials for linear polarization-sensitive photodetectors. This review focuses on perovskites and adopts a novel classification perspective: categorization from molecular-level dimensions. By citing innovations in synthesis methods, processing techniques, and materials, this review summarizes the research boom of linear polarization-sensitive perovskite photodetectors that began in 2016. image

关键词： active layer halide perovskite linear polarization-sensitive photodetector

来源：评论

学校读者我要写书评

暂无评论

Review Study on recent developments in Fire sensing Methods

引用

IEEE ACCESS 2023年 11卷 90269-90282页

作者： Sulthana, S. Fouziya Wise, Cross T. Asha Ravikumar, C. V. Anbazhagan, Rajesh Idayachandran, G. Pau, Giovanni SRM Inst Sci & Technol Fac Engn & Technol Dept Mechatron Engn Kattankulathur 603203 Tamil Nadu India Vellore Inst Technol Sch Elect Engn Vellore 632014 India SASTRA Univ Sch Elect & Elect Engn Thanjavur 613401 India Vellore Inst Technol Sch Elect Engn Chennai 600127 India Kore Univ Enna Fac Engn & Architecture I-94100 Enna Italy

Scientific society has envisioned a considerable advancement in various fire detection methods due to the development in the field of machine learning, information technology, sensors, and signal processing technology. These intelligent processing technologies help in reducing the detection time and false alerts from the sensors. Over the past few decades, there is substantial improvement in the computing power of computers and a decrease in the cost of image sensors, enabling video-based fire detection technology for real-time applications. The ability to differentiate between fire and non-fire threats is improved with the development of the Internet of Things (IoT) or Wireless Sensor Networks (WSN). Unmanned Aerial Vehicles (UAVs) are becoming a more realistic solution for monitoring and detecting fire due to their remote sensing capabilities. This paper summarizes various fire detection methods and the technologies behind them. The issues related to the present fire detection methods and future research initiatives are discussed. The primary aspects of the fire signatures like flame, smoke, ambient temperature, and surrounding gaseous levels concerning different sensors are analyzed with their benefits and drawbacks based on evaluating a range of parameters.

关键词： Sensors Detectors Heating systems Fires Temperature sensors Smoke detectors Gas detectors Fire sensors smoke detectors flame detectors heat detectors gas detector

来源：评论

学校读者我要写书评

暂无评论

Editorial to Special Issue "Multispectral image Acquisition, processing and Analysis-2nd Edition"

引用

remote sensing 2024年第23期16卷 4532-4532页

作者： Vozel, Benoit Lukin, Vladimir Bazi, Yakoub Univ Rennes Inst Elect & Telecommun IETR CNRS UMR 6164 F-22305 Lannion France Natl Aerosp Univ Dept Informat & Commun Technol UA-61070 Kharkiv Ukraine King Saud Univ Coll Comp & Informat Sci Comp Engn Dept Riyadh 11543 Saudi Arabia

Modern means of remote sensing (RS) in general and multispectral imaging in particular have experienced rapid development in recent years. Several factors facilitate the design and application of new imagers and methods for data processing. First, UAVs and drones have become possible carriers of such imagers, allowing one to operatively obtain data for desired regions from a wide range of altitudes and, respectively, with different resolutions. Second, convolutional neural networks and artificial intelligence approaches have sufficiently expanded the possibilities of data processing and the extraction of useful information. Third, more people and organizations are beginning to understand the capabilities and advantages of remote sensing and have began to exploit it for solving a wider set of practical tasks at the state and regional *** eleven papers featured in this Special Issue highlight the continued dedication of the remote sensing community to advancing innovative techniques that address the needs of end-users. These developments and enhancements are expected to further support the growth and refinement of remote sensing applications for operational purposes. We hope readers find this Special Issue both insightful and engaging.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Implementation of coded targets for metrology applications in MicMac, a free open-source photogrammetric software

Implementation of coded targets for metrology applications i...

引用

2024 Optical 3D Metrology, O3DM 2024

作者： Muller, Jean-Michael Daakir, Mehdi Deseilligny, Marc Pierrot Barcet, Florian Univ. Gustave Eiffel ENSG IGN LASTIG Saint-MandéF-94160 France CERN Geneva Switzerland

image-based metrology is an increasingly utilized technique across a wide range of industrial applications, largely due to its reliance on precisely measurable and automatically detectable patterns within images. In photogrammetry, coded and uncoded targets, such as ground control points, are commonly used throughout the photogrammetric processing chain. This study presents recent developments in the integration of coded-targets within MicMac, a free open-source photogrammetric software. These developments were undertaken in collaboration between IGN and CERN for future accelerator alignments using image-based ecartometric measurement. One key goal, addressed in this paper, is the creation of a flexible coded-target generator within MicMac, allowing users to specify various constraints for target generation. Additionally, detection and simulation tools were implemented and evaluated. This paper focuses on the use of a common circular coded-target pattern, and introduces a novel home-made target design optimized for both image measurements and topometric instruments. Results from 2D and 3D simulations, as well as real data, demonstrate performance similar to commercial software solutions using circular coded-target, or even superior in certain configurations using our home-made target pattern. To our best knowledge, MicMac is the only free and open-source software achieving these levels of performance. © Author(s) 2024.

关键词： Photogrammetry

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：