检索结果-内蒙古大学图书馆

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Zhengwu Yuan Yang Deng Aixia Yang Fan Zhang College of Computer Science and Technology Chongqing University of Posts and Telecommunication Chongqing China State Key Laboratory of Remote Sensing Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing China

The semantic segmentation of high-resolution remote sensing images is of paramount importance for applications such as land use, land cover, and cartography, and it holds great potential for widespread use. The characteristics of high-resolution remote sensing images are addressed in this study, and an end-to-end semantic segmentation network model is devised. An improved Resnet was employed to extract image features, and an efficient channel attention module was introduced to enhance the weights of important channels, with only a marginal increase in parameters. Due to significant scale variations among objects in high-resolution remote sensing images, a multi-scale algorithm was utilized to extract more comprehensive information. An object-enhancement algorithm was introduced, which, by incorporating object features, enhanced the contextual information of pixels in the high-level feature space. Through an analysis of the ultimate predictive performance, the model proposed in this paper demonstrated a certain advantage over popular semantic segmentation models such as Unet, DAnet, DeeplabV3, in predicting high-resolution remote sensing images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IIDM: Improved Implicit Diffusion Model with Knowledge Distillation to Estimate the Spatial Distribution Density of Carbon Stock in remote sensing Imagery

arXiv

引用

arXiv 2024年

作者： Yu, Zhenyu Wang, Jinnian Idris, Mohd Yamani Idna Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Kuala Lumpur50603 Malaysia Faculty of Geography and Remote Sensing Guangzhou University Guangdong Province Guangzhou510006 China

Forests play a critical role as terrestrial carbon sinks, effectively reducing atmospheric CO2 concentrations and mitigating climate change. remote sensing facilitates large-scale, high-accuracy carbon stock estimation, with optical imagery enabling long-term monitoring. This study focuses on Huize County, Qujing City, Yunnan Province, China, utilizing GF-1 WFV satellite imagery. We propose an Improved Implicit Diffusion Model (IIDM), integrating Knowledge Distillation (KD) for feature extraction and spatial distribution modeling. The key contributions are as follows: (1) A knowledge distillation-enhanced VGG (KD-VGG) module for efficient feature extraction, reducing inference time while preserving crucial spectral and spatial information. (2) A KD-UNet architecture with cross-attention and MLP modules for improved feature fusion, effectively capturing global-local relationships and enhancing estimation accuracy. (3) A novel IIDM framework incorporating generative diffusion modeling and implicit neural representations, enabling high-resolution spatial carbon stock estimation. IIDM achieves state-of-the-art accuracy, with an RMSE of 12.17%, outperforming traditional regression models by 41.69% to 42.33%. The model effectively extracts deep spatial and spectral features, surpassing existing methods and reinforcing the feasibility of AI-generated content in quantitative remote sensing. The high-resolution (16-meter) carbon stock distribution maps provide a solid foundation for refining forest carbon sink regulations and improving regional carbon stock management strategies. Copyright © 2024, The Authors. All rights reserved.

关键词： Global warming

来源：评论

学校读者我要写书评

暂无评论

Research on optimization selection of radar high-resolution range target recognition features

Research on optimization selection of radar high-resolution ...

引用

Frontiers technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Zhansheng Zhang Yongjie Zhang Zhen Lin Chuanxiong Zhou Danyang Liu Institute of Beijing Remote Sensing Device Beijing China College of Electronics Science and Technology National University of Defense Technology Changsha Hunan China Unit 61580 Beijing China

A set of feature combinations with high recognition rate is proposed for the identification of vehicle targets and corner reflectors in this article. In the process of target recognition based on high-resolution range profiles (HRRP) from radar; extracting target features and selecting the appropriate features are crucial. The stability and effectiveness of the selected features directly impact the quality of recognition. This paper proposes 15 identification features and determines the optimal feature combination for specific problems. These feature combinations are validated using a neural network classifier, resulting in a satisfactory verification outcome.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics For Groundwater Resources Using SVM And Deep Radial Basis Approaches In Smart City Planning For Feature Extraction And Prediction 2

Predictive Analytics For Groundwater Resources Using SVM And...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Padmavathi, N. Rafee, Shaik Mohammad Ahmed, Salman Kanagavalli, N. Gangwar, Prashant Kumar Meenakshi, S. Rmd Engineering College Department of Electronics and Instrumentation Engineering Tamilnadu Chennai India Sasi Institute of Technology & Engineering Department of Ai&ml Andhra Pradesh Tadepalligudem India Aligarh Muslim University Interdisciplinary Department of Remote Sensing & Gis Applications Uttar Pradesh Aligarh India Rajalakshmi Institute of Technology Department of Computer Science and Engineering Tamilnadu Chennai India Woldia University Department of Construction Technology & Management Woldia Town Ethiopia Tamilnadu Kavarapettai India

ISBN: (纸本)9798350371055

The growth of smart cities is happening at the same time that there is an increasing demand for water resources. Controlling groundwater in a responsible manner is absolutely necessary in order to ensure sustainability. When it comes to groundwater forecast, traditional methods are frequently wrong, which in turn leads to inefficient use of resources and bad planning. Specifically, the research employs a two technique, which combines Support Vector Machines (SVMs) for efficient feature extraction with DRB Approaches (DRBAs) for accurate prediction. SVM is excellent at extracting significant properties from complicated datasets, whereas DRB takes use of neural network capabilities to produce variable predictions. DRB employs neural network capabilities. When compared to methods that are considered to be more conventional, the findings indicate a significant improvement in the accuracy of this prediction. It is exciting to see that the combined support vector machine and DRB model are producing positive results when it comes to estimating groundwater resources. © 2024 IEEE.

关键词： Deep Radial Basis Groundwater Resources Predictive Analytics Smart City SVM

来源：评论

学校读者我要写书评

暂无评论

Method for differential phase delay resolution of phase referencing VLBI technique and its experimental verification

引用

Research in Astronomy and Astrophysics 2021年第11期21卷 267-272页

作者： Huan Zhou Jian-Guo Yan De-Zhen Xu Yong Huang Hai-Tao Li State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhan 430070China Beijing Institute of Tracking and Telecommunications Technology Beijing 100094China Shanghai Astronomical Observatory Chinese Academy of ScienceShanghai 200030China

The phase referencing Very Long Baseline Interferometry(VLBI)technique is a newly developed tool to measure the angular position of a deep space exploration probe in the *** alternating observations between the probe and a nearby reference radio source,their accurate relative angular separation can be obtained from the radio images generated by this *** meet the requirements of the current orbit determination software,differential delay should be firstly derived from those radio images.A method to resolve the differential phase delay from the phase referencing VLBI technique is proposed in this paper,and as well the mathematical model for differential phase ambiguity resolution is *** method is verified with practical measurement data from the Chang’E-3 *** differential phase delay between the Chang’E-3 lander and rover was derived from the phase referencing VLBI measurements,and was then imported into the Shanghai astronomical observatory Orbit Determination program(SODP)to calculate the position of the rover relative to the lander on the lunar *** results are consistent with those acquired directly from radio images,indicating that the differential phase ambiguity has been correctly *** proposed method can be used to promote applications of the phase referencing VLBI technique in future lunar or deep space explorations,and more accurate orbit determination becomes promising.

关键词： Phase referencing VLBI technique differential phase delay radio interferometry Chang’E-3 mission

来源：评论

学校读者我要写书评

暂无评论

Estimation of Terrestrial Net Primary Productivity in China from Fengyun-3D Satellite Data

引用

Journal of Meteorological Research 2022年第3期36卷 401-416页

作者： Yonghong LIU Xiuzhen HAN Fuzhong WENG Yongming XU Yeping ZHANG Shihao TANG Earth System Modeling and Prediction Center China Meteorological AdministrationBeijing 100081 State Key Laboratory of Severe Weather Chinese Academy of Meteorological SciencesChina Meteorological AdministrationBeijing 100081 National Satellite Meteorological Center China Meteorological AdministrationBeijing 100081 School of Remote Sensing and Geomatics Engineering Nanjing University of Information Science&TechnologyNanjing 210044

Currently,the satellite data used to estimate terrestrial net primary productivity(NPP)in China are predominantly from foreign satellites,and very few studies have based their estimates on data from China’s Fengyun ***,despite their importance,the influence of land cover types and the normalized difference vegetation index(NDVI)on NPP estimation has not been *** study employs the Carnegie–Ames–Stanford approach(CASA)model to compute the fraction of absorbed photosynthetically active radiation and the maximum light use efficiency suitable for the main vegetation types in China in accordance with the finer resolution observation and monitoring-global land cover(FROM-GLC)classification ***,the NPP is estimated from the Fengyun-3D(FY-3D)data and compared with the Moderate Resolution Imaging Spectroradiometer(MODIS)NPP *** FY-3D NPP is also validated with existing research results and historical field-measured NPP *** addition,the effects of land cover types and the NDVI on NPP estimation are *** results show that the CASA model and the FY-3D satellite data estimate an average NPP of 441.2 g C m^(−2) yr^(−1) in 2019 for China’s terrestrial vegetation,while the total NPP is 3.19 Pg C yr^(−1).Compared with the MODIS NPP,the FY-3D NPP is overestimated in areas of low vegetation productivity and is underestimated in high-productivity *** discrepancies are largely due to the differences between the FY-3D NDVI and MODIS *** with historical field-measured data,the FY-3D NPP estimation results outperformed the MODIS NPP results,although the deviation between the FY-3D NPP estimate and the in-situ measurement was large and may exceed 20%at the pixel *** land cover types and the NDVI significantly affected the spatial distribution of NPP and accounted for NPP deviations of 17.0%and 18.1%,***,the total deviation resulting from the two factors reached 29.5%.These results show that

关键词： net primary productivity(NPP) Carnegie-Ames-Stanford approach(CASA)model maximum light use efficiency Fengyun-3D(FY-3D) finer resolution observation and monitoring-global land cover(FROM-GLC)land cover types Moderate Resolution Imaging Spectroradiometer(MODIS)

来源：评论

学校读者我要写书评

暂无评论

Hyperspectral Tensor Completion Using Low-Rank Modeling and Convex Functional Analysis

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第8期35卷 10736-10750页

作者： Lin, Chia-Hsiang Liu, Yangrui Chi, Chong-Yung Hsu, Chih-Chung Ren, Hsuan Quek, Tony Q. S. National Cheng Kung University Department of Electrical Engineering Tainan70101 Taiwan National Tsing Hua University Department of Electrical Engineering Hsinchu300044 Taiwan National Cheng Kung University Department of Statistics Tainan70101 Taiwan National Central University Center for Space and Remote Sensing Research Taoyuan320317 Taiwan Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore487372 Singapore National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Hyperspectral tensor completion (HTC) for remote sensing, critical for advancing space exploration and other satellite imaging technologies, has drawn considerable attention from recent machine learning community. Hyperspectral image (HSI) contains a wide range of narrowly spaced spectral bands hence forming unique electrical magnetic signatures for distinct materials, and thus plays an irreplaceable role in remote material identification. Nevertheless, remotely acquired HSIs are of low data purity and quite often incompletely observed or corrupted during transmission. Therefore, completing the 3-D hyperspectral tensor, involving two spatial dimensions and one spectral dimension, is a crucial signal processing task for facilitating the subsequent applications. Benchmark HTC methods rely on either supervised learning or nonconvex optimization. As reported in recent machine learning literature, John ellipsoid (JE) in functional analysis is a fundamental topology for effective hyperspectral analysis. We therefore attempt to adopt this key topology in this work, but this induces a dilemma that the computation of JE requires the complete information of the entire HSI tensor that is, however, unavailable under the HTC problem setting. We resolve the dilemma, decouple HTC into convex subproblems ensuring computational efficiency, and show state-of-the-art HTC performances of our algorithm. We also demonstrate that our method has improved the subsequent land cover classification accuracy on the recovered hyperspectral tensor. © 2012 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Ship Detection and Classification in Cas500-1 Images Based on Yolo Model

Ship Detection and Classification in Cas500-1 Images Based o...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： Tae-Ho Kim Yeongbin Park Soyeong Jang Chan-Su Yang Department of Remote Sensing Underwater Survey Technology 21 Corp South Korea Marine Domain & Security Research Department Korea Institute Ocean Science and Technology South Korea

In 2021, compared to the last year, global port container logistic volumes increased by 7% (857 million 20-foot equivalent units (TEU)), while deliveries of newly built container ships increased by 18% (10,929 thousand gross tons) [1]. Hence, the problem instigated by an increased volume of logistics and port congestion can be solved through the efficient operation of the port, and ship detection and volume data processing have become important. Ship monitoring related to port logistics is possible by checking the Auto Identification System (AIS) [2]. The Terrestrial AIS (T-AIS) system is capable of detecting only short-range communication up to 50 nautical miles [3], and there is an omission to monitor the ship when the navigator controls the transmission-receiving of AIS [4]. Therefore, as the ability of satellites increases, there is a movement to detect missing ships using satellite images [5]. In this study, ship detection was conducted to monitor container ships that were not operate in the anchorage area around the port or berth at the pier. In order to find container ships through deep learning, four types of vessels (container ships, bulk ships, oil tankers, and small ships) were extracted from Compact Advanced Satellite 500-1 (CAS500-1) satellite images in the yellow sea and one port to make a training dataset. The CAS500 satellites carry different sensors for different Earth observation missions. CAS500-1 has the panchromatic and multispectral modes using the AEISS-C (Advanced Earth Imaging Sensor System) payload for land surface imagery, land topography imagery, and vegetation-type imagery. Although improvement in remote surface reflectance is needed, it can be beneficial at sea. The detection model was established through YOLOv5 (You Only Look Once version 5) [6] deep learning algorithm. The model's performance was evaluated by applying them to the CAS500-1, and Korea Multi-Purpose Satellite-3 (KOMPSAT-3), taken at the Busan New Port, Korea, and Oakland

关键词：

来源：评论

学校读者我要写书评

暂无评论

China's greenhouse gas budget during 2000-2023

引用

National science Review 2025年第4期12卷 24-36页

作者： Wenping Yuan Minqi Liang Yuanyi Gao Ling Huang Li Dan Hongtao Duan Songbai Hong Fei Jiang Weimin Ju Tingting Li Ziyang Lou Shilong Luan Xiao Lu Zhangcai Qin Lishan Ran Lulu Shen Fei Teng Xiangjun Tian Yilong Wang Jing Wei Jiangzhou Xia Xiaosheng Xia Lijun Yu Xu Yue Haicheng Zhang Wen Zhang Yuzhong Zhang Xu Zhao Qiuan Zhu Shilong Piao Xuhui Wang Institute of Carbon Neutrality Sino-French Institute for Earth System Science College of Urban and Environmental Sciences Peking University School of Atmospheric Sciences Guangdong Province Data Center of Terrestrial and Marine Ecosystems Carbon Cycle Sun Yat-sen University Key Laboratory of Regional Climate-Environment for Temperate East Asia Institute of Atmospheric PhysicsChinese Academy of Sciences Key Laboratory of Lake and Watershed Science for Water Security Nanjing Institute of Geography and LimnologyChinese Academy of Sciences State Key Laboratory of Lake Science and Environment Nanjing Institute of Geography and LimnologyChinese Academy of Sciences School of Urban Planning and Design Shenzhen Graduate School Peking University Frontiers Science Center for Critical Earth Material Cycling Nanjing University Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology International Institute for Earth System Science Nanjing University Key Laboratory of Atmospheric Environment and Extreme Meteorology Institute of Atmospheric PhysicsChinese Academy of Sciences Shanghai Engineering Research Center of Solid Waste Treatment and Resource Recovery School of Environmental Science & Engineering Shanghai Jiao Tong University Department of Geography The University of Hong Kong Department of Atmospheric and Oceanic Sciences School of PhysicsPeking University Institute of Energy Environment and Economy Tsinghua University State Key Laboratory of Tibetan Plateau Earth System Resources and Environment (TPESRE)Institute of Tibetan Plateau ResearchChinese Academy of Sciences Tianjin Key Laboratory of Water Resources and Environment Tianjin Normal University State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry (LAPC) Institute of Atmospheric PhysicsChinese Academy of Sciences Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Collaborative Innovation Center of Atmospheric Environment and Equipment Technology School of

National greenhouse gas（GHG） budget,including CO2,CH4and N2O has increasingly become a topic of concern in international climate *** is paying increasing attention to reducing GHG emissions and increasing land sinks to effectively mitigate climate *** estimates of GHG fluxes are crucial for monitoring progress toward mitigating GHG emissions in *** study used comprehensive methods,including emission factor methods,process-based models,atmospheric inversions,and data-driven models,to estimate the long-term trends of GHG sources and sinks from all anthropogenic and natural sectors in China's mainland during 2000-2023,and produced an up-to-date China GHG Budget dataset（CNGHG）.The total gross emissions of the three GHGs show a 3-fold increase from 5.0（95% CI:4.9-5.1） Gt CO2-eq yr-1（in 2000） to 14.3（95% CI:13.8-14.8） Gt CO2-eqyr-1（in2023）.CO2emissions represented 81.8% of the GHG emissions in 2023,while 12.7% and 5.5% were for CH4and N2O,*** the largest CO2source,the energy sector contributed 87.4% *** contrast,the agriculture,forestry and other land use sector was the largest sector of CH4and N2O,representing 50.1% and 6 6.3% emissions,***,China's terrestrial ecosystems serve as a net CO2sink(1.0 Gt CO2yr-1,9596 CI:0.2-1.9 Gt CO2yr-1) during 2012 to 2021,equivalent to an average of 14.3% of fossil *** GHG emission estimates showed a general consistency with national GHG inventories,with gridded and sector-specific estimates of GHG fluxes over China,providing the basis for curtailing GHG emissions for each region and sector.

关键词： greenhouse gas budget China carbon dioxide methane nitrous oxide

来源：评论

学校读者我要写书评

暂无评论

Shape Control of an Adaptive Spherical Shell Reflector under Space Environment 8

Shape Control of an Adaptive Spherical Shell Reflector under...

引用

8th Symposium on Novel Photoelectronic Detection technology and Applications

作者： Wang, Kainan Preumont, André Institute of Aerospace Science and Technology School of Remote Sensing and Information Engineering Wuhan University Wuhan430072 China CP. 165-55 50 Av. F.D. Roosevelt BrusselsB-1050 Belgium

ISBN: (数字)9781510653122

ISBN: (纸本)9781510653115

This paper discusses a new concept of the active spherical shell reflector made of polymer materials, which exhibits excellent areal density and stowability and paves the way to future lightweight large-aperture space telescopes for potential observation of various wavelengths. The shape control of a small-scale technology demonstrator is performed, and the design criteria of patterned electrodes is proposed. The stress-stiffening effect on the piezoelectric strain actuation is investigated and the influence of manufacturing errors on the structural dynamics is also considered to give a preliminary study on evaluating the morphing capability under complex environment in space. © 2022 SPIE

关键词： Structural dynamics

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：