检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Nie, Han Luo, Bin Liu, Jun Fu, Zhitao Liu, Weixing Su, Xin The State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China The School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China The Faculty of Land Resources Engineering Kunming University of Science and Technology Kunming650031 China

We present REMM, a rotation-equivariant framework for end-to-end multimodal image matching, which fully encodes rotational differences of descriptors in the whole matching pipeline. Previous learning-based methods mainly focus on extracting modal-invariant descriptors, while consistently ignoring the rotational invariance. In this paper, we demonstrate that our REMM is very useful for multimodal image matching, including multimodal feature learning module and cyclic shift module. We first learn modal-invariant features through the multimodal feature learning module. Then, we design the cyclic shift module to rotationally encode the descriptors, greatly improving the performance of rotation-equivariant matching, which makes them robust to any angle. To validate our method, we establish a comprehensive rotation and scale-matching benchmark for evaluating the anti-rotation performance of multimodal images, which contains a combination of multi-angle and multi-scale transformations from four publicly available datasets. Extensive experiments show that our method outperforms existing methods in benchmarking and generalizes well to independent datasets. Additionally, we conducted an in-depth analysis of the key components of the REMM to validate the improvements brought about by the cyclic shift module. Code and dataset at https://***/HanNieWHU/REMM. Copyright © 2024, The Authors. All rights reserved.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised segmentation of individual buildings from SAR imagery

Semi-supervised segmentation of individual buildings from SA...

引用

Urban remote sensing Joint Event

作者： Qingyu Li Yao Sun Lichao Mou Yilei Shi Xiao Xiang Zhu Data Science in Earth Observation Technical University of Munich (TUM) Munich Germany Data Science in Earth Observation Technical University of Munich (TUM) Remote Sensing Technology Institute (IMF) German Aerospace Center (DLR) Munich Germany Chair of Remote Sensing Technology Technical University of Munich (TUM) Munich Germany

Buildings are essential geo-targets that contribute to the monitoring of urban development. Synthetic aperture radar (SAR) provides excellent opportunities for building segmentation as it is insensitive to sunlight illumination and weather conditions. Nevertheless, the majority of existing approaches that exploit convolutional neural networks (CNNs), need to collect an enormous quantity of annotations for network training. Therefore, we propose an innovative semi-supervised method for individual building segmentation from SAR imagery. Our approach has three modules: a weights-shared encoder, a main decoder as well as an auxiliary decoder. For unlabeled samples, given the perturbation added to the encoder’s output, we enforce the consistency between the feature and output of the auxiliary decoder and those of the main decoder. This allows for the use of abundant unlabeled samples to make up for a lack of supervisory information. The experiments are carried out on a SAR dataset that is collected from the city of Berlin, Germany. Quantitative and qualitative results suggest that our approach is superior to other competitors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

THE DEPLOYMENT OF A WI-FI POSITIONING SYSTEM VIA CROWDSOURCING 7

THE DEPLOYMENT OF A WI-FI POSITIONING SYSTEM VIA CROWDSOURCI...

引用

7th International Conference on Ubiquitous Positioning, Indoor Navigation and Location-Based Services, UPINLBS 2022

作者： Cao, X. Chen, G. Zhuang, Y. Wang, X. Yang, X. State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China School of Environment Science and Spatial Informatics China University of Mining and Technology Xuzhou China Wuhan Institute of Quantum Technology Wuhan China

Wi-Fi fingerprint positioning is widely used because of its ready hardware and high accuracy. However, its application is considerably restricted by time-consuming and labor-intensive works of offline collection and irregular fluctuation of signals. To address the above problems, we proposed a novel method to deploy the Wi-Fi fingerprint database based on implicit crowdsourcing and improved the weighted k-nearest neighbor (WKNN) algorithm to eliminate the influence of neighbor mismatching and device heterogeneity. First, ordinary users continuously gather Wi-Fi information instead of collecting one point after another. Meanwhile, video surveillance cameras record users' trajectories without any intervention and use monocular vision based on plane constraints to obtain users' location at the moment of each scanning. At the localization phase, the morphology similarity distance instead of the Euclidean distance is used to measure the similarity of signals to solve the problem of device heterogeneity. Outlier detection is also utilized for a secondary selection of neighbor points. Finally, geometric and signal morphology similarity distances are used to determine the combined weight of all neighbors after the dimensionless treatment. Results of the experiments conducted in a real indoor environment show that the proposed strategy improves the efficiency of fingerprint collection and achieves higher positioning accuracy. © Copyright:

关键词： combined weight device heterogeneity morphology similarity distance outlier detection Wi-Fi fingerprint indoor positioning

来源：评论

学校读者我要写书评

暂无评论

Study on the correction factors in detection efficiency measurements based on spontaneous parametric down-conversion

引用

Optics Express 2025年第13期33卷 27358-27370页

作者： Zhihan Jin Bing Yu Junwei Chu Jianjun Li Xiaobing Zheng Anhui Province Key Laboratory of Optical Quantitative Remote Sensing Hefei Institutes of Physical Science Chinese Academy of Sciences Hefei Anhui Province 230031 China University of Science and Technology of China Hefei Anhui Province 230026 China Xi'an Institute of Applied Optics Xi'an Shanxi Province 710065 China

This study discusses the correction factors in detection efficiency measurements based on spontaneous parametric down-conversion (SPDC) and coincidence counting. To address the coincidence loss induced by relative delays between two detection channels, this study proposes an accurate calculation analysis based on counting probability statistics derived from coincidence events. Additionally, an approximate method utilizing histograms and the photon count rate of detectors is proposed, which can effectively reduce the errors in coincidence loss corrections. Furthermore, the study discusses the dead time of single-photon detectors (SPDs) and proposes a weighted-average method applicable for correcting the influence of dead time.

关键词： Calibration Detectors Parametric down conversion Photodetectors Photon counting Single-photon avalanche diodes

来源：评论

学校读者我要写书评

暂无评论

Improving the UNet with channel attention mechanism for Taihu Lake water body recognition

Improving the UNet with channel attention mechanism for Taih...

引用

2024 International Conference on remote sensing and Global Positioning Algorithm, RSGPA 2024

作者： Nie, Shiliang Zhao, Limin Jiang, Mingyong Li, Zhiliang Liu, Shumin Li, Jiaguo Wan, Wei Sun, Yuan School of Software Engineering Jiangxi University of Science and Technology Nanchang330013 China Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China School of Space Information Space Engineering University Beijing101416 China Institute of Remote Sensing and GIS School of Earth and Space Sciences Peking University Beijing100871 China

Accurate recognition of surface water bodies is important for disaster management and resource planning. To explore a higher-precision water body recognition method, propose an improved channel attention mechanism UNet (ECA-UNet) water body recognition model based on Sentinel-2A remote sensing images. Utilizing ECA-UNet, UNet, PSPnet, and DeeplabV3, as well as the traditional normalized water body index (NDWI), recognize the water body in the Taihu Lake area. Through comparative analysis, the following main conclusions are drawn: (1) The recognition accuracy of the deep learning network model is better than the traditional NDWI method, among which the ECA-UNet network model has the highest accuracy of 98.67%, and the lowest recognition accuracy of NDWI is 89.06%. (2) The ECA-UNet network model can effectively extract water body recognition targets, has a better recognition effect on local features of water bodies, and can improve the water body extraction effect. The above results show that the improved channel attention mechanism ECA-UNet has the highest accuracy in water body recognition in Taihu Lake, which provides a reference for subsequent research and applications in this field. © 2024 Institute of Physics Publishing. All rights reserved.

关键词： Lakes

来源：评论

学校读者我要写书评

暂无评论

Should phenological information be applied to predict agronomic traits across growth stages of winter wheat?

引用

The Crop Journal 2022年第5期10卷 1346-1352页

作者： Yu Zhao Yang Meng Shaoyu Han Haikuan Feng Guijun Yang Zhenhai Li Key Laboratory of Quantitative Remote Sensing in Agriculture of Ministry of Agriculture and Rural Affairs Information Technology Research CenterBeijing Academy of Agriculture and Forestry SciencesBeijing 100097China Collaborative Innovation Center for Modern Crop Production Co-sponsored by Province and Ministry Nanjing Agricultural UniversityNanjing 210095JiangsuChina College of Geomatics Shandong University of Science and TechnologyQingdao 266590ShandongChina

Most existing agronomic trait models of winter wheat vary across growing seasons, and it is an open question whether a unified statistical model can be developed to predict agronomic traits using a vegetation index(VI) across multiple growing seasons. In this study, we constructed a hierarchical linear model(HLM) to automatically adapt the relationship between VIs and agronomic traits across growing seasons and tested the model’s performance by sensitivity analysis. Results demonstrated that(1) optical VIs give poor performance in predicting AGB and PNC across all growth stages, whereas VIs perform well for LAI, LGB, LNC, and SPAD.(2) The sensitivity indices of the phenological information in the AGB and PNC prediction models were 0.81–0.86 and 0.66–0.73, whereas LAI, LGB, LNC, and SPAD prediction models produced sensitivity indexes of 0.01–0.02, 0.01–0.02, 0.01–0.02, and 0.02–0.08, respectively.(3) The AGB and PNC prediction models considering ZS were more accurate than the prediction models based on VI. Whether or not phenological information is used, there was no difference in model accuracy for LGB,LNC, SPAD, and LAI. This study may provide a guideline for deciding whether phenological correction is required for estimation of agronomic traits across multiple growing seasons.

关键词： Agronomic traits Phenological effect Vegetation index Hierarchical linear model Winter wheat

来源：评论

学校读者我要写书评

暂无评论

China Land Carbon Budget(CLCB1.0):a comprehensive estimate of the land carbon budget in China

引用

National science Review 2025年第4期12卷 15-18页

作者： Jiangzhou Xia Xiaosheng Xia Xuhui Wang Weimin Ju Zhengyang Lin Zhangcai Qin Yuxing Sang Yanzi Yan Wenping Yuan Xu Yue Haicheng Zhang Hao Zhou Qiuan Zhu Tianjin Key Laboratory of Water Resources and Environment Tianjin Normal University School of Atmospheric Sciences Sun Yat-sen University Institute of Carbon Neutrality Sino-French Institute for Earth System ScienceCollege of Urban and Environmental SciencesPeking University International Institute for Earth System Sciences Nanjing University Jiangsu Center for Collaborative Innovation in Geographic Information Resource Development and Application School of Atmospheric Sciences Guangdong Province Key Laboratory for Climate Change and Natural Disaster Studies Key Laboratory of Tropical Atmosphere-Ocean System (Ministry of Education) Sun Yat-sen University Department of Soil and Environment Swedish University of Agricultural Sciences Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Collaborative Innovation Center of Atmospheric Environment and Equipment Technology School of Environmental Science and Engineering Nanjing University of Information Science & Technology (NUIST) Carbon-Water Research Station in Karst Regions of Northern Guangdong School of Geography and Planning Sun Yat-sen University College of Meteorology and Oceanography National University of Defense Technology College of Geography and Remote Sensing Hohai University

The terrestrial ecosystem plays an important role in regulating the regional carbon balance, in particular for China, where ecological projects during past decades [1,2] have led to large increases in China's land carbon sinks, partially offsetting fossil fuel emissions. Therefore, accurate evaluation of land carbon fluxes in China is critical for improving our understanding of the magnitude of China's carbon budget, and projecting its future changes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Rethinking the Role of Panchromatic Images in Pan-sharpening

引用

IEEE Transactions on Multimedia 2025年

作者： Wang, Jiaming Chen, Xitong Huang, Xiao Zhang, Ruiqian Wang, Yu Lu, Tao Wuhan Institute of Technology School of Computer Science and Engineering Wuhan430205 China Emory Univwersity Department of Environmental Sciences AtlantaGA30322 United States Chinese Academy of Surveying and Mapping Institute of Photogrammetry and Remote Sensing Beijing100036 China Wuhan University State Key Laboratory for Information Engineering in Surveying Mapping and Remote Sensing Wuhan430079 China

Recent pan-sharpening methods have predominantly utilized techniques tailored for natural image scenes, often overlooking the unique features arising from non-overlapping spectral responses. In light of this, we have reevaluated the utility of panchromatic (PAN) images and introduced a theory anchored in the spectral response of satellite sensors. This posits that a PAN image is effectively a linear weighted summation of individual bands from its corresponding multi-spectral (MS) image, offset by an error map. We developed a deep unmixing network termed "DUN"that integrates an unmixing network, a fusion mechanism, and a distinctive mutual information contrastive loss function. Notably, the unmixing network is adept at decomposing a PAN image into its MS counterpart and error map. Further, the demixed image alongside the low-resolution MS image is channeled into the fusion network for pan-sharpening. Recognizing the challenges of achieving robust supervised learning directly from the unmixing phase, we have innovated a mutual information contrastive learning loss function, ensuring enhanced separation and minimizing overlap during the unmixing process. Preliminary experiments underscore both the quantitative and qualitative prowess of the proposed method. © 2025 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Hyperspectral and Multispectral Image Fusion Based on Deep Adaptive Attention Network

Unsupervised Hyperspectral and Multispectral Image Fusion Ba...

引用

IEEE International Symposium on Geoscience and remote sensing (IGARSS)

作者： Haoyang Yu Chengjun Wang Jia Jia Ke Zheng Yuchao Yang Yulei Wang Meiping Song Center of Hyperspectral Imaging in Remote Sensing (CHIRS) Information Science and Technology College Dalian Maritime University Dalian China College of Geography and Environment Liaocheng University Liaocheng China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Due to the limitations of satellite imaging hardware, it is more demand to fuse hyperspectral image (HSI) and multispectral image (MSI) in an unsupervised manner in real application scenarios. However, current research has certain limitations, either relying on more prior knowledge or lack of verification of model performance with real satellite data. In order to solve the above problems, this paper designs a deep unsupervised adaptive attention network (DUAA-Net). This model can adaptively learn the mapping relationship between HSI and MSI. Compared with related unsupervised deep learning methods, this model not only simulates data achieved better indicators but also more accurate results in classification applications of real data.

关键词： Training Measurement Adaptation models Adaptive systems Satellites Attention mechanisms Imaging

来源：评论

学校读者我要写书评

暂无评论

Fire Hotspots Mapping and Forecasting in Indonesia Using Deep Learning Algorithm 3

Fire Hotspots Mapping and Forecasting in Indonesia Using Dee...

引用

3rd International Conference on Electrical Engineering and Informatics, ICon EEI 2022

作者： Listia Rosa, Sri Abdul Kadir, Evizal Syukur, Abdul Irie, Hitoshi Wandri, Rizky Evizal, Muhammad Fikri Universitas Islam Riau Department of Informatics Engineering Pekanbaru28284 Indonesia National Taiwan University Science and Technology Computer Science and Information Engineering Taipei Taiwan Chiba University Centre for Environmental Remote Sensing Chiba263-0022 Japan National Dong Hwa University Computer Science and Information Engineering Hualien Taiwan

ISBN: (数字)9781665454346

ISBN: (纸本)9781665454346

Indonesia is one of the countries in South East Asia has significant forest fire with dangerous impact to neighboring countries of the emission of haze and carbon. In this research aims to do plotting and mapping location with high number fire hotspot then forecasting potential number of hotspots in future time based on previous of history data collected. The forecasting data achieve is very important and beneficial for the authorities as one of references for preventive action and avoid scattering of forest fire. Long Short-Term Memory (LSTM) algorithm implemented in this research for analysis and forecasting of fire hotspot number while Python programming used to plot hotspot point. The source of fire hotspot dataset is referred to The National Aeronautics and Space Administration (NASA) Moderate Resolution Imaging Spectroradiometer (MODIS) recorded from year 2021 with total number is about 100,000 hotspots in Indonesia region. Results show the distribution of fire hotspot concentration most in Sumatra and Kalimantan Island because the typical of land which peat that potential for getting fire. Forecasting of number hotspot for the year 2022 has achieve with good results with error less than 5% which only 4.56%. © 2022 IEEE.

关键词： Forecasting

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：