检索结果-内蒙古大学图书馆

2024 International co.ference on Image, Signal Processing, and Pattern Reco.nition, ISPP 2024

作者： Li, Xiaolei Zhou, Juefan Xiao, Xingjie Lin, Jiayu Yang, Siyuan Sha, Zongyao Tu, Jianguang School of Remote Sensing and Information Engineering Wuhan University Hubei Province 430079 China Wuhan ALLPRS Remote Sensing Data Technology Co. Ltd. Hubei Province 430079 China

ISBN: (纸本)9781510680425

Leveraging visual sensing technologies for the detection and tracking of vehicles represents a critical application domain for unmanned aerial vehicles (UAVs), notably in challenging operational *** study focuses on enhancing UAV functionalities in intricate environments through the development of a specialized dataset, derived from battlefield scenarios, to facilitate advanced research on vehicle detection and multi-target tracking under co.plex co.ditions.A co.prehensive co.lection of vehicular movement videos spanning diverse scenarios was amassed and manually annotated, culminating in the creation of the " Cross-Scenario Vehicle Detection" (CSVD) *** dataset enco.passes a wide array of environmental settings, featuring urban landscapes, plains, and forests, across the four seasons, resulting in a total of 13,025 meticulously annotated *** several state-of-the-art deep learning models, we established robust benchmarks for object ***, an extensive evaluation and performance validation were co.ducted using cutting-edge multi-object tracking algorithms on the CSVD dataset, inco.porating diverse assessment *** co.ducted experiments demonstrate the dataset's robust applicability and versatility, endorsing its effectiveness for the development and evaluation of UAV-based vehicle detection and multi-target tracking systems in co.plex settings. © 2024 SPIE.

关键词： Aircraft detection

来源：评论

学校读者我要写书评

暂无评论

Revealing the Spatial co.Occurrence Patterns of Multi-Emotions from Social Media data

SSRN

引用

SSRN 2023年

作者： Wang, Dongyang Wang, Yandong Fu, Xiaokang Dou, Mingxuan Dong, Shihai Zhang, Duocai State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan430079 China Center for Geographic Analysis Harvard University CambridgeMA1737 United States Xi’An Aerospace Remote Sensing Data Technology Co. Ltd. Xi’an710100 China

Emotions play a critical role in understanding human behavior and are direct indicators of residents' well-being and quality of life. Assessing spatial-emotional interactions is crucial for human-centered urban planning and public mental health. However, prior research has focused on the spatial analysis of individual emotions, ignoring the intricate interactions between multi-emotions and space. To address this gap, we propose a novel framework to reveal the spatial co.occurrence patterns of multi-emotions using massive social media data in wuhan, China. Specifically, the BERT (bidirectional enco.er representations from transformers) pre-trained model is utilized to classify each post into one of five basic emotions. Given the implementation of the K-means algorithm on these emotional results, the emotion-based similarities among different grids are investigated. The qualitative and quantitative results reveal six spatial co.occurrence patterns of co.flicting or co.sistent emotions in urban space, namely, happiness-fear, happiness-anger, balanced emotion, happiness dominated, happiness-surprise, and happiness-sadness. In particular, the balanced emotion pattern is the most prevalent and tends to be spatially co.centrated in the city center, while patterns of happiness-anger and happiness-sadness are mainly observed in the suburbs. Plus, results of the Multinomial Logit Model (MNLM) indicate that the spatial multi-emotions co.occurrence patterns are significantly co.related with land use characteristics based on points-of-interest (POIs) data. These findings provide an innovative perspective for understanding the co.plex interactions between emotions and space, with theoretical and practical implications for designing and maintaining an emotionally healthy city. © 2023, The Authors. All rights reserved.

关键词： Land use

来源：评论

学校读者我要写书评

暂无评论

Change detection of built-up areas based on ensemble learning 3

Change detection of built-up areas based on ensemble learnin...

引用

2021 3rd International Forum on Geoscience and Oceanography, IFGO 2021

作者： Chen, Lei Li, Yingcheng Geng, Zhongyuan Li, Xilin Xue, Yanli Wang, Guangliang Wang, Yanhui College of Resource Environment and Tourism Capital Normal University Beijing100048 China Key Laboratory for Aerial Remote Sensing Technology Ministry of Natural Resources Beijing100039 China China TopRS Technology Co. Ltd. Beijing100039 China Beijing Low Altitude Remote Sensing Data Processing Engineering Technology Research Center Beijing100039 China Wuhan Sunmap Remote Sensing Technology Co. Ltd. Wuhan430223 China

The paper presents a new method for the change detection of built-up areas based on ensemble learning. The method selects the feature generation part of VGG network to replace the enco.er of UNet network, and makes full use of the advantages of VGG network in feature interpretation to co.struct a new network VGG-UNet, so as to improve the information extraction accuracy of built-up areas. First, the slice sample sets co.taining built-up areas and non-built-up areas were established. Seco.dly, the model was trained and tested to obtain several optimal models with high precision. Thirdly, these optimal models were used to extract the change information of built-up areas in the experimental area. Finally, the results were ensemble optimized and the accuracy was verified by co.paring with the field measurements. The experimental results in Xinjiang demonstrate the advantages, feasibility and reliability of the proposed method. Moreover, the ensemble optimization of multiple model results can further improve the change detection accuracy of built-up areas. © Published under licence by IOP Publishing Ltd.

关键词： Change detection

来源：评论

学校读者我要写书评

暂无评论

The Privacy co.puting for Digital Eco.omy Development under New technology Based on Spatial-Temporal Information Matrix, Especially among RCEP Nations 3

The Privacy Computing for Digital Economy Development under ...

引用

3rd International co.ference on Pattern Reco.nition and Machine Learning, PRML 2022

作者： Liu, Haitao Zheng, Shenjun Hong, Yong Cao, Yujuan Lu, Yun Tian, Tian Guangxi Artificial Intelligence and Big Data Applying Institute Nanning530201 China Hangzhou ChinaOly Technology Co. Ltd. Hangzhou310015 China Wuhan University State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan430079 China Guangxi Academy of Social Sciences Nanning530201 China

ISBN: (数字)9781665499507

ISBN: (纸本)9781665499507

With the co.ing of intelligent era, the wide using of new generation information technology, such as Internet on Things, AI, Big data and Cloud co.puting, digital eco.omic development is more and more prosperous for every eco.omic entity, specially, for some emerging eco.omic entities, such as RCEP nations. However, the problem of objective evaluation of ability of digital eco.omic development of different nations and dependence of digital eco.omic development among each nation are very hard but necessary under not leaking digital eco.omic data of all parts. For solving this problem, an improvement Meta Learning approach was proposed creatively which co.structed temporal dimension factor and spatial dimension factor based on spatial-temporal information matrix method. It co.ld make knowledge transfer from source network to target network acco.ding to the orthogonal rule between temporal dimension factor and spatial dimension factor. 3 different type and smart test ways were designed in order to validate the performance of the approach of this paper co.prehensively. Digital eco.omic development data of RECP nations were co.lected and employed for testing. The amount and accuracy of knowledge transfer from different source network to various target network were validated one by one. The results not only validate the effectiveness of improving Meta Learning approach of this article but also reveal that the diversity of digital eco.omy development among RECP nations but impacting tightly each other. Moreover, there also have relative co.tribution on opening knowledge transfer from source network to target network under privacy data not be leaked. This co.tent would be researched at more co.plex industrial data forward. © 2022 IEEE.

关键词： Eco.omic and social effects

来源：评论

学校读者我要写书评

暂无评论

State of the art in dense image matching co.t co.putation for high-resolution satellite stereo 24

State of the art in dense image matching cost computation fo...

引用

2021 24th ISPRS co.gress co.mission II: Imaging Today, Foreseeing Tomorrow

作者： Wang, Yue Gong, Danchao Hu, Hualong Wang, Shugen Han, Yilong Wang, Yuan Ma, Xiaoliang Wuhan Geomatics Institute Wuhan China State Key Laboratory of Geo-information Engineering Xi'an China School of Remote Sensing and Information Engineering Wuhan University Wuhan China School of Geographic and Oceanographic Science Nanjing University Nanjing China Xi'An Geovis Spatial Data Technology Co. Ltd. Xi'an China

Large-scale Digital Surface Model (DSM) generated with high-resolution satellite images (HRSI) are co.parable, cheaper, and more accessible when co.paring to Light Detection and Ranging (LiDAR) data and aerial remotely sensed images. Several photogrammetric co.mercial/open-source software packages are being developed for satellite image-based 3D reco.struction, in which, most of them adopt a modified version of Semi-Global Matching (SGM) algorithm for dense image matching. With the co.tinuous development of matching co.t co.putation methods, the existing methods can be divided into classical (low-level) and learning-based algorithms (non-end-to-end learning and end-to-end learning methods). On Middlebury and KITTI datasets, learning-based algorithms has shown their superiority co.pared to SGM derived methods. In this co.text, we assume that matching co.t is the key factor of DIM. This paper reviews and evaluates Census Transform, and MC-CNN on a WorldView-3 typical city scene satellite stereo images on the premise that the overall SGM framework remains unchanged, providing a preliminary co.parison for academic and industrial. We first co.pute the co.t valume of these two methods, obtains the final DSM after semi-global optimization, and co.pares their gemetric accuracy with the co.responding LiDAR derived ground truth. We presented our co.parison and findings in the experimental section. © 2021 International Archives of the Photogrammetry, remote sensing and Spatial Information Sciences - ISPRS Archives. All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

UNco.ERING the AGGREGATION PATTERN of GPS TRAJECTORY BASED on SPATIOTEMPORAL CLUSTERING and 3D VISUALIZATION

UNCOVERING the AGGREGATION PATTERN of GPS TRAJECTORY BASED o...

引用

2020 International co.ference on Geomatics in the Big data Era, ICGBD 2020

作者： Liu, C.K. Qin, K. Chen, K. Ma, R. Changjiang Survey Planning Design and Research Co. Ltd Wuhan China Changjiang Spatial Information Technology Engineering Co. Ltd Wuhan China Water Resources Information Perception Big Data Engineering Research Center of Hubei Province Wuhan China School of Remote Sensing and Information Engineering Wuhan University Wuhan China

co.strained by road network structure, travel choice and city function zoning, GPS trajectory data exhibits significant spatiotemporal co.relation. Unveiling the clustering and distribution patterns of GPS trajectory can help to better understand the travel behaviour as well as the co.responding spatial and temporal characteristics. This paper proposes an approach to identify and visualize the aggregation pattern from GPS trajectory data. Firstly, slow feature trajectory sequences are extracted from raw taxi trajectory data. Together with taxi states information, these sequences are processed as shorter length tracks for faster disco.ery of cluster similarity. Thereafter, the temporal and spatial similarity and dissimilarity metrics between the trajectories are established, and the temporal and spatial distances between the trajectories are defined to form a space-time cylinder model. Next, based on the idea of density clustering, the DBSCAN spatiotemporal expansion of trajectory data is proposed. Feature trajectory sequences are then clustered into groups with high similarity. Finally, for a more intuitive understanding of the trajectory aggregate distribution, time dimension info of each point in the sequences is used as Z axis, thus the sequences are stretched on the map in different co.our for 3D visualization. The proposed method is validated by a case study of taxi trajectory data analysis in wuhan City, China. © 2020 C. K. Liu et al.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

State of the Art in Digital Surface Modelling from Multi-View High-Resolution Satellite Images 24

State of the Art in Digital Surface Modelling from Multi-Vie...

引用

2020 24th ISPRS co.gress on Technical co.mission II

作者： Han, Yilong Wang, Shugen Gong, Danchao Wang, Yue Wang, Yuan Ma, Xiaoliang School of Remote Sensing and Information Engineering Wuhan University Wuhan China State Key Laboratory of Geo-information Engineering Xi'an China Wuhan Geomatics Institute Wuhan China School of Geographic and Oceanographic Science Nanjing University Nanjing China Xi'an Geovis Spatial Data Technology Co. Ltd Xi'an China

data from the optical satellite imaging sensors running 24/7, is co.lecting in embarrassing abundance nowadays. Besides more suitable for large-scale mapping, multi-view high-resolution satellite images (HRSI) are cheaper when co.paring to Light Detection And Ranging (LiDAR) data and aerial remotely sensed images, which are more accessible sources for digital surface modelling and updating. Digital Surface Model (DSM) generation is one of the most critical steps for mapping, 3D modelling, and semantic interpretation. co.puting DSM from this dataset is relatively new, and several solutions exist in the market, both co.mercial and open-source solutions, the performances of these solutions have not yet been co.prehensively analyzed. Although some works and challenges have focused on the DSM generation pipeline and the geometric accuracy of the generated DSM, the evaluations, however, do not co.sider the latest solutions as the fast development in this domain. In this work, we discussed the pipeline of the co.sidered both co.mercial and opensource solutions, assessed the accuracy of the multi-view satellite image-based DSMs generation methods with LiDAR-derived DSM as the ground truth. Three solutions, including Satellite Stereo Pipeline (S2P), PCI Geomatica, and Agisoft Metashape, are evaluated on a WorldView-3 multi-view satellite dataset both quantitatively and qualitatively with the LiDAR ground truth. Our co.parison and findings are presented in the experimental section. © 2020 co.ernicus GmbH. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

A Spatial Downscaling Method for Smap Soil Moisture co.sidering Vegetation Memory and Spatiotemporal Fusion

SSRN

引用

SSRN 2023年

作者： Cui, Changlu Meng, Yizhuo Xiang, Daxiang Hong, ZhiMing Hu, Fengmin Yang, Beibei Tao, Chongxin Wei, Zushuai Zhang, Wen Li, Linyi Viterbi School of Engineering University of Southern California Los AngelesCA United States Changjiang River Scientific Research Institute Changjiang River Water Resources Commission Wuhan430010 China College of Surveying and Geo-Informatics North China University of Water Resources and Electric Power Zhengzhou450046 China Changjiang Spatial Information Technology Engineering Co. Ltd Hubei Wuhan430010 China College of Public Administration Xinjiang Agricultural University Urumqi China School of Artifical Intelligence Jianghan University Wuhan430056 China Water Resources Information Perception and Big Data Engineering Research Center of Hubei Province Hubei Wuhan430010 China School of Remote Sensing and Information Engineering Wuhan University Hubei Wuhan430079 China

Soil moisture (SM) plays an essential role in the hydrological cycle, drought monitoring, agricultural production, and water resources management. However, SM products of passive microwave remote sensing have co.rse spatial resolutions (approximately 25-40km), which may largely limit the applications of SM in hydrology and agriculture. In this study, the ESTARFM and Random Forest(RF) models, along with multi-source remote sensing data, were used jointly to generate downscaled SM at 1 km spatial resolution. First, to improve the spatiotemporal co.pleteness of SM estimates, the Normalized Difference Vegetation Index (NDVI) at 30 m×30 m was generated using a data fusion approach. Seco.d, the RF model was developed using fused NDVI at the fine spatial resolution, lagged NDVI with about a month lag behind soil moisture, and ancillary variables such as soil properties, albedo, temperature, and topography as model inputs. Last, the downscaled SM was verified by 48 in situ SM measurements and daily precipitation data. The results show that the downscaled SM is highly co.sistent with the in situ SM measurements. The co.relation ranges from 0.403 to 0.717 with an average of 0.497. The root mean square error (RMSE) ranges from 0.038 to 0.153 m3/m3 with an average of 0.070 m3/m3. The ubRMSE range from 0.027 to 0.081 m3/m3 with an average of 0.049 m3/m3. The bias ranges from -0.130 to 0.128 m3/m3 with an average of -0.014 m3/m3. The proposed method maximizes the potential of data fusion, RF model, and lagged vegetation data for soil moisture downscaling, which can provide more detailed soil water information with 1 km spatial resolution and promote the accuracy of soil moisture at the regional scale. © 2023, The Authors. All rights reserved.

关键词： Soil moisture

来源：评论

学校读者我要写书评

暂无评论

Characterizing Oil Reservoir from Three-Dimensional Surface Deformation Using Multi-Track Insar: A Case Study in the Liaohe Oilfield, Northeast China

SSRN

引用

SSRN 2023年

作者： Tang, Wei Gong, Zhiqiang Sun, Xiubo Liu, Yu'an Motagh, Mahdi Li, Zhicai Li, Jing Malinowska, Agnieszka Jiang, Jinbao Wei, Lianhuan Zhang, Xin Wei, Xing Li, Hui Geng, Xu College of Geoscience and Surveying Engineering China University of Mining and Technology Beijing China Key Laboratory of Natural Resources Monitoring and Supervision in Southern Hilly Region Ministry of Natural Resources China State Key Laboratory of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan China Shenyang Center of China Geological Survey Shenyang China National Marine Environmental Monitoring Center Dalian China GFZ German Research Centre for Geosciences Department of Geodesy Section of Remote Sensing and Geoinformatics Potsdam Germany Institute of Photogrammetry and GeoInformation Leibniz University Hannover Hannover Germany AGH University of Science and Technology Faculty of Geo-Data Science Geodesy and Environmental Engineering Krakow Poland School of Resources and Civil Engineering Northeastern University Shenyang China Shenyang Geotechnical Investigation & Surveying Research Institute Co. Ltd. Shenyang China Chemical Geological Prospecting Institute of Liaoning Province Co. Ltd. Jinzhou China

Oil productions can result in land subsidence, causing damages to oil production facilities and surface infrastructures. The surface displacement is predominantly vertical subsidence, which has a great impact on co.stal plains near sea level, leading to permanent inundation. The Liaohe oilfield, located in Liaohe River Delta (LRD), northeast of China, is one of the most significant subsidence areas in China as a direct co.sequence of oil extraction from the reservoir. In this work, we investigate the production-induced surface displacement in the LRD region by taking advantage of multiple geometries of Sentinel-1 radar images. Images from two ascending and two descending tracks are processed by an Interferometric Synthetic Aperture Radar (InSAR) time series analysis over the 2017 to 2021 period, providing displacement rate maps and displacement time series in the radar line-of-sight (LOS) *** studies carried out in this area assumed the oil production-induced displacement retrieved from InSAR co.responds only to vertical deformation. Here, for the first time, we proposed a method to retrieve the full three-dimensional (3D) displacement field over the oilfield. We retrieved the vertical and east-west displacement co.ponents by co.bining the multiple InSAR geometries LOS observations and retrieved the north-south co.ponent based on the assumption of a physical relationship between the horizontal and vertical *** derived 3D displacement fields over Shuguang oilfield exhibit a circular subsidence bowl with a maximum subsiding rate reaching 212 mm/year, acco.panied by a centripetal pattern of horizontal displacements with maximum rates up to 50-60 mm/year moving towards the subsidence center. The retrieved-3D displacements are in good agreement with predictions from the geomechanical modeling by assuming a disk-shaped reservoir subject to a uniform reduction in pore fluid pressure. Finally, we show the importance of knowing both the vertical a

关键词： Subsidence

来源：评论

学校读者我要写书评

暂无评论

A lightweight deep learning based cloud detection method for Sentinel-2A imagery fusing multi-scale spectral and spatial features

arXiv

引用

arXiv 2021年

作者： Li, Jun Wu, Zhaoco.g Hu, Zhongwen Jian, Canliang Luo, Shaojie Mou, Lichao Zhu, Xiao Xiang Molinier, Matthieu The School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China The MNR Key Laboratory for Geo-Environmental Monitoring of Great Bay Area Shenzhen University Shenzhen518060 China The Administration Department Fujian Tendering Purchasing Group Co. Ltd Fuzhou350001 China The Hangzhou Power Supply Company State Grid Zhejiang Power Supply Company Hangzhou310000 China The Remote Sensing Technology Institute German Aerospace Center Wessling82234 Germany The Data Science in Earth Observation Technical University of Munich Munich80333 Germany VTT Technical Research Centre of Finland Ltd Espoo02044 Finland

Clouds are a very important factor in the availability of optical remote sensing images. Recently, deep learning-based cloud detection methods have surpassed classical methods based on rules and physical models of clouds. However, most of these deep models are very large which limits their applicability and explainability, while other models do not make use of the full spectral information in multi-spectral images such as Sentinel-2. In this paper, we propose a lightweight network for cloud detection, fusing multi-scale spectral and spatial features (CDFM3SF) and tailored for processing all spectral bands in Sentinel-2A images. The proposed method co.sists of an enco.er and a deco.er. In the enco.er, three input branches are designed to handle spectral bands at their native resolution and extract multiscale spectral features. Three novel co.ponents are designed: a mixed depth-wise separable co.volution (MDSC) and a shared and dilated residual block (SDRB) to extract multi-scale spatial features, and a co.catenation and sum (CS) operation to fuse multi-scale spectral and spatial features with little calculation and no additional parameters. The deco.er of CD-FM3SF outputs three cloud masks at the same resolution as input bands to enhance the supervision information of small, middle and large clouds. To validate the performance of the proposed method, we manually labeled 36 Sentinel-2A scenes evenly distributed over mainland China. The experiment results demonstrate that CD-FM3SF outperforms traditional cloud detection methods and state-of-the-art deep learning-based methods in both accuracy and speed. co.yright © 2021, The Authors. All rights reserved.

关键词： Signal enco.ing

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：