检索结果-南通市图书馆

Image City sharing platform and its typical applications

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science china(information Sciences) 2011年第8期54卷 1738-1746页

作者： shao zhenfeng & li deren state {4. laboratory for {4. engineering in Surveying,map.ing and remote sensing,wuhan University,wuhan 4.0079,china state key laboratory for information {4. in Surveying Mapping and Remote Sensing Wuhan University Wuhan China

In this paper,the trend of urban spatial information sharing service from the electronic map to image is analyzed and its sharing framework based on service-oriented architecture is ***,the service implementation,feedback data service procedure and its processing service model are explored. Based on the software with independent intellectual property rights,image city of Taizhou is developed as an example to realize various image data and processing servicesLastly,the bright future prospects of image city are described.

关键词： Image City service-oriented architecture image data service function service model service

Deep learning-based local climate zone classification using Sentinel-1 SAR and Sentinel-2 multispectral imagery

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Geo-Spatial information Science 2022年第3期25卷 383-398页

作者： lin Zhou zhenfeng shao Shugen Wang Xiao Huang School of remote sensing and information engineering Wuhan UniversityWuhanChina state key laboratory of information {4. in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina Department of Geosciences University of ArkansasFayettevilleNCUSA

As a newly developed classification system,the LCZ scheme provides a research framework for Urban Heat Island(UHI)studies and standardizes the worldwide urban temperature *** the growing popularity of deep learning,deep learning-based approaches have shown great potential in LCZ *** major cities in china are selected as the study *** this study,we design a deep convolutional neural network architecture,named Residual combined Squeeze-and-Excitation and Non-local Network(RSNNet),that consists of the Squeeze-and-Excitation(SE)block and non-local block to classify LCZ using freely available Sentinel-1 SAR and Sentinel-2 multispectral *** Accuracy(OA)of 0.9202,0.9524.and 0.9004.for three selected cities are obtained by applying RSNNet and training data of individual city,and OA of 0.9328 is obtained by training RSNNet with data from all three *** outperforms other popular Convolutional Neural Networks(CNNs)in terms of LCZ map.ing *** further design a series of experiments to investigate the effect of different characteristics of Sentinel-1 SAR data on the performance of RSNNet in LCZ *** results suggest that the combination of SAR and multispectral data can improve the accuracy of LCZ *** proposed RSNNet achieves an OA of 0.94.5 when integrat-ing the three decomposed components with Sentinel-2 multispectral images,2.4.%higher than using Sentinel-2 images alone.

关键词： Local Climate Zone(LCZ) deep learning Sentinel-1 Sentinel-2

map.ing impervious surfaces with a hierarchical spectral mixture analysis incorporating endmember spatial distribution

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Geo-Spatial information Science 2022年第4期25卷 550-567页

作者： zhenfeng shao Yuan Zhang Cheng Zhang Xiao Huang Tao Cheng state key laboratory of information {4. in Surveying Mapping and Remote SensingWuhanChina Department of Geosciences University of ArkansasFayettevilleARUSA

Impervious surface map.ing is essential for urban environmental *** Mixture Analysis(SMA)and its extensions are widely employed in impervious surface estimation from medium-resolution *** SMA,inappropriate endmember combinations and inadequate endmember classes have been recognized as the primary reasons for estimation ***,the spectral-only SMA,without considering urban spatial distribution,fails to consider spectral variability in an adequate *** lack of endmember class diversity and their spatial variations lead to over/*** mitigate these issues,this study integrates a hierarchical strategy and spatially varied endmember spectra to map impervious surface abundance,taking wuhan and Wuzhou as two study ***,the piecewise convex multiple-model endmember detection algorithm is applied to automatically hierarch-ize images into three regions,and distinct endmember combinations are independently developed in each ***,spatially varied endmember spectra are synthesized through neighboring spectra using the distance-based *** analysis indicates that the proposed method achieves better performance than Hierarchical SMA and Fixed Four-endmembers SMA in terms of MAE,SE,and *** analysis suggests that the hierarch-ical strategy can expand endmember class types and considerably improve the performance for the study areas in general,specifically in less developed ***,we find that spatially varied endmember spectra facilitate the reduction of heterogeneous surface material variations and achieve the improved performance in developed areas.

关键词： Impervious surface Spectral Mixture Analysis(SMA) hierarchical strategy endmember class spatially varied endmember spectra

Integrating Sentinel-1 and 2 with liDAR data to estimate aboveground biomass of subtropical forests in northeast Guangdong, china

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Digital Earth 2023年第1期16卷 158-182页

作者： linjing Zhang Xiaoxue Zhang zhenfeng shao Wenhao Jiang Huimin Gao College of Geodesy and Geomatics Shandong University of Science and TechnologyQingdaoPeople’s Republic of China key laboratory of Ocean Geomatics Ministry of Natural ResourcesQingdaoPeople’s Republic of China state key laboratory of information {4. in Surveying Mapping and Remote SensingWuhan UniversityWuhanPeople’s Republic of China

Accurate monitoring of forest aboveground biomass(AGB)is vital for sustainable forest ***,the AGB is estimated by combining satellite images andfield ***,field plots are inaccessible in complex forest *** to the limitations related to either optical or SAR data alone,combining the two data types is ***,we explored the liDAR-derived biomass as training/testing samples for the combination of yearly time-series of Sentinel-1 and Sentinel-2 images to estimate AGB in north-eastern Conghua,Guangdong province,*** AGB reference map derived from airborne liDAR data andfield plots could provide more samples for satellite-based AGB estimation with a limited amount of sampling *** designed four groups of experiments based on diverse Sentinel-1 and Sentinel-2 variables,including backscatter,backscatter indices,texture features,spectral bands,vegetation indices,and biophysical *** different prediction methods(support vector regression,multi-layer perceptron neural network,K-nearest neighbour,and random forest(RF))were separately used to estimate *** showed that the RF model achieved the best accuracy for AGB *** Sentinel-1 and Sentinel-2 experiment(R^(2):0.72,RMSEr:17.65%)performed better than the monthly complementary experiment(R^(2):0.66,RMSEr:19.01%).Additionally,the arid period images were observed to be sensitive for estimating *** most contributing Sentinels predictors were determined via a sequential forward ***,the proposed methodology has great potential for low-cost,large-scale,and high-precision AGB estimation.

关键词： Sentinel liDAR aboveground biomass non-parametric models subtropical forest

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

论万物互联时代的地球空间信息学

测绘学报 2022年第1期51卷 1-8页

作者：李德仁徐小迪邵振峰武汉大学遥感信息工程学院湖北武汉430079 武汉大学测绘遥感信息工程国家重点实验室湖北武汉430079

随着5G/6G、云计算、物联网和人工智能等新技术的发展,人类已经进入了万物互联时代。本文探讨万物互联时代地球空间信息技术的五大特点:定位技术从GNSS和地面测量走向无所不在的定位导航定时(PNT)服务体系;遥感技术从孤立的遥感卫星走... 详细信息

随着5G/6G、云计算、物联网和人工智能等新技术的发展,人类已经进入了万物互联时代。本文探讨万物互联时代地球空间信息技术的五大特点:定位技术从GNSS和地面测量走向无所不在的定位导航定时(PNT)服务体系;遥感技术从孤立的遥感卫星走向空天地传感网络;地理信息服务从地图数据库为主走向真三维实景和数字孪生;3S集成从移动测量发展到智能机器人服务;学科研究范围从对地观测走向物联监测和对人类活动的感知。笔者基于这些特点进一步剖析新时代面临的挑战,并提出新时代地球空间信息学发展亟待解决的三大科学技术问题:测绘学科如何服务人与机器人的共同需求?遥感影像解译的机理是什么和如何突破实现技术的瓶颈?如何利用时空大数据挖掘人与自然的关系,从空间感知走向空间认知?万物互联时代的地球空间信息学,必须且完全可能为万物互联的数字地球和智慧社会做出更大的贡献!

关键词：地球空间信息学万物互联时空大数据云计算人工智能空间感知与认知

维普期刊数据库博看期刊

基于时空位置大数据的公共疫情防控服务让城市更智慧

在线全文

学校读者我要写书评

暂无评论

武汉大学学报（信息科学版） 2020年第4期45卷 475-487,556页

作者：李德仁邵振峰于文博朱欣焰周素红武汉大学测绘遥感信息工程国家重点实验室湖北武汉430079 武汉大学遥感信息工程学院湖北武汉430079 中山大学地理科学与规划学院广东广州510275 广东省公共安全与灾害工程技术研究中心广东广州510275

智慧城市离不开时空位置大数据服务。总结国内外公共疫情防控事件对时空位置大数据的要求,调研其在当前疫情防控中提供的具体服务情况,讨论还有哪些方面无法满足公共疫情防控需求之处,重点分析下一步应该如何完善时空位置大数据服务,以... 详细信息

智慧城市离不开时空位置大数据服务。总结国内外公共疫情防控事件对时空位置大数据的要求,调研其在当前疫情防控中提供的具体服务情况,讨论还有哪些方面无法满足公共疫情防控需求之处,重点分析下一步应该如何完善时空位置大数据服务,以更好地服务于公共疫情防控,并分别从平时时空大数据位置服务的建设内容和战时数据共享机制等多方面给出建议。该文旨在采取科学手段完善时空大数据服务,力争在平时为公共疫情防控建立好技术支撑系统,并出台"战时"面向疫情防控需求的数据共享机制。

关键词：时空位置大数据公共疫情防控智慧城市位置服务

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

地图图像智能识别与理解:特征、方法与展望

武汉大学学报（信息科学版） 2022年第5期47卷 641-650页

作者：周熙然李德仁薛勇汪云甲邵振峰中国矿业大学环境与测绘学院江苏徐州221116 武汉大学测绘遥感信息工程国家重点实验室湖北武汉430079

随着测绘制图与通讯技术的发展,公众能够借助各种平台和工具实时地自由创建、发布、编辑和共享地图图像大数据资源和产品,地图图像在地图内容、绘图标准等方面具有了显著的泛在性,导致难以创建大规模、高质量的地图图像标注数据。因此,... 详细信息

随着测绘制图与通讯技术的发展,公众能够借助各种平台和工具实时地自由创建、发布、编辑和共享地图图像大数据资源和产品,地图图像在地图内容、绘图标准等方面具有了显著的泛在性,导致难以创建大规模、高质量的地图图像标注数据。因此,尽管现有深度学习方法在识别标准地图的内容中取得了突破性的进展,但受制于地图图像标注数据的局限,依然无法有效应对地图图像的识别和理解。根据目前国内外的相关研究进展与挑战,结合地理空间人工智能技术,探讨支持泛源地图图像大数据识别的理论与技术框架。首先,提出既能够表达地图图像内容,又能够为模型或算法表征的地图特征;然后,探讨面向地图图像内容识别的地理空间人工智能技术,以及面向地图图像理解的语义分析方法;最后,总结和展望基于地图图像大数据的相关应用及潜在价值。需要进一步研究支持地图图像表征的理论与方法,且集成地图图像显式内容的识别(地图感知)和地图图像潜在语义的分析(地图认知)才可充分挖掘地图图像大数据的价值。希望能够从数据表征和地理空间人工智能的角度为地图图像的研究提供新思路。

关键词：地理空间人工智能地图图像识别泛源地图语义分析

A study of long-term sea level variability in the East china Sea

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Acta Oceanologica Sinica 2015年第11期34卷 109-117页

作者： XU Ying liN Mingsen ZHENG Quanan YE Xiaomin li Junyi {4. Benlu College of information Science and engineering Ocean University of China National Satellite Ocean Application Service State Oceanic Administration key laboratory of Space Ocean remote sensing and App{4.cation State Oceanic Administration Department of Atmospheric and Oceanic Science University of Maryland College Park state key laboratory of Marine Environmental Science College of Ocean & Earth Sciences Xiamen University Fujian Marine Forecasts

From the analyses of the satellite altimeter maps of Sea Level Anomaly （MSLA） data, tidal gauge sea level data and historical sea level data, this paper investigates the long-term sea level variability in the East china Sea （ECS）. Based on the correlation analysis, we calculate the correlation coefficient between tidal gauge and the closest MSLA grid point, then generate the map of correlation coefficient of the entire ECS. The results show that the satellite altimeter MSLA data is effective to observe coastal sea level variability. An important finding is that from map of correlation coefficient we can identify the Kuroshio. The existence of Kuroshio decreases the correlation between coastal and the Pacific sea level. Kurishio likes a barrier or a wall, which blocks the effect of the Pacific and the global change. Moreover, coastal sea level in the ECS is mainly associated with local systems rather than global change. In order to calculate the long-term sea level variability trend, the empirical mode decomposition （EMD） method is applied to derive the trend on each MSLA grid point in the entire ECS. According to the 2-D distribution of the trend and rising rate, the sea level on the right side of the axis of Kuroshio rise faster than in its left side. This result supports the barrier effect of Kuroshio in the ECS. For the entire ECS, the average sea level rose 4..0 mm between 1993 and 2010, with a rising rate of （2.5_＋0.4. mm/a which is slower than global average. The relatively slower sea level rising rate further proves that sea level rise in the ECS has less response to global change due to its own local system effect.

关键词： East china Sea sea level variability correlation analysis empirical mode decomposition

维普期刊数据库

基于多源高分辨率遥感影像的2 m不透水面一张图提取

在线全文

学校读者我要写书评

暂无评论

武汉大学学报（信息科学版） 2018年第12期43卷 1909-1915页

作者：邵振峰张源黄昕朱秀丽吴亮万波武汉大学测绘遥感信息工程国家重点实验室湖北武汉430079 武汉大学遥感信息工程学院湖北武汉430079 国家基础地理信息中心北京100830 中国地质大学(武汉)信息工程学院湖北武汉430074

不透水率是衡量城市生态环境状况的一个重要指标。当前全球范围内仅有1km和30m分辨率尺度的不透水面专题信息,无法满足城市尺度水文模型建模、海绵城市规划和建设需求。提出了图谱信息融合的不透水面提取模型,实现了基于深度学习的不透... 详细信息

不透水率是衡量城市生态环境状况的一个重要指标。当前全球范围内仅有1km和30m分辨率尺度的不透水面专题信息,无法满足城市尺度水文模型建模、海绵城市规划和建设需求。提出了图谱信息融合的不透水面提取模型,实现了基于深度学习的不透水面提取新方法,研制了不透水面遥感全流程提取和监测软件。基于多源高分辨率遥感影像首次完成了中国31个省(直辖市、自治区)的2m不透水面专题信息提取,形成全国不透水面一张图,为海绵城市和生态城市的建设提供了基础数据支撑和技术监测手段。

关键词：地表覆盖产品不透水面提取模型深度学习高分辨率遥感影像