作者机构：
[夏天; 吴文斌; 周清波] Key Laboratory of Agricultural Information Technology, Ministry of Agriculture, Beijing, 100081, China;[周勇] College of Urban and Environment Sciences, Huazhong Normal University, Wuhan 430079, China;[夏天; 吴文斌; 周清波] Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, China
通讯机构：
Key Laboratory of Agricultural Information Technology, Ministry of Agriculture, China
关键词：
遥感;回归分析;神经网络;估算;冬小麦;反演方法
摘要：
冬小麦叶面积指数(LAI, leaf area index)是评价其长势和预测产量的重要农学参数,高光谱遥感能够实现快速无损地监测叶面积指数。该文旨在将田间监测与高光谱遥感相结合,探索研究不同冬小麦叶面积指数高光谱反演方法的模拟精度及适应性。针对国际上普遍应用的2种高光谱遥感反演LAI模型方法,即回归分析法和BP神经网络法,在介绍2种LAI反演模型的基础上,选择位于黄淮海平原的山东省济南市长清区为研究区域,通过ASD地物光谱仪和SunScan冠层分析系统对冬小麦的冠层光谱及LAI变化进行田间观测,然后利用回归分析法和BP神经网络法构建冬小麦LAI反演模型,将模型估算LAI值和田间观测LAI值进行比对,分析评价2种方法的反演精度。结果表明,BP神经网络法较回归分析法估算冬小麦LAI的精度有较大提高,检验方程的决定系数(R2)为0.990、均方根误差(RMSE)为0.105。利用BP神经网络法构建反演模型能较好的对冬小麦LAI进行反演。研究结果可为不同冬小麦长势遥感监测提供理论和技术上的支持,并为大尺度传感器监测冬小麦长势和估产提供参考。
作者机构：
[刘鹏程; 毕旭] College of Urban and Environment Science, Central China Normal University, 152 Luoyu Road, Wuhan 430079, China;[艾廷华] School of Resource and Environment Science, Wuhan University, 129 Luoyu Road, Wuhan 430079, China
通讯机构：
College of Urban and Environment Science, Central China Normal University, 152 Luoyu Road, China
作者机构：
[李畅] College of Urban and Environmental Science, Central China Normal University, Wuhan 430079, China;[李芳芳] Key Laboratory of Information Systems Engineering, National University of Defense Technology, Changsha 410073, China
通讯机构：
[Li, C.] C;College of Urban and Environmental Science, Central China Normal University, China
作者机构：
[张忠杰; 焦铭; Shan, Shi-Gang; 陈姣娥; 马萍] College of Basic Medical, Hubei University of Science and Technology, Xianning 437100, China;[杨旭; 武阳; 马萍] Laboratory of Environment Science, College of Life Science, Huazhong Normal University, Wuhan 430079, China
通讯机构：
Laboratory of Environment Science, College of Life Science, Huazhong Normal University, China
作者机构：
[叶染枫; 刘旭东; 李慧; 杨旭; 闵安娜; 张玉超; 陈明清; 刘锋明; 赵莉琴] Laboratory of Environmental Science, College of Life Sciences, Huazhong Normal University, Wuhan 430079, China
通讯机构：
Laboratory of Environmental Science, College of Life Sciences, Huazhong Normal University, China
期刊：
Telkomnika (Telecommunication Computing Electronics and Control),2013年11(12):7462-7469 ISSN：1693-6930
通讯作者：
Li, C.(lichang@mail.ccnu.edu.cn)
作者机构：
[Chang LI] Key Laboratory of Disaster Reduction, Emergency Response Engineering of the Ministry of Civil Affairs, 6 Guangbai East Road, Chaoyang District, Beijing, 100124, China;[Fangfang LI] College of Information Systems and Management, China National University of Defense Technology, Changsha 410073, China;[Wenzhong SHI] Joint Spatial Information Research Laboratory, The Hong Kong Polytechnic University and Wuhan University, Hong Kong and Wuhan, China;[Chang LI] College of Urban and Environmental Science, Central China Normal University, 152 Luoyu Road, Wuhan 430079, China
摘要：
Current methods of remotely sensed image change detection almost assume that the DEM of the surface objects do not change. However, for the geological disasters areas (such as: landslides, mudslides and avalanches, etc.), this assumption does not hold. And the traditional approach is being challenged. Thus, a new theory for change detection needs to be extended from two-dimensional (2D) to three-dimensional (3D) urgently. This paper aims to present an innovative scheme for change detection method, object-oriented simultaneous three-dimensional geometric and physical change detection (OOS3DGPCD) using GIS-guided knowledge. This aim will be reached by realizing the following specific objectives: a) to develop a set of automatic multi-feature matching and registration methods; b) to propose an approach for simultaneous detecting 3D geometric and physical attributes changes based on the object-oriented strategy; c) to develop a quality control method for OOS3DGPCD; d) to implement the newly proposed OOS3DGPCD method by designing algorithms and developing a prototype system. For aerial remotely sensed images of YingXiu, Wenchuan, preliminary experimental results of 3D change detection are shown so as to verify our approach.
期刊：
Journal of Convergence Information Technology,2012年7(19):546-553 ISSN：1975-9320
通讯作者：
Li, F.(lifangfang83@163.com)
作者机构：
[Li, Fangfang] Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, Changsha 410073, China;[Mao, Xingliang] Internet News Management Office of Publicity, Department of Hunan Provincial CCP Committees, Changsha 410011, China;[Xiao, Benlin] Civil Engineering and Architecture School, Hubei University of technology, Wuhan 430068, China;[Li, Chang] College of Urban and Environmental Science, HuaZhong Normal University, Wuhan 430079, China
摘要：
Aquatic vegetation plays an important role in the maintenance of wetland biodiversity and ecological function. As the complex spectral characteristics and growth environment, its spatial distribution is affected by many factors. This study investigated the potential of using remote sensing to map aquatic vegetation distribution on a large scale in Honghu Lake, China. According to aquatic vegetation's ecological characteristics, the study firstly analyzed the selection and extraction of optimal feature images benefiting aquatic vegetation classification. Next, classification knowledge mining based on these feature images was discussed. Finally, a multi-classifier combination method, which combines decision tree classifier, naive bayes classifier and supporting vector machine classifier, was proposed to distinguish different wetland types. Validation using in situ surveys suggested that this approach could get higher accuracy than each single classifier in mapping aquatic vegetation distribution on a large scale.
会议名称：
2010 International Conference on Bio-inspried System and Signal Processing(2010 IEEE生物系统与信号处理国际会议 ICBSSP 2010)
会议时间：
2010-10-26
会议地点：
厦门
会议主办单位：
[Qu Chenxiao;Cai Caongfa] Huazhong Agr Univ, Coll Resources & Environm, Wuhan 430070, Peoples R China.^[Meng Qingxiang] Henan Agr Univ, Coll Resources Environm, Zhengzhou 450002, Peoples R China.^[Lin Yan] Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Peoples R China.
会议论文集名称：
2010 International Conference on Bio-inspried System and Signal Processing(2010 IEEE生物系统与信号处理国际会议 ICBSSP 2010)论文集
摘要：
According to the characteristics of land consolidation project, this paper established the quality indicators of land consolidation from micro-topography, soil, water, landscape and other factors. The weights of these indexes were reckoned by AHP, and then the land quality based on the land consolidation project about Baiyang town and Guqiao township were evaluated, which both are hilly area in Henan province. The results showed that discrepancy topography had been changed significantly before and after land consolidation in the level of spatial distribution, size and overall quality. Land consolidation had a great impact on land quality, and project area in Baiyang town was up to 75.7% and Guqiao township to 37.3%.
作者机构：
[刘鹏程] College of Urban and Environmental Science, Huazhong Normal University, Wuhan 430079, China;[艾廷华; 杨敏] School of Resources and Environment Science, Wuhan University, Wuhan 430079, China
通讯机构：
[Liu, P.] C;College of Urban and Environmental Science, Huazhong Normal University, China
作者机构：
[杨敏; 艾廷华; 成晓强] School of Resources and Environment Science, Wuhan University, Wuhan 430072, China;[刘鹏程] College of Urban and Environment Science, Central China Normal University, Wuhan 430079, China
通讯机构：
[Yang, M.] S;School of Resources and Environment Science, Wuhan University, China
摘要：
POS, integrated by GPS / INS (Inertial Navigation Systems), has allowed rapid and accurate determination of position and attitude of remote sensing equipment for MMS (Mobile Mapping Systems). However, not only does INS have system error, but also it is very expensive. Therefore, in this paper error distributions of vanishing points are studied and tested in order to substitute INS for MMS in some special land-based scene, such as ground façade where usually only two vanishing points can be detected. Thus, the traditional calibration approach based on three orthogonal vanishing points is being challenged. In this article, firstly, the line clusters, which parallel to each others in object space and correspond to the vanishing points, are detected based on RANSAC (Random Sample Consensus) and parallelism geometric constraint. Secondly, condition adjustment with parameters is utilized to estimate nonlinear error equations of two vanishing points (VX, VY). How to set initial weights for the adjustment solution of single image vanishing points is presented. Solving vanishing points and estimating their error distributions base on iteration method with variable weights, co-factor matrix and error ellipse theory. Thirdly, under the condition of known error ellipses of two vanishing points (VX, VY) and on the basis of the triangle geometric relationship of three vanishing points, the error distribution of the third vanishing point (VZ) is calculated and evaluated by random statistical simulation with ignoring camera distortion. Moreover, Monte Carlo methods utilized for random statistical estimation are presented. Finally, experimental results of vanishing points coordinate and their error distributions are shown and analyzed.
作者机构：
[刘鹏程; 李畅] College of Urban and Environmental Science, Huazhong Normal University, 152 Luoyu Road, Wuhan 430079, China;[李奇] Center for Earth Observation and Digital Earth Airborne Remote Sensing Center, Chinese Academy of Sciences, A 3 Datun Road, Beijing 100101, China;[李芳芳] Science and Technology on Information Systems Engineering Laboratory, National University of Defense Technology, 47 Yanwachizheng Street, Changsha 410073, China
通讯机构：
College of Urban and Environmental Science, Huazhong Normal University, 152 Luoyu Road, China
作者机构：
[罗静; 闫月花] College of Urban and Environment Science, Central China Normal University, Wuhan 430079, China;[王东亮] School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China
通讯机构：
College of Urban and Environment Science, Central China Normal University, China
