作者机构:
[刘轲; 陈仲新; 周清波; 唐华俊; 吴文斌] Key Laboratory of Agri-informatics, Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing, China;[吴文斌] College of Urban &, Environmental Sciences, Central China Normal University, Wuhan, China
通讯机构:
Key Laboratory of Agri-informatics, Ministry of Agriculture/Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing, China
作者机构:
[李畅] Hubei Province Key Laboratory for Geographical Process Analysing &, Modelling, Central China Normal University, Wuhan, 430079, China;[董才林] School of Mathematics and Statistics, Central China Normal University, Wuhan, 430079, China;[马浩] School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, 430079, China;[李畅] College of Urban and Environmental Science, Central China Normal University, Wuhan, 430079, China
通讯机构:
School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China
期刊:
Lecture Notes in Computer Science,2015年4552(PART 3):544-552 ISSN:0302-9743
通讯作者:
Zhu, Aiqin
作者机构:
[Zhu, Aiqin] Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Hubei, Peoples R China.;[Luo, Qi] Wuhan Univ Sci & Technol, Wuhan 430223, Hubei, Peoples R China.
通讯机构:
[Zhu, Aiqin] C;Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Hubei, Peoples R China.
会议名称:
Human-computer interaction.
会议时间:
2007
会议地点:
Beijing, China
会议论文集名称:
Human-computer interaction.
关键词:
E-Learning;SFS;GRNN;MNN;affective computing
摘要:
Aiming at emotion deficiency in present E-Learning system, speech emotion recognition system is proposed in the paper. A corpus of emotional speech from various subjects, speaking different languages is collected for developing and testing the feasibility of the system. The potential prosodic features are first identified and extracted from the speech data. Then we introduce a systematic feature selection approach which involves the application of Sequential Forward Selection (SFS) with a General Regression Neural Network (GRNN) in conjunction with a consistency-based selection method. The selected features are employed as the input to a Modular Neural Network (MNN) to realize the classification of emotions. Our simulation experiment results show that the proposed system gives high recognition performance.
期刊:
测绘学报,2015年44(12):1378-1383 and 1400 ISSN:1001-1595
作者机构:
[禹文豪; 艾廷华] Key Laboratory of Urban Land Resources Monitoring and Simulation, Ministry of Land and Resources, Shenzhen, 518000, China;[刘鹏程] College of Urban and Environmental Science, Central China Normal University, Wuhan, 430079, China;[禹文豪] School of Marine Science and Technology, Tianjin University, Tianjin, 300072, China;[禹文豪; 何亚坤; 艾廷华] School of Resource and Environmental Sciences, Wuhan University, Wuhan, 430079, China
关键词:
热点;网络核密度;POI点分析;空间分析;城市分析
摘要:
设施POI(point of interest)在城市地理空间中往往聚集分布,呈现热点特征。对该类POI分布热点的分析大多采用基于欧氏距离的空间密度估计,忽略了城市空间通达、连接是沿着街道路径的事实,从而很难准确、客观地反映城市功能的热点布局。本研究针对该缺陷,利用基于网络路径距离的核密度计算方法确定热点的区域密度,并提出了一种简单、高效的网络分析算法。该算法扩展二维栅格膨胀操作,以一维形态算子的连续扩展计算POI在网络单元上的密度值,通过评价试验表明,该算法比现有算法具有更好的性能和可扩展性。通过实际POI数据分析发现,考虑街道网络约束的热点范围可凸显设施功能沿交通网络布局的空间特征,为区域规划、导航以及地理信息查询等应用提供有价值的空间知识与信息服务。
作者机构:
[王绪杨; 武阳; 罗慧; 马萍; 陆杰; 代园园; 龚金锋] College of Basic Medical, Hubei University of Science and Technology, Xianning, China;[武阳; 马萍; 杨旭] Laboratory of Environment Biomedicine, School of Life Science, Central China Normal University, Wuhan, China
通讯机构:
College of Basic Medical, Hubei University of Science and Technology, Xianning, China
作者机构:
[曹隽隽; 聂艳; 周勇; 耿雷; 朱强; 洪永胜; 于雷] Key Laboratory for Geographical Process Analysis &, Simulation, Central China Normal University, Wuhan, Hubei Province, China
关键词:
土壤;遥感;回归;土壤有机质;高光谱;显著性波段;偏最小二乘回归;江汉平原
摘要:
为实现基于光谱分析土壤有机质含量的快速测定,该文以江汉平原公安县的土壤为研究对象,进行室内理化分析、光谱测量与处理等一系列工作,在土壤原始光谱反射率(raw spectral reflectance,R)的基础上,提取了其倒数之对数(inverse-log reflectance,LR)、一阶微分(first order differential reflectance,FDR)和连续统去除(continuum removal, CR)3种光谱指标,分析4种不同形式的光谱指标与有机质含量的相关性,对相关系数进行P=0.01水平上的显著性检验来确定显著性波段的范围,并基于全波段(400~2 400 nm)和显著性波段运用偏最小二乘回归(partial least squares regression, PLSR)建立了该区域土壤有机质高光谱的预测模型,通过模型精度的比较确定最优模型。结果表明,进行CR变换后,光谱曲线的特征吸收带更加明显,相关系数在可见光波段范围内有所提高;基于全波段的PLSR建模效果要优于显著性波段,其中以CR的预测精度最为突出,其模型的决定系数R~2和相对分析误差RPD分别为0.84、2.58;显著性波段的PLSR模型与全波段对比在模型精度方面虽有一定差距,但从模型的复杂程度来比较,具有模型简单、运算量小、变量更少的特点;最后,综合比较了全波段和显著性波段4种光谱指标的反演精度,发现CR-PLSR模型的建模和预测的效果比R-PLSR、LR-PLSR、FDR-PLSR模型都要显著。该研究可为将CR-PLSR高光谱反演模型用于该区域土肥信息的遥感监测提供参考。
摘要:
The purpose of this study is to develop an assessment framework of ecological security at the watershed scale to meet the need of watershed management, and to assess ecological security using this framework in the middle and lower reaches of Hanjiang River Basin (in Hubei Province, China). The states and their changes of ecological security in the study region are investigated with the support of ERDAS and ARC/INFO platform. The results show that the ecological security index (P) values in 1995 and 2000 were 0.685 and 0.699 respectively in the study region. While in 2005 and 2010, the P values were decreased to 0.657 and 0.624. In 1995, there were 5 counties with degree II state (the poor state) of ecological security, and 14 counties with degree III state (the common state). By 2000, the amount of counties with degree II decreased to 4 counties. And the number of counties with degree II is the same as 2000 in 2005. The result of 2010 shows there were 12 countries with degree III state as well as 7 counties with degree II state. The results of our case study of the Hanjiang River Basin reflect that the ES situation is very grim in the study area. The degree of ecological security developed in this study can be used as a useful tool for watershed managers and decision-makers.
作者机构:
[李畅] Key Lab. of Disaster Reduction and Emergency Response Eng. of the Ministry of Civil Affairs, Beijing 100124, China;[孙明伟] School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China;[李奇] Center for Earth Observation and Digital Earth Chinese Academy of Sciences, Airborne Remote Sensing Center, Beijing 100101, China;[王欢] Investment Dept. of The Third Construction Eng. Ltd. Liability Co. of China Constr. Third Eng. Bur., Wuhan 430074, China;[王欢; 李畅] College of Urban and Environmental Science, Central China Normal University, Wuhan 430079, China
通讯机构:
Key Lab. of Disaster Reduction and Emergency Response Eng. of the Ministry of Civil Affairs, China
作者机构:
[Guangming Yu; Huanghuang Jia] Laboratory of Global Change and Disasters, College of Urban and Environment Science, Central China Normal University, Wuhan, 430079, China
期刊:
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2014年11(8):1394-1398 ISSN:1545-598X
通讯作者:
Li, Chang
作者机构:
[Li, Chang] Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Peoples R China.;[Li, Chang] Minist Civil Affairs China, Key Lab Disaster Reduct & Emergency Response Engn, Beijing 100124, Peoples R China.;[Shi, Wenzhong] Hong Kong Polytech Univ, Joint Spatial Informat Res Lab, Hong Kong, Hong Kong, Peoples R China.;[Shi, Wenzhong] Wuhan Univ, Wuhan 430079, Peoples R China.
通讯机构:
[Li, Chang] C;Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Peoples R China.
关键词:
Generalized-line-based iterative transformation model (GLBITM);ground control lines (GCLs);imagery registration;iterative method with variable weights;polynomial model;posterior variance estimation
摘要:
Imagery registration and rectification is a process of transforming different sets of data into one coordinate system. A new model, i.e., the generalized-line-based iterative transformation model (GLBITM), is proposed by integrating the line-based transformation model (LBTM) and generalized point photogrammetry (GPP). First, the initial value of an affine transformation is acquired by LBTM. Then, on the basis of ground control lines (GCLs), not ground control points, the linear feature adjustment model with GPP is extended to a quadratic polynomial model and utilized to iteratively solve transformation coefficients. This process eliminates the translation amount and recalculates the scale and rotation coefficients. The authors suggest an iterative method with variable weights that is based on posterior variance estimation to improve quality control. A significant characteristic of the GLBITM is that the two endpoints of the corresponding GCLs are not necessarily conjugate points. The GLBITM integrates the advantages of the LBTM and GPP and avoids their respective shortfalls. Finally, this experiment verifies that the GLBITM gives correct, robust, and effective results that can be applied in high-resolution satellite imagery processing of multiple sensors, angles, and resolutions.
期刊:
Journal of Chemical and Pharmaceutical Research,2014年6(8):243-254 ISSN:0975-7384
通讯作者:
Wu, Dianting
作者机构:
[Zhao, Lin; Wu, Dianting] School of Geography, Beijing Normal University, Beijing, China;[Liu, X.; Zhang, Ming] Jinkou High School, Wuhan, China;[Wu, Qing] Institute of Urban and Environmental, Huazhong Normal University, Wuhan, China
期刊:
IOP Conference Series: Earth and Environmental Science,2014年17(1) ISSN:1755-1307
通讯作者:
Zhou, Wei
作者机构:
[Li, Qi; Zhou, Wei] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, 9 Dengzhuang South Rd, Beijing 100094, Peoples R China.;[Li, Chang] Huazhong Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Peoples R China.
通讯机构:
[Zhou, Wei] C;Chinese Acad Sci, Inst Remote Sensing & Digital Earth, 9 Dengzhuang South Rd, Beijing 100094, Peoples R China.
会议名称:
35th International Symposium on Remote Sensing of Environment (ISRSE35)
会议时间:
APR 22-26, 2013
会议地点:
Inst Remote Sensing & Digital Earth, Beijing, PEOPLES R CHINA
会议主办单位:
Inst Remote Sensing & Digital Earth
会议论文集名称:
IOP Conference Series-Earth and Environmental Science
摘要:
Small-Footprint Airborne LiDAR(light detection and ranging) remote sensing is a breakthrough technology for deriving forest canopy structural characteristics. Because the technique is relatively new as applied to canopy measurement in China, there is a tremendous need for experiments that integrate field work, LiDAR remote sensing and subsequent analyses for retrieving the full complement of structural measures critical for forestry applications. Data storage capacity and high processing speed available today have made it possible to digitally sample and store the entire reflected waveform, instead of only extracting the discrete coordinates which form the so-called point clouds. Return waveforms can give more detailed insights into the vertical structure of surface objects, surface slope, roughness and reflectivity than the conventional echoes. In this paper, an improved Expectation Maximum (EM) algorithm is adopted to decompose raw waveform data. Derived forest biophysical parameters, such as vegetation height, subcanopy topography, crown volume, ground reflectivity, vegetation reflectivity and canopy closure, are able to describe the horizontal and vertical forest canopy structure.
期刊:
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS,2014年11(1):210-214 ISSN:1545-598X
通讯作者:
Hao, Ming
作者机构:
[Zhang, Hua; Hao, Ming] China Univ Min & Technol, Sch Environm Sci & Spatial Informat, Xuzhou 221116, Peoples R China.;[Shi, Wenzhong] Hong Kong Polytech Univ, Dept Land Surveying & Geoinformat, Hong Kong, Hong Kong, Peoples R China.;[Li, Chang] Cent China Normal Univ, Coll Urban & Environm Sci, Wuhan 430079, Peoples R China.
通讯机构:
[Hao, Ming] C;China Univ Min & Technol, Sch Environm Sci & Spatial Informat, Xuzhou 221116, Peoples R China.
关键词:
Expectation-maximization (EM);level set method;remote sensing;unsupervised change detection
摘要:
The level set method, because of its implicit handling of topological changes and low sensitivity to noise, is one of the most effective unsupervised change detection techniques for remotely sensed images. In this letter, an expectation-maximization-based level set method (EMLS) is proposed to detect changes. First, the distribution of the difference image generated from multitemporal images is supposed to satisfy Gaussian mixture model, and expectation-maximization (EM) is then used to estimate the mean values of changed and unchanged pixels in the difference image. Second, two new energy terms, based on the estimated means, are defined and added into the level set method to detect those changes without initial contours and improve final accuracy. Finally, the improved level set method is implemented to partition pixels into changed and unchanged pixels. Landsat and QuickBird images were tested, and experimental results confirm the EMLS effectiveness when compared to state-of-the-art unsupervised change detection methods.
作者机构:
[梁明; 胡最; 孙毅中] Key Laboratory of Virtual Geographic Environment Ministry of Education, Nanjing Normal University, Nanjing, China;[Chen, Zhao] Guangdong Institute of Eco-environment and Soil Sciences, Guangzhou, China;[罗荣] School of Urban and Environmental Science, Central China Normal University, Wuhan, China
通讯机构:
Key Laboratory of Virtual Geographic Environment Ministry of Education, Nanjing Normal University, Nanjing, China
作者机构:
[张忠杰; 焦铭; 廖文莉; 马萍; 武阳; 陈姣娥] College of Basic Medical, Hubei University of Science and Technology, Xianning , China;[杨旭; 马萍; 武阳] Laboratory of Environment Biomedicine, School of Life Science, Central China Normal University, Wuhan , China
通讯机构:
College of Basic Medical, Hubei University of Science and Technology, Xianning, China
作者机构:
[Yu, Guangming; Wang, Sa; Tian, Xiaojuan; Yu, Qiwu; Zhou, Xia; Zhang, Shu; Wu, Lei; Fan, Yong; Jia, Huanhuan; He, Xiaoli] Cent China Normal Univ, Coll Urban & Environm Sci, Lab Global Change & Disasters, Wuhan 430079, Peoples R China.
通讯机构:
[Yu, Guangming] C;Cent China Normal Univ, Coll Urban & Environm Sci, Lab Global Change & Disasters, Wuhan 430079, Peoples R China.
关键词:
The regional human-environment system;Flood;Disaster-causing factor;Disaster-bearing factor;Disaster-regulating factor;Disaster-bearing capability;Limit
摘要:
A series of interesting questions will be proposed and tried to be answered in this paper such as: Is there a limit of disaster-bearing capability in a region human-environment system (HES) when the system is hit by an extreme flood disaster? If so, what does it mean and how can it be explained? An assumption, naming the regional limit of flood-bearing capability (LFBC), is suggested and proved to respond these questions in this study. The LFBC model consists of three factors, namely, the disaster-causing factor (DCF), disaster-bearing factor (DBF) and disaster-regulating factor (DRF). The DCF can be selected from the cause analysis of flood, the DBF can be extracted from analysis of flood risk and vulnerability, and the DRF is responding to the analysis of flood risk management and measures. The logical relations among the three factors are determined by the analysis of flood inundation-loss models. The limit of disaster-bearing capability in regional HES is introduced by the principles of threshold analysis in terms of large-scale system theory, and can be expressed as the regional inundated depth or the amount of water in a flood. The LFBC model is built up following this idea, and approaches of its application are stated with the support of remote sensing (RS) and geographical information system (GIS). Substantial changes in terms of system succession, such as reservoir resettlement, population migration and land use pattern change, would occur only when extreme flood beyond its limit of disaster-bearing capability in a regional HES. Otherwise, the difference can be use to measures the damage conditions. Combining the occurrence probability of extreme flood, the LFBC model could be used to provide the data support for flood damage assessment, regional disaster control and reduction countermeasures, and regional development planning.
摘要:
Honghu Lake, one of the seven largest fresh-water lakes in China, is well known for its ecological and economic importance, as well as its rapid changes in recent years. This study investigates the potential of using remote sensing to map and monitor aquatic vegetation changes in Honghu Lake on a large scale. Landsat TM/ETM+ images dated July 27, 2000, July 9, 2002, and July 17, 2008, and CBERS image dated August 12, 2005, are employed to map the aquatic vegetation distribution in the lake. A hybrid classification method, combining the power of the decision tree classifier, naive Bayes classifier, and supporting vector machine classifier is used to distinguish different wetland types. A novel polar coordinate map method is proposed to map the changes of aquatic vegetation on a large scale. The map demonstrates vegetation patch size changes and percentage changes in the whole lake directions during four periods. Validation using in situ surveys and historical ancillary data suggests that this approach could map the distribution and monitor the changes of aquatic vegetation on a large scale efficiently. (C) 2013 Society of Photo-Optical Instrumentation Engineers (SPIE) [DOI:10.1117/1.JRS.7.073593]