机载LiDAR点云与遥感影像融合的地物分类技术研究
|
摘要
激光雷达测量（LiDAR）作为一种快速获取空间数据的新手段，在地球空间信息科学领域得到了广泛应用。借助LiDAR技术获取的地物三维点云数据与传统意义上的遥感技术获取的影像数据相比，仍存在语义信息匮乏、特征不连续等缺陷，使得地物智能化分类和识别等处理难度加大。而高分辨率影像虽具有光谱特征显著、纹理信息丰富等优点，但同物异谱、同谱异物等现象导致利用影像进行目标自动解译可靠性降低。因此，针对不同传感器获取数据的优点和局限性，将点云与影像数据融合进行地物智能分类和识别以弥补单个数据源的缺陷具有重要的研究价值。
本文基于多源数据融合理论，以支持向量机（SVM）、决策树为分类器，对机载LiDAR点云与高分辨率多光谱遥感影像融合的地物分类理论和技术进行深入研究，通过实验及特征空间分析揭示两种数据融合分类的深刻内涵。研究工作及创新点主要包括：
1．从技术层面对机载LiDAR点云与遥感影像融合分类涉及的配准和滤波问题进行了研究。尤其是利用统计矩原理实现了基于偏度平衡的点云滤波算法，该算法最大的优势在于无需阈值或参数支持，且独立于LiDAR数据格式和分辨率，采用非监督分类法将地面点与非地面点自动分离。与传统算法相比，此算法在Ⅱ类误差的控制上略有不足，但高效、智能化处理的特点使其仍具有较大的实用价值。
2．针对以往点云与影像融合分类技术中存在的“特征少，精度低”的缺点，重点加强点云特征优化提取策略研究。将点云特征依据不同的提取原则分为直接特征和间接特征，提出了在特征向量中加入原始点云局部几何属性特征以提高分类精度及稳定性的思路，并实现了五类法向量特征提取方法。对特征影像的分析表明，法向量特征能够有效区分道路、不同形状的建筑物、植被，并对车辆和植被识别有较强的敏感性。
3．将SVM引入点云与影像融合分类，提出了影像辅助点云及点云辅助影像两种多特征分类模式。分类结果表明，本文方法对不同数据均具有较强的适应性，并且两种分类模式都获得了较高的分类精度，特别是点云总体分类精度和Kappa值达到了90%以上，且成功实现车辆这一特殊地物类型的提取。对比实验表明，无论在分类精度上还是在地物类别数量上，本文方法均明显优于传统的分类方法。
4．采用正反向结合方法对影像辅助点云及点云辅助影像两种分类模式下的特征空间进行了深入分析，得出如下结论：①在影像辅助点云模式下，点云归一化高度（NH）特征对分类精度影响最大；②加入点云局部几何属性特征后，大大降低了建筑物与树木类的错分概率，解决了建筑物边缘点提取难题；③两种分类模式的对比分析表明，点云对影像分类的贡献量远大于影像对点云分类的贡献量，点云辅助影像分类更具实际意义；④以机载LiDAR点云为辅助数据的地物融合分类技术将在未来占有重要的战略地位。
5．改进了非线性Mode滤波器以改善点云和影像数据的分类结果质量。针对点云和影像两种数据的不同特点，分别利用k近邻型和窗口型Mode滤波器去除斑点噪声和椒盐噪声。对比实验结果证明，改进的Mode滤波器能有效地提高点云和影像两种数据分类结果的精度。
6．提出并实现了点云高程数据支持下影像上地物精细分类的方法。为保证高精度地同类别地物再划分，综合考虑辅助数据源、Mode滤波器、点云密度及影像空间分辨率、首次回波四种因素，利用决策树显著地提高了影像上建筑物、植被的分类数量，使点云与影像的融合分类优势得到进一步体现，达到了分类精度与地物类别数量相统一的预期目的。
7．提出并实现了多光谱影像辅助下点云中树种分类的方法。为避免特征提取单一而导致分类精度下降问题，除归一化高度、强度等直接特征外，重点提取点云中能够描述树种冠层表面信息的间接特征，包括冠层回波特征、冠层几何属性特征、冠层垂直结构特征。实验结果表明，联合机载LiDAR点云与多光谱影像数据并且利用SVM分类器获得了较高的树种分类精度和更精确的类别数量。
Airborne Light Detection and Ranging(LiDAR) is widely applied in the domain ofGeo-spatial information sciences as an emerging means which is a quick access to spatial data.Compared with remote sensing imagery data in tradition, the3D point clouds data acquired byLiDAR technology have a lot of flaws, such as the scarcity of semantic information,discontinuous characteristics and so on. Thus, it is more difficult in intelligent classification andrecognition of land cover types. Meanwhile, though very high resolution imagery can provide alarge amount of spectral features and texture information, the phenomenon of spectralheterogeneity even within the same class and different objects becoming more spectrally similarmake the reliability of automatic target interpretation in imagery decrease a lot. Consequently,according to the specific advantages and disadvantages of different sensors, integrating pointclouds and imagery to complement single data resource to perform intelligent classification andidentification of land cover types has important research values.
Based on the theories of multi-source data fusion and classifier of Support VectorMachine(SVM) and decision tree, this thesis aims to investigate an intensive and deep study onthe theory and technology of classification of land cover by fusing airborne LiDAR point cloudsand high spatial resolution multi-spectral remote sensing imagery. Subsequently, profoundsignificance is revealed through experiment and feature space analysis. The main contents andinnovations in this thesis can be summarized as follows:
1. The subjects of registration and filtering involved in classification of fusing airborneLiDAR and remote sensing imagery are researched from a technical level. Especially a filteringalgorithm based on skewness balancing for point clouds is achieved by exploiting statisticalmoments. The main advantages of the algorithm are threshold-freedom and independence fromLiDAR data format and resolution, and it separates ground points and non-ground pointsautomatically by unsupervised classification method. Compared with conventional algorithms, inspite of its drawback of the typeⅡerror control, it has great values of practical application due toits high efficiency and intelligence.
2. In connection with the shortcomings of "few features, low accuracy" which is existed inthe classification of fusing point clouds and imagery, the emphasis is placed on the optimizedextraction strategy for point clouds. According to the different principles of extraction, thefeatures for point clouds are divided into direct and indirect features. The way of adding localgeometric properties of raw point clouds to feature vector to improve the classification accuracyand stability is proposed, and five kinds of features belonging to normal vectors are extracted.The analysis of feature images indicates that the normal vector can not only distinguish roads, buildings with different shapes and vegetation, but also have a strong sensitivity in recognition ofvehicles and vegetation.
3. SVM is introduced to the classification of fusing point clouds and imagery, two types ofmulti-features classification modes which are point clouds complemented by imagery andimagery complemented by point clouds are developed. The classification results show that ourmethods exhibit great adaptability to various types of data, and both of the modes achieve highaccuracy. In particular, the overall classification accuracy and Kappa of point clouds reach above90%, and the vehicles are successfully identified as a special kind of object. The contrastexperiments prove that the methods developed in this thesis evidently outperforms the traditionalclassification methods, no matter on the accuracy or on the quantity of land cover types.
4. Combined methods of pros and cons are conducted to analyze deeply the feature spacesassociated with the two classification modes of the point clouds complemented by imagery andthe imagery complemented by point clouds, the conclusion are considered as follows: Firstly, inthe mode of point clouds complemented by imagery, normalized height(NH) of point clouds hasthe greatest impact on the classification accuracy; Secondly, after adding the local geometricproperties of point clouds, the misclassification probability between buildings and trees reducesconsiderably, and the problems in extracting building edge points are tackled; Thirdly,comparative analysis of the two classification modes indicate that point clouds contribute a lot tothe imagery classification, which is far superior to the mode of point clouds complemented byimagery, so the classification mode of imagery complemented by point clouds presents furtherpractical significance; Fourthly, combined classification technologies of land cover, whosecomplementary data are airborne LiDAR point clouds, will have important strategic status in thefuture.
5. A nonlinear Mode filter is designed and improved to enhance the classification resultquality of point clouds and imagery. According to the different characteristics of point clouds andimagery, k-nearest neighbor and window-based Mode filters are respectively developed toremove speckle and salt and pepper noises. Contrast experimental results demonstrate that theimproved Mode filters can boost the classification accuracy of point clouds and imagery dataeffectively.
6. The method of refined classification in image with the support of point clouds elevationdata is proposed and carried out. In order to create high accuracy of subdividing the same kind ofland cover type, four factors are taken into consideration, which includes supplementary datasource, Mode filter, point clouds density and image spatial resolution and point clouds firstechoes. Decision tree is developed to improve remarkably the classification quantity of buildingsand vegetation, which represents further superiority of classification of fusing point clouds and imagery, and achieves the desired goal of the unity of classification accuracy and quantity.
7. The method of classification of tree species in point clouds data complemented bymulti-spectral imagery is proposed and carried out. In order to avoid the low accuracy caused byinadequate features, besides the direct features, such as normalized height, intensity, and so on,this thesis focuses on extracting the indirect features from point clouds which can depict thecanopy information of tree species, including the echoes of canopy, geometric properties ofcanopy, vertical structure of canopy. The experimental results show that, by synergistic use ofairborne LiDAR point clouds and multi-spectral imagery, the method based on SVM classifierobtains higher classification accuracy and more accurate categories of tree species.
本文基于多源数据融合理论，以支持向量机（SVM）、决策树为分类器，对机载LiDAR点云与高分辨率多光谱遥感影像融合的地物分类理论和技术进行深入研究，通过实验及特征空间分析揭示两种数据融合分类的深刻内涵。研究工作及创新点主要包括：
1．从技术层面对机载LiDAR点云与遥感影像融合分类涉及的配准和滤波问题进行了研究。尤其是利用统计矩原理实现了基于偏度平衡的点云滤波算法，该算法最大的优势在于无需阈值或参数支持，且独立于LiDAR数据格式和分辨率，采用非监督分类法将地面点与非地面点自动分离。与传统算法相比，此算法在Ⅱ类误差的控制上略有不足，但高效、智能化处理的特点使其仍具有较大的实用价值。
2．针对以往点云与影像融合分类技术中存在的“特征少，精度低”的缺点，重点加强点云特征优化提取策略研究。将点云特征依据不同的提取原则分为直接特征和间接特征，提出了在特征向量中加入原始点云局部几何属性特征以提高分类精度及稳定性的思路，并实现了五类法向量特征提取方法。对特征影像的分析表明，法向量特征能够有效区分道路、不同形状的建筑物、植被，并对车辆和植被识别有较强的敏感性。
3．将SVM引入点云与影像融合分类，提出了影像辅助点云及点云辅助影像两种多特征分类模式。分类结果表明，本文方法对不同数据均具有较强的适应性，并且两种分类模式都获得了较高的分类精度，特别是点云总体分类精度和Kappa值达到了90%以上，且成功实现车辆这一特殊地物类型的提取。对比实验表明，无论在分类精度上还是在地物类别数量上，本文方法均明显优于传统的分类方法。
4．采用正反向结合方法对影像辅助点云及点云辅助影像两种分类模式下的特征空间进行了深入分析，得出如下结论：①在影像辅助点云模式下，点云归一化高度（NH）特征对分类精度影响最大；②加入点云局部几何属性特征后，大大降低了建筑物与树木类的错分概率，解决了建筑物边缘点提取难题；③两种分类模式的对比分析表明，点云对影像分类的贡献量远大于影像对点云分类的贡献量，点云辅助影像分类更具实际意义；④以机载LiDAR点云为辅助数据的地物融合分类技术将在未来占有重要的战略地位。
5．改进了非线性Mode滤波器以改善点云和影像数据的分类结果质量。针对点云和影像两种数据的不同特点，分别利用k近邻型和窗口型Mode滤波器去除斑点噪声和椒盐噪声。对比实验结果证明，改进的Mode滤波器能有效地提高点云和影像两种数据分类结果的精度。
6．提出并实现了点云高程数据支持下影像上地物精细分类的方法。为保证高精度地同类别地物再划分，综合考虑辅助数据源、Mode滤波器、点云密度及影像空间分辨率、首次回波四种因素，利用决策树显著地提高了影像上建筑物、植被的分类数量，使点云与影像的融合分类优势得到进一步体现，达到了分类精度与地物类别数量相统一的预期目的。
7．提出并实现了多光谱影像辅助下点云中树种分类的方法。为避免特征提取单一而导致分类精度下降问题，除归一化高度、强度等直接特征外，重点提取点云中能够描述树种冠层表面信息的间接特征，包括冠层回波特征、冠层几何属性特征、冠层垂直结构特征。实验结果表明，联合机载LiDAR点云与多光谱影像数据并且利用SVM分类器获得了较高的树种分类精度和更精确的类别数量。
Airborne Light Detection and Ranging(LiDAR) is widely applied in the domain ofGeo-spatial information sciences as an emerging means which is a quick access to spatial data.Compared with remote sensing imagery data in tradition, the3D point clouds data acquired byLiDAR technology have a lot of flaws, such as the scarcity of semantic information,discontinuous characteristics and so on. Thus, it is more difficult in intelligent classification andrecognition of land cover types. Meanwhile, though very high resolution imagery can provide alarge amount of spectral features and texture information, the phenomenon of spectralheterogeneity even within the same class and different objects becoming more spectrally similarmake the reliability of automatic target interpretation in imagery decrease a lot. Consequently,according to the specific advantages and disadvantages of different sensors, integrating pointclouds and imagery to complement single data resource to perform intelligent classification andidentification of land cover types has important research values.
Based on the theories of multi-source data fusion and classifier of Support VectorMachine(SVM) and decision tree, this thesis aims to investigate an intensive and deep study onthe theory and technology of classification of land cover by fusing airborne LiDAR point cloudsand high spatial resolution multi-spectral remote sensing imagery. Subsequently, profoundsignificance is revealed through experiment and feature space analysis. The main contents andinnovations in this thesis can be summarized as follows:
1. The subjects of registration and filtering involved in classification of fusing airborneLiDAR and remote sensing imagery are researched from a technical level. Especially a filteringalgorithm based on skewness balancing for point clouds is achieved by exploiting statisticalmoments. The main advantages of the algorithm are threshold-freedom and independence fromLiDAR data format and resolution, and it separates ground points and non-ground pointsautomatically by unsupervised classification method. Compared with conventional algorithms, inspite of its drawback of the typeⅡerror control, it has great values of practical application due toits high efficiency and intelligence.
2. In connection with the shortcomings of "few features, low accuracy" which is existed inthe classification of fusing point clouds and imagery, the emphasis is placed on the optimizedextraction strategy for point clouds. According to the different principles of extraction, thefeatures for point clouds are divided into direct and indirect features. The way of adding localgeometric properties of raw point clouds to feature vector to improve the classification accuracyand stability is proposed, and five kinds of features belonging to normal vectors are extracted.The analysis of feature images indicates that the normal vector can not only distinguish roads, buildings with different shapes and vegetation, but also have a strong sensitivity in recognition ofvehicles and vegetation.
3. SVM is introduced to the classification of fusing point clouds and imagery, two types ofmulti-features classification modes which are point clouds complemented by imagery andimagery complemented by point clouds are developed. The classification results show that ourmethods exhibit great adaptability to various types of data, and both of the modes achieve highaccuracy. In particular, the overall classification accuracy and Kappa of point clouds reach above90%, and the vehicles are successfully identified as a special kind of object. The contrastexperiments prove that the methods developed in this thesis evidently outperforms the traditionalclassification methods, no matter on the accuracy or on the quantity of land cover types.
4. Combined methods of pros and cons are conducted to analyze deeply the feature spacesassociated with the two classification modes of the point clouds complemented by imagery andthe imagery complemented by point clouds, the conclusion are considered as follows: Firstly, inthe mode of point clouds complemented by imagery, normalized height(NH) of point clouds hasthe greatest impact on the classification accuracy; Secondly, after adding the local geometricproperties of point clouds, the misclassification probability between buildings and trees reducesconsiderably, and the problems in extracting building edge points are tackled; Thirdly,comparative analysis of the two classification modes indicate that point clouds contribute a lot tothe imagery classification, which is far superior to the mode of point clouds complemented byimagery, so the classification mode of imagery complemented by point clouds presents furtherpractical significance; Fourthly, combined classification technologies of land cover, whosecomplementary data are airborne LiDAR point clouds, will have important strategic status in thefuture.
5. A nonlinear Mode filter is designed and improved to enhance the classification resultquality of point clouds and imagery. According to the different characteristics of point clouds andimagery, k-nearest neighbor and window-based Mode filters are respectively developed toremove speckle and salt and pepper noises. Contrast experimental results demonstrate that theimproved Mode filters can boost the classification accuracy of point clouds and imagery dataeffectively.
6. The method of refined classification in image with the support of point clouds elevationdata is proposed and carried out. In order to create high accuracy of subdividing the same kind ofland cover type, four factors are taken into consideration, which includes supplementary datasource, Mode filter, point clouds density and image spatial resolution and point clouds firstechoes. Decision tree is developed to improve remarkably the classification quantity of buildingsand vegetation, which represents further superiority of classification of fusing point clouds and imagery, and achieves the desired goal of the unity of classification accuracy and quantity.
7. The method of classification of tree species in point clouds data complemented bymulti-spectral imagery is proposed and carried out. In order to avoid the low accuracy caused byinadequate features, besides the direct features, such as normalized height, intensity, and so on,this thesis focuses on extracting the indirect features from point clouds which can depict thecanopy information of tree species, including the echoes of canopy, geometric properties ofcanopy, vertical structure of canopy. The experimental results show that, by synergistic use ofairborne LiDAR point clouds and multi-spectral imagery, the method based on SVM classifierobtains higher classification accuracy and more accurate categories of tree species.
引文
[1] Shan Jie, Toth C K. Topographic Laser Ranging and Scanning: Principles and Processing[M]. Florida:CRC Press,2008.
[2]张永军,吴磊,林立文,等.基于LiDAR数据和航空影像的水体自动提取[J].武汉大学学报:信息科学版,2010,35(8):936-940.
[3]苏伟,李京,陈云浩,等.基于多尺度影像分割的面向对象城市土地覆被分类研究[J].遥感学报,2007,11(4):521-530.
[4]刘同时,夏祖勋,解洪成.数据融合技术及其应用[M].北京:国防工业出版社,1998.
[5]韩玲.多源遥感信息融合技术及多源信息在地学中的应用研究[D].西安:西北大学,2005.
[6]韩玲,吴汉宁.多源遥感影像数据融合的理论与技术[J].西北大学学报:自然科学版,2004,34(4):457-460.
[7]贾永红,李德仁,孙家抦.多源遥感影像数据融合[J].遥感技术与应用,2000,(1):19-23.
[8] Pohl C. and Van Genderen J.L. Multisensor Image Fusion in Remote Sensing: Concepts, Methods andApplications[J]. International Journal of Remote Sensing,1998,19,823-954.
[9] G.W.Geerling, M.Labrador-Garcia, J.G.P.W.Clevers, et al. Classification of Floodplain Vegetation by DataFusion of Spectral(CASI) and LiDAR Data[J]. International Journal of Remote Sensing,2007,28(19):4263-4284.
[10] Leckie D.G., Cloney E., Jay C. and Paradine D. Automated Mapping of Stream Features with HighResolution Multispectral Imagery: an Example of The Capabilities[J]. Photogrammetric Engineering andRemote Sensing,2005,71,145-155.
[11] SITHOLE G, VOSSELMAN G. Experimental Comparison of Filter Algorithms for Bare-Earth Extractionfrom Airborne Laser Scanning Point Clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2004,59(1-2):85-101.
[12] G. Sithole, G. Vosselman. Filtering of Airborne Laser Point Scanner Data Base on Segmented PointClouds[J]. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences,2005,36(Part3/W19):66-71.
[13] Bartels M, Wei H, Mason D C. DTM generation from LiDAR data us ing Skewness Balancing[C].Proceedings of the18th International Conference on Pattern Recognition,2006, I:566-569.
[14] Bartels M, Wei H. Threshold-free object and ground point separation in LiDAR data[J]. PatternRecognition Letters,2010,31:1089-1099.
[15] Axelsson P. DEM Generation from Laser Scanner Data Using Adaptive TIN Models[J]. InternationalArchives of Photogrammetry, Remote Sensing and Spatial Information Science,1999,33(B4/1):110-117.
[16] Elberink S O., Maas H G. The Use of Anisotropic Height Texture Measurements for the Segmentation ofAirborne Laserscanner Data[J]. International Archives of Photogrammetry and Remote Sensing,2000,33(B3):678-684.
[17] Jeong Heon Song, Soo Hee Han, Ki Yun Yu, et al. A Study on Using LiDAR Intensity Data for LandCover Classification[C]. In ISPRS Commission Ⅲ, Symposium2002September9-13,2002, Graz,Austria,2002.
[18] Hossein Arefi, Michael Hahn. A Hierarchical Procedure for Segmentation and Classification of airborneLiDAR Images[C]. IEEE International Geoscience and Remote Sensing Symposium,IGARSS-Proceedings,2005,7:4950-4953.
[19] R. Brennan and T.L. Webster. Object-oriented Land Cover Classification of Lidar-derived Surfaces[J].Canadian Journal of Remote Sensing,2006,32(6):162-172.
[20] Amolins Krista, Zhang Yun, Dare Peter. Classification of LiDAR Data Using Standard Deviation ofElevation and Characteristic Point Features[C]. IEEE International Geoscience and Remote SensingSymposium, IGARSS-Proceedings,2008,871-874.
[21] A.S. Antonarakis, K.S. Richards, J. Brasington. Object-based Land Cover Classification Us ing AirborneLiDAR[J]. Remote Sensing of Environment,2008,112(6):2988-2998.
[22] Carlberg Matthew, Gao Peiran, Chen George, et al. Classifying Urban Landscape in Aerial LiDAR USing3D Shape Analys is[C]. IEEE International Conference on Image Processing, ICIP-Proceedings,2009,1701-1704.
[23] Samadzadegan Farhad, Bigdeli Behnaz, Ramzi Pouria. A Multiple Classifier System for Classification ofLiDAR Remote Sensing Data Using Multi-class SVM. Lecture Notes in Computer Science,2010,5997/2010:254-263.
[24] Fischler M.A., Bolles R.C. Random Sample Consensus: a Paradigm for Model Fitting with Application toImage Analysis and Automated Cartography[J]. Communications of The ACM,1981,24(6):381-395.
[25] Wu Jun, Guo Ning, Liu Rong, et al. Aerial Lidar Data Classification Using We ighted Support VectorMachines[C]. Third International Conference on Digital Image Processing(ICDIP),2011, v8009.
[26] Chen Yunhao, Su Wei, Li J ing, et al. Hierarchical Object Oriented Classification Using Very HighResolution Imagery and LiDAR Data Over Urban Areas[J]. Advances in Space Research,2008,43(7):1101-1110.
[27] Yu Bailang, Liu Hongxing, Zhang Li, et al. An Object-based Two-stage Method For a DetailedClassification of Urban Landscape Components by Integrating Airborne LiDAR and Color InfraredImage Data: a Case Study of Downtown Houston[J]. IEEE Urban Remote Sensing Joint Event,2009,1-8.
[28] Ke Yinghai, J. Quackenbush Lindi, Im Jungho. Synergistic Use of QuickBird Multispectral Imagery andLiDAR Data for Object-based Forest Species Classification[J]. Remote Sensing of Environment,2010,114(6):1141-1154.
[29] Takeshi Sasaki, Junichi Imanishi, Keiko Ioki, et al. Object-based Classification of Land Cover and TreeSpecies by Intergrating Airborne LiDAR and High Spatial Resolution Imagery Data[J]. InternationalConsoritium of Landscape and Ecological Engineering and Springer,2011,8(2):157-171.
[30] Mariano García, David Ria o, Emilio Chuvieco, et al. Mutispectral and LiDAR Data Fusion for FuelType Mapping Us ing Support Vector Machine and Decision Rules[J]. Remote Sensing of Enviroment,2011,115(6):1369-1379.
[31] Kotez B., Morsdort F., Curt T. Fusion of Imaging Spectrometer and Lidar Data Us ing Support VectorMachine for Land Cover Classification in The Context of Forest Fire Management[C]. Proceedings of theISPRS Commission Ⅶ, WG1,2008.
[32] María C. Alonso, José A. Malpica. Classification of Multispectral High-Resolution Satellite ImageryUsing LiDAR Elevation Data[J]. Advances in Visual Computing, PTⅡ, Proceedings,2008,5359:85-94.
[33] A. Arquero, E. Martínez. Analysis of Thematic Classified Aerial Images through Multispectral andLiDAR Data[J]. IEEE Latin America Transactions,2011,9(1):1-9.
[34] Rottensteiner F., Jansa J. Automatic Extraction of Buildings from LiDAR Data and Aerial Images[C].Proceedings of the ISPRS Commission Ⅳ Symposium in Ottawa, International Archives ofPhotogrammetry and Remote Sensing,2002, XXXIV/4,569-574.
[35] Rottensteiner F., Trinder J., Clode S., et al. Using The Dempster Shafer Method for The Fusion of LiDARData and Multi-spectral Image for Building Detection[J]. Information Fusion,2004,6(4):283-300.
[36] Amin P.Charaniya, Roberto M, Suresh K.Lodha. Supervised Parametric Classification of Aerial LiDARData[J]. Computer Vision and Pattern Recognition Workshop,2004,25-32.
[37] Suresh K. Lodha, Edward J. Kreps, David P. Helmbold, et al. Aerial LiDAR Data Classification Us ingSupport Vector Machines(SVM)[C]. IEEE Proceedings of the Third International Conference on3DData Processing Visualization and Transmission(3DPVT),2006,567-574.
[38] Suresh K. Lodha, Darren M. Fitzpatrick, David P. Helmbold. Aerial LiDAR Data Classification Us ingAdaBoost[C]. IEEE Proceedings of the Sixth International Conference on3D Digital Imaging andModeling(3DIM),2007,435-442.
[39] Secord J., Zakhor A. Tree Detection in Aerial LiDAR and Image Data[C]. IEEE International Conferenceon Image Processing, ICIP,2006:2317-2320.
[40] Bartels Marc, Wei Hong, Ferryman James. Analysis of LiDAR Data Fused with Co-Registered Bands[C].Proceedings of the IEEE International Conference on Video and Signal Based Surveillance,2006,60-60.
[41] Bartels Marc, Wei Hong. Rule-based Improvement of Maximum Likelihood Classification LiDAR DataFused with Co-Registered Bands[C]. Annual Conference of the Remote Sensing and PhotogrammetrySociety, Cambridge, United Kingdom,2006.
[42] Cao Yang, Zhao Huijie, Li Na. Land-Cover Classification by Airborne LiDAR Data Fused with AerialOptical Images[J]. International Workshop on Multi-Platform/Multi-Sensor Remote Sensing andMapping(M2RSM),2011, pp1-6.
[43] Wang Xin, Luo Yiping, Jiang Ting, et al. A New Classification Method for LiDAR Data Based onUnbalance Support Vector Machine[C]. International Symposium of Image and Data Fusion(ISIDF),2011:1-4.
[44]张小红.机载激光雷达测量技术理论与方法[M].武汉:武汉大学出版社,2007.
[45]梁欣廉,张继贤,李海涛.一种应用于城市区域的自适应形态学滤波方法[J].遥感学报,2007,11(2):276-281.
[46]李勇,吴华意.基于形态学梯度的机载激光扫描数据滤波方法[J].遥感学报,2008,12(4):633-639.
[47]隋立春,张熠斌,柳艳,等.基于改进的数学形态学算法的LiDAR点云数据滤波[J].测绘学报,2010,39(4):390-396.
[48]罗伊萍,姜挺,王鑫,等.基于数学形态学的LiDAR数据滤波新方法[J].测绘通报,2011,(3):15-19.
[49]沈晶,刘纪平,林祥国.用形态学重建方法进行机载LiDAR数据滤波[J].武汉大学学报:信息科学版,2011,36(2):167-175.
[50]闫利,张毅.基于法向量模糊聚类的道路面点云数据滤波[J].武汉大学学报:信息科学版,2007,32(12):1119-1122.
[51]蒋晶珏,张祖勋,明英.复杂城市环境的机载LiDAR点云滤波[J].武汉大学学报:信息科学版,2007,32(5):402-405.
[52]成晓倩,马洪超,赵红强,等.一种基于区域增长的机载LiDAR滤波[J].测绘科学,2010,35(1):61-63.
[53]周晓明.机载激光雷达点云数据滤波算法的研究与应用[D].郑州:信息工程大学,2011.
[54]黄先锋,李卉,王潇,等.机载LiDAR数据滤波方法评述[J].测绘学报,2009,38(5):466-469.
[55]刘经南,张小红.利用激光强度信息分类激光扫描测高数据[J].武汉大学学报:信息科学版,2005,30(3):189-192.
[56]蒋晶珏. LiDAR数据基于点集的表示与分类[D].武汉:武汉大学,2006.
[57]杨海全,余洁,秦昆,等.基于知识的LiDAR数据地物提取研究[J].测绘通报,2006,(12):9-15.
[58]刘峰,龚健雅.基于3D LiDAR数据的城区植被识别研究[J].地理与地理信息科学,2009,25(6):5-8.
[59]乔纪纲,刘小平,张亦汉.基于LiDAR高度纹理和神经网络的地物分类[J].遥感学报,2011,15(3):546-553.
[60]苏伟,李京,陈云浩,等.基于多尺度影像分割的面向对象城市土地覆被分类研究[J].2007,11(4):521-530.
[61]余柏蒗,刘红星,吴健平.一种应用机载LiDAR数据和高分辨率遥感影像提取城市绿地信息的方法[J].中国图象图形学报,2010,15(5):782-789.
[62]管海燕,邓非,张剑清,等.面向对象的航空影像与LiDAR数据融合分类[J].武汉大学学报:信息科学版,2009,34(7):830-833.
[63]袁夏,赵春霞,张浩峰,等.基于点云数据的自然地形分类算法[J].南京理工大学学报(自然科学版),2010,34(2):222-237.
[64]杨耘,隋立春.面向对象的LiDAR数据多特征融合分类[J].测绘通报,2010,(8):11-14.
[65]罗伊萍. LiDAR数据滤波和影像辅助提取建筑物[D].郑州:信息工程大学,2010.
[66]钟良. LiDAR同机影像辅助点云分类相关技术研究[D].武汉:武汉大学,2011.
[67] Franz Rottensteiner, Caroline Baillard, Gunho Sohn, et al. ISPRS Test Project on Urban Classification and3D Building Reconstruction[EB/OL]. ISPRS-Commission Ⅲ, Working Group Ⅲ/4,2011. URL:http://www.commission3.isprs.org/wg4/ComplexScenes.pdf.
[68] Kornus W., Ruiz A. Strip Adustment of LiDAR Data[J]. International Archives of Photogrammetry andRemote Sensing,2003,34(3/w):47-50.
[69] Ayman Fawzy Habib, Rita Wai Ting Cheng, Eui-Myoung Kim, et al. Automatic Surface Matching for TheRegistration of LiDAR Data and MR Imagery[J]. ETRI Journal,2006,28(2):162-174.
[70]姚春静.机载LiDAR点云数据与遥感影像配准方法的研究[D].武汉:武汉大学,2010.
[71]张帆,黄先锋,李德仁.激光扫描与光学影像数据配准的研究进展[J].测绘通报,2008,(2):7-10.
[72] ZHANG K, CHEN S C, WHITMAN D, et al. A Progressive Morphological Filter for RemovingNonground Measurement from LiDAR Data[J]. IEEE Transactions on Geoscience and Remote Sensing,2003,41(4):872-882.
[73] Axelsson P. DEM Generation from Laser Scanner Data Using Adaptive TIN Models[J]. InternationalArchives of Photogrammetry, Remote Sensing and Spatial Information Science,1999,33(B4/1):110-117.
[74] Sithole G. Segmentation and Classification of Airborne Laser Scanner[D]. Delft University of Technology,2005.
[75] BAO Yunfei, CAO Chunxiang, CHANG Chaoyi, et al. Segmentation to The Point Clouds of LiDAR DataBased on Change of Kurtosis[C]. International Symposium on Photoelectronic Detection and Imaging:Image Processing,2007,6623:1N-7.
[76] R.O. Duda, P.E. Hart, D.G. Stork. Pattern Classification[M]. New York:Wiley,2001.
[77]梁欣廉,张继贤,李海涛,等.激光雷达应用中的几种数据表达方式[J].遥感信息,2005,6:60-64.
[78] M. Alexa, J. Behr, D. Cohen-Or, et al. Point Set Surfaces[J]. IEEE Visualization2001,2001:21-28.
[79] Nina Amenta, Marshall Bern, Manolis Kamvysselis. A New Voronoi-Based Surface ReconstructionAlgorithm[J]. Siggraph’98,1998,415-421.
[80] Mattis Andersson, Joachim Giesen, Mark Pauly, et al. Bounds on The k-Neighborhood for LocallyUniformly Sampled Surfaces[C]. Proceedings of the Eurographics Symposium on Point-Based Graphics,2004:167-171.
[81] J.L. Bentley. Multidimensional Binary Search Trees Used for Associative Searching[J]. Communicationsof the ACM,1975,18(9):509-517.
[82] S. Arya, H. A. Fu. Expected-case Complexity of Approximate Nearest Neighbor Searching[J]. SIAMJournal on Computing,2003,32(2):793-815.
[83] Maas H G. The Potential of Height Texture Measurement for the Segmentation of Airborne LaserScanning Data[C]. The4thInternational Airborne Remote Sensing Conference and Exhibition/21stCanadian Symposium on Remote Sensing, Ottawa, Ontario, Canada,1999a.
[84] Huang J., Menq C H. Automatic Data Segmentation for Geometric Feature Extraction from Unorganized3-D Coordinate Points[J]. IEEE Transactions on Robotics and Automation(S1042-296X),2001,17(3):268-279.
[85]刘信伟,靖常峰,罗德利,等.一种提高三维点云特征点提取精度的方法探讨[J].城市勘测,2013,(1):9-11.
[86] Michael Garland. Quadric-Based Polygonal Surface Simplication[D]. Ph.D. thesis,1999.
[87]解亚龙.应用高分辨率彩红外DMC影像进行昆明市城区绿化信息提取[D].昆明:昆明理工大学,2006.
[88]田野,徐恒力,刘双,等.基于归一化植被指数变化分级的千山植被变化[J].中国水土保持,2010,(1):25-28.
[89]王晶,白雪,邓晓曲,等.基于NDVI的三峡大坝岸边植被时空特征分析[J].地球信息科学,2008,10(6):808-815.
[90]武永峰,李茂松,刘布春,等.基于NOAA NDVI的中国植被绿度始期变化[J].地理科学进展,2008,27(6):32-40.
[91]周廷刚,郭达志,陶康华. NCIVI及其在城市绿化航空遥感调查中的应用—以宁波市为例[J].城市环境与城市生态,2003,16(1):25-27.
[92]黄昕.高分辨率遥感影像多尺度纹理、形状特征提取与面向对象分类研究[D].武汉:武汉大学,2009.
[93] R. M. Haralick, K. Shanmugam, I. Dinstein. Textural Feature for Image Classification[J]. IEEE Trans. OnSystems, Man and Cybernetics,1973,3(6):610-621.
[94] Ohanian P P, Dubes R C. Performance Evaluation for Four Class of Texture Features[J]. PatternRecognition,1992,25:819-833.
[95]贾永红.数字图像处理[M].武汉:武汉大学出版社,2003.
[96] Benediktsson J. A., Swain P. H., Ersoy O. K. Neural Network Approaches Versus Statistical Methods inClassification of Multisource Remote Sensing Data[J]. IEEE Transactions on Geoscience and RemoteSensing,1990,28:540-552.
[97] C. Cortes, V. Vapnik. Support Vector Networks[J]. Machine Learning,1995,20:273-295.
[98] V.N. Vapnik, A.J. Hervonenkis. On The Uniform Convergence of Relative Frequencies of Events to TheirProbabilities[J]. Theory of Probability and Applications,1971,16:264-280.
[99] V.N. Vapnik, A.J. Chervonenkis. Ordered Risk Minimization(Ⅰand Ⅱ)[J]. Automation and RemoteControl,1974,34:1226-1235and1403-1412.
[100] V.Vapnik, A. Chervonenkis. Theory of Pattern Recognition[M]. Nauka, Moscow,1974.
[101] V.N. Vapnik. Estimation of Dependences Based on Empirical Data[M]. Springer-Verlag, Berlin,1982.
[102] V.N. Vapnik, E. Levin, Y.L. Cunn. Measuring the VC Dimension of A Learning Machine[J]. NeuralComputation,1994,6:851-876.
[103] B.E. Boser, I.M. Guyon, V.N. Vapnik. A Training Algorithm for Optimal Margin Classifiers[C]. InProceedings of The5thAnnual ACM Workshop on Computational Learning Theory,1992,:144-152.
[104] V. Vapnik. The Nature of Statistical Learning Theory[M]. Springer-Verlag, New York, NY,1995.
[105]路威.面向目标探测的高光谱影像特征提取与分类技术研究[D].郑州:信息工程大学,2005.
[106] Vapnik N.V.著;许建华,张学工译.统计学习理论[M].北京:电子工业出版社,2004:274-322.
[107] S.S. Keerthi, C.-J. Lin. Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel[J].Neural Computation,2003,15(7):1667-1689.
[108]杨国鹏.基于机器学习方法的高光谱影像分类研究[D].郑州:信息工程大学,2010.
[109] H.-T. Lin, C.-J. Lin. A Study on Sigmoid Kernels for SVM and The Training of Non-PSD Kernels bySMO-type Methods[R]. Technical Report, Department of Computer Science, National Taiwan University,2003. URL http://www.csie.ntu.edu.tw/~cjlin/papers/tanh.pdf.
[110] C.-C. Chang, C.-J. Lin. LIBSVM: A Library for Support Vector Machines[J]. ACM Transactions onIntelligent Systems and Technology,2:27:1-27:27,2011. Software available athttp://www.csie.ntu.edu.tw/~cjlin/libsvm.
[111] C.-C. Chang, C.-J. Lin. LIBSVM: A Library for Support Vector Machines[R]. Technical Report,Department of Computer Science, National Taiwan University, Initial Version:2001, Last Updated: May20,2011. URL http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf.
[112] C.-W. Hsu, C.-J. Lin. A Comparison of Methods for Multi-class Support Vector Machines[J]. IEEETransactions on Neural Networks,2002,13(2):415-425.
[113] Grejner-Brzezinska, D.A., Toth, C. Deriving Vehicle Topology and Attribute Information overTransportation Corridors from LiDAR Data[C]. Proceedings, ION59thAnnual Meeting, June23-25,Albuquerque, New Mexico,2003:404-410.
[114] Toth C., Grejner-Brzezinska D. Vehicle Classification from LiDAR Data to Support Traffic FlowEstimates[C]. Proceedings of3rdInternational Sysposium on Mobile Mapping Technology, Kunming,China, March29-31,2004.
[115] Toth C., Grejner-Brzezinska D., Moafipoor S. Presise Vehicle Topology and Road Surface ModelingDerived from Airborne LiDAR Data[C]. The60thAnnual Meeting of ION2004, Dayton, OH, June7-9,2004.
[116] Wei Yao, Stefan Hinz, Uwe Stilla. Automatic Vehicle Extraction from Airborne LiDAR Data of UrbanAreas Aaided by Geodesic Morphology[J]. Pattern Recognition Letters,2010,31(10):1100-1108.
[117] Quinlan J. R. Induction of Decision Tree[J]. Machine Learning,1986,1(1):81-106.
[118]龙际珍,任海叶,易华容.一种改进决策树算法的探讨[J].株洲师范高等专科学校学报,2006,11(2):64-66.
[119] Nelson R., Krabill W., Maaclean G. Determining Forest Canopy Characteristics Using Airborne LaserData[J]. Remote Sensing of Environment,1984,15(3):201-212.
[120] Hyypp J. Development and Feasibility of Airborne Ranging Radar for Forest Assessment[D]. PhDThesis, Helsinki University of Technology, Laboratory of Space Technology,1993.
[121] Hyypp J., Hallikainen M. A Helicopter-borne Eight-channel Ranging Scatterometer for RemoteSensing[J]. IEEE Transactions on Geoscience and Remote Sensing,1993,31(1):170-179.
[122] Hyypp J., Hyypp H., Leckie D. et al. Review of Methods of Small-footprint Airborne Laser Scanningfor Extracting Forest Inventory Data in Boreal Forests[J]. International Journal of Remote Sensing,2008,29(5):1339-1366.
[123] Hyypp J., Holopainen M., Olsson H. Laser Scanning in Forests[J]. Remote Sensing,2012,4(10):2919-2922.
[124] Brandtberg T., Warner T., Landenberger R., et al. Detection and Analysis of Individual Leaf-off TreeCrowns in Small Footprint, High Sampling Density LiDAR Data from The Eastern Deciduous Forest inNorth America[J]. Remote Sensing of Environment,2003,85(3):290-303.
[125] Holmgren J., Persson A. Identifying Species of Individual Trees Using Airborne Laser Scanning[J].Remote Sensing of Environment,2004,90(4):415-423.
[126] Moffiet T., Mengersen K., Witte C., et al. Airborne Laser Scanning: Exploratory Data Analysis IndicatesPotential Variables for Classification of Individual Trees or Forest Stands According to species[J]. ISPRSJournal of Photogrammetry and Remote Sensing,2005,59(5):289-309.
[127] Liang X., Hyypp J., Matikainen L. Deciduos-coniferous Tree Classification Us ing Difference betweenFirst and Last Pulse Laser Signatures[C]. International Archives of Photogrammetry, Remote Sensing andSpatial Information Science, ISPRS,2007,3(Part3/W52):253-257.
[128] Kim S. Individual Tree Species Identification Us ing LiDAR-derived Crown Structures and IntensityData[D]. PhD Thesis, College of Forest Resouces, University of Washinton,2007.
[129] rka H.O., N sset E., Bollands s O.M. Classifying Species of Individual Trees by Intensity andStructure Features Derived From Airborne Laser Scanning Data[J]. Remote Sensing of Environment,2009,113(6):1163-1174.
[130] ZHANG Z., LIU X. Support Vector Machines for Tree Species Identification Using LiDAR-derivedStructure and Intensity Variables[J]. GeoCarto International,2012, pp1-15.
[131] Brandtberg T. Individual Tree-based Species Classification in High Spatial Resolution Aerial Images ofForests Using Fuzzy Sets[J]. Fuzzy Sets and Systems,2002,132(3):371-387.
[132] Bohlin J., Olsson H., Olofsson K., et al. Tree Species Discrimination by Aid of Template MatchingApplied to Digital Air Photos[C]. Proceedings of The International Workshop on3D Remote Sensing inForestry,2006, pp199-203.
[133] Persson., Holmgren J., S derman U. Identification of Tree Species of Individual Trees by CombiningVery High Resolution Laser Data with Multi-spectral Images[C]. Proceedings of The InternationalWorkshop3D Remote Sensing in Forestry,2006, pp91-96.
[134] Packalén P., Maltamo M. Predicting The Plot Volume by Tree Species Using Airborne Laser Scanningand Aerial Photographs[J]. Forest Science,2006,52(6):611-622.
[135] Koetz B., Morsdorf F., van der Linden, et al. Multi-source Land Cover Classification for Forest FireManagement Based on Imaging Spectrometry and LiDAR Data[J]. Forest Ecology and Management,2008,256(3):263-271.
[136] White R. A., Dietterick B. C. Use of LiDAR and Multispectral Imagery to Determine Conifer Mortalityand Burn Severity Following the Lockheed Fire[C]. Proceedings of Coast Redwood Forests in aChanging California: A Symposium for Scientists and Managers,2012, pp667-675.
[137]赵峰,李增元,王韵晟,等.机载激光雷达(LiDAR)数据在森林资源调查中的应用综述[J].遥感信息,2008(1):106-110.
[138]庞勇,赵峰,李增元,等.机载激光雷达平均树高提取研究[J].遥感学报,2008,12(1):152-158.
[139]周淑芳.基于机载LiDAR与航空像片的单木树高提取研究[D].哈尔滨:东北林业大学,2007.
[140]庞勇,李增元.基于机载激光雷达的小兴安岭温带森林组分生物量反演[J].植物生态学报,2012,36(10):1095-1105.
[141]骆社周.激光雷达遥感森林叶面积指数提取方法研究与应用[D].北京:中国地质大学,2012.
[142]刘丽娟.基于机载LiDAR和高光谱融合的森林参数反演研究[D].哈尔滨:东北林业大学,2011.
[143]赵旦.基于激光雷达和高光谱遥感的森林单木关键参数提取[D].北京:中国林业科学研究院,2012.
[144] Lillesand T.M., Kiefer R.W., Chipman J.W. Remote Sensing and Image Interpretation[M]. John Wiley,New York,2008.
[145] Kim S., McGaugher R.J., Andersen, H.-E., et al. Tree Species Differentiation Using Intensity DataDerived From Leaf-on and Leaf-off Airborne Laser Scanning Data[J]. Remote Sensing of Environment,2009,113:1575-1586.
[146] Korpela I., rka H.O., Hyypp c J., et al. Range and AGC Normalization in Airborne Discrete-returnLiDAR Intensity Data for Forest Canopies[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2010,65:369-379.
[2]张永军,吴磊,林立文,等.基于LiDAR数据和航空影像的水体自动提取[J].武汉大学学报:信息科学版,2010,35(8):936-940.
[3]苏伟,李京,陈云浩,等.基于多尺度影像分割的面向对象城市土地覆被分类研究[J].遥感学报,2007,11(4):521-530.
[4]刘同时,夏祖勋,解洪成.数据融合技术及其应用[M].北京:国防工业出版社,1998.
[5]韩玲.多源遥感信息融合技术及多源信息在地学中的应用研究[D].西安:西北大学,2005.
[6]韩玲,吴汉宁.多源遥感影像数据融合的理论与技术[J].西北大学学报:自然科学版,2004,34(4):457-460.
[7]贾永红,李德仁,孙家抦.多源遥感影像数据融合[J].遥感技术与应用,2000,(1):19-23.
[8] Pohl C. and Van Genderen J.L. Multisensor Image Fusion in Remote Sensing: Concepts, Methods andApplications[J]. International Journal of Remote Sensing,1998,19,823-954.
[9] G.W.Geerling, M.Labrador-Garcia, J.G.P.W.Clevers, et al. Classification of Floodplain Vegetation by DataFusion of Spectral(CASI) and LiDAR Data[J]. International Journal of Remote Sensing,2007,28(19):4263-4284.
[10] Leckie D.G., Cloney E., Jay C. and Paradine D. Automated Mapping of Stream Features with HighResolution Multispectral Imagery: an Example of The Capabilities[J]. Photogrammetric Engineering andRemote Sensing,2005,71,145-155.
[11] SITHOLE G, VOSSELMAN G. Experimental Comparison of Filter Algorithms for Bare-Earth Extractionfrom Airborne Laser Scanning Point Clouds[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2004,59(1-2):85-101.
[12] G. Sithole, G. Vosselman. Filtering of Airborne Laser Point Scanner Data Base on Segmented PointClouds[J]. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences,2005,36(Part3/W19):66-71.
[13] Bartels M, Wei H, Mason D C. DTM generation from LiDAR data us ing Skewness Balancing[C].Proceedings of the18th International Conference on Pattern Recognition,2006, I:566-569.
[14] Bartels M, Wei H. Threshold-free object and ground point separation in LiDAR data[J]. PatternRecognition Letters,2010,31:1089-1099.
[15] Axelsson P. DEM Generation from Laser Scanner Data Using Adaptive TIN Models[J]. InternationalArchives of Photogrammetry, Remote Sensing and Spatial Information Science,1999,33(B4/1):110-117.
[16] Elberink S O., Maas H G. The Use of Anisotropic Height Texture Measurements for the Segmentation ofAirborne Laserscanner Data[J]. International Archives of Photogrammetry and Remote Sensing,2000,33(B3):678-684.
[17] Jeong Heon Song, Soo Hee Han, Ki Yun Yu, et al. A Study on Using LiDAR Intensity Data for LandCover Classification[C]. In ISPRS Commission Ⅲ, Symposium2002September9-13,2002, Graz,Austria,2002.
[18] Hossein Arefi, Michael Hahn. A Hierarchical Procedure for Segmentation and Classification of airborneLiDAR Images[C]. IEEE International Geoscience and Remote Sensing Symposium,IGARSS-Proceedings,2005,7:4950-4953.
[19] R. Brennan and T.L. Webster. Object-oriented Land Cover Classification of Lidar-derived Surfaces[J].Canadian Journal of Remote Sensing,2006,32(6):162-172.
[20] Amolins Krista, Zhang Yun, Dare Peter. Classification of LiDAR Data Using Standard Deviation ofElevation and Characteristic Point Features[C]. IEEE International Geoscience and Remote SensingSymposium, IGARSS-Proceedings,2008,871-874.
[21] A.S. Antonarakis, K.S. Richards, J. Brasington. Object-based Land Cover Classification Us ing AirborneLiDAR[J]. Remote Sensing of Environment,2008,112(6):2988-2998.
[22] Carlberg Matthew, Gao Peiran, Chen George, et al. Classifying Urban Landscape in Aerial LiDAR USing3D Shape Analys is[C]. IEEE International Conference on Image Processing, ICIP-Proceedings,2009,1701-1704.
[23] Samadzadegan Farhad, Bigdeli Behnaz, Ramzi Pouria. A Multiple Classifier System for Classification ofLiDAR Remote Sensing Data Using Multi-class SVM. Lecture Notes in Computer Science,2010,5997/2010:254-263.
[24] Fischler M.A., Bolles R.C. Random Sample Consensus: a Paradigm for Model Fitting with Application toImage Analysis and Automated Cartography[J]. Communications of The ACM,1981,24(6):381-395.
[25] Wu Jun, Guo Ning, Liu Rong, et al. Aerial Lidar Data Classification Using We ighted Support VectorMachines[C]. Third International Conference on Digital Image Processing(ICDIP),2011, v8009.
[26] Chen Yunhao, Su Wei, Li J ing, et al. Hierarchical Object Oriented Classification Using Very HighResolution Imagery and LiDAR Data Over Urban Areas[J]. Advances in Space Research,2008,43(7):1101-1110.
[27] Yu Bailang, Liu Hongxing, Zhang Li, et al. An Object-based Two-stage Method For a DetailedClassification of Urban Landscape Components by Integrating Airborne LiDAR and Color InfraredImage Data: a Case Study of Downtown Houston[J]. IEEE Urban Remote Sensing Joint Event,2009,1-8.
[28] Ke Yinghai, J. Quackenbush Lindi, Im Jungho. Synergistic Use of QuickBird Multispectral Imagery andLiDAR Data for Object-based Forest Species Classification[J]. Remote Sensing of Environment,2010,114(6):1141-1154.
[29] Takeshi Sasaki, Junichi Imanishi, Keiko Ioki, et al. Object-based Classification of Land Cover and TreeSpecies by Intergrating Airborne LiDAR and High Spatial Resolution Imagery Data[J]. InternationalConsoritium of Landscape and Ecological Engineering and Springer,2011,8(2):157-171.
[30] Mariano García, David Ria o, Emilio Chuvieco, et al. Mutispectral and LiDAR Data Fusion for FuelType Mapping Us ing Support Vector Machine and Decision Rules[J]. Remote Sensing of Enviroment,2011,115(6):1369-1379.
[31] Kotez B., Morsdort F., Curt T. Fusion of Imaging Spectrometer and Lidar Data Us ing Support VectorMachine for Land Cover Classification in The Context of Forest Fire Management[C]. Proceedings of theISPRS Commission Ⅶ, WG1,2008.
[32] María C. Alonso, José A. Malpica. Classification of Multispectral High-Resolution Satellite ImageryUsing LiDAR Elevation Data[J]. Advances in Visual Computing, PTⅡ, Proceedings,2008,5359:85-94.
[33] A. Arquero, E. Martínez. Analysis of Thematic Classified Aerial Images through Multispectral andLiDAR Data[J]. IEEE Latin America Transactions,2011,9(1):1-9.
[34] Rottensteiner F., Jansa J. Automatic Extraction of Buildings from LiDAR Data and Aerial Images[C].Proceedings of the ISPRS Commission Ⅳ Symposium in Ottawa, International Archives ofPhotogrammetry and Remote Sensing,2002, XXXIV/4,569-574.
[35] Rottensteiner F., Trinder J., Clode S., et al. Using The Dempster Shafer Method for The Fusion of LiDARData and Multi-spectral Image for Building Detection[J]. Information Fusion,2004,6(4):283-300.
[36] Amin P.Charaniya, Roberto M, Suresh K.Lodha. Supervised Parametric Classification of Aerial LiDARData[J]. Computer Vision and Pattern Recognition Workshop,2004,25-32.
[37] Suresh K. Lodha, Edward J. Kreps, David P. Helmbold, et al. Aerial LiDAR Data Classification Us ingSupport Vector Machines(SVM)[C]. IEEE Proceedings of the Third International Conference on3DData Processing Visualization and Transmission(3DPVT),2006,567-574.
[38] Suresh K. Lodha, Darren M. Fitzpatrick, David P. Helmbold. Aerial LiDAR Data Classification Us ingAdaBoost[C]. IEEE Proceedings of the Sixth International Conference on3D Digital Imaging andModeling(3DIM),2007,435-442.
[39] Secord J., Zakhor A. Tree Detection in Aerial LiDAR and Image Data[C]. IEEE International Conferenceon Image Processing, ICIP,2006:2317-2320.
[40] Bartels Marc, Wei Hong, Ferryman James. Analysis of LiDAR Data Fused with Co-Registered Bands[C].Proceedings of the IEEE International Conference on Video and Signal Based Surveillance,2006,60-60.
[41] Bartels Marc, Wei Hong. Rule-based Improvement of Maximum Likelihood Classification LiDAR DataFused with Co-Registered Bands[C]. Annual Conference of the Remote Sensing and PhotogrammetrySociety, Cambridge, United Kingdom,2006.
[42] Cao Yang, Zhao Huijie, Li Na. Land-Cover Classification by Airborne LiDAR Data Fused with AerialOptical Images[J]. International Workshop on Multi-Platform/Multi-Sensor Remote Sensing andMapping(M2RSM),2011, pp1-6.
[43] Wang Xin, Luo Yiping, Jiang Ting, et al. A New Classification Method for LiDAR Data Based onUnbalance Support Vector Machine[C]. International Symposium of Image and Data Fusion(ISIDF),2011:1-4.
[44]张小红.机载激光雷达测量技术理论与方法[M].武汉:武汉大学出版社,2007.
[45]梁欣廉,张继贤,李海涛.一种应用于城市区域的自适应形态学滤波方法[J].遥感学报,2007,11(2):276-281.
[46]李勇,吴华意.基于形态学梯度的机载激光扫描数据滤波方法[J].遥感学报,2008,12(4):633-639.
[47]隋立春,张熠斌,柳艳,等.基于改进的数学形态学算法的LiDAR点云数据滤波[J].测绘学报,2010,39(4):390-396.
[48]罗伊萍,姜挺,王鑫,等.基于数学形态学的LiDAR数据滤波新方法[J].测绘通报,2011,(3):15-19.
[49]沈晶,刘纪平,林祥国.用形态学重建方法进行机载LiDAR数据滤波[J].武汉大学学报:信息科学版,2011,36(2):167-175.
[50]闫利,张毅.基于法向量模糊聚类的道路面点云数据滤波[J].武汉大学学报:信息科学版,2007,32(12):1119-1122.
[51]蒋晶珏,张祖勋,明英.复杂城市环境的机载LiDAR点云滤波[J].武汉大学学报:信息科学版,2007,32(5):402-405.
[52]成晓倩,马洪超,赵红强,等.一种基于区域增长的机载LiDAR滤波[J].测绘科学,2010,35(1):61-63.
[53]周晓明.机载激光雷达点云数据滤波算法的研究与应用[D].郑州:信息工程大学,2011.
[54]黄先锋,李卉,王潇,等.机载LiDAR数据滤波方法评述[J].测绘学报,2009,38(5):466-469.
[55]刘经南,张小红.利用激光强度信息分类激光扫描测高数据[J].武汉大学学报:信息科学版,2005,30(3):189-192.
[56]蒋晶珏. LiDAR数据基于点集的表示与分类[D].武汉:武汉大学,2006.
[57]杨海全,余洁,秦昆,等.基于知识的LiDAR数据地物提取研究[J].测绘通报,2006,(12):9-15.
[58]刘峰,龚健雅.基于3D LiDAR数据的城区植被识别研究[J].地理与地理信息科学,2009,25(6):5-8.
[59]乔纪纲,刘小平,张亦汉.基于LiDAR高度纹理和神经网络的地物分类[J].遥感学报,2011,15(3):546-553.
[60]苏伟,李京,陈云浩,等.基于多尺度影像分割的面向对象城市土地覆被分类研究[J].2007,11(4):521-530.
[61]余柏蒗,刘红星,吴健平.一种应用机载LiDAR数据和高分辨率遥感影像提取城市绿地信息的方法[J].中国图象图形学报,2010,15(5):782-789.
[62]管海燕,邓非,张剑清,等.面向对象的航空影像与LiDAR数据融合分类[J].武汉大学学报:信息科学版,2009,34(7):830-833.
[63]袁夏,赵春霞,张浩峰,等.基于点云数据的自然地形分类算法[J].南京理工大学学报(自然科学版),2010,34(2):222-237.
[64]杨耘,隋立春.面向对象的LiDAR数据多特征融合分类[J].测绘通报,2010,(8):11-14.
[65]罗伊萍. LiDAR数据滤波和影像辅助提取建筑物[D].郑州:信息工程大学,2010.
[66]钟良. LiDAR同机影像辅助点云分类相关技术研究[D].武汉:武汉大学,2011.
[67] Franz Rottensteiner, Caroline Baillard, Gunho Sohn, et al. ISPRS Test Project on Urban Classification and3D Building Reconstruction[EB/OL]. ISPRS-Commission Ⅲ, Working Group Ⅲ/4,2011. URL:http://www.commission3.isprs.org/wg4/ComplexScenes.pdf.
[68] Kornus W., Ruiz A. Strip Adustment of LiDAR Data[J]. International Archives of Photogrammetry andRemote Sensing,2003,34(3/w):47-50.
[69] Ayman Fawzy Habib, Rita Wai Ting Cheng, Eui-Myoung Kim, et al. Automatic Surface Matching for TheRegistration of LiDAR Data and MR Imagery[J]. ETRI Journal,2006,28(2):162-174.
[70]姚春静.机载LiDAR点云数据与遥感影像配准方法的研究[D].武汉:武汉大学,2010.
[71]张帆,黄先锋,李德仁.激光扫描与光学影像数据配准的研究进展[J].测绘通报,2008,(2):7-10.
[72] ZHANG K, CHEN S C, WHITMAN D, et al. A Progressive Morphological Filter for RemovingNonground Measurement from LiDAR Data[J]. IEEE Transactions on Geoscience and Remote Sensing,2003,41(4):872-882.
[73] Axelsson P. DEM Generation from Laser Scanner Data Using Adaptive TIN Models[J]. InternationalArchives of Photogrammetry, Remote Sensing and Spatial Information Science,1999,33(B4/1):110-117.
[74] Sithole G. Segmentation and Classification of Airborne Laser Scanner[D]. Delft University of Technology,2005.
[75] BAO Yunfei, CAO Chunxiang, CHANG Chaoyi, et al. Segmentation to The Point Clouds of LiDAR DataBased on Change of Kurtosis[C]. International Symposium on Photoelectronic Detection and Imaging:Image Processing,2007,6623:1N-7.
[76] R.O. Duda, P.E. Hart, D.G. Stork. Pattern Classification[M]. New York:Wiley,2001.
[77]梁欣廉,张继贤,李海涛,等.激光雷达应用中的几种数据表达方式[J].遥感信息,2005,6:60-64.
[78] M. Alexa, J. Behr, D. Cohen-Or, et al. Point Set Surfaces[J]. IEEE Visualization2001,2001:21-28.
[79] Nina Amenta, Marshall Bern, Manolis Kamvysselis. A New Voronoi-Based Surface ReconstructionAlgorithm[J]. Siggraph’98,1998,415-421.
[80] Mattis Andersson, Joachim Giesen, Mark Pauly, et al. Bounds on The k-Neighborhood for LocallyUniformly Sampled Surfaces[C]. Proceedings of the Eurographics Symposium on Point-Based Graphics,2004:167-171.
[81] J.L. Bentley. Multidimensional Binary Search Trees Used for Associative Searching[J]. Communicationsof the ACM,1975,18(9):509-517.
[82] S. Arya, H. A. Fu. Expected-case Complexity of Approximate Nearest Neighbor Searching[J]. SIAMJournal on Computing,2003,32(2):793-815.
[83] Maas H G. The Potential of Height Texture Measurement for the Segmentation of Airborne LaserScanning Data[C]. The4thInternational Airborne Remote Sensing Conference and Exhibition/21stCanadian Symposium on Remote Sensing, Ottawa, Ontario, Canada,1999a.
[84] Huang J., Menq C H. Automatic Data Segmentation for Geometric Feature Extraction from Unorganized3-D Coordinate Points[J]. IEEE Transactions on Robotics and Automation(S1042-296X),2001,17(3):268-279.
[85]刘信伟,靖常峰,罗德利,等.一种提高三维点云特征点提取精度的方法探讨[J].城市勘测,2013,(1):9-11.
[86] Michael Garland. Quadric-Based Polygonal Surface Simplication[D]. Ph.D. thesis,1999.
[87]解亚龙.应用高分辨率彩红外DMC影像进行昆明市城区绿化信息提取[D].昆明:昆明理工大学,2006.
[88]田野,徐恒力,刘双,等.基于归一化植被指数变化分级的千山植被变化[J].中国水土保持,2010,(1):25-28.
[89]王晶,白雪,邓晓曲,等.基于NDVI的三峡大坝岸边植被时空特征分析[J].地球信息科学,2008,10(6):808-815.
[90]武永峰,李茂松,刘布春,等.基于NOAA NDVI的中国植被绿度始期变化[J].地理科学进展,2008,27(6):32-40.
[91]周廷刚,郭达志,陶康华. NCIVI及其在城市绿化航空遥感调查中的应用—以宁波市为例[J].城市环境与城市生态,2003,16(1):25-27.
[92]黄昕.高分辨率遥感影像多尺度纹理、形状特征提取与面向对象分类研究[D].武汉:武汉大学,2009.
[93] R. M. Haralick, K. Shanmugam, I. Dinstein. Textural Feature for Image Classification[J]. IEEE Trans. OnSystems, Man and Cybernetics,1973,3(6):610-621.
[94] Ohanian P P, Dubes R C. Performance Evaluation for Four Class of Texture Features[J]. PatternRecognition,1992,25:819-833.
[95]贾永红.数字图像处理[M].武汉:武汉大学出版社,2003.
[96] Benediktsson J. A., Swain P. H., Ersoy O. K. Neural Network Approaches Versus Statistical Methods inClassification of Multisource Remote Sensing Data[J]. IEEE Transactions on Geoscience and RemoteSensing,1990,28:540-552.
[97] C. Cortes, V. Vapnik. Support Vector Networks[J]. Machine Learning,1995,20:273-295.
[98] V.N. Vapnik, A.J. Hervonenkis. On The Uniform Convergence of Relative Frequencies of Events to TheirProbabilities[J]. Theory of Probability and Applications,1971,16:264-280.
[99] V.N. Vapnik, A.J. Chervonenkis. Ordered Risk Minimization(Ⅰand Ⅱ)[J]. Automation and RemoteControl,1974,34:1226-1235and1403-1412.
[100] V.Vapnik, A. Chervonenkis. Theory of Pattern Recognition[M]. Nauka, Moscow,1974.
[101] V.N. Vapnik. Estimation of Dependences Based on Empirical Data[M]. Springer-Verlag, Berlin,1982.
[102] V.N. Vapnik, E. Levin, Y.L. Cunn. Measuring the VC Dimension of A Learning Machine[J]. NeuralComputation,1994,6:851-876.
[103] B.E. Boser, I.M. Guyon, V.N. Vapnik. A Training Algorithm for Optimal Margin Classifiers[C]. InProceedings of The5thAnnual ACM Workshop on Computational Learning Theory,1992,:144-152.
[104] V. Vapnik. The Nature of Statistical Learning Theory[M]. Springer-Verlag, New York, NY,1995.
[105]路威.面向目标探测的高光谱影像特征提取与分类技术研究[D].郑州:信息工程大学,2005.
[106] Vapnik N.V.著;许建华,张学工译.统计学习理论[M].北京:电子工业出版社,2004:274-322.
[107] S.S. Keerthi, C.-J. Lin. Asymptotic Behaviors of Support Vector Machines with Gaussian Kernel[J].Neural Computation,2003,15(7):1667-1689.
[108]杨国鹏.基于机器学习方法的高光谱影像分类研究[D].郑州:信息工程大学,2010.
[109] H.-T. Lin, C.-J. Lin. A Study on Sigmoid Kernels for SVM and The Training of Non-PSD Kernels bySMO-type Methods[R]. Technical Report, Department of Computer Science, National Taiwan University,2003. URL http://www.csie.ntu.edu.tw/~cjlin/papers/tanh.pdf.
[110] C.-C. Chang, C.-J. Lin. LIBSVM: A Library for Support Vector Machines[J]. ACM Transactions onIntelligent Systems and Technology,2:27:1-27:27,2011. Software available athttp://www.csie.ntu.edu.tw/~cjlin/libsvm.
[111] C.-C. Chang, C.-J. Lin. LIBSVM: A Library for Support Vector Machines[R]. Technical Report,Department of Computer Science, National Taiwan University, Initial Version:2001, Last Updated: May20,2011. URL http://www.csie.ntu.edu.tw/~cjlin/papers/libsvm.pdf.
[112] C.-W. Hsu, C.-J. Lin. A Comparison of Methods for Multi-class Support Vector Machines[J]. IEEETransactions on Neural Networks,2002,13(2):415-425.
[113] Grejner-Brzezinska, D.A., Toth, C. Deriving Vehicle Topology and Attribute Information overTransportation Corridors from LiDAR Data[C]. Proceedings, ION59thAnnual Meeting, June23-25,Albuquerque, New Mexico,2003:404-410.
[114] Toth C., Grejner-Brzezinska D. Vehicle Classification from LiDAR Data to Support Traffic FlowEstimates[C]. Proceedings of3rdInternational Sysposium on Mobile Mapping Technology, Kunming,China, March29-31,2004.
[115] Toth C., Grejner-Brzezinska D., Moafipoor S. Presise Vehicle Topology and Road Surface ModelingDerived from Airborne LiDAR Data[C]. The60thAnnual Meeting of ION2004, Dayton, OH, June7-9,2004.
[116] Wei Yao, Stefan Hinz, Uwe Stilla. Automatic Vehicle Extraction from Airborne LiDAR Data of UrbanAreas Aaided by Geodesic Morphology[J]. Pattern Recognition Letters,2010,31(10):1100-1108.
[117] Quinlan J. R. Induction of Decision Tree[J]. Machine Learning,1986,1(1):81-106.
[118]龙际珍,任海叶,易华容.一种改进决策树算法的探讨[J].株洲师范高等专科学校学报,2006,11(2):64-66.
[119] Nelson R., Krabill W., Maaclean G. Determining Forest Canopy Characteristics Using Airborne LaserData[J]. Remote Sensing of Environment,1984,15(3):201-212.
[120] Hyypp J. Development and Feasibility of Airborne Ranging Radar for Forest Assessment[D]. PhDThesis, Helsinki University of Technology, Laboratory of Space Technology,1993.
[121] Hyypp J., Hallikainen M. A Helicopter-borne Eight-channel Ranging Scatterometer for RemoteSensing[J]. IEEE Transactions on Geoscience and Remote Sensing,1993,31(1):170-179.
[122] Hyypp J., Hyypp H., Leckie D. et al. Review of Methods of Small-footprint Airborne Laser Scanningfor Extracting Forest Inventory Data in Boreal Forests[J]. International Journal of Remote Sensing,2008,29(5):1339-1366.
[123] Hyypp J., Holopainen M., Olsson H. Laser Scanning in Forests[J]. Remote Sensing,2012,4(10):2919-2922.
[124] Brandtberg T., Warner T., Landenberger R., et al. Detection and Analysis of Individual Leaf-off TreeCrowns in Small Footprint, High Sampling Density LiDAR Data from The Eastern Deciduous Forest inNorth America[J]. Remote Sensing of Environment,2003,85(3):290-303.
[125] Holmgren J., Persson A. Identifying Species of Individual Trees Using Airborne Laser Scanning[J].Remote Sensing of Environment,2004,90(4):415-423.
[126] Moffiet T., Mengersen K., Witte C., et al. Airborne Laser Scanning: Exploratory Data Analysis IndicatesPotential Variables for Classification of Individual Trees or Forest Stands According to species[J]. ISPRSJournal of Photogrammetry and Remote Sensing,2005,59(5):289-309.
[127] Liang X., Hyypp J., Matikainen L. Deciduos-coniferous Tree Classification Us ing Difference betweenFirst and Last Pulse Laser Signatures[C]. International Archives of Photogrammetry, Remote Sensing andSpatial Information Science, ISPRS,2007,3(Part3/W52):253-257.
[128] Kim S. Individual Tree Species Identification Us ing LiDAR-derived Crown Structures and IntensityData[D]. PhD Thesis, College of Forest Resouces, University of Washinton,2007.
[129] rka H.O., N sset E., Bollands s O.M. Classifying Species of Individual Trees by Intensity andStructure Features Derived From Airborne Laser Scanning Data[J]. Remote Sensing of Environment,2009,113(6):1163-1174.
[130] ZHANG Z., LIU X. Support Vector Machines for Tree Species Identification Using LiDAR-derivedStructure and Intensity Variables[J]. GeoCarto International,2012, pp1-15.
[131] Brandtberg T. Individual Tree-based Species Classification in High Spatial Resolution Aerial Images ofForests Using Fuzzy Sets[J]. Fuzzy Sets and Systems,2002,132(3):371-387.
[132] Bohlin J., Olsson H., Olofsson K., et al. Tree Species Discrimination by Aid of Template MatchingApplied to Digital Air Photos[C]. Proceedings of The International Workshop on3D Remote Sensing inForestry,2006, pp199-203.
[133] Persson., Holmgren J., S derman U. Identification of Tree Species of Individual Trees by CombiningVery High Resolution Laser Data with Multi-spectral Images[C]. Proceedings of The InternationalWorkshop3D Remote Sensing in Forestry,2006, pp91-96.
[134] Packalén P., Maltamo M. Predicting The Plot Volume by Tree Species Using Airborne Laser Scanningand Aerial Photographs[J]. Forest Science,2006,52(6):611-622.
[135] Koetz B., Morsdorf F., van der Linden, et al. Multi-source Land Cover Classification for Forest FireManagement Based on Imaging Spectrometry and LiDAR Data[J]. Forest Ecology and Management,2008,256(3):263-271.
[136] White R. A., Dietterick B. C. Use of LiDAR and Multispectral Imagery to Determine Conifer Mortalityand Burn Severity Following the Lockheed Fire[C]. Proceedings of Coast Redwood Forests in aChanging California: A Symposium for Scientists and Managers,2012, pp667-675.
[137]赵峰,李增元,王韵晟,等.机载激光雷达(LiDAR)数据在森林资源调查中的应用综述[J].遥感信息,2008(1):106-110.
[138]庞勇,赵峰,李增元,等.机载激光雷达平均树高提取研究[J].遥感学报,2008,12(1):152-158.
[139]周淑芳.基于机载LiDAR与航空像片的单木树高提取研究[D].哈尔滨:东北林业大学,2007.
[140]庞勇,李增元.基于机载激光雷达的小兴安岭温带森林组分生物量反演[J].植物生态学报,2012,36(10):1095-1105.
[141]骆社周.激光雷达遥感森林叶面积指数提取方法研究与应用[D].北京:中国地质大学,2012.
[142]刘丽娟.基于机载LiDAR和高光谱融合的森林参数反演研究[D].哈尔滨:东北林业大学,2011.
[143]赵旦.基于激光雷达和高光谱遥感的森林单木关键参数提取[D].北京:中国林业科学研究院,2012.
[144] Lillesand T.M., Kiefer R.W., Chipman J.W. Remote Sensing and Image Interpretation[M]. John Wiley,New York,2008.
[145] Kim S., McGaugher R.J., Andersen, H.-E., et al. Tree Species Differentiation Using Intensity DataDerived From Leaf-on and Leaf-off Airborne Laser Scanning Data[J]. Remote Sensing of Environment,2009,113:1575-1586.
[146] Korpela I., rka H.O., Hyypp c J., et al. Range and AGC Normalization in Airborne Discrete-returnLiDAR Intensity Data for Forest Canopies[J]. ISPRS Journal of Photogrammetry and Remote Sensing,2010,65:369-379.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |