Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services...Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services is influenced by species diversity,tree health,and the distribution and the composition of trees.Traditionally,data on urban trees has been collected through field surveys and manual interpretation of remote sensing images.In this study,we evaluated the effectiveness of multispectral airborne laser scanning(ALS)data in classifying 24 common urban roadside tree species in Espoo,Finland.Tree crown structure information,intensity features,and spectral data were used for classification.Eight different machine learning algorithms were tested,with the extra trees(ET)algorithm performing the best,achieving an overall accuracy of 71.7%using multispectral LiDAR data.This result highlights that integrating structural and spectral information within a single framework can improve the classification accuracy.Future research will focus on identifying the most important features for species classification and developing algorithms with greater efficiency and accuracy.展开更多
对比仅包含多光谱信息、仅可实现二维土地覆盖分类的传统光学遥感数据,机载多光谱激光雷达(multispectral light detection and ranging,MS-LiDAR)的优势在于同时包含多光谱和空间信息、可实现三维土地覆盖分类,但现有的机载MS-LiDAR数...对比仅包含多光谱信息、仅可实现二维土地覆盖分类的传统光学遥感数据,机载多光谱激光雷达(multispectral light detection and ranging,MS-LiDAR)的优势在于同时包含多光谱和空间信息、可实现三维土地覆盖分类,但现有的机载MS-LiDAR数据的土地覆盖分类研究所需特征维度过高、算法复杂度高。因此,提出了一种整合空间相关性和归一化差分比率指数(Normalized Difference Ratio Index,NDRI)特征的逐步分类算法。该算法首先融合机载MS-LiDAR数据的多波段独立点云,获取兼具空间位置及其多光谱信息的单一点云数据;然后利用空间邻域增长下的地面滤波算法分离地面和非地面点;接着基于不同目标的激光反射特性差异设计将草地(树木)自地面(非地面)中分离的NDRI指数,并利用类间方差最大原则下的自适应最优NDRI指数实现地面和非地面点的精细分类;最后利用3D多数投票法优化分类结果。采用加拿大Optech Titan实测MS-LiDAR数据测试提出算法的有效性及可行性,实验结果表明:算法的平均总体精度和Kappa系数分别可达90.17%和0.861,可有效实现城区MS-LiDAR数据的三维土地覆盖分类;分步处理的方式更有利于针对具体的分离目标的特点设计简单且有效的规则,算法设计更简单、复杂度低;NDRI可为其他机器学习算法的显著性特征的设计和选择提供理论支撑。展开更多
文摘Urban tree species provide various essential ecosystem services in cities,such as regulating urban temperatures,reducing noise,capturing carbon,and mitigating the urban heat island effect.The quality of these services is influenced by species diversity,tree health,and the distribution and the composition of trees.Traditionally,data on urban trees has been collected through field surveys and manual interpretation of remote sensing images.In this study,we evaluated the effectiveness of multispectral airborne laser scanning(ALS)data in classifying 24 common urban roadside tree species in Espoo,Finland.Tree crown structure information,intensity features,and spectral data were used for classification.Eight different machine learning algorithms were tested,with the extra trees(ET)algorithm performing the best,achieving an overall accuracy of 71.7%using multispectral LiDAR data.This result highlights that integrating structural and spectral information within a single framework can improve the classification accuracy.Future research will focus on identifying the most important features for species classification and developing algorithms with greater efficiency and accuracy.
文摘对比仅包含多光谱信息、仅可实现二维土地覆盖分类的传统光学遥感数据,机载多光谱激光雷达(multispectral light detection and ranging,MS-LiDAR)的优势在于同时包含多光谱和空间信息、可实现三维土地覆盖分类,但现有的机载MS-LiDAR数据的土地覆盖分类研究所需特征维度过高、算法复杂度高。因此,提出了一种整合空间相关性和归一化差分比率指数(Normalized Difference Ratio Index,NDRI)特征的逐步分类算法。该算法首先融合机载MS-LiDAR数据的多波段独立点云,获取兼具空间位置及其多光谱信息的单一点云数据;然后利用空间邻域增长下的地面滤波算法分离地面和非地面点;接着基于不同目标的激光反射特性差异设计将草地(树木)自地面(非地面)中分离的NDRI指数,并利用类间方差最大原则下的自适应最优NDRI指数实现地面和非地面点的精细分类;最后利用3D多数投票法优化分类结果。采用加拿大Optech Titan实测MS-LiDAR数据测试提出算法的有效性及可行性,实验结果表明:算法的平均总体精度和Kappa系数分别可达90.17%和0.861,可有效实现城区MS-LiDAR数据的三维土地覆盖分类;分步处理的方式更有利于针对具体的分离目标的特点设计简单且有效的规则,算法设计更简单、复杂度低;NDRI可为其他机器学习算法的显著性特征的设计和选择提供理论支撑。
