机载激光雷达人工林单木分割方法比较和精度分析
|
摘要
【目的】研究分水岭算法、四次多项式拟合法和基于点云的距离判别聚类法对人工林单木分割的适用性,分析3种方法对人工林单木分割的精度,探索进行单木分割时3种方法关键参数的最优选择。【方法】结合地面实测数据和目视解译方法,计算单木探测率、准确率和F得分,比较分水岭算法、四次多项式拟合法和基于点云的距离判别聚类法的单木分割精度,并通过改变栅格化冠层高度模型(CHM)的分辨率及调整基于点云的距离判别聚类法的距离阈值,分别对3种方法进行单木提取效果的敏感性分析。【结果】1)分水岭算法、四次多项式拟合法和基于点云的距离判别聚类法对人工林单木总体分割精度较高(F=0.76～0.83); 2)对于"复杂林型"样地,基于点云的距离判别聚类法的分割精度最高(F=0.78),优于分水岭算法(F=0.74)和四次多项式拟合法(F=0.53);对于"中等复杂林型"样地,基于点云的距离判别聚类法的分割精度最高(F=0.89),优于分水岭算法(F=0.84)和四次多项式拟合法(F=0.75);对于"简单林型"样地,基于点云的距离判别聚类法(F=0.89)、分水岭算法(F=0.89)和四次多项式拟合法(F=0.93)的分割精度都较高; 3)敏感性分析结果表明,当CHM分辨率为0.5 m×0.5 m时,分水岭算法和四次多项式拟合法的分割精度最高;当基于点云的距离判别聚类法的距离阈值近似样地平均冠幅半径时,其分割精度最高。【结论】对多种类型样地进行单木分割,体现了分水岭算法、四次多项式拟合法和基于点云的距离判别聚类法对人工林单木分割的适用性;结合多种类型样地充分评估并比较了3种方法对人工林单木分割的精度;通过对3种方法进行敏感性分析,阐述了进行单木分割时关键参数的最优选择。
【Objective】 This paper studies the applicability of the watershed algorithm, polynomial fitting method and Point cloud-based cluster segmentation for individual tree segmentation, analyzes the accuracy and explores the optimal selection of the key parameters of the three methods for individual tree segmentation.【Method】 The field measured and visual interpretation data were combined to calculate the individual tree detection rate, precision of detected trees and overall accuracy index. In addition, the grid canopy height model(CHM, canopy height model)resolution of the watershed algorithm and polynomial fitting was changed and the distance threshold of point cloud-based cluster segmentation was adjusted to perform the sensitivity analysis of individual tree extraction.【Result】 The result showed that: 1) The three segmentation methods used to segment individual trees in planted forests have relatively high overall accuracy(overall accuracy F=0.76-0.83).2) For "complex forest type" samples, point cloud-based cluster segmentation has a higher extracting accuracy(overall accuracy F=0.78)than the watershed algorithm(overall accuracy F=0.74)and polynomial fitting(overall accuracy F=0.53); for the "moderately complex forest type" samples, point cloud-based cluster segmentation has a higher extracting accuracy(overall accuracy F=0.89)than the watershed algorithm(overall accuracy F=0.84) and polynomial fitting(overall accuracy F=0.75); for the "simple forest type" samples, point cloud-based cluster segmentation(overall accuracy F=0.89), the watershed algorithm(overall accuracy F=0.89)and polynomial fitting(overall accuracy F=0.93)have similar precisions. 3) Sensitivity analysis result showed that when the CHM resolution is 0.5 m×0.5 m, the watershed algorithm and the polynomial fitting segmentation accuracy has the highest accuracy, whereas when the threshold approximately equals to the average of the crown projection radius, the point cloud-based cluster segmentation reaches the highest precision.【Conclusion】 The individual tree segmentation of multiple types of plots reflects the applicability of the three methods to the planted forests. The accuracy of individual tree segmentation of planted forest by three methods is fully evaluated and compared with many types of plots. The sensitivities of the three methods were analyzed, and the optimal choice of key parameters during individual tree segmentation was described.
【Objective】 This paper studies the applicability of the watershed algorithm, polynomial fitting method and Point cloud-based cluster segmentation for individual tree segmentation, analyzes the accuracy and explores the optimal selection of the key parameters of the three methods for individual tree segmentation.【Method】 The field measured and visual interpretation data were combined to calculate the individual tree detection rate, precision of detected trees and overall accuracy index. In addition, the grid canopy height model(CHM, canopy height model)resolution of the watershed algorithm and polynomial fitting was changed and the distance threshold of point cloud-based cluster segmentation was adjusted to perform the sensitivity analysis of individual tree extraction.【Result】 The result showed that: 1) The three segmentation methods used to segment individual trees in planted forests have relatively high overall accuracy(overall accuracy F=0.76-0.83).2) For "complex forest type" samples, point cloud-based cluster segmentation has a higher extracting accuracy(overall accuracy F=0.78)than the watershed algorithm(overall accuracy F=0.74)and polynomial fitting(overall accuracy F=0.53); for the "moderately complex forest type" samples, point cloud-based cluster segmentation has a higher extracting accuracy(overall accuracy F=0.89)than the watershed algorithm(overall accuracy F=0.84) and polynomial fitting(overall accuracy F=0.75); for the "simple forest type" samples, point cloud-based cluster segmentation(overall accuracy F=0.89), the watershed algorithm(overall accuracy F=0.89)and polynomial fitting(overall accuracy F=0.93)have similar precisions. 3) Sensitivity analysis result showed that when the CHM resolution is 0.5 m×0.5 m, the watershed algorithm and the polynomial fitting segmentation accuracy has the highest accuracy, whereas when the threshold approximately equals to the average of the crown projection radius, the point cloud-based cluster segmentation reaches the highest precision.【Conclusion】 The individual tree segmentation of multiple types of plots reflects the applicability of the three methods to the planted forests. The accuracy of individual tree segmentation of planted forest by three methods is fully evaluated and compared with many types of plots. The sensitivities of the three methods were analyzed, and the optimal choice of key parameters during individual tree segmentation was described.
引文
曹林, 代劲松, 徐建新, 等. 2014.基于机载小光斑LiDAR技术的亚热带森林参数信息优化提取.北京林业大学学报, 36(5):13-21.(Cao L, Dai J S, Xu J X, et al. 2014.Optimized extraction of forest parameters in subtropical forests based on airborne small footprint LiDAR technology. Journal of Beijing Forestry University, 36(5):13-21. [in Chinese])
霍达, 邢艳秋, 田昕, 等. 2015. 基于机载LiDAR的四次多项式拟合法估测单木冠幅. 西北林学院学报,30(3):164-169.(Huo D, Xing Y Q, Tian X, et al. 2015. Estimating individual tree crow diameter using fourth fegree polynomial fitting method based on airborne LiDAR. Journal of Northwest Forestry University, 30(3):164-169. [in Chinese])
李增元, 刘清旺, 庞勇. 2016. 激光雷达森林参数反演研究进展. 遥感学报, 20(5): 1138-1150.(Li Z Y, Liu Q W, Pang Y. 2016. Review on forest parameters inversion using LiDAR. Journal of Remote Sensing, 20(5): 1138-1150. [in Chinese])
刘鲁霞,庞勇.2014.机载激光雷达和地基激光雷达林业应用现状.世界林业研究,27(1):49-56.(Liu L X, Pang Y. 2014. Applications of airborne laser scanning and terrestrial laser scanning to forestry. World Forestry Research, 27(1):49-56. [in Chinese])
刘清旺, 李增元, 陈尔学, 等. 2010. LIDAR点云数据估测单株木生物量.高技术通讯, 20(7): 765-770.(Liu Q W, Li Z Y, Chen E X, et al. 2010. Estimating biomass of individual trees using point cloud data of airborne LIDAR. Chinese High Technology Letters, 20(7): 765-770. [in Chinese])
刘清旺, 李增元, 陈尔学, 等. 2008.利用机载激光雷达数据提取单株木树高和树冠.北京林业大学学报, 30(6): 83-89.(Liu Q W, Li Z Y, Chen E X, et al. 2008. Extracting height and crown of individual tree using airborne LIDAR data. Journal of Beijing Forestry University, 30(6): 83-89. [in Chinese])
申鑫, 曹林, 佘光辉.2016.高光谱与高空间分辨率遥感数据的亚热带森林生物量反演.遥感学报, 20(6):1446-1460.(Shen X, Cao L, She G H.2016.Subtropical forest biomass estimation based on hyperspectral and high resolution remotely sensed data. Journal of Remote Sensing, 20(6):1446-1460. [in Chinese])
舒清态, 唐守正. 2005.国际森林资源监测的现状与发展趋势.世界林业研究, 18(3):33-37.(Shu Q T, Tang S Z.2005. The status and trend of international forest resources monitoring. Journal of Beijing Forestry University, 18(3):33-37. [in Chinese])
吴楠, 李增元, 廖声熙, 等. 2017.国内外林业遥感应用研究概况与展望. 世界林业研究, 30(6):34-40.(Wu N, Li Z Y, Liao S X, et al. 2017. Current situation and prospect of research on application of remote sensing to forestry. World Forestry Research, 30(6):34-40. [in Chinese])
Alexander C. 2009. Delineating tree crowns from airborne laser scanning point cloud data using Delaunay triangulation. International Journal of Remote Sensing, 30(14): 3843-3848.
Brandtberg T. 2007. Classifying individual tree species under leaf-off and leaf-on conditions using airborne lidar. ISPRS Journal of Photogrammetry and Remote Sensing, 61(5): 325-340.
Chen Q, Baldocchi D, Gong P, et al. 2006. Isolating individual trees in a savanna woodland using small footprint LIDAR data. Photogrammetric Engineering & Remote Sensing, 72(8):923-932.
Culvenor D S.2002.TIDA: an algorithm for the delineation of tree crowns in high spatial resolution remotely sensed imagery. Computers & Geosciences, 28(1):33-44.
Dalponte M, Coomes D A.2016.Tree-centric mapping of forest carbon density from airborne laser scanning and hyperspectral data. Methods in Ecology & Evolution, 7(10):1236-1245.
Goutte C, Gaussier E. 2005.A probabilistic interpretation of precision, recall and f-score, with implication for evaluation. International Journal of Radiation Biology & Related Studies in Physics Chemistry & Medicine, 51(5):952-952.
Kaartinen H, Hyyppä J, Yu X W, et al. 2012. An international comparison of individual tree detection and extraction using airborne laser scanning. Remote Sensing, 4(4):950-974.
Koch B, Heyder U, Weinacker H. 2006. Detection of individual tree crowns in airborne lidar data. Photogrammetric Engineering and Remote Sensing, 72(4): 357-363.
Larsen M, Eriksson M, Descombes X, et al. 2011. Comparison of six individual tree crown detection algorithms evaluated under varying forest conditions. International Journal of Remote Sensing, 32(20): 5827-5852.
Li W K, Guo Q H, Jakubowski M K, et al. 2012. A new method for segmenting individual trees from the LiDAR point cloud. Photogrammetric Engineering and Remote Sensing, 78(1): 75-84.
Meyer F, Beucher S.1990. Morphological segmentation. Journal of Visual Communication & Image Representation, 1(1):21-46.
Najman L, Couprie M, Bertrand G. 2005.Watersheds, mosaics, and the emergence paradigm. Elsevier Science Publishers B V.
Payn T, Carnus J M, Freer-Smith P, et al. 2015. Changes in planted forests and future global implications. Forest Ecology and Management, 352(4): 57-67.
Popescu S C. 2007. Estimating biomass of individual pine trees using airborne LiDAR. Biomass and Bioenergy, 31(9): 646-655.
Popescu S C, Wynne R H. 2004.Seeing the trees in the forest: using lidar and multispectral data fusion with local filtering and variable window size for estimating tree height. Photogrammetric Engineering & Remote Sensing, 70(5):589-604.
Popescu S C, Wynne R H, Nelson R F. 2003.Measuring individual tree crown diameter with LiDAR and assessing its influence on estimating forest volume and biomass. Canadian Journal of Remote Sensing, 29(5):564-577.
Reitberger J, Schnörr C, Krzystek P, et al. 2009. 3D segmentation of single trees exploiting full waveform LIDAR data. ISPRS Journal of Photogrammetry and Remote Sensing, 64(6): 561-574.
Sokolova M, Japkowicz N, Szpakowicz S. 2006. Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. AI 2006: Advances in Artificial Intelligence. Springer Berlin Heidelberg,1015-1021.
Szulecka J, Zalazar E M. 2017. Forest plantations in paraguay: historical developments and a critical diagnosis in a swot-ahp framework. Land Use Policy, 60: 384-394.
Walsworth N A, King D J.1999. Image modeling of forest changes associated with acid mine drainage. Comput Geosci,25(5):567-580.
Wang L, Gong P, Biging G S.2004. Individual tree-crown delineation and treetop detection in high-spatial-resolution aerial imagery. Photogrammetric Engineering & Remote Sensing, 351-358.
Wulder M, Niemann K O, Goodenough D G. 2000.Local maximum filtering for the extraction of tree locations and basal area from high spatial resolution imagery. Remote Sensing of Environment, 73(1):103-114.
Wulder M A, White J C, Stinson G, et al. 2010. Implications of differing input data sources and approaches upon forest carbon stock estimation. Environmental Monitoring & Assessment, 166(1/4):543-561.
Xu B, Guo Z D, Piao S L. 2010.Biomass carbon stocks in China’s forests between 2000 and 2050: a prediction based on forest biomass-age relationships. Science China Life Sciences, 53(7):776.
Yu X W, Hyyppä J, Vastaranta M, et al. 2011. Predicting individual tree attributes from airborne laser point clouds based on the random forests technique. ISPRS Journal of Photogrammetry and Remote Sensing, 66(1): 28-37.
Zhao K, Popescu S, Nelson R. 2009.LiDAR remote sensing of forest biomass: a scale-invariant estimation approach using airborne lasers. Remote Sensing of Environment,113(1):182-196.
霍达, 邢艳秋, 田昕, 等. 2015. 基于机载LiDAR的四次多项式拟合法估测单木冠幅. 西北林学院学报,30(3):164-169.(Huo D, Xing Y Q, Tian X, et al. 2015. Estimating individual tree crow diameter using fourth fegree polynomial fitting method based on airborne LiDAR. Journal of Northwest Forestry University, 30(3):164-169. [in Chinese])
李增元, 刘清旺, 庞勇. 2016. 激光雷达森林参数反演研究进展. 遥感学报, 20(5): 1138-1150.(Li Z Y, Liu Q W, Pang Y. 2016. Review on forest parameters inversion using LiDAR. Journal of Remote Sensing, 20(5): 1138-1150. [in Chinese])
刘鲁霞,庞勇.2014.机载激光雷达和地基激光雷达林业应用现状.世界林业研究,27(1):49-56.(Liu L X, Pang Y. 2014. Applications of airborne laser scanning and terrestrial laser scanning to forestry. World Forestry Research, 27(1):49-56. [in Chinese])
刘清旺, 李增元, 陈尔学, 等. 2010. LIDAR点云数据估测单株木生物量.高技术通讯, 20(7): 765-770.(Liu Q W, Li Z Y, Chen E X, et al. 2010. Estimating biomass of individual trees using point cloud data of airborne LIDAR. Chinese High Technology Letters, 20(7): 765-770. [in Chinese])
刘清旺, 李增元, 陈尔学, 等. 2008.利用机载激光雷达数据提取单株木树高和树冠.北京林业大学学报, 30(6): 83-89.(Liu Q W, Li Z Y, Chen E X, et al. 2008. Extracting height and crown of individual tree using airborne LIDAR data. Journal of Beijing Forestry University, 30(6): 83-89. [in Chinese])
申鑫, 曹林, 佘光辉.2016.高光谱与高空间分辨率遥感数据的亚热带森林生物量反演.遥感学报, 20(6):1446-1460.(Shen X, Cao L, She G H.2016.Subtropical forest biomass estimation based on hyperspectral and high resolution remotely sensed data. Journal of Remote Sensing, 20(6):1446-1460. [in Chinese])
舒清态, 唐守正. 2005.国际森林资源监测的现状与发展趋势.世界林业研究, 18(3):33-37.(Shu Q T, Tang S Z.2005. The status and trend of international forest resources monitoring. Journal of Beijing Forestry University, 18(3):33-37. [in Chinese])
吴楠, 李增元, 廖声熙, 等. 2017.国内外林业遥感应用研究概况与展望. 世界林业研究, 30(6):34-40.(Wu N, Li Z Y, Liao S X, et al. 2017. Current situation and prospect of research on application of remote sensing to forestry. World Forestry Research, 30(6):34-40. [in Chinese])
Alexander C. 2009. Delineating tree crowns from airborne laser scanning point cloud data using Delaunay triangulation. International Journal of Remote Sensing, 30(14): 3843-3848.
Brandtberg T. 2007. Classifying individual tree species under leaf-off and leaf-on conditions using airborne lidar. ISPRS Journal of Photogrammetry and Remote Sensing, 61(5): 325-340.
Chen Q, Baldocchi D, Gong P, et al. 2006. Isolating individual trees in a savanna woodland using small footprint LIDAR data. Photogrammetric Engineering & Remote Sensing, 72(8):923-932.
Culvenor D S.2002.TIDA: an algorithm for the delineation of tree crowns in high spatial resolution remotely sensed imagery. Computers & Geosciences, 28(1):33-44.
Dalponte M, Coomes D A.2016.Tree-centric mapping of forest carbon density from airborne laser scanning and hyperspectral data. Methods in Ecology & Evolution, 7(10):1236-1245.
Goutte C, Gaussier E. 2005.A probabilistic interpretation of precision, recall and f-score, with implication for evaluation. International Journal of Radiation Biology & Related Studies in Physics Chemistry & Medicine, 51(5):952-952.
Kaartinen H, Hyyppä J, Yu X W, et al. 2012. An international comparison of individual tree detection and extraction using airborne laser scanning. Remote Sensing, 4(4):950-974.
Koch B, Heyder U, Weinacker H. 2006. Detection of individual tree crowns in airborne lidar data. Photogrammetric Engineering and Remote Sensing, 72(4): 357-363.
Larsen M, Eriksson M, Descombes X, et al. 2011. Comparison of six individual tree crown detection algorithms evaluated under varying forest conditions. International Journal of Remote Sensing, 32(20): 5827-5852.
Li W K, Guo Q H, Jakubowski M K, et al. 2012. A new method for segmenting individual trees from the LiDAR point cloud. Photogrammetric Engineering and Remote Sensing, 78(1): 75-84.
Meyer F, Beucher S.1990. Morphological segmentation. Journal of Visual Communication & Image Representation, 1(1):21-46.
Najman L, Couprie M, Bertrand G. 2005.Watersheds, mosaics, and the emergence paradigm. Elsevier Science Publishers B V.
Payn T, Carnus J M, Freer-Smith P, et al. 2015. Changes in planted forests and future global implications. Forest Ecology and Management, 352(4): 57-67.
Popescu S C. 2007. Estimating biomass of individual pine trees using airborne LiDAR. Biomass and Bioenergy, 31(9): 646-655.
Popescu S C, Wynne R H. 2004.Seeing the trees in the forest: using lidar and multispectral data fusion with local filtering and variable window size for estimating tree height. Photogrammetric Engineering & Remote Sensing, 70(5):589-604.
Popescu S C, Wynne R H, Nelson R F. 2003.Measuring individual tree crown diameter with LiDAR and assessing its influence on estimating forest volume and biomass. Canadian Journal of Remote Sensing, 29(5):564-577.
Reitberger J, Schnörr C, Krzystek P, et al. 2009. 3D segmentation of single trees exploiting full waveform LIDAR data. ISPRS Journal of Photogrammetry and Remote Sensing, 64(6): 561-574.
Sokolova M, Japkowicz N, Szpakowicz S. 2006. Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. AI 2006: Advances in Artificial Intelligence. Springer Berlin Heidelberg,1015-1021.
Szulecka J, Zalazar E M. 2017. Forest plantations in paraguay: historical developments and a critical diagnosis in a swot-ahp framework. Land Use Policy, 60: 384-394.
Walsworth N A, King D J.1999. Image modeling of forest changes associated with acid mine drainage. Comput Geosci,25(5):567-580.
Wang L, Gong P, Biging G S.2004. Individual tree-crown delineation and treetop detection in high-spatial-resolution aerial imagery. Photogrammetric Engineering & Remote Sensing, 351-358.
Wulder M, Niemann K O, Goodenough D G. 2000.Local maximum filtering for the extraction of tree locations and basal area from high spatial resolution imagery. Remote Sensing of Environment, 73(1):103-114.
Wulder M A, White J C, Stinson G, et al. 2010. Implications of differing input data sources and approaches upon forest carbon stock estimation. Environmental Monitoring & Assessment, 166(1/4):543-561.
Xu B, Guo Z D, Piao S L. 2010.Biomass carbon stocks in China’s forests between 2000 and 2050: a prediction based on forest biomass-age relationships. Science China Life Sciences, 53(7):776.
Yu X W, Hyyppä J, Vastaranta M, et al. 2011. Predicting individual tree attributes from airborne laser point clouds based on the random forests technique. ISPRS Journal of Photogrammetry and Remote Sensing, 66(1): 28-37.
Zhao K, Popescu S, Nelson R. 2009.LiDAR remote sensing of forest biomass: a scale-invariant estimation approach using airborne lasers. Remote Sensing of Environment,113(1):182-196.