浏览全部资源
扫码关注微信
Published： 2019-7 ，
Accepted： 16 March 2018
扫 描 看 全 文
马振宇, 庞勇, 李增元, 卢昊, 刘鲁霞, 陈博伟. 2019. 地基激光雷达森林近地面点云精细分类与倒木提取. 遥感学报, 23(4): 743–755
Ma Z Y, Pang Y, Li Z Y, Lu H, Liu L X and Chen B W. 2019. Fine classification of near-ground point cloud based on terrestrial laser scanning and detection of forest fallen wood. Journal of Remote Sensing, 23(4): 743–755
本文利用地基激光雷达实现天然林区近地面点云数据的精细分类和倒木提取。对大兴安岭天然林区的3个倒木样地进行了近地面1.3 m以内点云精细分类和倒木信息提取。为避免点云密度差异和遮挡的形态特征，点云分类时基于自适应临近搜索法计算团块协方差特征值构造3D和2D特征。使用
k
临近递增的团块协方差特征值得到的线性特征、面状特征和发散状特征构造最大熵函数，用最大熵函数取得最大值时的临近点云计算特征参数，根据递归特征排除法(RFE)筛选重要变量进行随机森林分类。利用自适应kNN特征得到3块研究样地(A、B、C)的分类总体精度分别为93.17%、94.52%、95.16%；固定
k
临近搜索时，总体精度分别为92.65%、89.09%、92.99%，表明自适应kNN搜索方法使分类精度有一定提高。提取倒木点云去噪处理后进行随机抽样一致圆柱拟合，根据轴线方向进行圆柱的筛选与合并，实现倒木的识别，样地倒木识别率为100%。
Terrestrial Laser Scanning (TLS) can effectively describe complex forest scenes. This study aimed to classify ground point cloud within the height of 1.3 m into ground
vegetation
fallen wood
and standing trunk based on the TLS obtained from fallen wood plots in Daxing’anling. Fallen wood cloud point was segmented and merged. The optimal 3D neighborhood of each individual point was calculated through the Shannon entropy constructed by linearity
planarity
and scattering to avoid the difference in cloud density and the morphological characteristics introduced by occlusion. Shannon entropy could be maximized across the increasing kNN with an interval of 5 points. The optimal neighborhood size was used to compute the covariance eigenvalues for constructing 3D and 2D features. Key features were selected following the recursive feature elimination criteria
and a random forest classification algorithm was used to classify the points. Noise removal approach was applied to the fallen wood points classified by self-adjusting kNN features
and random sample consensus (RANSAC) segmentation was implemented to segment cylinders. Fallen wood cylinders were selected and merged depending on the axis direction less than 12° and the distance less than 0.1 m between each other. The overall classification accuracies of self-adjusting kNN method in plots A
B
and C were 93.17%
94.52%
and 95.16%
respectively
and corresponding Kappa coefficients were 0.8771
0.9145
and 0.9242
respectively. The overall accuracies of non-self-adjusting kNN were 92.65%
89.09%
and 92.99%
and the Kappa coefficients were 0.8684
0.8909
and 0.9299. Point cloud of plots B and C was classified using the model we trained using plot A. The classification accuracies of plots B and C were 62.38% and 59.80%
and the user precisions of fallen wood point cloud were 79.31% and 48.06%. All fallen woods had the same number as the ground measurement
and the parameters of fallen wood could be estimated roughly. Compared with the non-self-adjusting kNN method
the near-ground point cloud classification accuracy was improved by the self-adjusting kNN point cloud feature. Classification of plots B and C using the training result of plot A suggested that the selected key features in the complex forest could explain the dependent variable well. RANSAC could effectively segment the cylinder and estimate the parameters of the fallen wood. This research is significant for extracting parameters of the existing work. Further ecological research will be considered accordingly.
地基激光雷达点云倒木随机森林分类随机抽样一致
Terrestrial Laser Scanning (TLS)point cloudfallen woodrandom forest classificationRandom Sample Consensus (RANSAC)
Breiman L. 2001. Random forests. Machine Learning, 45(1): 5–32
Carmona M R, Armesto J J, Aravena J C and Pérez C A. 2002. Coarse woody debris biomass in successional and primary temperate forests in Chiloé Island, Chile. Forest Ecology and Management, 164(1/3): 265–275
Cornaby B W and Waide J B. 1973. Nitrogen fixation in decaying chestnut logs. Plant and Soil, 39(2): 445–448
Fischler M A and Bolles R C. 1981. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Communications of the ACM, 24(6): 381–395
Granitto P M, Furlanello C, Biasioli F and Gasperi F. 2006. Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products. Chemometrics and Intelligent Laboratory Systems, 83(2): 83–90
Kankare V, Holopainen M, Vastaranta M, Puttonen E, Yu X W, Hyyppä J, Vaaja M, Hyyppä H and Alho P. 2013. Individual tree biomass estimation using terrestrial laser scanning. ISPRS Journal of Photogrammetry and Remote Sensing, 75: 64–75
Király G and Brolly G. 2007. Tree height estimation methods for terrestrial laser scanning in a forest reserve//International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. Finland: ISPRS: 211-215
Lalonde J F, Vandapel N, Huber D F and Hebert M. 2006. Natural terrain classification using three‐dimensional ladar data for ground robot mobility. Journal of Field Robotics, 23(10): 839–861
Liang X L, Litkey P, Hyyppä J, Kaartinen H, Vastaranta M and Holopainen M. 2012. Automatic stem mapping using single-scan terrestrial laser scanning. IEEE Transactions on Geoscience and Remote Sensing, 50(2): 661–670
Lindberg E, Hollaus M, Mücke W, Fransson J E S and Pfeifer N. 2013. Detection of lying tree stems from airborne laser scanning data using a line template matching algorithm. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, II-5/W2: 169–174
刘鲁霞. 2014. 机载和地基激光雷达森林垂直结构参数提取研究. 北京: 中国林业科学研究院
Liu L X. 2014. Retrieving Vertical Structural Parameters of Forest Using Terrestrial and Airborne Laser Scanning Data. Beijing: Chinese Academy of Forestry
Liu L X, Pang Y, Li Z Y, Si L and Liao S X. 2017. Combining airborne and terrestrial laser scanning technologies to measure forest Understorey volume. Forests, 8(4): 111
Ma L X, Zheng G, Eitel J U H, Moskal L M, He W and Huang H B. 2016. Improved Salient feature-based approach for automatically separating photosynthetic and nonphotosynthetic components within terrestrial Lidar point cloud data of forest canopies. IEEE Transactions on Geoscience and Remote Sensing, 54(2): 679–696
Mallet C, Bretar F, Roux M, Soergel U and Heipke C. 2011. Relevance assessment of full-waveform Lidar data for urban area classification. ISPRS Journal of Photogrammetry and Remote Sensing, 66(S6): S71–S84
Moskal L M and Zheng G. 2011. Retrieving forest inventory variables with terrestrial laser scanning (TLS) in urban heterogeneous forest. Remote Sensing, 4(1): 1–20
娜丽. 2015. 内蒙古大兴安岭典型森林群落结构与倒木特征研究. 呼和浩特: 内蒙古农业大学
Na L. 2015. Typical forest community structure and fallen log characteristics in Inner Mongolia greater Khingan mountains. Hohhot: Inner Mongolia Agricultural University
Nyström M, Holmgren J, Fransson J E S and Olsson H. 2014. Detection of windthrown trees using airborne laser scanning. International Journal of Applied Earth Observation and Geoinformation, 30: 21–29
Olofsson K, Holmgren J and Olsson H. 2014. Tree stem and height measurements using terrestrial laser scanning and the RANSAC algorithm. Remote Sensing, 6(5): 4323–4344
Polewski P, Yao W, Heurich M, Krzystek P and Stilla U. 2015. Detection of fallen trees in ALS point clouds using a Normalized Cut approach trained by simulation. ISPRS Journal of Photogrammetry and Remote Sensing, 105: 252–271
Pyle C and Brown M M. 1999. Heterogeneity of wood decay classes within hardwood logs. Forest Ecology and Management, 114(2/3): 253–259
Rowell E M, Seielstad C A and Ottmar R D. 2016. Development and validation of fuel height models for terrestrial Lidar – RxCADRE 2012. The International Journal of Wildland Fire, 25(1): 38–47
Rubino D L and McCarthy B C. 2003. Evaluation of coarse woody debris and forest vegetation across topographic gradients in a southern Ohio forest. Forest Ecology and Management, 183(1/3): 221–238
Sandberg D V, Riccardi C L and Schaaf M D. 2006. Fire potential rating for wildland Fuelbeds using the fuel characteristic classification system. Canadian Journal of Forest Research, 37(12): 2456–2463
Wang D, Hollaus M, Puttonen E and Pfeifer N. 2016. Automatic and self-adaptive stem reconstruction in landslide-affected forests. Remote Sensing, 8(12): 974
Weinmann M, Jutzi B and Mallet C. 2014. Semantic 3D scene interpretation: a framework combining optimal neighborhood size selection with relevant features. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, II-3: 181–188
Weinmann M, Urban S, Hinz S, Jutzi B and Mallet C. 2015. Distinctive 2D and 3D features for automated large-scale scene analysis in urban areas. Computers and Graphics, 49: 47–57
辛魏巍. 2012. 大兴安岭兴安落叶松原始林倒木特征及其更新机制研究. 呼和浩特: 内蒙古农业大学
Xin W W. 2012. Research on Daxing’anling Larix Regeneration of Fallen Tree Characteristics and Update Mechanism. Hohhot: Inner Mongolia Agricultural University.
杨丽韫, 代力民, 张扬建. 2002. 长白山北坡暗针叶林倒木贮量和分解的研究. 应用生态学报, 13(9): 1069–1071
Yang L Y, Dai L M and Zhang Y J. 2002. Storage and decomposition of fallen wood in dark coniferous forest on the north slope of Changbai Mountain. Chinese Journal of Applied Ecology, 13(9): 1069–1071
雍凯. 2008. 随机森林的特征选择和模型优化算法研究. 哈尔滨: 哈尔滨工业大学
Yong K. 2008. Research on Feature Selection and Model Optinization of Random Forest. Harbin: Harbin Institute of Technology
赵英时. 2013. 遥感应用分析原理与方法. 北京: 科学出版社
Zhao Y S. 2013. Remote Sensing Application Analysis Principles and Methods. Beijing: Science Press
Zheng G, Moskal L M and Kim S H. 2013. Retrieval of effective leaf area index in heterogeneous forests with terrestrial laser scanning. IEEE Transactions on Geoscience and Remote Sensing, 51(2): 777–786
相关文章
相关作者
相关机构
京公网安备11010802024621