文献类型： 外文期刊
作者： Yun, Ting 1 ; Chen, Bangqian 2 ; Li, Weizheng 3 ; Sun, Yuan 4 ; Xue, Lianfeng 1 ;
作者机构： 1.Nanjing Forestry Univ, Sch Informat Sci & Technol, Nanjing 210037, Jiangsu, Peoples R China
2.Chinese Acad Trop Agr Sci, Minist Agr, Rubber Res Inst, Danzhou Invest & Expt Stn Trop Crops, Danzhou 571737, Peoples R China
3.Nanjing Forestry Univ, Adv Anal & Testing Ctr, Nanjing 210037, Jiangsu, Peoples R China
4.Nanjing Forestry Univ, Coll Forestry, Nanjing 210037, Jiangsu, Peoples R China
5.Nanjing Forestry Univ, Joint Ctr Sustainable Forestry Studies Southern C, Nanjing 210037, Jiangsu, Peoples R China
关键词： Terrestrial Laser Scanning (TLS);Point Cloud Data (PCD);Tree organ classification;Leaf surface reconstruction
期刊名称：BULGARIAN CHEMICAL COMMUNICATIONS （ 影响因子：0.242； 五年影响因子：0.322 ）
ISSN： 0324-1130
年卷期： 2017 年 49 卷 1 期
页码：
收录情况： SCI
摘要： Terrestrial Laser Scanning (TLS) enables easy and fast Point Cloud Data (PCD) acquisition from objects, and it has been widely used in complex scene survey. However, trees have seriously irregular and complex morphology, and scanning process always be influenced by external environment variation and have occlusion effect, so quantifying the 3- D morphology structure and assessing parameters of forest stands by TLS is challenging. In order to solve these problems, we applied computer technique to improve Terrestrial Laser Scanning (TLS) performance in forestry measurement. Here, new PCD feature vectors, including shape, orientation, normal vector distribution and normal vectors of tangent plane, was proposed, and Supervised Locally Linear Embedding (SLLE) algorithm and Gaussian Mixture Model (GMM) were adopted for the feature dimensionality reduction and PCD classification as well. Hence, the algorithm efficiency was improved and various tree organs could be automatically identified. Moreover, a leaf modeling method using polynomial fitting method and Moving Least Squares (MLS) were presented to depict real foliage silhouette and eliminate ghost points, yielding accurate reconstruction of complex foliage surface. As detailed experimental comparison stated, the recognition rate remained higher than 87.51 % while our classification method was applied to different tree PCD, and accurate 3D morphological reconstruction of leaf models have similar leaf area versus manually LI-3000C measurement results. Thus, our method show promise in further exploration of utilizing TLS as an effective tool for forestry parameter retrieval.
- 相关文献
作者其他论文 更多>>
-
Synergizing a Deep Learning and Enhanced Graph-Partitioning Algorithm for Accurate Individual Rubber Tree-Crown Segmentation from Unmanned Aerial Vehicle Light-Detection and Ranging Data
作者：Zhu, Yunfeng;Chen, Bangqian;Wang, Xiangjun;Zhu, Yunfeng;Lin, Yuxuan;Yun, Ting;Yun, Ting
关键词：deep learning; graph partitioning; UAV LiDAR; individual tree-crown segmentation; rubber tree
-
Improving the accuracy of canopy height mapping in rubber plantations based on stand age, multi-source satellite images, and random forest algorithm
作者：Gao, Yuanfeng;Yun, Ting;Wang, Xincheng;Gao, Yuanfeng;Chen, Bangqian;Lai, Hongyan;Wang, Xincheng;Wang, Guizhen;Wang, Xiangjun;Wu, Zhixiang;Kou, Weili
关键词：Canopy height; Rubber plantations; Stand age; GEDI
-
Integrative cultivation pattern, distribution, yield and potential benefit of rubber based agroforestry system in China
作者：Qi, Dongling;Wu, Zhixiang;Chen, Bangqian;Zhang, Xicai;Yang, Chuan;Fu, Qingmao;Qi, Dongling;Wu, Zhixiang;Chen, Bangqian;Zhang, Xicai;Yang, Chuan;Fu, Qingmao;Qi, Dongling;Wu, Zhixiang;Chen, Bangqian;Zhang, Xicai;Yang, Chuan;Fu, Qingmao
关键词：Rubber tree (Hevea brasiliensis); Agroforestry system; Rubber intercropping; Integrative systems; Distribution
-
Utilizing Multi-Source Data and Cloud Computing Platform to Map Short-Rotation Eucalyptus Plantations Distribution and Stand Age in Hainan Island
作者：Yin, Xiong;Li, Mingshi;Lai, Hongyan;Chen, Bangqian;Kou, Weili;Chen, Yue
关键词：eucalyptus plantations; CCDC-SMA; random forest; Google Earth Engine
-
Early identification of immature rubber plantations using Landsat and Sentinel satellite images
作者：Wang, Xincheng;Gao, Yuanfeng;Yun, Ting;Wang, Xincheng;Chen, Bangqian;Gao, Yuanfeng;Wang, Guizhen;Lai, Hongyan;Wu, Zhixiang;Yang, Chuan;Dong, Jinwei;Kou, Weili;Kou, Weili
关键词：Immature rubber plantations; Early identification; Random forest; Google Earth Engine
-
Tracking changes in coastal land cover in the Yellow Sea, East Asia, using Sentinel-1 and Sentinel-2 time-series images and Google Earth Engine
作者：Liu, Yongchao;Li, Jialin;Sun, Chao;Tian, Peng;Zhang, Haitao;Liu, Yongchao;Xiao, Xiangming;Wang, Xinxin;Wang, Xinxin;Chen, Bangqian;Wang, Jie;Xiao, Xiangming;Li, Jialin
关键词：Coastal land cover; Rule-based Time Series Classification algorithm; Sentinel-1; 2 images; GEE; Yellow Sea
-
A reinterpretation of the gap fraction of tree crowns from the perspectives of computer graphics and porous media theory
作者：Zhu, Yunfeng;Li, Dongni;Yun, Ting;Fan, Jiangchuan;Zhang, Huaiqing;Eichhorn, Markus P.;Eichhorn, Markus P.;Wang, Xiangjun;Yun, Ting
关键词：volume-based gap fraction; porous media theory; fine geometric characterization; equivalent leaf thickness; computer graphics
