предыдущий|следующий

Information extraction and system construction of digital forest system based on multisource remote sensing data

  • role： First author第一作者
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Jointly Sponsored by the Institute of Remote Sensing Applications of Chinese Academy of Sciences and Beijing Normal University, Beijing Normal University, Beijing 100875, China

  • Email：xiedonghui@bnu.edu.cn
  • Introduction：谢东辉， 研究方向为定量遥感机理和遥感应用。E-mail：xiedonghui@bnu.edu.cn
XIE Donghui1,  
  • role： Corresponding author通信作者
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Jointly Sponsored by the Institute of Remote Sensing Applications of Chinese Academy of Sciences and Beijing Normal University, Beijing Normal University, Beijing 100875, China

  • Email：yili@mail.bnu.edu.cn
  • Introduction：李益， 研究方向为植被定量遥感。E-mail： yili@mail.bnu.edu.cn
LI Yi1*,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Jointly Sponsored by the Institute of Remote Sensing Applications of Chinese Academy of Sciences and Beijing Normal University, Beijing Normal University, Beijing 100875, China

ZHOU Kun1,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Jointly Sponsored by the Institute of Remote Sensing Applications of Chinese Academy of Sciences and Beijing Normal University, Beijing Normal University, Beijing 100875, China

ZHANG Zhixiang1,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Jointly Sponsored by the Institute of Remote Sensing Applications of Chinese Academy of Sciences and Beijing Normal University, Beijing Normal University, Beijing 100875, China

JIN Lin1,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Jointly Sponsored by the Institute of Remote Sensing Applications of Chinese Academy of Sciences and Beijing Normal University, Beijing Normal University, Beijing 100875, China

YAN Guangjian1,  
  • Affiliation：

    State Key Laboratory of Remote Sensing Science, Jointly Sponsored by the Institute of Remote Sensing Applications of Chinese Academy of Sciences and Beijing Normal University, Beijing Normal University, Beijing 100875, China

MU Xihan1,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

LI Wenhang2,  
  • Affiliation：

    Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China

FENG Gongyao2

реферат

Digital forestry is the foundation of forestry informationization and modernization, which can help management with scientific programming, scientific management, and scientific decision. With the development of 3S (GIS, RS, and GNSS) technology, improving the level of digital forestry becomes feasible, especially for the monitoring scale from forest-compartment level to single-tree level by using high spatial- and spectral-resolution remote sensing data and Light Detection And Ranging (LiDAR). This paper aims to develop a forestry digital system by combining the advantages of remote sensing and GIS technology, which can improve the precision management ability of forest farm.Saihanba Mechanical Forest Farm in Hebei Province, China is taken as the research area, and airborne data, including LiDAR, CCD image, and hyperspectral image, are used to study single tree segmentation and classification methods. First, an algorithm combined water shed and Connection Center Evolution methods is applied to segment each single tree based on the airborne LiDAR scanner (ALS). Then, the random forest algorithm is applied to classify the tree species of each single tree based on the combination of the 50 characteristics from ALS, CCD, and hyperspectral image. The 3D model reconstruction is also examined by using terrestrial laser scanning data, with the procedure of branch reconstruction and leaf addition. Forest scenarios are reconstructed based on each single tree model. Finally, WebGIS technology is used to develop a forestry digital system with the functions of data storage, management, query, analysis, and visualization.More than 9706 thousand single trees within the airborne flight area of 270 km2 are segmented and classified. Combined with the survey data of ground quadrats, the single tree segmentation accuracy can reach over 0.6 matching rate, and the single tree classification accuracy of four typical tree species in the study area can reach more than 97%.The information of single tree, including location, tree height, crown breadth, and the structures of branches and leaves, are extracted based on airborne and field data, which can help analyze the multiscale forest characteristics from organs (branches and leaves)-single tree-region scales. On this basis, this paper explores the forestry digitization method based on single tree information and develops a digital forestry system using WebGIS technology. The system preliminarily completes the functions of storage, management, query, analysis, and visualization of relevant data in the study area, providing reliable basic data for forest management and decision-making planning.

ключеви́че слова́

remote sensing;digital forestry;lidar;hyperspectral image;tree segmentation;classification;3D reconstruction

References

  1. 1.
    Breiman L. 2001. Random forests. Machine Learning, 45(1): 5-32
  2. 2.
    Chen S P and Cheng W M. 2001. World forest watching by digital earth. Journal of Remote Sensing, 5(5): 321-326
  3. 3.
    Clausi D A. 2002. An analysis of co-occurrence texture statistics as a function of grey level quantization. Canadian Journal of Remote Sensing, 28(1): 45-62
  4. 4.
    Dalponte M, Bruzzone L and Gianelle D. 2012. Tree species classification in the Southern Alps based on the fusion of very high geometrical resolution multispectral/hyperspectral images and LiDAR data. Remote Sensing of Environment, 123: 258-270[DOI: 10.1016/j.rse.2012.03.013]
  5. 5.
    Guo Q H, Liu J, Tao S L, Xue B L, Li L, Xu G C, Li W K, Wu F F, Li Y M, Chen L H and Pang S X. 2014. Perspectives and prospects of LiDAR in forest ecosystem monitoring and modeling. Chinese Science Bulletin, 59(6): 459-478
  6. 6.
    Guo Q H, Su Y J, Hu T Y, Guan H C, Jin S C, Zhang J, Zhao X X, Xu K X, Wei D J, Kelly M and Coops N C. 2021. Lidar boosts 3D ecological observations and modelings: a review and perspective. IEEE Geoscience and Remote Sensing Magazine, 9(1): 232-257
  7. 7.
    Guyon I, Weston J, Barnhill S and Vapnik V. 2002. Gene selection for cancer classification using support vector machines. Machine Learning, 46(1/3): 389-422
  8. 8.
    Haralick R M, Shanmugam K and Dinstein I H. 1973. Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6): 610-621
  9. 9.
    Li Y, Xie D H, Wang Y J, Jin S N, Zhou K, Zhang Z X, Li W H, Zhang W M, Mu X H and Yan G J. 2023. Individual tree segmentation of airborne and UAV LiDAR point clouds based on the watershed and optimized connection center evolution clustering. Ecology and Evolution, 13(7): e10297
  10. 10.
    Li Y R. 2022. Application of random forest in agriculture. South Agricultural Machinery, 53(22): 63-65, 87
  11. 11.
    Li Z Y, Liu Q W and Pang Y. 2016. Review on forest parameters inversion using LiDAR. Journal of Remote Sensing (in Chinese), 20(5): 1138-1150
  12. 12.
    Ma Y X. 2008. The application of “3S” technology in digital forestry. Forest Science and Technology, (8): 36-37
  13. 13.
    Mu X H, Yan G J, Zhou H M, Pang Y, Qiu F, Zhang Q, Zhang Y G, Xie D H, Zhou Y J, Zhao T J, Zhong B, Song J L, Sun R, Jiang L M, Yin S Y, Li F, Jiao Z T, Qu Y H, Zhang W M, Cheng S and Cui T X. 2021. Airborne comprehensive remote sensing experiment of forest and grass resources in Xiaoluan River Basin. National Remote Sensing Bulletin, 25(4): 888-903
  14. 14.
    Pang Y, Li Z Y, Ju H B, Lu H, Jia W, Si L, Guo Y, Liu Q W, Li S M, Liu L X, Xie B B, Tan B X and Dian Y. 2016. LiCHy: the CAF’s LiDAR, CCD and hyperspectral integrated airborne observation system. Remote Sensing, 8(5): 398
  15. 15.
    Pang Y, Liang X J, Jia W, Si L, Yan G J and Shi J C. 2021. The comprehensive airborne remote sensing experiment in Saihanba forest farm. National Remote Sensing Bulletin, 25(4): 904-917
  16. 16.
    Pang Y, Wang W W, Du L M, Zhang Z J, Liang X J, Li Y N and Wang Z Y. 2021. Nyström-based spectral clustering using airborne LiDAR point cloud data for individual tree segmentation. International Journal of Digital Earth, 14(10): 1452-1476
  17. 17.
    Qi J B, Xie D H, Guo D S and Yan G J. 2017. A large-scale emulation system for realistic three-dimensional (3-D) forest simulation. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 10(11): 4834-4843
  18. 18.
    Qin H M, Zhou W Q, Yao Y and Wang W M. 2022. Individual tree segmentation and tree species classification in subtropical broadleaf forests using UAV-based LiDAR, hyperspectral, and ultrahigh-resolution RGB data. Remote Sensing of Environment, 280: 113143
  19. 19.
    Raumonen P, Kaasalainen M, Åkerblom M, Kaasalainen S, Kaartinen H, Vastaranta M, Holopainen M, Disney M and Lewis P. 2013. Fast automatic precision tree models from terrestrial laser scanner data. Remote Sensing, 5(2): 491-520
  20. 20.
    Shen X and Cao L. 2017. Tree-species classification in subtropical forests using airborne hyperspectral and LiDAR data. Remote Sensing, 9(11): 1180
  21. 21.
    Soh L K and Tsatsoulis C. 1999. Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Transactions on Geoscience and Remote Sensing, 37(2): 780-795
  22. 22.
    Wang B, He B H, Lin N, Wang W and Li T Y. 2022. Tea plantation remote sensing extraction based on random forest feature selection. Journal of Jilin University (Engineering and Technology Edition), 52(7): 1719-1732
  23. 23.
    Yan G J, Zhao T J, Mu X H, Wen J G, Pang Y, Jia L, Zhang Y G, Chen D Q, Yao C B, Cao Z Y, Lei Y H, Ji D B, Chen L F, Liu Q H, Lyu L Q, Chen J M and Shi J C. 2021. Comprehensive remote sensing experiment of carbon cycle, water cycle and energy balance in Luan River Basin. National Remote Sensing Bulletin, 25(4): 856-870
  24. 24.
    Zhang W M, Qi J B, Wan P, Wang H T, Xie D H, Wang X Y and Yan G J. 2016. An easy-to-use airborne LiDAR data filtering method based on cloth simulation. Remote Sensing, 8(6): 501
  25. 25.
    Zhao G, Shao G F, Reynolds K M, Wimberly M C, Warner T, Moser J W, Rennolls K, Magnussen S, Köhl M, Anderson H E, Mendoza G A, Dai L M, Huth A, Zhang L J, Brey J, Sun Y J, Ye R H, Martin B A and Li F R. 2005. Digital forestry: a white paper. Journal of Forestry, 103(1): 47-50

Читать полностью

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website