Anterior|Siguiente

Análisis de los factores que influyen en la precisión de la clasificación de especies de árboles individuales mediante hiperespectrales aéreas y LiDAR

  • role： First author第一作者
  • Affiliation：

    Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, China

    Key Laboratory of Forestry Remote Sensing and Information System, National Forestry and Grassland Administration, Beijing 100091, China

  • Email：jiawen@ifrit.ac.cn
  • Introduction：荚文，研究方向为机载高光谱数据处理、树种分类、森林定量遥感、森林灾害遥感。E-mail：jiawen@ifrit.ac.cn
JIA Wen,  
  • role： Corresponding author通信作者
  • Affiliation：

    Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, China

    Key Laboratory of Forestry Remote Sensing and Information System, National Forestry and Grassland Administration, Beijing 100091, China

  • Email：pangy@ifrit.ac.cn
  • Introduction：庞勇，研究方向为林业遥感机理模型、激光雷达信号处理及林业应用、森林碳汇计量、森林变化监测。E-mail：pangy@ifrit.ac.cn
PANG Yong*,  
  • Affiliation：

    Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, China

    Key Laboratory of Forestry Remote Sensing and Information System, National Forestry and Grassland Administration, Beijing 100091, China

LI Zengyuan,  
  • Affiliation：

    Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, China

    Key Laboratory of Forestry Remote Sensing and Information System, National Forestry and Grassland Administration, Beijing 100091, China

KONG Dan,  
  • Affiliation：

    Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, China

    Key Laboratory of Forestry Remote Sensing and Information System, National Forestry and Grassland Administration, Beijing 100091, China

LIANG Xiaojun

resumen

La información precisa de las especies de árboles es crucial para la monitorización de los recursos forestales, la gestión de las explotaciones, la evaluación de los ecosistemas y la investigación de la biodiversidad. La combinación de datos hiperespectrales aéreos y LiDAR (Light Detection and Ranging) brinda nuevas oportunidades para la clasificación de especies de árboles forestales. Aunque ha habido muchas investigaciones de clasificación de pequeña escala de especies de árboles a partir de datos hiperespectrales y LiDAR en los últimos años, aún existe una falta de estudios cuantitativos sobre los factores que influyen en la precisión de la clasificación de datos hiperespectrales y LiDAR aéreos en escenarios forestales de mayor escala debido a la diversidad de tipos de árboles y la complejidad de la estructura de edad de los bosques. Con el fin de mejorar la precisión de la clasificación fina de especies de árboles en bosques artificiales a una mayor escala para una aplicación práctica, se diseñaron cuatro estrategias de clasificación (índices de vegetación derivados de imágenes multibanda no corregidas por la función de distribución bidireccional de la reflectancia (BRDF); índices de vegetación derivados de imágenes multibanda corregidas por BRDF; índices de vegetación derivados de imágenes corregidas por BRDF + características de altura de árboles; índices de vegetación derivados de imágenes corregidas por BRDF + características de altura de árboles + información sobre la copa individual), y tomando el terreno del bosque mecanizado de Sihangba como ejemplo, se realizó un análisis comparativo para evaluar el efecto de estas cuatro estrategias de clasificación en la coherencia espectral de las imágenes multibanda aéreas, la introducción de características de altura de árboles y la influencia de la información de la copa individual en la precisión de la clasificación fina de las especies de árboles forestales artificiales. El estudio muestra (1) que la clasificación de especies de árboles basada en la información de segmentación individual de árboles puede reducir eficazmente los errores de clasificación para los mismos píxeles pertenecientes a diferentes especies dentro de la misma copa de árbol, lo que contribuye significativamente a la mejora de la precisión de la clasificación de especies de árboles (10.74%); (2) que aunque la corrección de la radiación coherente entre las imágenes aéreas reduce las diferencias de reflectancia espectral de las mismas especies de árboles debido a la geometría sol-observador, esto tiene un efecto limitado en la mejora de la precisión de la clasificación de especies de árboles (3.48%); (3) en regiones donde diferentes especies de árboles tienen estructuras verticales similares, o la misma especie de árboles se distribuye en múltiples clases de edad, la contribución de la altura de copa (CHM - Canopy Height Model) a la mejora de la precisión de la clasificación de especies de árboles puede ser prácticamente despreciable (0.67%). En conclusión, aunque la clasificación fina de especies de árboles basada en la combinación de datos hiperespectrales aéreos y LiDAR presenta un gran valor de aplicación y un gran potencial en extensos bosques artificiales, es necesario analizar y optimizar en profundidad muchos factores influyentes para establecer una base científica más eficaz para la monitorización efectiva de recursos forestales, la gestión y otras aplicaciones de teledetección forestal.

palabra clave

Clasificación de especies de árboles; Datos hiperespectrales aéreos; Corrección BRDF; Datos LiDAR; Segmentación de árboles individuales; Bosque mecanizado de Sihangba

References

  1. 1.
    Alonzo M, Bookhagen B and Roberts D A. 2014. Urban tree species mapping using hyperspectral and lidar data fusion. Remote Sensing of Environment, 148: 70-83
  2. 2.
    Bunting P and Lucas R. 2006. The delineation of tree crowns in Australian mixed species forests using hyperspectral Compact Airborne Spectrographic Imager (CASI) data. Remote Sensing of Environment, 101(2): 230-248
  3. 3.
    Clark M L, Roberts D A and Clark D B. 2005. Hyperspectral discrimination of tropical rain forest tree species at leaf to crown scales. Remote Sensing of Environment, 96(3/4): 375-398
  4. 4.
    Colgan M S, Baldeck C A, Féret J B and Asner G P. 2012. Mapping savanna tree species at ecosystem scales using support vector machine classification and BRDF correction on airborne hyperspectral and LiDAR data. Remote Sensing, 4(11): 3462-3480
  5. 5.
    Fassnacht F E, Latifi H, Stereńczak K, Modzelewska A, Lefsky M, Waser L T, Straub C and Ghosh A. 2016. Review of studies on tree species classification from remotely sensed data. Remote Sensing of Environment, 186: 64-87
  6. 6.
    Furniss J, Rahimzadeh-Bajgiran P, Gara T W, Daigle J and Costanza K K L. 2022. Mapping ash species across a mixed forest using hyperspectral imagery. Remote Sensing Letters, 13(5): 441-451
  7. 7.
    Ghosh A, Fassnacht F E, Joshi P K and Koch B. 2014. A framework for mapping tree species combining hyperspectral and LiDAR data: role of selected classifiers and sensor across three spatial scales. International Journal of Applied Earth Observation and Geoinformation, 26: 49-63
  8. 8.
    Guan Y W, Zhou Y R, He B B, Liu X Z, Zhang H G and Feng S L. 2020. Improving land cover change detection and classification with BRDF correction and spatial feature extraction using Landsat time series: a case of urbanization in Tianjin, China. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 4166-4177
  9. 9.
    Hakula A, Ruoppa L, Lehtomäki M, Yu X W, Kukko A, Kaartinen H, Taher J, Matikainen L, Hyyppä E, Luoma V, Holopainen M, Kankare V and Hyyppä J. 2023. Individual tree segmentation and species classification using high-density close-range multispectral laser scanning data. ISPRS Open Journal of Photogrammetry and Remote Sensing, 9: 100039
  10. 10.
    Isenburg M. 2012. LAStools-efficient tools for LiDAR processing[EB/OL].
  11. 11.
    Jensen D J, Simard M, Cavanaugh K C and Thompson D R. 2018. Imaging spectroscopy BRDF correction for mapping Louisiana’s coastal ecosystems. IEEE Transactions on Geoscience and Remote Sensing, 56(3): 1739-1748
  12. 12.
    Jia W and Pang Y. 2023. Tree species classification in an extensive forest area using airborne hyperspectral data under varying light conditions. Journal of Forestry Research, 34(5): 1359-1377
  13. 13.
    Jia W, Pang Y and Tortini R. 2024. The influence of BRDF effects and representativeness of training data on tree species classification using multi-flightline airborne hyperspectral imagery. ISPRS Journal of Photogrammetry and Remote Sensing, 207: 245-263
  14. 14.
    Jia W, Pang Y, Tortini R, Schläpfer D, Li Z Y and Roujean J L. 2020. A kernel-driven BRDF approach to correct airborne hyperspectral imagery over forested areas with rugged topography. Remote Sensing, 12(3): 432
  15. 15.
    Jia W, Pang Y, Yue C R, Li Z Y, Che T and Ma M G. 2016. The processing of airborne AISA EagleII data in Ejina banner study area. Remote Sensing Technology and Application, 31(3): 504-510
  16. 16.
    Jones T G, Coops N C and Sharma T. 2010. Assessing the utility of airborne hyperspectral and LiDAR data for species distribution mapping in the coastal Pacific Northwest, Canada. Remote Sensing of Environment, 114(12): 2841-2852
  17. 17.
    Korpela I, Heikkinen V, Honkavaara E, Rohrbach F and Tokola T. 2011. Variation and directional anisotropy of reflectance at the crown scale—Implications for tree species classification in digital aerial images. Remote Sensing of Environment, 115(8): 2062-2074
  18. 18.
    Kwak D A, Lee W K, Lee J H, Biging G S and Gong P. 2007. Detection of individual trees and estimation of tree height using LiDAR data. Journal of Forest Research, 12(6): 425-434
  19. 19.
    Li X, Wang H, Luan J W, Gao B, Wang Y and Liu S R. 2023. Effects of tree species diversity and soil microbial diversity on productivity of plantations. Acta Ecologica Sinica, 43(12): 4984-4994
  20. 20.
    Li Z Y and Chen E X. 2021. Development course of forestry remote sensing in China. National Remote Sensing Bulletin, 25(1): 292-301
  21. 21.
    Lisiewicz M, Kamińska A, Kraszewski B and Stereńczak K. 2022. Correcting the results of CHM-based individual tree detection algorithms to improve their accuracy and reliability. Remote Sensing, 14(8): 1822
  22. 22.
    Ma Y, Zhao Y T, Im J, Zhao Y H and Zhen Z. 2024. A deep-learning-based tree species classification for natural secondary forests using unmanned aerial vehicle hyperspectral images and LiDAR. Ecological Indicators, 159: 111608
  23. 23.
    Maignan F, Bréon F M and Lacaze R. 2004. Bidirectional reflectance of Earth targets: evaluation of analytical models using a large set of spaceborne measurements with emphasis on the Hot Spot. Remote Sensing of Environment, 90(2): 210-220
  24. 24.
    Mäyrä J, Keski-Saari S, Kivinen S, Tanhuanpää T, Hurskainen P, Kullberg P, Poikolainen L, Viinikka A, Tuominen S, Kumpula T and Vihervaara P. 2021. Tree species classification from airborne hyperspectral and LiDAR data using 3D convolutional neural networks. Remote Sensing of Environment, 256: 112322
  25. 25.
    Michałowska M and Rapiński J. 2021. A review of tree species classification based on airborne LiDAR data and applied classifiers. Remote Sensing, 13(3): 353
  26. 26.
    Modzelewska A, Fassnacht F E and Stereńczak K. 2020. Tree species identification within an extensive forest area with diverse management regimes using airborne hyperspectral data. International Journal of Applied Earth Observation and Geoinformation, 84: 101960
  27. 27.
    Ni H Y, Li L, Yao W, Li W and Tao R. 2023. Tree species classification combined with hyperspectral and airborne LiDAR. Laser and Infrared, 53(2): 313-320
  28. 28.
    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
  29. 29.
    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
  30. 30.
    Patel S and Swaminarayan P. 2023. A novel approach for improving post classification accuracy of satellite images by using majority analysis. Indonesian Journal of Electrical Engineering and Informatics, 11(2): 431-441
  31. 31.
    Plakman V, Janssen T, Brouwer N and Veraverbeke S. 2020. Mapping species at an individual-tree scale in a temperate forest, using Sentinel-2 images, airborne laser scanning data, and random forest classification. Remote Sensing, 12(22): 3710
  32. 32.
    Pu R L. 2021. Mapping tree species using advanced remote sensing technologies: a state-of-the-art review and perspective. Journal of Remote Sensing, 2021: 9812624
  33. 33.
    Qi Y J. 2012. Random forest for bioinformatics//Zhang C and Ma Y Q, eds. Ensemble Machine Learning: Methods and Applications. New York: Springer: 307-323
  34. 34.
    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
  35. 35.
    Quan Y, Li M Z, Hao Y S, Liu J Y and Wang B. 2023. Tree species classification in a typical natural secondary forest using UAV-borne LiDAR and hyperspectral data. GIScience and Remote Sensing, 60(1): 2171706
  36. 36.
    Queally N, Ye Z W, Zheng T, Chlus A, Schneider F, Pavlick R P and Townsend P A. 2022. FlexBRDF: a flexible BRDF correction for grouped processing of airborne imaging spectroscopy flightlines. Journal of Geophysical Research: Biogeosciences, 127(1): e2021JG006622
  37. 37.
    Rina S, Ying H, Shan Y, Du W L, Liu Y, Li R and Deng D Z. 2023. Application of machine learning to tree species classification using active and passive remote sensing: a case study of the Duraer forestry zone. Remote Sensing, 15(10): 2596
  38. 38.
    Roujean J L, Leroy M and Deschamps P Y. 1992. A bidirectional reflectance model of the Earth’s surface for the correction of remote sensing data. Journal of Geophysical Research: Atmospheres, 97(D18): 20455-20468
  39. 39.
    Schaaf C B, Gao F, Strahler A H, Lucht W, Li X W, Tsang T, Strugnell N C, Zhang X Y, Jin Y F, Muller J P, Lewis P, Barnsley M, Hobson P, Disney M, Roberts G, Dunderdale M, Doll C, d'Entremont R P, Hu B X, Liang S L, Privette J L and Roy D. 2002. First operational BRDF, albedo nadir reflectance products from MODIS. Remote Sensing of Environment, 83(1/2): 135-148
  40. 40.
    Shen X and Cao L. 2017. Tree-species classification in subtropical forests using airborne hyperspectral and LiDAR data. Remote Sensing, 9(11): 1180
  41. 41.
    Shi Y F, Skidmore A K, Wang T J, Holzwarth S, Heiden U, Pinnel N, Zhu X and Heurich M. 2018. Tree species classification using plant functional traits from LiDAR and hyperspectral data. International Journal of Applied Earth Observation and Geoinformation, 73: 207-219
  42. 42.
    Shi Y F, Wang T J, Skidmore A K and Heurich M. 2020. Improving LiDAR-based tree species mapping in Central European mixed forests using multi-temporal digital aerial colour-infrared photographs. International Journal of Applied Earth Observation and Geoinformation, 84: 101970
  43. 43.
    Sicard P, Coulibaly F, Lameiro M, Araminiene V, De Marco A, Sorrentino B, Anav A, Manzini J, Hoshika Y, Moura B B and Paoletti E. 2023. Object-based classification of urban plant species from very high-resolution satellite imagery. Urban Forestry and Urban Greening, 81: 127866
  44. 44.
    Sims D A and Gamon J A. 2002. Relationships between leaf pigment content and spectral reflectance across a wide range of species, leaf structures and developmental stages. Remote Sensing of Environment, 81(2/3): 337-354
  45. 45.
    Sothe C, Dalponte M, Almeida C M D, Schimalski M B, Lima C L, Liesenberg V, Miyoshi G T and Tommaselli A M G. 2019. Tree species classification in a highly diverse subtropical forest integrating UAV-based photogrammetric point cloud and hyperspectral data. Remote Sensing, 11(11): 1338
  46. 46.
    Sun Z Q, Wu D, Lv Y F and Zhao Y S. 2017. Bidirectional polarized reflectance factors of vegetation covers: influence on the BRF models results. IEEE Transactions on Geoscience and Remote Sensing, 55(10): 5687-5701
  47. 47.
    Tian X M, Zhang X L and Wu Y S. 2020. Classification of planted forest species in southern China with airborne hyperspectral and LiDAR data. Journal of Forest Research, 25(6): 369-378
  48. 48.
    Tiemann A and Ring I. 2022. Towards ecosystem service assessment: developing biophysical indicators for forest ecosystem services. Ecological Indicators, 137: 108704
  49. 49.
    Wagner F H, Ferreira M P, Sanchez A, Hirye M C M, Zortea M, Gloor E, Phillips O L, De Souza filho C R, Shimabukuro Y E and Aragão L E O C. 2018. Individual tree crown delineation in a highly diverse tropical forest using very high resolution satellite images. ISPRS Journal of Photogrammetry and Remote Sensing, 145: 362-377
  50. 50.
    Wang K P, Wang T J and Liu X H. 2018. A review: individual tree species classification using integrated airborne LiDAR and optical imagery with a focus on the urban environment. Forests, 10(1): 1
  51. 51.
    Wei S S, Yin T G, Yuan B, Ow G L F, Yusof M L M, Gastellu-Etchegorry J P and Whittle A J. 2024. Estimation of chlorophyll content for urban trees from UAV hyperspectral images. International Journal of Applied Earth Observation and Geoinformation, 126: 103617
  52. 52.
    Wietecha M, Jełowicki Ł, Mitelsztedt K, Miścicki S and Stereńczak K. 2019. The capability of species-related forest stand characteristics determination with the use of hyperspectral data. Remote Sensing of Environment, 231: 111232
  53. 53.
    Wu Y S and Zhang X L. 2019. Object-based tree species classification using airborne hyperspectral images and LiDAR data. Forests, 11(1): 32
  54. 54.
    Xu Z, Shen X, Cao L, Coops NC, Goodbody TR, Zhong T, Zhao W, Sun Q, Ba S, Zhang Z and Wu X. 2020. Tree species classification using UAS-based digital aerial photogrammetry point clouds and multispectral imageries in subtropical natural forests. International Journal of Applied Earth Observation and Geoinformation, 92, 102173
  55. 55.
    Yang G, Zhao Y L, Li B X, Ma Y T, Li R R, Jing J B and Dian Y. 2019. Tree species classification by employing multiple features acquired from integrated sensors. Journal of Sensors, 2019(1): 3247946
  56. 56.
    Yang H J, Yu B, Che X Y, Yu S T, Fan D D and Huang X R. 2016. Study on scenic beauty of forest interior landscape in Saihanba mechanized forest farm. Forest Resources Management, 3: 98-103, 111
  57. 57.
    Zhang H R, Lei X D and Li F R. 2020. Research progress and prospects of forest management science in China. Scientia Silvae Sinicae, 56(9): 130-142
  58. 58.
    Zhao C H, Qin B A, Feng S, Zhu W X, Sun W W, Li W and Jia X P. 2023. Hyperspectral image classification with multi-attention transformer and adaptive superpixel segmentation-based active learning. IEEE Transactions on Image Processing, 32: 3606-3621
  59. 59.
    Zhao D, Pang Y, Li Z Y and Liu L J. 2014. Isolating individual trees in a closed coniferous forest using small footprint LiDAR data. International Journal of Remote Sensing, 35(20): 7199-7218
  60. 60.
    Zhao D, Pang Y, Li Z Y and Sun G Q. 2013. Filling invalid values in a LiDAR-derived canopy height model with morphological crown control. International Journal of Remote Sensing, 34(13): 4636-4654
  61. 61.
    Zhao D, Pang Y, Liu L J and Li Z Y. 2020. Individual tree classification using airborne LiDAR and hyperspectral data in a natural mixed forest of northeast China. Forests, 11(3): 303
  62. 62.
    Zhong H, Lin W S, Liu H R, Ma N, Liu K K, Cao R Z, Wang T T and Ren Z Z. 2022. Identification of tree species based on the fusion of UAV hyperspectral image and LiDAR data in a coniferous and broad-leaved mixed forest in Northeast China. Frontiers in Plant Science, 13: 964769
  63. 63.
    Zhong L H, Dai Z Q, Fang P F, Cao Y and Wang L G. 2024. A review: tree species classification based on remote sensing data and classic deep learning-based methods. Forests, 15(5): 852

Leer el texto completo

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