IJAT Vol.15 No.3 pp. 268-273
doi: 10.20965/ijat.2021.p0268


Classification of Grass and Forb Species on Riverdike Using UAV LiDAR-Based Structural Indices

Naoko Miura*1,†, Tomoyo F. Koyanagi*2, Susumu Yamada*3, and Shigehiro Yokota*4

*1Graduate School of Agricultural and Life Sciences, The University of Tokyo
1-1-1 Yayoi, Bunkyo-ku, Tokyo 113-8657, Japan

Corresponding author

*2Field Studies Institute for Environmental Education, Tokyo Gakugei University, Koganei, Japan

*3Faculty of Agriculture, Tokyo University of Agriculture, Atsugi, Japan

*4Faculty of Environmental Studies, Tokyo City University, Yokohama, Japan

October 30, 2020
March 2, 2021
May 5, 2021
UAV, LiDAR, herbaceous vegetation, grass, riverdike

Herbaceous vegetation on riverdikes plays an important role in preventing soil erosion, which, otherwise, may lead to the collapse of riverdikes and consequently, severe flooding. It is crucial for managers to keep suitable vegetation conditions, which include native grass species such as Imperata cylindrica, and to secure visibility of riverdikes for inspection. If managers can efficiently find where suitable grass and unsuitable forb species grow on vast riverdikes, it would help in vegetation management on riverdikes. Classification and quantification of herbaceous vegetation is a challenging task. It requires spatial resolution and accuracy high enough to recognize small, complex-shaped vegetation on riverdikes. Recent developments in unmanned aerial vehicle (UAV) technology combined with light detection and ranging (LiDAR) may offer the solution, since it can provide highly accurate, high-spatial resolution, and denser data than conventional systems. This paper aims to develop a model to classify grass and forb species using UAV LiDAR data alone. A combination of UAV LiDAR-based structural indices, V-bottom (presence of vegetation up to 50 cm from the ground) and V-middle (presence of vegetation 50–100 cm from the ground), was tested and validated in 94 plots owing to its ability to classify grass and forb species on riverdikes. The proposed method successfully classified the “upright” grass species and “falling” grass species / forb species with an accuracy of approximately 83%. Managers can efficiently prioritize the inspection areas on the riverdikes by using this method. The method is versatile and adjustable in other grassland environments.

Cite this article as:
Naoko Miura, Tomoyo F. Koyanagi, Susumu Yamada, and Shigehiro Yokota, “Classification of Grass and Forb Species on Riverdike Using UAV LiDAR-Based Structural Indices,” Int. J. Automation Technol., Vol.15, No.3, pp. 268-273, 2021.
Data files:
  1. [1] S. Yamada and M. Nemoto, “Effects of Bare-Ground Revegetation Techniques Using Imperata cylindrica on Changes in the Plant Cover and Species Richness during Early Succession,” Open J. of Ecology, Vol.6, No.8, pp. 471-483, 2016.
  2. [2] T. Suzuki, Y. Amano, T. Hashizume, S. Suzuki, and A. Yamaba, “Generation of Large Mosaic Images for Vegetation Monitoring Using a Small Unmanned Aerial Vehicle,” J. Robot. Mechatron., Vol.22, No.2, pp. 212-220, 2010.
  3. [3] W. R. Catchpole and C. J. Wheeler, “Estimating plant biomass: A review of techniques,” Australian J. of Ecology, Vol.17, Issue 2, pp. 121-131, 1992.
  4. [4] J. Sandino, F. Gonzalez, K. Mengersen, and K. J. Gaston, “UAVs and Machine Learning Revolutionising Invasive Grass and Vegetation Surveys in Remote Arid Lands,” Sensors, Vol.18, Issue 2, 605, 2018.
  5. [5] J. Bendig, A. Bolten, S. Bennertz, J. Broscheit, S. Eichfuss, and G. Bareth, “Estimating Biomass of Barley Using Crop Surface Models (CSMs) Derived from UAV-Based RGB Imaging,” Remote Sensing, Vol.6, Issue 11, pp. 10395-10412, 2014.
  6. [6] J. Forsmoo, K. Anderson, C. J. A. Macleod, M. E. Wilkinson, and R. Brazier, “Drone based structure from motion photogrammetry captures grassland sward height variability,” J. of Applied Ecology, Vol.55, Issue 6, pp. 2587-2599, 2018.
  7. [7] E. Grüner, T. Astor, and M. Wachendorf, “Biomass Prediction of Heterogeneous Temperate Grasslands Using an SfM Approach Based on UAV Imaging,” Agronomy, Vol.9, Issue 2, 54, 2019.
  8. [8] U. Lussem, A. Bolten, J. Menne, M. L. Gnyp, J. Schellberg, and G. Bareth, “Estimating biomass in temperate grassland with high resolution canopy surface models from UAV-based RGB images and vegetation indices,” J. of Applied Remote Sensing, Vol.13, Issue 3, 034525, 2019.
  9. [9] H. Zhang, Y. Sun, L. Chang, Y. Qin, J. Chen, Y. Qin, J. Du, S. Yi, and Y. Wang, “Estimation of Grassland Canopy Height and Aboveground Biomass at the Quadrat Scale Using Unmanned Aerial Vehicle,” Remote Sensing, Vol.10, 851, 2018.
  10. [10] N. Viljanen, E. Honkavaara, R. Nasi, T. Hakala, O. Niemelainen, and J. Kaivosoja, “A Novel Machine Learning Method for Estimating Biomass of Grass Swards Using a Photogrammetric Canopy Height Model, Images and Vegetation Indices Captured by a Drone,” Agriculture-Basel, Vol.8, Issue 5, 70, 2018.
  11. [11] R. Nasi, N. Viljanen, J. Kaivosoja, K. Alhonoja, T. Hakala, L. Markelin, and E. Honkavaara, “Estimating Biomass and Nitrogen Amount of Barley and Grass Using UAV and Aircraft Based Spectral and Photogrammetric 3D Features,” Remote Sensing, Vol.10, Issue 7, 1082, 2018.
  12. [12] N. Miura, S. Yamada, and Y. Niwa, “Estimation of canopy height and biomass of Miscanthus sinensis in semi-natural grassland using time-series UAV data,” ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., Vol.V-3-2020, pp. 497-503, 2020.
  13. [13] J. Hyyppä, H. Hyyppä, D. Leckie, F. Gougeon, X. Yu, and M. Maltamo, “Review of methods of small-footprint airborne laser scanning for extracting forest inventory data in boreal forests,” Int. J. of Remote Sensing, Vol.29, Issue 5, pp. 1339-1366, 2008.
  14. [14] M. Maltamo, P. Packalen, X. Yu, K. Eerikainen, J. Hyyppa, and J. Pitkanen, “Identifying and quantifying structural characteristics of heterogeneous boreal forests using laser scanner data,” Forest Ecology and Management, Vol.216, Issues 1-3, pp. 41-50, 2005.
  15. [15] E. Naesset and R. Nelson, “Using airborne laser scanning to monitor tree migration in the boreal-alpine transition zone,” Remote Sensing of Environment, Vol.110, Issue 3, pp. 357-369, 2007.
  16. [16] F. Morsdorf, C. Nichol, T. Malthus, and I. H. Woodhouse, “Assessing forest structural and physiological information content of multi-spectral LiDAR waveforms by radiative transfer modelling,” Remote Sensing of Environment, Vol.113, Issue 10, pp. 2152-2163, 2009.
  17. [17] S. Solberg, A. Brunner, K. H. Hanssen, H. Lange, E. Naesset, M. Rautiainen, and P. Stenberg, “Mapping LAI in a Norway spruce forest using airborne laser scanning,” Remote Sensing of Environment, Vol.113, Issue 11, pp. 2317-2327, 2009.
  18. [18] D. Wang, X. Xin, Q. Shao, M. Brolly, Z. Zhu, and J. Chen, “Modeling Aboveground Biomass in Hulunber Grassland Ecosystem by Using Unmanned Aerial Vehicle Discrete Lidar,” Sensors, Vol.17, Issue 1, 180, 2017.
  19. [19] N. Miura, S. Yokota, Y. F. Koyanagi, and S. Yamada, “Hervaceous vegetation height map on riverdike from UAV LiDAR data,” Proc. of the 2018 IEEE Int. Geoscience and Remote Sensing Symp. (IGARSS 2018), pp. 5469-5472, 2018.
  20. [20] N. Miura, T. F. Koyanagi, S. Yokota, and S. Yamada, “Can UAV LiDAR derive vertical structure of herbaceous vegetation on riverdike?,” ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., Vol.IV-2/W5, pp. 127-132, 2019.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on May. 10, 2021