Ecology and Resilient Infrastructure

Korean Society of Ecology and Infrastructure Engineering (응용생태공학회)
권호 표지
DOI QR코드

DOI QR Code

Comparative Analysis of Filtering Techniques for Vegetation Points Removal from Photogrammetric Point Clouds at the Stream Levee

하천 제방의 영상 점군에서 식생 점 제거 필터링 기법 비교 분석

  • Park, Heeseong (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology) ;
  • Lee, Du Han (Department of Hydro Science and Engineering Research, Korea Institute of Civil Engineering and Building Technology)
  • 박희성 (한국건설기술연구원 수자원하천연구본부) ;
  • 이두한 (한국건설기술연구원 수자원하천연구본부)
  • Received : 2021.12.03
  • Accepted : 2021.12.14
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

This study investigated the application of terrestrial light detection and ranging (LiDAR) to inspect the defects of the vegetated levee. The accuracy of vegetation filtering techniques was compared by applying filtering techniques on photogrammetric point clouds of a vegetated levee generated by terrestrial LiDAR. Representative 10 vegetation filters such as CIVE, ExG, ExGR, ExR, MExG, NGRDI, VEG, VVI, ATIN, and ISL were applied to point cloud data of the Imjin River levee. The accuracy order of the 10 techniques based on the results was ISL, ATIN, ExR, NGRDI, ExGR, ExG, MExG, VVI, VEG, and CIVE. Color filters show certain limitations in the classification of vegetation and ground and classify grass flower image as ground. Morphological filters show a high accuracy of the classification, but they classify rocks as vegetation. Overall, morphological filters are superior to color filters; however, they take 10 times more computation time. For the improvement of the vegetation removal, combined filters of color and morphology should be studied.

본 연구에서는 식생이 무성한 제방의 이상유무 점검을 위한 지상 LiDAR(Light Detection And Ranging) 측량의 적용성을 검토하였다. 지상 LiDAR 측량으로 생성된 제방의 영상 점군 자료에 색상필터 및 형태필터를 적용하여 각 기법별 정확성과 특성을 평가하였다. 임진강 제방의 영상 점군 자료를 이용하여 CIVE, ExG, ExGR, ExR, MExG, NGRDI, VEG, VVI, ATIN, ISL 등의 10가 식생 제거 필터를 적용하였다. 결과에 의하면 정확성은 ISL, ATIN, ExR, NGRDI, ExGR, ExG, MExG, VVI, VEG, CIVE 등의 순서로 나타났다. 색상필터는 지반 구분에 한계를 보였으며 풀꽃을 지반으로 구분하기도 했다. 형태필터는 지반 구분 정확도가 우수하나 거석을 식생으로 인식하는 한계도 보였다. 전체적으로 형태필터가 우수하나 계산 시간에서 10 배 정도 소요되었다. 정확도와 속도 향상을 위해서 형태필터와 색상필터를 결합한 복합필터에 대한 연구가 필요하다.

Keywords

Acknowledgement

본 연구는 국토교통과학기술진흥원의 물관리 연구사업국토해양부 건설기술혁신사업의 연구비지원(21AWMP-B114119-06)에 의해 수행되었습니다.

References

  1. Axelsson, P. 1999. Processing of laser scanner data-algorithms and applications. Journal of Photogrammetry and Remote Sensing 54: 138-147, doi:10.1016/S0924-2716(99)00008-8.
  2. Axelsson, P. 2000. DEM generation from laser scanner data using adaptive TIN models. International Archives of the Photogrammetry, Remote Sensing and Spatial Information 33: 110-117.
  3. Burgos-Artizzu, X.P., Ribeiro, A., Guijarro, M. and Pajares, G. 2011. Real-time image processing for crop/weed discrimination in maize fields. Computers and Electronics in Agriculture 75(2): 337-346. https://doi.org/10.1016/j.compag.2010.12.011
  4. CIRIA and USACE. 2013. The International Levee Handbook. London.
  5. Guerrero, J.M., Pajares, G., Montalvo, M., Romeo, J. and Guijarro, M. 2012. Support vector machines for crop/weeds identification in maize fields. Expert Systems with Applications 39: 11149-11155. https://doi.org/10.1016/j.eswa.2012.03.040
  6. Hague, T., Tillet, N. and Wheeler, H. 2006. Automated crop and weed monitoring in widely spaced cereals. Precision Agriculture 1(1): 95-113.
  7. Hamuda, E., Glavin, M., and Jones, E. 2016. A survey of image processing techniques for plant extraction and segmentation in the field: Computers and Electronics in Agriculture 125: 184-199. https://doi.org/10.1016/j.compag.2016.04.024
  8. Hunt, E.R., Cavigelli, M., Daughtry, C.S.T., McMurtrey, J.E. and Walthall, C.L. 2005. Evaluation of digital photography from model aircraft for remote sensing of crop biomass and nitrogen status. Precision Agriculture 6: 359-378. https://doi.org/10.1007/s11119-005-2324-5
  9. Kataoka, T., Kaneko, T., Okamoto, H. and Hata, S. 2003. Crop growth estimation system using machine vision. Proceeding of 2003 IEEE/ASME International Conference. Advanced Intelligent Mechatronics (AIM 2003) 2: 1079-1083.
  10. Kraus, K. and Pfeifer, N. 1998. Determination of terrain models in wooded areas with airborne laser scanner data. ISPRS Journal of Photogrammetry and Remote Sensing 53: 193-203. https://doi.org/10.1016/S0924-2716(98)00009-4
  11. Lamm, R.D., Slaughter, D.C. and Giles, D.K. 2002. Precision weed control for cotton. Transactions of the American Society of Agricultural Engineers 45: 231-238.
  12. Meng, X., Currit, N. and Zhao, K. 2010. Ground filtering algorithms for airborne LiDAR Data: a review of critical issues. Remote Sensing 2: 833-860. https://doi.org/10.3390/rs2030833
  13. Meyer, G.E., Camargo Neto, J., Jones, D.D., and Hindman, T.W. 2004. Intensified fuzzy clusters for classifying plant, soil, and residue regions of interest from color images: Computers and Electronics in Agriculture 42(3): 161-180. https://doi.org/10.1016/j.compag.2003.08.002
  14. Meyer, G.E., Hindman, T.W. and Lakshmi, K. 1999. Machine vision detection parameters for plant species identification. In: Meyer, G.E., DeShazer, J.A. (Eds.), Precision Agriculture and Biological Quality, Proceedings of SPIE 3543: 327-335.
  15. Montealegre, A.L., Lamelas, M.T. and de la Riva, J. 2015. A comparison of open-source LiDAR filtering algorithms in a mediterranean forest environment. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 8: 4072-4085, doi:10.1109/JSTARS.2015.2436974.
  16. Planetary Habitability Laboratory (PHL). Visible vegetation index (VVI). Available online: https://phl.upr.edu/projects/visible-vegetation-index-vvi (accessed on 2 Dec. 2021).
  17. Ribeiro, A., Fernandez-Quintanilla, C., Barroso, J. and Garcia-Alegre, M.C. 2005. Development of an image analysis system for estimation of weed. Proceedings of the 5th European Conference on Precision Agriculture (5ECPA): 169-174.
  18. Sithole, G. and Vosselman, G. 2004. Experimental comparison of filter algorithms for bare-Earth extraction from airborne laser scanning point clouds. Journal of Photogrammetry and Remote Sensing 59: 85-101. https://doi.org/10.1016/j.isprsjprs.2004.05.004
  19. Tian, L.F. and Slaughter, D.C. 1998. Environmentally adaptive segmentation algorithm for outdoor image segmentation. Computers and Electronics in Agriculture 21: 153-168. https://doi.org/10.1016/S0168-1699(98)00037-4
  20. Woebbecke, D., Meyer, G., VonBargen, K. and Mortensen, D. 1995. Color indices for weed identification under various soil, residue, and lighting conditions. Transactions of the American Society of Agricultural Engineers 38(1): 271-281. https://doi.org/10.13031/2013.27839
  21. Yilmaz, V., Konakoglu, B., Serifoglu, C., Gungor, O. and Gokalp, E. 2016. Image classification-based ground filtering of point clouds extracted from UAV-based aerial photos. Geocarto International 33(3): 310-320. https://doi.org/10.1080/10106049.2016.1250825