DOI QR코드

DOI QR Code

Land Cover Mapping and Availability Evaluation Based on Drone Images with Multi-Spectral Camera

다중분광 카메라 탑재 드론 영상 기반 토지피복도 제작 및 활용성 평가

  • Xu, Chun Xu (Dept. of Civil Engineering, Chungnam National University) ;
  • Lim, Jae Hyoung (Dept. of Civil Engineering, Chungnam National University) ;
  • Jin, Xin Mei (Dept. of Landscape Architecture, Chonbuk National University) ;
  • Yun, Hee Cheon (Dept. of Civil Engineering, Chungnam National University)
  • Received : 2018.11.23
  • Accepted : 2018.12.11
  • Published : 2018.12.31

Abstract

The land cover map has been produced by using satellite and aerial images. However, these two images have the limitations in spatial resolution, and it is difficult to acquire images of a area at desired time because of the influence of clouds. In addition, it is costly and time-consuming that mapping land cover map of a small area used by satellite and aerial images. This study used multispectral camera-based drone to acquire multi-temporal images for orthoimages generation. The efficiency of produced land cover map was evaluated using time series analysis. The results indicated that the proposed method can generated RGB orthoimage and multispectral orthoimage with RMSE (Root Mean Square Error) of ${\pm}10mm$, ${\pm}11mm$, ${\pm}26mm$ and ${\pm}28mm$, ${\pm}27mm$, ${\pm}47mm$ on X, Y, H respectively. The accuracy of the pixel-based and object-based land cover map was analyzed and the results showed that the accuracy and Kappa coefficient of object-based classification were higher than that of pixel-based classification, which were 93.75%, 92.42% on July, 92.50%, 91.20% on October, 92.92%, 91.77% on February, respectively. Moreover, the proposed method can accurately capture the quantitative area change of the object. In summary, the suggest study demonstrated the possibility and efficiency of using multispectral camera-based drone in production of land cover map.

토지피복도는 지금까지 주로 위성영상과 항공영상을 이용하여 제작되어 왔지만 이 두 영상은 공간적 해상도의 한계가 따르고 구름의 영향으로 원하는 시점에 원하는 지역의 영상을 취득하기에는 역부족이다. 또한, 소규모 지역에 대한 토지피복도를 제작하기에는 시간적 및 경제성 측면에서 비효율적이다. 이에 본 연구에서는 다중분광 카메라 기반의 드론을 사용하여 다중시기 영상을 취득하고 정사영상을 생성한 후 토지피복도를 제작하여 시계열 분석을 통해 활용성을 평가 하였다. 그 결과 RMSE (Root Mean Square Error)가 X, Y, H에서 각각 ${\pm}10mm$, ${\pm}11mm$, ${\pm}26mm$인 RGB 정사영상과 ${\pm}28mm$, ${\pm}27mm$, ${\pm}47mm$인 다중분광 정사영상을 생성할 수 있었다. 픽셀기반 및 객체기반 분류로 각각 제작된 토지피복도의 정확도를 분석한 결과 전체 정확도와 Kappa 계수에서 객체기반 분류가 시기별로 각각 7월 93.75%, 92.42%, 10월 92.50%, 91.20%, 2월 92.92%, 91.77%로 더 높게 나타났으며 시계열 분석 결과 특정 객체의 면적 변화량을 정량적으로 정확하게 파악할 수 있었다. 이를 통해 다중분광 카메라 기반의 드론을 활용한 효율적인 토지피복도 제작 가능성과 활용성을 확인하였다.

Keywords

GCRHBD_2018_v36n6_589_f0001.png 이미지

Fig. 1. GCP locations in study area

GCRHBD_2018_v36n6_589_f0002.png 이미지

Fig. 2. The acquired sample image

GCRHBD_2018_v36n6_589_f0003.png 이미지

Fig. 3. February RGB DEM and orthoimage

GCRHBD_2018_v36n6_589_f0004.png 이미지

Fig. 4. February multispectral DEM and orthoimage

GCRHBD_2018_v36n6_589_f0005.png 이미지

Fig. 5. NDVI generation result

GCRHBD_2018_v36n6_589_f0006.png 이미지

Fig. 6. July pixel-based classification result

GCRHBD_2018_v36n6_589_f0007.png 이미지

Fig. 7. October pixel-based classification result

GCRHBD_2018_v36n6_589_f0008.png 이미지

Fig. 8. February pixel-based classification result

GCRHBD_2018_v36n6_589_f0009.png 이미지

Fig. 9. July object-based classification result

GCRHBD_2018_v36n6_589_f0010.png 이미지

Fig. 10. October object-based classification result

GCRHBD_2018_v36n6_589_f0011.png 이미지

Fig. 11. February object-based classification result

GCRHBD_2018_v36n6_589_f0012.png 이미지

Fig. 12. July inland wetland and mixed forest

GCRHBD_2018_v36n6_589_f0013.png 이미지

Fig. 13. October inland wetland and mixed forest

GCRHBD_2018_v36n6_589_f0014.png 이미지

Fig. 14. February inland wetland and mixed forest

GCRHBD_2018_v36n6_589_f0015.png 이미지

Fig. 15. Comparison graph of area percentage by period

Table 1. The acquired GCP coordinates

GCRHBD_2018_v36n6_589_t0001.png 이미지

Table 2. The input values for automatic flight

GCRHBD_2018_v36n6_589_t0002.png 이미지

Table 3. RGB orthoimage accuracy analysis result

GCRHBD_2018_v36n6_589_t0003.png 이미지

Table 4. Multispectral orthoimage accuracy analysis result

GCRHBD_2018_v36n6_589_t0004.png 이미지

Table 5. Classification and color system

GCRHBD_2018_v36n6_589_t0005.png 이미지

Table 6. Classification accuracy analysis by error matrix

GCRHBD_2018_v36n6_589_t0006.png 이미지

Table 7. Comparison of area percentage by period

GCRHBD_2018_v36n6_589_t0007.png 이미지

References

  1. Colomina, I. and Molina, P. (2014), Unmanned aerial systems for photogrammetry and remote sensing: A review, ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 92, pp. 79-97. https://doi.org/10.1016/j.isprsjprs.2014.02.013
  2. Feng, Q.L., Liu, J.T., and Gong, J.H. (2015), UAV remote sensing for urban vegetation mapping using random forest and texture analysis, Journal of Remote Sensing, Vol. 7, No. 1, pp. 1074-1094. https://doi.org/10.3390/rs70101074
  3. Foody, G.M., Campbell, N.A., Trodd, N.M., and Wood, T.F. (1992), Derivation and applications of probabilistic measures of class membership from the maximumlikelihood classification, Photogrammetric Engineering & Remote Sensing, Vol. 58, No. 9, pp. 1335-1341.
  4. Fuyi, T., Chun, B.B., Mat Jafri, M.Z., Lim, H.S., Abdullah, K., and Tahrin, N.M. (2012), Land cover/use mapping using multi-band imageries captured by cropcam unmanned aerial vehicle autopilot(UAV) over Penang Island, Malaysia, Proceedings of SPIE, The International Society for Optics and Photonics, 8 November 2012, Edinburgh, United Kingdom, Vol. 8540, pp. 1-6.
  5. Gay, A., Stewart, T.P., Angel, R., Easey, M., Eves, A.J., Thomas, N.J., Pearce, D. A., and Kemp, A.I. (2009), Developing unmanned aerial vehicles for local and flexible environmental and agricultural monitoring, Proceedings of the Remote Sensing and Photogrammetry Society Conference, Remote Sensing and Photogrammetry Society, 8-11 September 2009, Leicester, UK, pp. 471-476.
  6. Gini, R., Passoni, D., Pinto, L., and Sona, G. (2013), Use of unmanned aerial systems for multispectral survey and tree classification: a test in a park area of northern Italy, European Journal of Remote Sensing, Vol. 47, No. 1, pp. 251-269. https://doi.org/10.5721/EuJRS20144716
  7. Jensen, J.R., Guptill, S., and Cowen, D. (2012), Change Detection Technology Evaluation, Task T007 Report, Bureau of the Census, U.S., 232p.
  8. Kim, B.S. (2015), Crop classification using unmanned aerial vehicle imagery and object-based classification method, Master's thesis, Chungbuk National University, Cheongju, Korea, 76p.
  9. Kit, O. and Ludeke, M. (2013), Automated detection of slum area change in hyderabad, India using multitemporal satellite imagery, ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 83, pp. 130-137. https://doi.org/10.1016/j.isprsjprs.2013.06.009
  10. Lee, H.S., Kim, D.J., Oh, J.H., Shin, J.G., and Jung, J.S. (2017), Tidal flat DEM generation and seawater changes estimation at hampyeong bay using drone images, Korean Journal of Remote Sensing, Vol. 33, No. 3, pp. 325-331. (in Korean with English abstract) https://doi.org/10.7780/kjrs.2017.33.3.7
  11. Lucieer, A., Steven, M., and Turner, D. (2014), Mapping landslide displacements using structure from motion(SFM) and image correlation of multi-temporal UAV photography, Progress in Physical Geography, SAGE, Vol. 38, No. 1, pp. 97-116. https://doi.org/10.1177/0309133313515293
  12. Marcis, M., Bartak, P., Valaska, D., Frastia1, M., and Trhan, O. (2016), Use of image based modelling for documentation of intricately shaped objects, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 12-19 July, Prague, Czech Republic, Vol. XLI-B5, pp. 327-334.
  13. Park, J.S. (2017), Soil classification and characterization using unmanned aerial vehicle and digital image processing, Ph.D. dissertation, Seoul National University, Seoul, Korea, 191p.
  14. Torres-Sanchez, J., Pena, J.M., De Castro, A.I., and Lopez-Granados, F. (2014), Multi-temporal mapping of the vegetation fraction in early-season wheat fields using images from UAV, Computers and Electronics in Agriculture, Vol. 103, pp. 104-113. https://doi.org/10.1016/j.compag.2014.02.009
  15. Vapnik, V.N. (1995), The Nature of Statistical Learning Theory, Springer-Verlag, New York, N.Y.