Journal of Korean Society for Geospatial Information Science (대한공간정보학회지)

Korea Spatial Information Society (대한공간정보학회)
권호 표지
DOI QR코드

DOI QR Code

Accuracy Assessment of Supervised Classification using Training Samples Acquired by a Field Spectroradiometer: A Case Study for Kumnam-myun, Sejong City

지상 분광반사자료를 훈련샘플로 이용한 감독분류의 정확도 평가: 세종시 금남면을 사례로

  • 신정일 ((주)지오스토리, 기술연구소) ;
  • 김익재 ((주)지오스토리, 기술연구소) ;
  • 김동욱 ((주)지오스토리, 기술연구소)
  • Received : 2016.03.15
  • Accepted : 2016.03.28
  • Published : 2016.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Many studies are focused on image data and classifier for comparison or improvement of classification accuracy. Therefore studies are needed aspect of the training samples on supervised classification which depend on reference data or skill of analyst. This study tries to assess usability of field spectra as training samples on supervised classification. Classification accuracies of hyperspectral and multispectral images were assessed using training samples from image itself and field spectra, respectively. The results shown about 90% accuracy with training sample collected from image. Using field spectra as training sample, accuracy was decreased 10%p for hyperspectral image, and 20%p for multispectral image. Especially, some classes shown very low accuracies due to similar spectral characteristics on multispectral image. Therefore, field spectra might be used as training samples on classification of hyperspectral image, although it has limitation for multispectral image.

많은 연구들에서 영상자료와 분류 알고리즘 측면에서 분류정확도를 비교하였지만, 참조자료 또는 분석자에 의존하는 훈련샘플에 의한 분류정확도 비교와 관련된 연구는 부족한 실정이다. 본 연구는 감독분류에 있어 훈련샘플로써 지상 분광반사자료의 유용성을 평가하고자 하였다. 이를 위하여 초분광영상과 다중분광영상을 대상으로 영상 수집 훈련샘플과 지상 분광반사자료를 사용하여 분류 정확도를 비교하였다. 그 결과 영상 수집 훈련샘플 사용 시 초분 광영상과 다중분광영상에서 공통적으로 약 90%의 분류정확도를 얻을 수 있었다. 그러나 지상 분광반사자료를 훈련 샘플로 사용하면 초분광영상의 경우 약 10%p, 다중분광영상의 경우 약 20%p의 분류정확도 감소가 발생하였다. 특히 다중분광영상에서 분광반사특성이 유사하게 나타나는 클래스들의 경우 분류정확도가 초분광영상에 비해 매우 낮게 나타났다. 따라서 지상 분광반사자료는 다중분광영상에 적용하는 데에는 한계가 있지만, 초분광영상을 이용한 토지피복분류에 있어 유용한 훈련샘플이 될 수 있다.

Keywords

References

  1. Burai, P., Deak, B., Valko, O. and Tomor, T., 2015, Classification of herbaceous vegetation using airborne hyperspectral imagery, Remote Sensing, Vol. 7, No. 2, pp. 2046-2066. https://doi.org/10.3390/rs70202046
  2. Byun, Y. G., Eo, Y. D. and Yu, K. Y., 2007, Classification of hyperspectral image using spectral mutual information, Journal of the Korean Society for Geospatial Information System, Vol. 15, No. 3, pp. 33-39.
  3. Cerra, D., Mueller, R. and Reinartz, P., 2012, A classification algorithm for hyperspectral data based on synergetics theory, Proc. of ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, International Society for Photogrammetry and Remote Sensing, Melbourne, Australia, Vol. I-7, pp. 71-76.
  4. Chang, C. I., 2003, Hyperspectral imaging: Techniques for spectral detection and classification, Kluwer Academic/Plenum Publishers, New York, pp. 2-35.
  5. Cho, H. G., Kim, D. W. and Shin, J. I., 2014, Study of comparison of classification accuracy of airborne hyperspectral image land cover classification though resolution change, Journal of the Korean Society for Geospatial Information System, Vol. 22, No. 3, pp. 155-160. https://doi.org/10.7319/kogsis.2014.22.3.155
  6. Cho, H. G. and Lee, K. S., 2014, Comparison between hyperspectral and multispectral images for the classification of coniferous species, Korean Journal of Remote Sensing, Vol. 30, No. 1, pp. 25-36. https://doi.org/10.7780/kjrs.2014.30.1.3
  7. Choi, B. G., Na, Y. W., Kim, S. H. and Lee, J. I., 2014, A study on the improvement classification accuracy of land cover using the aerial hyperspectral image with PCA, Journal of the Korean Society for Geospatial Information System, Vol. 22, No. 1, pp. 81-88.
  8. Dalponte, M., Bruzzone, L., Vescovo, L. and Gianelle, D., 2009, The role of spectral resolution and classifier complexity in the analysis of hyperspectral images of forest areas, Remote Sensing of Environment, Vol. 113, No. 11, pp. 2345-2355. https://doi.org/10.1016/j.rse.2009.06.013
  9. Han, D. Y., Kim, H. J., Kim, D. S., Cho, Y. W. and Kim, Y. I., 2003, Feature selection for image classification of hyperion data, Korean Journal of Remote Sensing, Vol. 19, No. 2, pp. 171-179. https://doi.org/10.7780/kjrs.2003.19.2.18
  10. Heiden, U., Roessner, S. S. and Kaufmann, H., 2007, Determination of robust spectral features for identification of urban surface materials in hyperspectral remote sensing data, Remote Sensing of Environment, Vol. 111, No. 4, pp. 537-552. https://doi.org/10.1016/j.rse.2007.04.008
  11. Herold, M., Margaret, E. and Roberts, D. A., 2003, Spectral resolution requirements for mapping urban areas, IEEE Transactions on Geoscience and Remote Sensing, Vol. 41, No. 9, pp. 1907-1919. https://doi.org/10.1109/TGRS.2003.815238
  12. Hochberg, E. J. and Atkinson, M. J., 2003, Capabilities of remote sensors to classify coral, algae and sand as pure and mixed spectra, Remote Sensing of Environment, Vol. 85, No. 2, pp. 174-189. https://doi.org/10.1016/S0034-4257(02)00202-X
  13. Jensen, J. R., 2005, Introductory digital image processing: A remote sensing perspective, 3rd Edition, Upper Saddle River, NJ: Pearson Prentice Hall, pp. 431-465.
  14. Jia, X. and Richards, J. A., 1993, Binary coding of imaging spectrometer data for fast spectral matching and classification, Remote Sensing of Environment, Vol. 43, No. 1, pp. 47-53. https://doi.org/10.1016/0034-4257(93)90063-4
  15. Lu, Q., Huang, X. and Zhang, L., 2014, A Novel clustering-based feature representation for the classification of hyperspectral imagery, Remote Sensing, Vol. 6, No. 6, pp. 5732-5753. https://doi.org/10.3390/rs6065732
  16. Manolakis, D., Marden, D. and Shaw, G. A., 2003, Hyperspectral image processing for automatic target detection applications, Lincoln Laboratory Journal, Vol. 14, No. 1, pp. 79-116.
  17. Mockel, T., Dalmayne, J., Prentice, H. C., Eklundh, L., Purschke, O., Schmidtlein, S. and Hall, K., 2014, Classification of grassland successional stages using airborne hyperspectral imagery, Remote Sensing, Vol. 6, No. 8, pp. 7732-7761. https://doi.org/10.3390/rs6087732
  18. Nasarudin, N. E. M. and Shafri, H. Z. M., 2011, Development and utilization of urban spectral library for remote sensing of urban environment, Journal of Urban and Environmental Engineering, Vol. 5, No. 1, pp. 44-56. https://doi.org/10.4090/juee.2011.v5n1.044056
  19. Richards, J. A. and Jia, X., 2006, Remote sensing digital image analysis: An introduction, Fourth Edition, Springer, Germany, pp. 296-297.
  20. Shin, J. I., 2012, Comparative analysis and improvement of target detection algorithms in hyperspectral image, Doctoral thesis, Inha University, pp. 7-13.
  21. Stavrakoudis, D. G., Dragozi, E., Gitas, I. Z. and Karydas, C. G., 2014, Decision fusion based on hyperspectral and multispectral satellite imagery for accurate forest species mapping, Remote Sensing, Vol. 6, No. 8, pp. 6897-6928. https://doi.org/10.3390/rs6086897
  22. Tamir, C. and Arnon, K., 2015, Ground-level classification of a coral reef using a hyperspectral camera, Remote Sensing, Vol. 7, No. 6, pp. 7521-7544. https://doi.org/10.3390/rs70607521
  23. Van der Meer, F. D. and De Jong, S. M., 2003, Imaging spectrometry: Basic principles and prospective applications, Kluwer Academic Publishers, Netherlands, pp. 44-61.
  24. Zain, R. M., Ismail, M. H. and Zaki, P. H., 2013, Classifying forest species using hyperspectral data in balah forest reserve, Kelantan, Peninsular Malaysia, Journal of Forest Science, Vol. 29, No. 2, pp. 131-137.