Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

A Seamline Extraction Technique Considering the Characteristic of NDVI for High Resolution Satellite Image Mosaics

고해상도 위성영상 모자이크를 위한 NDVI 특성을 이용한 접합선 추출 기법

  • Received : 2015.07.22
  • Accepted : 2015.09.22
  • Published : 2015.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

High-resolution satellite image mosaics are becoming increasingly important in the field of remote sensing image analysis as an essential image processing to create a large image constructed from several smaller images. In this paper, we present an automatic seamline extraction technique and the procedure to generate a mosaic image by this technique. For more effective seamline extraction in the overlap region of adjacent images, an NDVI-based seamline extraction technique is developed, which takes advantage of the computational time and memory. The Normalized Difference Vegetation Index(NDVI) is an index of plant "greeness" or photosynthetic activity that is employed to extract the initial seamline. The NDVI can divide into manmade region and natural region. The cost image is obtained by the canny edge detector and the buffering technique is used to extract the ranging cost image. The seamline is extracted by applying the Dijkstra algorithm to a cost image generated through the labeling process of the extracted edge information. Histogram matching is also conducted to alleviate radiometric distortion between adjacent images acquired at different time. In the experimental results using the KOMPSAT-2/3 satellite imagery, it is confirmed that the proposed method greatly reduces the visual discontinuity caused by geometric difference of adjacent images and the computation time.

고해상도 위성영상 모자이크는 두 장 이상의 위성영상을 공간적으로 합성하여 보다 넓은 단일 영상을 만드는 영상 처리 과정으로 원격탐사 분야에서 그 중요성이 날로 커지고 있다. 본 연구에서는 영상 모자이크 작업 시 요구되는 접합선 자동 추출기법과 이를 기반으로 한 모자이크 영상 제작 방법을 제시하였다. 대용량인 고해상도 위성영상에서 보다 빠르고 효율적인 접합선 추출하기 위해서, NDVI의 특성을 활용하여 빠르게 경계선을 추출하는 NDVI 기반 접합선 추출 알고리즘을 개발하였다. NDVI는 식생의 분포량 및 활동성을 나타내는 정규화 식생지수로 이를 활용하여 인공지역과 자연지역을 분리하여 초기 접합선을 추출하였다. Canny 에지 연산자를 적용하여 비용범위이미지를 생성하고, 초기 접합선을 기준으로 버퍼링 기법을 사용하여 범위 비용 이미지를 생성하였다. 다익스트라 알고리즘을 사용하여 접합선을 추출하고, 획득시기가 다른 인접영상간의 방사 왜곡을 줄이기 위하여 히스토그램 매칭을 수행하였다. KOMPSAT-2/3 위성영상을 이용한 실험결과, 두 영상의 기하학적 차이로 인한 시각적 불연속 특징이 감소됨을 확인할 수 있었고, 접합선 추출시 소요되는 연산시간이 감소되는 것을 확인할 수 있었다.

Keywords

References

  1. Barbehenn M., 1998, A Note on the Complexity of Dijkstra's Algorithm for Graphs with Weighted Vertices. IEEE Transactions on Computers, 47(2): 263. https://doi.org/10.1109/12.663776
  2. Bielski C., J. Grazzini and P. Soille, 2007, Automated Morphological Image Composition for Mosaicking Large Image Data Sets, Proc. of 2007 Geoscience and Remote Sensing Symposium, Barcelona, Spain, July 23-27, pp. 4068-4071
  3. Chen M., R.A. Chowdhry, V. Ramachandran, D.L. Roche and L. Tong, 2007, Priority Queues and Dijkstra's Algorithm. UTCS Technical Report TR-07-54.
  4. Chon. J.C, H.S Kim and C.S. Lin. 2010. Seam-line determination for image mosaicking: A technique minimizing the maximum local mismatch and the global cost. ISPRS Journal of Photogrammetric Engineering and Remote Sensing, 65(2010): 86-92. https://doi.org/10.1016/j.isprsjprs.2009.09.001
  5. Dijkstra E.W., 1959, A Note on Two Problems in Connexion with Graphs, Numerische Mathematlk, Springer Berlin Heidelberg, Germany.
  6. Francois B. C., S. Baillarin, D. Greslou and C. Panem., 2010, Automatic and generic mosaicing of satellite images. Geoscience and Remote Sensing Symposium (IGARSS), 1(2010): 3158-3161.
  7. Gonzalez, R. C. and R. E. Woods, 2010. Digital Image Processing Third Edition, Prentice Hall, NJ, USA.
  8. Jin. K.H. and Y.S .Song. 2009. Automated Edge-based Seamline Extraction for Mosaicking of Highresolution Satellite Images. Journal of the Korean Society for Geo-Spatial Information System, 18(1): 61-69 (In Korean with English abstract).
  9. John C., 1986. A Computational Approach to Edge Detection. IEEE Transaction on Pattern Analysis and Machine Intelligence, 8(6): 679-698.
  10. Jun P. and M. Wang. 2011. A Seam-line Optimized Method Based on Difference Image and Gradient Image, Proc. of 2011 19th International Conference on Geoinformatics, Shanghai, 24-26 June. pp. 1-6.
  11. Kerschner M., 2000. Twin Snakes for Determining Seam Lines in Orthoimage Mosaicking. International Archives of Photogrammetry and Remote Sensing, 33(B4/3):454-461.
  12. Kirk J., 2006. Dijkstra's Shortest Path Algoritm. http://www.mathworks.co.kr/ matlabcentral/fileexchange/12850-dijkstras-shortest -pathalgorithm.
  13. Otsu N., 1979, A threshold selection method from gray level histograms, IEEE Transactions on Systems, Man and Cybernetics 9, 62-66. https://doi.org/10.1109/TSMC.1979.4310076
  14. Pan J., Q. Zhou, M. Wang, 2014. Seamline determination based on Segmentation for urban image mosaicking. IEEE Geoscience and Remote sensing Letters, 11(8): 1335-1339. https://doi.org/10.1109/LGRS.2013.2293197
  15. Singh D. and M. Rohit. 2012. Building Extraction from Very High Resolution Multispectral Images using NDVI based Segmentation and Morphological Operators. EURASIP Journal on Applied Signal Processing, 2005(14):2196-2206. https://doi.org/10.1155/ASP.2005.2196
  16. Soille P., 2006 Morphological image compositing, IEEE Transactions on Pattern Analysis and Machine Intelligence, 28(5): 673-683. https://doi.org/10.1109/TPAMI.2006.99
  17. Song N.H., S.H Lee, K.H. Oh and W.S. Cho . 2007. Technique of Seam-Line Extraction for Automatic Image Mosaic Generation. Journal of Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 25(1): 47-53 (In Korean with English abstract).
  18. Wan. Y.C., D.L. Wang, J.H., Xiao, X.D. Lai and J.Z. Xu, 2013. Automatic determination of seamlines for aerial image mosaicking based on vector roads alone. ISPRS Journal of Photogrammetric Engineering and Remote Sensing, 76(2013): 1-10. https://doi.org/10.1016/j.isprsjprs.2012.11.002
  19. Yang S.R., L. Li, and Gao P., 1989. Two Dimensional Seam-Point Searching in Digital Image Mosaicking. ASPRS Photogrammetric Engineering & Remote Sensing, 55(1): 49-53.