Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회지)

Korean Society of Surveying, Geodesy, Photogrammetry and Cartography (한국측량학회)
권호 표지
DOI QR코드

DOI QR Code

Improvement of Building Region Correspondence between SLI and Vector Map Based on Region Splitting

영역분할에 의한 SLI와 벡터 지도 간의 건물영역 일치도 향상

  • 이정호 (서울대학교 공학연구소) ;
  • 가칠오 (서울대학교 건설환경공학부) ;
  • 김용일 (서울대학교 건설환경공학부) ;
  • 유기윤 (서울대학교 건설환경공학부)
  • Received : 2012.08.13
  • Accepted : 2012.08.31
  • Published : 2012.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

After the spatial discrepancy between SLI(Street-Level Imagery) and vector map is removed by their conflation, the corresponding building regions can be found based on SLI parameters. The building region correspondence, however, is not perfect even after the conflation. This paper aims to improve the correspondence of building regions by region splitting of an SLI. Regions are initialized by the seed lines, projection of building objects onto SLI scene. First, sky images are generated by filtering, segmentation, and sky region detection. Candidates for split lines are detected by edge detector, and then images are splitted into building regions by optimal split lines based on color difference and sky existence. The experiments demonstrated that the proposed region splitting method had improved the accuracy of building region correspondence from 83.3% to 89.7%. The result can be utilized effectively for enhancement of SLI services.

SLI(Street-Level Imagery)와 벡터지도의 합성을 통해 두 데이터 간의 위치 편차를 제거한 후, SLI의 매개변수를 기반으로 두 데이터의 대응되는 건물영역을 찾을 수 있다. 그러나 합성 이후에도 여러 요인으로 인하여 건물영역이 완전히 일치하지는 않는다. 본 연구는 영상의 영역분할을 통해 두 데이터 간의 건물영역 일치도를 향상시키는 것을 목적으로 한다. 합성을 통해 생성한 벡터 지도의 건물 객체를 SLI 영상에 투영한 선을 영역분할의 초기 정보로 사용한다. 우선, 필터링, 분할(segmentation), 하늘영역 탐지를 통해 하늘 영상을 생성한다. 그리고 에지 검출자를 통해 건물 분리 후보선을 추출한 후, 색상 차이와 하늘정보를 함께 활용하여 건물 최적분리선을 추출함으로써 보다 정확한 건물영역으로 분할한다. 실제 데이터에 대한 실험 결과, 영역 분할을 통해 건물영역 일치 정확도가 83.3%에서 89.7%로 향상된 것을 확인하였다. 본 연구의 성과는 SLI 서비스를 강화하는데 유용하게 활용될 수 있을 것이다.

Keywords

References

  1. 구글, 2012, http://maps.google.co.kr
  2. 다음, 2012, http://local.daum.net
  3. 가칠오, 이정호, 양성철, 유기윤 (2012), SLI(Street-level Imagery)와 2D 지도간의 합성을 위한 위치 편차 제거, 한국지형공간정보학회지, 한국지형공간정보학회, 제20권, 제2호, pp. 63-71. https://doi.org/10.7319/kogsis.2012.20.2.063
  4. Anguelov, D., Dulong, C., Filip, D., Frueh, C., Lafon, S., Lyon, R., Ogale, A. S., Vincent, L., and Weaver, J. (2010), Google Street View: Capturing the World at Street Level, IEEE Computer, IEEE, Vol. 43, No. 6, pp. 32-38. https://doi.org/10.1109/MC.2010.170
  5. Canny, J. (1986), A Computational Approach to Edge Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, IEEE, Vol. 8, pp. 679-698. https://doi.org/10.1109/TPAMI.1986.4767851
  6. Chen, C. C., Knoblock, C. A., and Shahabi, C. (2006), Automatically Conflating Road Vector Data with Orthoimagery, GeoInformatica, Vol. 10, No. 4, pp. 495- 530. https://doi.org/10.1007/s10707-006-0344-6
  7. Cobb, M. A., Chung, M. J., Foley III, H., Petry, F. E., and Shaw, K. B. (1998), A Rule-based Approach for the Conflation of Attributed Vector Data, GeoInformatica, Kluwer Academic Publishers, Vol. 2, No. 1, pp. 7-35. https://doi.org/10.1023/A:1009788905049
  8. Comanicu, D. and Meer, P. (2002) Mean shift: A robust approach toward feature space analysis, IEEE Trans. Pattern Anal. Machine Intell., IEEE, Vol. 24, pp. 603-619. https://doi.org/10.1109/34.1000236
  9. Davis, L. S. and Benedikt, M. L. (1979), Computational Models of Space: Isovists and Isovist field", Computer Graphics and Image Processing, Elsevier Inc., Vol. 11, No. 1, pp. 49-72. https://doi.org/10.1016/0146-664X(79)90076-5
  10. Duda, R. O. and Hart, P. E. (1972), Use of the Hough Transformation to Detect Lines and Curves in Pictures, Comm. ACM, ACM, Vol. 15, pp. 11-15. https://doi.org/10.1145/361237.361242
  11. Jung, J., Lee, S., Cho, M., and Kim, J. (2011), Touch TT: Scene Text Extractor Using Touchscreen Interface, ETRI Journal, ETRI, Vol. 33, No. 1, pp. 78-88. https://doi.org/10.4218/etrij.11.1510.0029
  12. Laungrungthip, N. McKinnon, A. E., Churcher, C. D., Unsworth, K., Edge-based detection of sky regions in images for solar exposure prediction, IEEE, IVCNZ 2008. 23rd International Conference, IEEE.
  13. Li, Q., Lu, W, Yang, J., and James, Z. (2012), Thin Cloud Detection of All-Sky Images Using Markov Random Fields, IEEE Geoscience and Remote Sensing Letters, IEEE, Vol. 9, No. 3, pp. 417-421. https://doi.org/10.1109/LGRS.2011.2170953
  14. Lillesand and Kiefer, 2008, Remote Sensing and Image Interpretation, Jhon Wiley & Sons Inc., pp. 9-10.
  15. Neto, S. L. M., Wangenheim, A. V., Pereira, E. B., and Comunello, E. (2010), The use of Euclidean geometric distance on RGB color space for the classification of sky and cloud patterns, Journal of Atmospheric and Oceanic Technology, AMS, Vol. 27, No. 9, pp. 1504-1517. https://doi.org/10.1175/2010JTECHA1353.1
  16. Samal, A., Seth, S. and Cueto, K. (2004), A Feature-based Approach to Conflation of Geospatial Sources, International Journal of Geographical Information Science, Taylor & Francis, Vol. 18, No. 5, pp. 459-489. https://doi.org/10.1080/13658810410001658076
  17. Song, W., James M. Keller, Timothy L. Haithcoat, and Curt H. Davis (2011), Relaxation-Based Point Feature Matching for Vector Map Conflation, Transactions in GIS, Wiley, Vol. 15, No. 1, pp. 43-60. https://doi.org/10.1111/j.1467-9671.2010.01243.x
  18. Yuan S. and Tao C. V. (1999), Development of Conflation Components, Proceedings of Geoinformatics '99 Cconference on Geoinformatics and Socioinformatics, The Association of Chinese Professionals in GIS, Ann Arbor, Michigan, USA, June 19-21, 1999, pp. 579-591.