DOI QR코드

DOI QR Code

Road Extraction from High Resolution Satellite Image Using Object-based Road Model

객체기반 도로모델을 이용한 고해상도 위성영상에서의 도로 추출

  • 변영기 (한국항공우주연구원) ;
  • 한유경 (서울대학교 공과대학 건설환경공학부) ;
  • 채태병 (한국항공우주연구원)
  • Received : 2011.05.09
  • Accepted : 2011.06.02
  • Published : 2011.08.31

Abstract

The importance of acquisition of road information has recently been increased with a rapid growth of spatial-related services such as urban information system and location based service. This paper proposes an automatic road extraction method using object-based approach which was issued alternative of pixel-based method recently. Firstly, the spatial objects were created by MSRS(Modified Seeded Region Growing) method, and then the key road objects were extracted by using properties of objects such as their shape feature information and adjacency. The omitted road objects were also traced considering spatial correlation between extracted road and their neighboring objects. In the end, the final road region was extracted by connecting discontinuous road sections and improving road surfaces through their geometric properties. To assess the proposed method, quantitative analysis was carried out. From the experiments, the proposed method generally showed high road detection accuracy and had a great potential for the road extraction from high resolution satellite images.

도시 정보시스템 및 위치기반 서비스와 같은 공간정보 분야의 빠른 성장으로 인해 도심지 도로정보 취득 및 갱신에 대한 중요성이 날로 증가하고 있다. 본 연구에서는 고해상도 위성영상으로부터 도로 정보를 추출하기 위하여 최근 화소기반분석의 대안으로 주목을 받고 있는 객체기반 접근법을 이용한 자동 도로추출 방법을 제안한다. 이를 위해 우선 MSRG(Modified Seeded Region Growing)기법을 이용하여 공간객체를 생성한 후, 객체의 형상 특정정보와 인접성을 기반으로 핵심 도로 객체를 자동으로 추출하였다. 또한 추출된 핵심도로 객체와 인접한 객체들과의 공간적 상관성을 이용하여 일부 누락된 도로객체를 추적하였다. 최종적으로 도로의 기하학적인 특성을 이용한 단절된 도로 구간 연결 및 도로 변형 개선 과정을 통하여 최종도로영역을 추출하였다. 제안 기법의 성능 검증을 위한 정량적 평가 결과, 도로영역에 대해 높은 탐지정확도를 보임을 확인하였다. 결과적으로 제안된 방법은 고해상도 위성영상의 도로추출에 유용하게 적용될 수 있으리라 판단된다.

Keywords

References

  1. 변영기, 김용일, 2010, 고해상도 위성영상의 객체기반 분석을 위한 영상분할 기법 개발 및 평가, 한국측량학회지, 28(6): 523-532.
  2. 변영기, 이정호, 손정훈, 유기윤, 2006, LISA를 이용한 LiDAR 데이터로부터 건물 추출에 관한 연구, 한국측량학회지, 24(4): 335-341.
  3. 정인철, 손지연, 2001, 웨이블렛 변환과 다중해상도 분석을 이용한 고해상도 위성영상에서의 도로망 추출, 한국지리정보학회지, 4(3): 61-70.
  4. Anselin, L., 1995, Local Indicators of Spatial Association-LISA, Geographical Analysis, 27: 93-115
  5. Bacher, U. and H. Mayer, 2005, Automatic road extraction from multispectral high resolution satellite images, International Archives of the Phtogrammetry, Reomote Sensing, Vol. XXXVI, Part B3/W24, pp. 29-34.
  6. Colditz. R., T. Wehrmann, M. Bachmann, K. Steinnocher, G. Schmidt, and S. Dech, 2006, Influence of image fusion approaches on classification accuracy: A case study, International Journal of Remote Sensing, 27(15): 3311-3335. https://doi.org/10.1080/01431160600649254
  7. ESRI, 1996, Automation of Map Generalization: The Cutting-Edge Technology, G White Papers of ESRI Support Center.
  8. Gamba. P., F. Dell' Acqua, and G. Lisini, 2006, Improving urban road extraction in high resolution images exploiting directional filtering, perceptual grouping, and simple topological concepts, IEEE Transaction on Geoscience and Remote Sensing, 40(3): 387-391.
  9. Hedman, K., U. Stilla, G. Lisini, and P. Gamba, 2010, Road Network Extraction in VHR SAR images of urban and Suburban Areas by Means of Class-Aided Feature-Level Fusion, IEEE Transaction on Geoscience and Remote Sensing, 48(3): 1294-1296. https://doi.org/10.1109/TGRS.2009.2025123
  10. Long, H. and Z. Zhao, 2005, Urban road extraction from high resolution satellite images, International Journal of Remote sensing, 26(22): 4907-4921. https://doi.org/10.1080/01431160500258966
  11. Negri. M., P. Gamba, G. Lisini, and F. Tupin, 2006, Junction-aware extraction and regularization of urban road networks in high resolution SAR images, IEEE Transaction on Geoscience and Remote Sensing, 44(10): 2962-2971. https://doi.org/10.1109/TGRS.2006.877289
  12. Steger, C., 1998, An unbiased detector of curvilinear structures, IEEE Transactions on Pattern Analysis and Machine Intelligence, 20(2): 311-326.
  13. Song, M. and D. Civco, 2004, Road extraction using SVM and image segemtnation, Photogrammetric Engineering and Remote Sensing, 70(12): 1365-1371. https://doi.org/10.14358/PERS.70.12.1365
  14. Treash, K. and K. Amaratunga, 2000, Automatic road detection in gray scale aerial images, ASCE Journal of Computing in Civil Engineering, 14(1): 60-69. https://doi.org/10.1061/(ASCE)0887-3801(2000)14:1(60)
  15. Wiedemann. C., 2003, External Evaluation of Road networks, International Archives of the Phtogrammetry, Reomote Sensing and Spatial Information Sciences, Vol. XXXIV, Part 3/W8.
  16. Zhang, Q. and I. Couloigner, 2006, Automated road network extraction from high resolution multi-spectral imagery, In ASPRS proceedings, Reno, Nevada, May.1-May.5. on CD-ROM

Cited by

  1. Detection method of objects with a special pattern in satellite images using Histogram Of Gradients (HOG) feature and Support Vector Machine (SVM) classifier vol.30, pp.4, 2014, https://doi.org/10.7780/kjrs.2014.30.4.11