DOI QR코드

DOI QR Code

Relational matching for solving initial approximation

관계영상정합을 이용한 초기근사값 결정


Abstract

The objective of this research is to investigate the potential of relational matching in one of the fundamental photogrammetric processes, that is initial approximation problem. The automatic relative orientation procedures of aerial stereopairs have been investigated. The fact that the existing methods suffer from approximations, distortions (geometric and radiometric), occlusions, and breaklines is the motivation to investigate relational matching which appears to be a much more general solution. An elegant way of solving the initial approximation problem by using distinct(special) relationship from relational description is suggested and experimented. As for evaluation function, the cost function was implemented. The detection of erroneous matching is incorporated as a part of proposed relational matching scheme. Experiments with real urban area images where large numbers of repetitive patterns, breaklines, and occluded areas are present prove the feasibility of implementation of the proposed relational matching scheme. The investigation of relational matching in the domain of image matching problem provides advantages and disadvantages over the existing image matching methods and shows the future area of development and implementation of relational matching in the field of digital photogrammetry.

이 연구는 수치사진측량의 기본과정 중의 하나인 입체영상 표정에서 관계영상정합 (relational matching)을 이용한 초기 근사값 결정에 관한 연구를 목적으로 한다. 수치입체영상에 대한 상호표정(relative orientation)을 자동화하기 위한 연구가 수치사진측량(Digital Photogrammetry) 및 컴퓨터 비젼(Computer Vision) 분야에서 많이 이루어져 왔다. 그러나 현재 까지의 자동화된 상호표정에 있어서는 초기 근사값 산정에 의한 문제가 제약조건이 되어 왔으므 로, 보다 일반적인 적용을 목적으로 관계영상정합이 제안되고 이에 대해 연구가 시작되었다. 이 연구에서는 특수한 관계설정(relational description)을 사용하여, 초기 근사값을 결정하는 보다 유연한 방법이 제시되고 적용되었으며, Cost 함수를 평가함수(evaluation fuction)로 적용하였다. 본 연구에서 제시된 관계정합방법에 일부로서 매칭오류(mismatch) 탐색과정을 부가하였다. 또 한, 반복적인 형태, 파단선, 사각지역 등이 다수 포함되어 있는 도심지의 영상에 대해 적용하므르 서 본 연구에서 제시된 관계영상정합이 실제 적용가능하다는 것을 입증하였다. 영상정합의 분야에서의 관계영상정합에 대한 이 연구는 기존의 영상정합법에 대한 장단점을 도 출하였으며, 수치사진측량 분야에서의 관계영상정합의 응용과 개발에 대한 향후의 연구방향을 제 시하였다.

Keywords

References

  1. Computer Vision Ballard, Dana H.;Brown, Christopher M.
  2. IEEE Transactions on Pattern Analysis and Machine Intelligence v.10 no.2 Structural Stereopsis for 3-D Vision Boyer, K. L.;Kak, A. C.
  3. Ph.D. Dissertation, The Ohio State University Extracting Straght Lines Burns, J. B.;Hanson, A. R.;Riseman, E. M.
  4. Department of Geodetic Science and Surveying Digital Stereo Matching: In Perspective. Technical Notes in Photogrammetry No. 10 Doorn, B.;Agouris, P.;Al-Tahir, R.;Stefanidis, A.;Zilberstein, O.
  5. IEEE Transactions on Pattern Analysis and Machine Intelligence v.8 no.4 Extracting Straight Lines Burns, J. B.;Hanson, A. R.;Riseman, E. M.
  6. Corners and Centers of Circular Features. ISPRS Intercommissiom Workshop A Fast Operator for Detection and Precise location of Distinct Points Fostner, Wolfgang;Guch, E.
  7. Computer and Robot Vision Haralick, Rebert M.;Shapiro, Linda G.
  8. Proceedings of the 5th Joint Conference on Airtificial Intelligence Toward Automatic Visual Obstacle Avoidance Moravec, H.P.
  9. Department of Geodetic Science and Surveying Algorithms and Software Concepts for Digital Photogrammetric Workstations Reprot No. 418 Schenk, T.
  10. An Automatci Corrspondence for Digital Images Using Linear Feature. Ph D Dissertation Department of Geoetci Science and Surveying Shahin, Fayez.
  11. Proceedings on Integration, Automation, and Intelligence in Photogrammetry, Remote Sinsing and GIS . 3rd liesmara Colloquium An Automatic Procedure for the Relative Orientation of Aerial Images Tang, L.;Heipke, C.
  12. Institue of Photogrammetry A Graph-Theoretical Approach for Multiple Feature Matching and Its Application on Digital Point Transfer. Munich Commission III Tsingas, Vassilios
  13. Relational Matching. Lecture Notes in Computer Science 628 Vosselman, George
  14. International Archives of Photogrammetry and Remote Sensing, Commission III Relational Matching for Stereopsis Zilberstein, Ofer