Robust methodology for vanishing points detection in architectural scenes

  1. J. Finat 1
  2. M.Gonzalo-Tasis 1
  3. J. Gomez Lahoz 2
  4. D.Aguilera 2
  5. M. A. Claro-Irisarri 2
  1. 1 Universidad de Valladolid
    info

    Universidad de Valladolid

    Valladolid, España

    ROR https://ror.org/01fvbaw18

  2. 2 Universidad de Salamanca
    info

    Universidad de Salamanca

    Salamanca, España

    ROR https://ror.org/02f40zc51

Actas:
eArcom04 Congress

Año de publicación: 2004

Páginas: 1-11

Congreso: eArcom

Tipo: Aportación congreso

GOOGLE SCHOLAR

Resumen

In the past few years, there exists an increasing relevance for surveying, protection, restoration and dissemination of Cultural Heritage. This trend is supported by the power provided by Information and Communication Technologies in two remarkable aspects: the ability of computer based tools for representing 3D objects from digital images and the capability of available software tools to provide world wide access to this representation. Cultural Heritage representation is broadening in two directions: firstly, to efficiently and attractively render the architectural objects (stress on visualization quality) and secondly, to achieve high accuracy and reliability standards (stress on metric quality). We are aiming at enlargement of automatic modeling for architectural complex objects. Hence, we assume that we are able to deal with the large amount of blunders that are swept into the process due to a variety of reasons: the ill posed geometry of the recovery of the object shape from the imagery, occlusions, cast shadows, noise in the radiometry, and correlation within certain critical parameters. This paper focuses on the development of a robust methodology for vanishing points detection in order to provide a robust structure of the 3D scene. We assume that we are working with images in which the object exhibits strong perspective effects, i.e. we can take advantage in the identification and calculation of the vanishing points attached to the object structural lines. The robustness in vanishing points detection will come determined by the quality in the automatic extraction of perspectives lines (Canny’s algorithm), as well as the modeling of radial distortion coefficients of the camera, event quite habitual in Architecture due to the employment of digital cameras with big distortions in the lenses. The application of Iterative Least Squares procedures is supported by stochastic tests and robust procedures in vanishing points detection to avoid errors linked to outliers. We pay a special attention to the Danish estimator applied with Pope Test and the well known RANSAC algorithm, which allow us to detect blunders errors in a single iteration and independently of scene geometric configuration. Finally, in order to validate the methodology developed, we have developed two strategies: firstly, an implementation which includes simulated, wire frame, sketched images for an easy and efficient modeling of different factors to be analyzed and secondly, to extend this task to real raster images taken on relevant monuments of our Cultural Heritage such as the Santa Ana’s Cloister.

Referencias bibliográficas

  • [Agu03] Aguilera D.G, M.Gonzalo and J.Finat: "Grouping criteria in archtectural scenes from compatible orientations of polygonal regions", The Intl Arch.of the PhOtogrammetry, Remote Sensing and Spatial Information Sciences, Vol.XXXIV, Paret 5/W12, 13-16.
  • [Ame79] Amer, F., Theoretical Reliability Studies for Some Elementary Photogrametric Pro-cedures, Proceedings of the Aerial Triangulation Symposium, Department of Sur-veying, University of Queensland, Brisbane, Australia ,1979.
  • [Ber97] M.de Berg, M.Van Kreveld, M.Overmars, and O. Schwarzkopf: "Computational Geometry. Algorihtms and Applications", Springer-Verlag, 1997.
  • [Brä99] Bräuer Christian, Burchardt, Klauss Voss. “Robust Vanishing Point Determination in Noisy Images”. Digital Image Processing Group. Institute for Compute Science. University of Jena. Germany.
  • [Bri91] B. Brillault-O'Mahoney. New method for vanishing point detection. Computer Vision, Graphics, and Image Processing. Image Understanding, 54(2):289-300, September 1991.
  • [Dom00] Domingo Preciado Ana: "Investigación sobre los Métodos de Estimación Robusta aplicados a la resolución de los problemas fundamentales de la Fotogrametría". Tesis Doctoral. Universidad de Cantabria. Febrero 2000.
  • [Fin02] J.Finat , M.Gonzalo, M.J. Antolinez y S. Aguilar: "Dynamic Trapezoidal Maps For Coarse Perspective Models In Indoor Scenes", ISPRS'02.
  • [Hak81] El-Hakim. S. F., A practical Study of Gross-Error Detection in a Blundle Adjust-ment, Canadian Surveyor. "Blunder Detection in Horizontal Survey Networks" (1981).
  • [Har00] R.Hartley and A.Zisserman; "Multiple View Geometry in Computer Vision", Cambridge Univ. Press, 2000.
  • [Gom01] Gómez J. "Apuntes de Tercer Ciclo". E.PS. Ávila. Departamento de Ingeniería Cartográfica y del Terreno. Año 2001.
  • [Heu98] F.A. van den Heuvel. Vanishing point detection for architectural photogrammetry. In International Archives of Photogrammetry and Remote Sensing Vol. XXXII part 5, pages 652-659, 1998.
  • [Kan93] K.Kanatani: "Geometric Computation for Machine Vision", Oxford Univ. Press,1993.
  • [Kra93] Kraus, K . Advanced Methods and Applications Vol.2. Fundamentals and Estándar Processes Vol1. Institute for Photogrammetry Vienna University of Technology. Ferd. Dummler Verlag. Bonn 1993.
  • [Lut94] E. Lutton, H. Maitre, and J. Lopez -Krahe. Contribution to the determination of vanishing points using hough transform. In IEEE transactions on pattern analysis and machine intelligence, volume 16, pages 430-438, 1994.
  • [Mag84] M. J. Magee and J. K. Aggarwal. Determining vanishing points from perspective images. Computer Vision, Graphics, and Image Processing, 26(2):256-267, May 1984.
  • [Rth00] C. Rother. A new approach for vanishing point detection in architectural environments. Proceedings of the 11th British Machine Vision Conference (BMVC'00), 1:382-391, September 2000.
  • [Shf96] J.A. Shufelt. Performance evaluation and analysisof vanishing point detection techniques. In ARPA Image Understanding Workshop, pages 1113-1132. Morgan Kaufmann Publish-ers, Palm Springs, 1996.
  • [Str93] M. Straforini, C. Coelho, and M Campani. Extraction of vanishing points from images of indoor and outdoor scenes. In Image and Vision Computing, volume 11(2), pages 91-99, 1993.
  • [Tor03] P.H.S.Torr and C.Davidson: "IMPSAC: Synthesis of Importance Sampling and Random Sample Consensus", IEEE Trans on PAMI, Vol.25, n3, 2003, 354-364.
  • [Wil02] M.Wilczkowiak, E.Boyer and P.Sturm: "3D modeling using geometric constraints: A parallelepiped based approach", Proc of ECCV'02, Copenhagen, Vol.IV, 221-237, May 2002.