Pose Estimation from Airborne Video Sequences Using a Structural Approach for the Construction of Homographies and Fundamental Matrices
Abstract
A structural knowledge-based search method is utilized for the estimation of geometric transforms from airborne video sequences. Examples are projective planar homographies and constraints such as the fundamental matrix. These estimations are calculated from correspondences of interest points between two images. Different approaches are discussed to cope with the problem of outlier- correspondences. To ensure any-time performance the search process is implemented in a data-driven production system. The pose estimation from planar homographies is compared to estimations from fundamental matrices. A fusion of both approaches is proposed. The image processing is performed by bottom-up structural analysis using an assessment-driven control. Examples are from the thermal spectral domain.
Keywords
Interest Point Fundamental Matrix Fundamental Matrice Epipolar Constraint Random Sample ConsensusReferences
- 1.Ben-Ezra, M., Peleg, S., Werman, M.: Real Time Motion Analysis with Linear Programming. CVIU 78, 32–52 (1999)Google Scholar
- 2.Chum, O., Matas, J., Obdrzalek, S.: Epipolar Geometry from Three Correspondences. In: CVWW 2003, Vatlice, Czech Republic (2003)Google Scholar
- 3.Faugeras, O.: Three-Dimensional Computer Vision. MIT Press, Mass (1993)Google Scholar
- 4.Fischler, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. Assoc. Comp. Mach. 24, 381–395 (1981)MathSciNetGoogle Scholar
- 5.Foerstner, W.: A Framework for Low Level Feature Extraction. In: Eklundh, J.-O. (ed.) ECCV 1994. LNCS, vol. 801, pp. 383–394. Springer, Heidelberg (1994)CrossRefGoogle Scholar
- 6.Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)MATHGoogle Scholar
- 7.Holland, P.W., Welsch, R.E.: Robust regression using iteratively reweighted leastsquares. Comm. Statist. Theor. Meth. 6, 813–827 (1977)CrossRefGoogle Scholar
- 8.Jurie, F., Dhome, M.: Real Time Robust Template Matching. In: BMVC-2002, pp. 123–132 (2002)Google Scholar
- 9.Ma, Y., Soatto, S., Kosecka, J., Sastry, S.: An Invitation to 3-D Vision. Springer, Berlin (2000)Google Scholar
- 10.Michaelsen, E., Stilla, U.: Probabilistic Decisions in Production Nets: An Example from Vehicle Recognition. In: Caelli, T.M., Amin, A., Duin, R.P.W., Kamel, M.S., de Ridder, D. (eds.) SPR 2002 and SSPR 2002. LNCS, vol. 2396, pp. 225–233. Springer, Heidelberg (2002)CrossRefGoogle Scholar
- 11.Michaelsen, E., Stilla, U.: Good Sample Consensus Estimation of 2d-Homographies for Vehicle Movement Detection from Thermal Videos. In: Ebner, H., Hiepke, C., Mayer, H., Pakzad, K. (eds.) Photogrammetric Image Analysis PIA 2003. Intern. Arch. of Photogr. and Rem. Sens., vol. 34, Part 3/W8, pp. 125–130 (2003)Google Scholar
- 12.Michaelsen, E., Stilla, U.: Sensor Pose Inference from Airborne Videos by Decomposing Homography Estimates. Accepted for ISPRS 2004, Commission III, WG III/I (2004)Google Scholar
- 13.Torr, P.H.S., Davidson, C.: IIMSAC: Synthesis of importance sampling and random sample consensus. IEEE – PAMI 25(3), 354–364 (2003)Google Scholar
- 14.Sawhney, H.S.: Simplifying motion and structure analysis using planar parallax and image warping. In: ICPR 1994, vol. I, pp. 403–407. IEEE-Press, Los Alamitos (1994)Google Scholar
- 15.Stilla, U., Michaelsen, E., Lütjen, K.: Automatic Extraction of Buildings from Aerial Images. In: Leberl, F., Kalliany, R., Gruber, M. (eds.) Mapping Buildings, Roads and other Manmade Structures from Images, IAPR-TC7, Wien, Oldenburg, pp. 229–244 (1996)Google Scholar
- 16.Sujew, S., Ernst, I.: LUMOS Airborne Traffic Monitoring. In: Int. Workshop on Airborne Traffic Measurement, DLR, Berlin (2003)Google Scholar
- 17.Robust Estimation Library, rrel, university of Manchester (accessed December 24, 2003), http://paine.wiau.man.ac.uk/pub/doc_vxl/contrib/rpl/rrel/html/