STRUCTURE FROM OMNIDIRECTIONAL STEREO RIG MOTION FOR CITY MODELING

Michal Havlena, Tomáš Pajdla, Kurt Cornelis

Abstract

This paper deals with a step towards a 3D reconstruction system for city modeling from omnidirectional video sequences using structure from motion together with stereo constraints. We concentrate on two issues. First, we show how the tracking and reconstruction paradigm were adapted to use omnidirectional images taken by lenses with 180 degrees field of view. This concerns mainly camera calibration transforming the pixel locations into rays and solving the minimal problem for 3D-to-2D matches using RANSAC. Secondly, we compare the results of the reconstruction using additional stereo constraints to the results when these constraints are not used and show that they are needed to make the reconstruction stable. Performance of the system is demonstrated on a sequence of 870 images acquired while driving in a city.

References

  1. Akbarzadeh, A., Frahm, J.-M., Mordohai, P., Clipp, B., Engels, C., Gallup, D., Merrell, P., Phelps, M., Sinha, S., Talton, B., Wang, L., Yang, Q., Stewéius, H., Yang, R., Welch, G., Towles, H., Nistér, D., and Pollefeys, M. (2006). Towards urban 3d reconstruction from video. In 3DPVT. Invited paper.
  2. Antone, M. and Teller, S. (2000). Automatic recovery of relative camera rotations for urban scenes. In CVPR 2000, pages II:282-289.
  3. Antone, M. and Teller, S. (2001). Scalable, absolute position recovery for omni-directional image networks. In CVPR 2001, pages I:398-405.
  4. Bakstein, H. and Pajdla, T. (2002). Panoramic mosaicing with a 180? field of view lens. In Proc. IEEE Workshop on Omnidirectional Vision, pages 60-67.
  5. Benosman, R. and Kang, S. (2000). Panoramic Vision. Springer-Verlag.
  6. Brenner, C. and Haala, N. (1998). Fast production of virtual reality city models. IAPRS, 32(4):77-84.
  7. Chum, O. and Matas, J. (2002). Randomized ransac with td,d test. In BMVC 2002, pages 448-457.
  8. Cornelis, N., Cornelis, K., and Van Gool, L. (2006a). Fast compact city modeling for navigation previsualization. In CVPR 2006, pages II:1339-1344.
  9. Cornelis, N., Leibe, B., Cornelis, K., and Van Gool, L. (2006b). 3d city modeling using cognitive loops. In 3DPVT 2006, pages 9-16.
  10. Ehlgen, T. and Pajdla, T. (2007). Maneuvering aid for large vehicle using omnidirectional cameras. In WACV 2007, page 17.
  11. Fischler, M. and Bolles, R. (1981). Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. ACM, 24(6):381-395.
  12. Früh, C., Jain, S., and Zakhor, A. (2005). Data processing algorithms for generating textured 3d building facade meshes from laser scans and camera images. IJCV, 61(2):159-184.
  13. Früh, C. and Zakhor, A. (2001). 3d model generation for cities using aerial photographs and ground level laser scans. In CVPR 2001, pages II:31-38.
  14. Goedemé, T., Nuttin, M., Tuytelaars, T., and Van Gool, L. (2007). Omnidirectional vision based topological navigation. IJCV, 74(3):219-236.
  15. Grün, A. (1997). Automation in building reconstruction. In Fritsch, D. and Hobbie, D., editors, Photogrammetric Week'97, pages 175-186, Stuttgart.
  16. Haala, N., Brenner, C., and Stätter, C. (1998). An integrated system for urban model generation. In ISPRS Congress Comm. II, pages 96-103.
  17. Hartley, R. and Zisserman, A. (2003). Multiple View Geometry in Computer Vision. Cambridge University Press, second edition.
  18. Havlena, M., Cornelis, K., and Pajdla, T. (2007). Towards city modeling from omnidirectional video. In Grabner, M. and Grabner, H., editors, CVWW 2007, pages 123-130, St. Lambrecht.
  19. Maas, H. (2001). The suitability for airborne laser scanner data for automatic 3d object reconstruction. In Ascona01, pages 291-296.
  20. Matas, J., Chum, O., Urban, M., and Pajdla, T. (2004). Robust wide baseline stereo from maximally stable extremal regions. IVC, 22(10):761-767.
  21. Mauthner, T., Fraundorfer, F., and Bischof, H. (2006). Region matching for omnidirectional images using virtual camera planes. In Chum, O. and Franc, V., editors, CVWW 2006, pages 93-98, Telc?.
  22. Mic?us?ík, B. and Pajdla, T. (2006). Structure from motion with wide circular field of view cameras. IEEE Trans. PAMI, 28(7):1135-1149.
  23. Mouragnon, E., Dekeyser, F., Sayd, P., Lhuillier, M., and Dhome, M. (2006). Real time localization and 3d reconstruction. In CVPR 2006, pages I:363-370.
  24. Nistér, D. (2003). Preemptive ransac for live structure and motion estimation. In ICCV 2003, pages 199-206.
  25. Nistér, D. (2004a). An efficient solution to the five-point relative pose problem. IEEE Trans. PAMI, 26(6):756- 770.
  26. Nistér, D. (2004b). A minimal solution to the generalized 3-point pose problem. In CVPR 2004, pages I:560- 567.
  27. Stamos, I. and Allen, P. (2000). 3-d model construction using range and image data. In CVPR 2000, pages I:531-536.
  28. Sun, Y., Paik, J., Koschan, A., and Abidi, M. (2002). 3d reconstruction of indoor and outdoor scenes using a mobile range scanner. In ICPR 2002, pages III:653- 656.
  29. Teller, S., Antone, M., Bodnar, Z., Bosse, M., Coorg, S., Jethwa, M., and Master, N. (2003). Calibrated, registered images of an extended urban area. IJCV, 53(1):93-107.
  30. Triggs, B., McLauchlan, P., Hartley, R., and Fitzgibbon, A. (1999). Bundle adjustment: A modern synthesis. In Vision Algorithms: Theory and Practice, pages 298- 372, Corfu.
  31. Vestri, C. and Devernay, F. (2001). Using robust methods for automatic extraction of buildings. In CVPR 2001, pages I:133-138.
  32. Vosselman, G. and Dijkman, S. (2001). Reconstruction of 3d building models from laser altimetry data. IAPRS, 34(3):22-24.
Download


Paper Citation


in Harvard Style

Havlena M., Pajdla T. and Cornelis K. (2008). STRUCTURE FROM OMNIDIRECTIONAL STEREO RIG MOTION FOR CITY MODELING . In Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008) ISBN 978-989-8111-21-0, pages 407-414. DOI: 10.5220/0001081104070414


in Bibtex Style

@conference{visapp08,
author={Michal Havlena and Tomáš Pajdla and Kurt Cornelis},
title={STRUCTURE FROM OMNIDIRECTIONAL STEREO RIG MOTION FOR CITY MODELING},
booktitle={Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)},
year={2008},
pages={407-414},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001081104070414},
isbn={978-989-8111-21-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Third International Conference on Computer Vision Theory and Applications - Volume 1: VISAPP, (VISIGRAPP 2008)
TI - STRUCTURE FROM OMNIDIRECTIONAL STEREO RIG MOTION FOR CITY MODELING
SN - 978-989-8111-21-0
AU - Havlena M.
AU - Pajdla T.
AU - Cornelis K.
PY - 2008
SP - 407
EP - 414
DO - 10.5220/0001081104070414