Orientation and Pose estimation for Panoramic Imagery

• Autorzy: Laganiere R. , Kangni F.
• Języki publikacji: EN

Abstrakty

EN

In a database of geo-referenced images, determining the exact position of each panorama is an important step in order to ensure the consistency of visual information. This paper addresses the problem of camera pose recovery from spherical (360°) panoramas. The 3D information is extracted from a database of panoramic images sparsely distributed over a scene of interest. We present a two-stage algorithm to recover the position of omni-directional cameras using pair wise essential matrices. First, all rotations with respect to the world frame are found using an incremental bundle adjustment procedure, thus achieving what we call panorama alignment. Full camera positions are then computed using bundle adjustment. During this step, the previously computed panorama orientations, used to feed the global optimization process, can be further refined. Results are shown for indoor and outdoor panorama sets.

Słowa kluczowe

EN

omni-directional panorama; pose estimation; bundle adjustment; structure from motion

• Wydawca: Institute of Information Technology of the Warsaw University of Life Sciences – SGGW
• Czasopismo: Machine Graphics and Vision
• Rocznik: 2010
• Tom: Vol. 19, No. 3
• Strony: 339--363
• Opis fizyczny: Bibliogr. 17 poz., il., wykr.

Twórcy

autor

Laganiere R.

autor

Kangni F.

• VIVA Research Lab, School of Information technology and Engineering University of Ottawa. 800 King Edward, Ottawa, Ontario, K1N 6N5, Canada

Bibliografia

• [1] Hartley R.: In defense of the 8-point algorithm. IEEE trans. Pattern Analysis and Machine Intelligence, vol. 19, 580-593, 1995.
• [2] Zhang Z.: Motion and structure from two perspective views: from essential parameters to Euclidean motion through the fundamental matrix. Journal of the Optical Society of America A, vol. 14, 2938-2950, 1997.
• [3] Svoboda T., Pajdla T., Hlavác V.: Motion estimation using central panoramic cameras. IEEE International Conference on Intelligent Vehicles. S. Hahn, Ed. Stuttgart, Germany: Causal Productions, 335-340, 1998.
• [4] Fusiello A., Trucco E., Tommasini T., Roberto V.: Improving feature tracking with robust statistics. Pattern Analysis and Applications, vol. 2, pp. 312-320, 1999.
• [5] Triggs B., McLauchlan P., Hartley R., Fitzgibbon A.: Bundle adjustment A modern synthesis. Vision Algorithms: Theory and Practice, ser. LNCS, W. Triggs, A. Zisserman, and R. Szeliski, Eds. Springer Verlag, 298-375, 2000.
• [6] Faugeras O., Luong Q. T.: The geometry of multiple images. 1st ed. Cambridge University Press, ISBN: 0262062208, 2001.
• [7] Brown M., Lowe D. G.: Recognising panoramas. ICCV '03: Proc. of the 9th IEEE Int. Conf. onComputer Vision. Washington, DC, 1218-1225, 2003.
• [8] Kuehnel F.: On the minization over so(3) manifolds. Research Institute for Advanced Computer Science (RIACS), USA, Tech. Rep. TR.0312, 2003.
• [9] Levin A., Szeliski R.: Visual odometry and map correlation. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 611-618, 2004.
• [10] Bradley D., Brunton A., Fiala M., Roth G.: Image-based navigation in real environments using panoramas, IEEE Int. Workshop on Haptic Audio Visual Environments and their Applications, 57-59, 2005.
• [11] Fiala M., Roth G.: Automatic alignment and graph map building of panoramas. IEEE Int. Workshop on Haptic Audio Visual Environments and their Applications, 103-108, 2005.
• [12] Stewnius H., Nistr D.: Solutions to minimal generalized relative pose problems. Workshop on Omnidirectional Vision, China, 2005.
• [13] Makadia A., Daniilidis K., Rotation recovery from spherical images without correspondences. IEEE Trans. Pattern Anal. Mach. Intell., vol. 28, no. 7, pp. 1170-1175, 2006.
• [14] Ramalingam S., Lodha S. K., Sturm P.: A generic structure-from-motion framework. Comput. Vis. Image Underst., vol. 103, no. 3, 218-228, 2006.
• [15] Rodrigo C., Ankita K., Kostas D.: Structure from motion with known camera positions. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Washington, DC, 477-484, 2006.
• [16] Nistér D., Stewénius H.: A minimal solution to the generalised 3-point pose problem. J. Math. Imaging Vis., vol. 27, no. 1, 67-79, 2007.
• [17] Snavely N., Seitz S. M., Szeliski R.: Modeling the world from internet photo collections. Int. J. Comput. Vision, vol. 80, no. 2, 189-210, 2008.