iccv iccv2013 iccv2013-402 iccv2013-402-reference knowledge-graph by maker-knowledge-mining
Source: pdf
Author: Bryan Klingner, David Martin, James Roseborough
Abstract: We describe a structure-from-motion framework that handles “generalized” cameras, such as moving rollingshutter cameras, and works at an unprecedented scale— billions of images covering millions of linear kilometers of roads—by exploiting a good relative pose prior along vehicle paths. We exhibit a planet-scale, appearanceaugmented point cloud constructed with our framework and demonstrate its practical use in correcting the pose of a street-level image collection.
[1] S. Agarwal, K. Mierle, and Others. Ceres solver. https :
[2]
[3]
[4]
[5] //code . google . com/p/ceres- solver/. 6 S. Agarwal, N. Snavely, I. Simon, S. M. Seitz, and R. Szeliski. Building rome in a day. In ICCV, pages 72– 79. IEEE, 2009. 2 O. Ait-Aider, A. Bartoli, and N. Andreff. Kinematics from lines in a single rolling shutter image. In CVPR, 2007. 2 O. Ait-Aider and F. Berry. Structure and kinematics triangulation with a rolling shutter stereo rig. In ICCV, pages 1835–1840, 2009. 2 S. Baker, E. Bennett, S. B. Kang, and R. Szeliski. Removing rolling shutter wobble. In CVPR, pages 2392–2399, 2010. 2 995599
[6] H. Bay, A. Ess, T. Tuytelaars, and L. Van Gool. Speededup robust features (surf). Comput. Vis. Image Underst., 110(3):346–359, June 2008. 5
[7] D. Bradley, B. Atcheson, I. Ihrke, and W. Heidrich. Synchronization and rolling shutter compensation for consumer video camera arrays. In CVPR Workshops, pages 1–8, 2009. 2
[8] N. Dalal and B. Triggs. Histograms of oriented gradients for human detection. In CVPR, CVPR ’05, pages 886–893, Washington, DC, USA, 2005. IEEE Computer Society. 5
[9] P. Forssen and E. Ringaby. Rectifying rolling shutter video from hand-held devices. In CVPR, pages 507–5 14, 2010. 2
[10] C. Geyer, M. Meingast, and S. Sastry. Geometric models of rolling-shutter cameras. OMNIVIS, 2005. 2
[11] I. Gordon and D. G. Lowe. What and where: 3d object recognition with accurate pose. In CLOR06, pages 67–82, 2006. 2
[12] M. D. Grossberg and S. K. Nayar. A general imaging model
[13]
[14]
[15]
[16] and a method for finding its parameters. In ICCV, pages 108–1 15, 2001. 2 M. Grundmann, V. Kwatra, D. Castro, and I. Essa. Calibration-free rolling shutter removal. In ICCP, pages 1–8, 2012. 2 R. Hartley and A. Zisserman. Multiple View Geometry in Computer Vision. Cambridge University Press, 2nd edition, 2003. 2 J. Hedborg, P.-E. Forss ´en, M. Felsberg, and E. Ringaby. Rolling shutter bundle adjustment. In CVPR, pages 1434– 1441. IEEE, 2012. 2, 4 A. Irschara, C. Zach, J.-M. Frahm, and H. Bischof. From structure-from-motion point clouds to fast location recognition. In CVPR, pages 2599–2606, 2009. 2 Figure 11. Our point cloud in downtown Hong Kong (top), with a detail (bottom) showing street-level features like road markings, building facades, and billboards. Figure 12. A histogram of reprojection error, in pixels, for each of the 404 billion tracked features in our augmented point cloud. We downsample our imagery so that it all shares a common angular resolution of about 8 pixels per degree.
[17] Y. Li, N. Snavely, and D. P. Huttenlocher. Location recognition using prioritized feature matching. In ECCV, ECCV’ 10, pages 791–804, Berlin, Heidelberg, 2010. Springer-Verlag. 2
[18] C.-K. Liang, L.-W. Chang, and H. H. Chen. Analysis and compensation of rolling shutter effect. IEEE Transactions on Image Processing, 17(8): 1323–1330, 2008. 2
[19] D. G. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60:91–1 10, 2004. 5, 6
[20] L. Magerand and A. Bartoli. A generic rolling shutter camera model and its application to dynamic pose estimation. In 3DPVT, 2010. 2
[21] D. Nist e´r and H. Stew e´nius. A minimal solution to the generalized 3-point pose problem. Journal of Mathematical Imaging and Vision, 2006. 2
[22] R. Pless. Using many cameras as one. In CVPR, pages 587– 593, 2003. 2
[23] S. Se, D. Lowe, and J. Little. Vision-based mobile robot localization and mapping using scale-invariant features. In Proceedings of ICRA 2001., volume 2, pages 205 1–2058 vol.2, 2001. 2
[24] N. Snavely, S. M. Seitz, and R. Szeliski. Photo tourism: exploring photo collections in 3d. In ACM transactions on graphics, volume 25, pages 835–846. ACM, 2006. 2
[25] H. Stew e´nius, D. Nist e´r, M. Oskarsson, and K. Solutions to minimal generalized relative pose problems. In Workshop on Omnidirectional Vision, 2005. 2
[26] S. Umeyama. Least-squares estimation of transformation parameters between two point patterns. Pattern Analysis and Machine Intelligence, 13(4):376–380, 1991. 7 Åstr o¨m. 996600