Abstract
We present a new parsing framework for the line-based geometric analysis of a single image coming from a man-made environment. This parsing framework models the scene as a composition of geometric primitives spanning different layers from low level (edges) through mid-level (lines and vanishing points) to high level (the zenith and the horizon). The inference in such a model thus jointly and simultaneously estimates a) the grouping of edges into the straight lines, b) the grouping of lines into parallel families, and c) the positioning of the horizon and the zenith in the image. Such a unified treatment means that the uncertainty information propagates between the layers of the model. This is in contrast to most previous approaches to the same problem, which either ignore the middle levels (lines) all together, or use the bottom-up step-by-step pipeline.
For the evaluation, we consider a publicly available York Urban dataset of “Manhattan” scenes, and also introduce a new, harder dataset of 103 urban outdoor images containing many non-Manhattan scenes. The comparative evaluation for the horizon estimation task demonstrate higher accuracy and robustness attained by our method when compared to the current state-of-the-art approaches.
Chapter PDF
References
Schindler, G., Dellaert, F.: Atlanta world: An expectation maximization framework for simultaneous low-level edge grouping and camera calibration in complex man-made environments. In: CVPR, vol. (1), pp. 203–209 (2004)
Hoiem, D., Efros, A.A., Hebert, M.: Geometric context from a single image. In: ICCV, pp. 654–661 (2005)
Hoiem, D., Efros, A.A., Hebert, M.: Automatic photo pop-up. ACM Trans. Graph. 24, 577–584 (2005)
Hoiem, D., Efros, A.A., Hebert, M.: Putting objects in perspective. International Journal of Computer Vision 80, 3–15 (2008)
Duric, Z., Rosenfeld, A.: Image sequence stabilization in real time. Real-Time Imaging 2, 271–284 (1996)
McLean, G.F., Kotturi, D.: Vanishing point detection by line clustering. IEEE Trans. Pattern Anal. Mach. Intell. 17, 1090–1095 (1995)
Tuytelaars, T., Gool, L.J.V., Proesmans, M., Moons, T.: A cascaded hough transform as an aid in aerial image interpretation. In: ICCV, pp. 67–72 (1998)
Cipolla, R., Drummond, T., Robertson, D.P.: Camera calibration from vanishing points in image of architectural scenes. In: BMVC (1999)
Antone, M.E., Teller, S.J.: Automatic recovery of relative camera rotations for urban scenes. In: CVPR, pp. 2282–2289 (2000)
Almansa, A., Desolneux, A., Vamech, S.: Vanishing point detection without any a priori information. IEEE Trans. Pattern Anal. Mach. Intell. 25, 502–507 (2003)
Aguilera, D.G., Lahoz, J.G., Codes, J.F.: A new method for vanishing points detection in 3d reconstruction from a single view. In: Proc. of ISPRS Commission V (2005)
Tardif, J.P.: Non-iterative approach for fast and accurate vanishing point detection. In: ICCV (2009)
Collins, R., Weiss, R.: Vanishing point calculation as a statistical inference on the unit sphere. In: ICCV, pp. 400–403 (1990)
Kosecká, J., Zhang, W.: Video compass. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 476–490. Springer, Heidelberg (2002)
Rother, C.: A new approach for vanishing point detection in architectural environments. In: BMVC (2000)
Coughlan, J.M., Yuille, A.L.: Manhattan world: Compass direction from a single image by bayesian inference. In: ICCV, pp. 941–947 (1999)
Deutscher, J., Isard, M., MacCormick, J.: Automatic camera calibration from a single manhattan image. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2353, pp. 175–205. Springer, Heidelberg (2002)
Denis, P., Elder, J.H., Estrada, F.J.: Efficient edge-based methods for estimating manhattan frames in urban imagery. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 197–210. Springer, Heidelberg (2002)
Tu, Z., Chen, X., Yuille, A.L., Zhu, S.C.: Image parsing: Unifying segmentation, detection, and recognition. International Journal of Computer Vision 63, 113–140 (2005)
Barnard, S.: Interpreting perspective images. Artificial Intelligence 21, 435–462 (1983)
Beardsley, P., Murray, D.: Camera calibration using vanishing points. In: BMVC, pp. 416–425 (1992)
Barinova, O., Lempitsky, V., Kohli, P.: On detection of multiple object instances using hough transforms. In: CVPR (2010)
Besag, J.: On the statistical analysis of dirty pictures. Journal of the Royal Statistical Society B-48, 259–302 (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2010 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Barinova, O., Lempitsky, V., Tretiak, E., Kohli, P. (2010). Geometric Image Parsing in Man-Made Environments. In: Daniilidis, K., Maragos, P., Paragios, N. (eds) Computer Vision – ECCV 2010. ECCV 2010. Lecture Notes in Computer Science, vol 6312. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-15552-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-15552-9_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-15551-2
Online ISBN: 978-3-642-15552-9
eBook Packages: Computer ScienceComputer Science (R0)