Abstract
Extracting 3D information from a moving camera is traditionally based on interest point detection and matching. This is especially challenging in the built environment, where the number of distinctive interest points is naturally limited. While common Structure-from-Motion (SfM) approaches usually manage to obtain the correct camera poses, the number of accurate 3D points is very small due to the low number of matchable features. Subsequent Multi-view Stereo approaches may help to overcome this problem, but suffer from a high computational complexity. We propose a novel approach for the task of 3D scene abstraction, which uses straight line segments as underlying features. We use purely geometric constraints to match 2D line segments from different images, and formulate the reconstruction procedure as a graph-clustering problem. We show that our method generates accurate 3D models, with a low computational overhead compared to SfM alone.
References
Akinlar, C., Topal, C.: EDLines: real-time line segment detection by edge drawing. In: International Conference on Image Processing (ICIP) (2011)
Ayache, N., Faverjon, B.: Efficient registration of stereo images by matching graph descriptions of edge segments. Int. J. Comput. Vis. (IJCV) 1(2), 107–113 (1987)
Bay, H., Ferrari, V., van Gool, L.: Wide-baseline stereo matching with line segments. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2005)
Donoser, M.: Replicator graph clustering. In: British Machine Vision Conference (BMVC) (2013)
Elqursh, A., Elgammal, A.: Line-based relative pose estimation. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2011)
Felzenszwalb, P., Huttenlocher, F.: Efficient graph-based image segmentation. Int. J. Comput. Vis. (IJCV) 59(2), 167–181 (2004)
Frahm, J.-M., Fite-Georgel, P., Gallup, D., Johnson, T., Raguram, R., Wu, C., Jen, Y.-H., Dunn, E., Clipp, B., Lazebnik, S., Pollefeys, M.: Building Rome on a cloudless day. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part IV. LNCS, vol. 6314, pp. 368–381. Springer, Heidelberg (2010)
Furukawa, Y., Ponce, J.: Towards internet-scale multi-view stereo. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2010)
von Gioi, R., Jakubowicz, J., Morel, J.M., Randall, G.: LSD: a fast fine segment detector with a false detection control. Trans. Pattern Anal. Mach. Intell. (PAMI) 32(4), 722–732 (2010)
Havlena, M., Schindler, K.: VocMatch: efficient multiview correspondence for structure from motion. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part III. LNCS, vol. 8691, pp. 46–60. Springer, Heidelberg (2014)
Hofer, M., Donoser, M., Bischof, H.: Semi-global 3D line modeling for incremental structure-from-motion. In: British Machine Vision Conference (BMVC) (2014)
Hofer, M., Maurer, M., Bischof, H.: Improving sparse 3D models for man-made environments using line-based 3D reconstruction. In: International Conference on 3D Vision (3DV) (2014)
Hofer, M., Wendel, A., Bischof, H.: Incremental line-based 3D reconstruction using geometric constraints. In: British Machine Vision Conference (BMVC) (2013)
Hofer, M., Wendel, A., Bischof, H.: Line-based 3D reconstruction of wiry objects. In: Computer Vision Winter Workshop (CVWW) (2013)
Irschara, A., Zach, C., Bischof, H.: Towards wiki-based dense city modeling. In: International Conference on Computer Vision (ICCV) (2007)
Jain, A., Kurz, C., Thormaehlen, T., Seidel, H.: Exploiting global connectivity constraints for reconstruction of 3D line segments from images. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2010)
Labatut, P., Pons, J., Keriven, R.: Efficient multi-miew reconstruction of large-scale scenes using interest points, delaunay triangulation and graph cuts. In: International Conference on Computer Vision (ICCV) (2007)
Lowe, D.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. (IJCV) 60(2), 91–110 (2004)
Micusik, B., Wildenauer, H.: Structure from motion with line segments under relaxed endpoint constraints. In: International Conference on 3D Vision (3DV) (2014)
Raposo, C., Antunes, M., Barreto, J.P.: Piecewise-planar StereoScan:structure and motion from plane primitives. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014, Part II. LNCS, vol. 8690, pp. 48–63. Springer, Heidelberg (2014)
Rothermel, M., Wenzel, K., Fritsch, D., Haala, N.: SURE: photogrammetric surface reconstruction from imagery. In: LCD Workshop (2012)
Rumpler, M., Daftry, S., Tscharf, A., Prettenthaler, R., Hoppe, C., Mayer, G., Bischof, H.: Automated end-to-end workflow for precise and Geo-accurate reconstructions using fiducial markers. In: Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences (ISPRS) (2014)
Schindler, G., Krishnamurthy, P., Dellaert, F.: Line-based structure from motion for urban environments. In: International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT) (2006)
Snavely, N., Seitz, S., Szeliski, R.: Photo tourism: exploring image collections in 3D. ACM Trans. Graph. (SIGGRAPH) 25, 835–846 (2006)
Strecha, C., von Hansen, W., Van Gool, L., Fua, P., Thoennessen, U.: On benchmarking camera calibration and multi-view stereo for high resolution imagery. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2008)
Wu, C.: Towards linear-time incremental structure-from-motion. In: International Conference on 3D Vision (3DV) (2013)
Zhang, L., Koch, R.: Line matching using appearance similarities and geometric constraints. In: Pinz, A., Pock, T., Bischof, H., Leberl, F. (eds.) DAGM and OAGM 2012. LNCS, vol. 7476, pp. 236–245. Springer, Heidelberg (2012)
Zhang, L., Xu, C., Lee, K.-M., Koch, R.: Robust and efficient pose estimation from line correspondences. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012, Part III. LNCS, vol. 7726, pp. 217–230. Springer, Heidelberg (2013)
Zhang, Y., Yang, H., Liu, X.: A line matching method based on local and global appearance. In: International Congress on Image and Signal Processing (ICISP) (2011)
Zhiheng, W., Fuchao, W., Zhanyi, H.: MSLD: a robust descriptor for line matching. Pattern Recogn. 39, 889–896 (2009)
Acknowledgements
This work has been supported by the Austrian Research Promotion Agency (FFG) project FreeLine (Bridge1/843450) and OMICRON electronics GmbH.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Hofer, M., Maurer, M., Bischof, H. (2015). Line3D: Efficient 3D Scene Abstraction for the Built Environment. In: Gall, J., Gehler, P., Leibe, B. (eds) Pattern Recognition. DAGM 2015. Lecture Notes in Computer Science(), vol 9358. Springer, Cham. https://doi.org/10.1007/978-3-319-24947-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-319-24947-6_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-24946-9
Online ISBN: 978-3-319-24947-6
eBook Packages: Computer ScienceComputer Science (R0)