Abstract
To provide high-quality augmented reality service in a car navigation system, accurate 6 degrees of freedom (DoF) localization is required. To ensure such accuracy, most current vision-based solutions rely on an off-line large-scale modelling of the environment. Nevertheless, while existing solutions to model the environment require expensive equipments and/or a prohibitive computation time, we propose in this paper a complete framework that automatically builds an accurate large-scale database of landmarks using only a standard camera, a low-cost global positioning system (GPS) and a geographic information system (GIS). As illustrated in the experiments, only few minutes are required to model large-scale environments. The resulting databases can then be used by an on-line localization algorithm to ensure high-quality augmented reality experiences.
Similar content being viewed by others
Notes
The DEM used is a geometric model where each road is presented by a plane.
The 3D building models used are a geometric model where each facade is presented by a plane.
GPU is not used.
Several clicks are performed for each building corner. Then, the mean of these clicks is considered as a ground truth.
References
Irschara, A., Zach, C., Frahm, J.M., Bischof, H.: From structure-from-motion point clouds to fast location recognition. In: CVPR (2009)
Li, Y., Snavely, N., Huttenlocher, D., Fua, P.: Worldwide pose estimation using 3d point clouds. In: ECCV (2012)
Zamir, A.R., Shah, M.: Accurate image localization based on google maps street view. In: ECCV (2010)
Mouragnon, E., Lhuillier, M., Dhome, M., Dekeyser, F., Sayd, P.: Real time localization and 3D reconstruction. In: CVPR (2006)
Taneja, A., Ballan, L., Pollefeys, M.: Registration of spherical panoramic images with cadastral 3D models. In: 3DIMPVT (2012)
Agarwal, S., Furukawa, Y., Snavely, N., Simon, I., Curless, B., Seitz, S.M., Szeliski, R.: Building Rome in a day. Commun. ACM 54, 105–112 (2011)
Frahm, J.M., Fite-Georgel, P., Gallup, D., Johnson, T., Raguram, R., Wu, C., Y. H. Jen, E. Dunn, B. Clipp, S. Lazebnik, M. Pollefeys, Building Rome on a cloudless day. In: ECCV (2010)
Klingner, B., Martin, D., Roseborough, J.: Street view motion-from-structure-from-motion. In: ICCV (2013)
Kaminsky, R.S., Snavely, N., Seitz, S.M., Szeliski, R.: Alignment of 3D point clouds to overhead images. In: CVPR Workshop (2009)
Strecha, C., Pylvänäinen, T., Fua, P.: Dynamic and scalable large scale image reconstruction. In: CVPR (2010)
Pylvänäinen, T., Roimela, K., Vedantham, R., Itäranta, J., Wang, R., Grzeszczuk, R.: Automatic alignment and multi-view segmentation of street view data using 3D shape priors. In: 3DPVT (2010)
Lothe, P., Bourgeois, S., Dekeyser, F., Royer, E., Dhome, M.: Towards geographical referencing of monocular SLAM reconstruction using 3D city models: application to real-time accurate vision-based localization. In: CVPR (2009)
Larnaout, D., Bourgeois, S., Gay-Bellile, V., Dhome, M.: Towards bundle adjustment with GIS constraints for online geo-localization of a vehicle in urban center. In: 3DIMPVT (2012)
Hideyuki, K., Takafumi, T., Tomokazu, S., Naokazu, Y.: Extrinsic camera parameter estimation using video images and GPS considering GPS positioning accuracy. In: ICPR (2010)
Michot, J., Bartoli, A., Gaspard, F.: Bi-objective bundle adjustment with application to multi-sensor SLAM. In: 3DPVT (2010)
Lhuillier, M.: Incremental fusion of structure-from-motion and GPS using constrained bundle adjustments. PAMI 34, 2489–2495 (2012)
Marquardt, D.W.: An algorithm for least-squares estimation of nonlinear parameters. J. Soc. Indus. Appl. Math. 11, 431–441 (1963)
Recky, M., Wendel, A., Leberl, F.: Facade segmentation in a multi-view scenario. In: 3DIMPVT (2011)
Brostow, G.J., Shotton, J., Fauqueur, J., Cipolla, R.: Segmentation and recognition using structure from motion point clouds. In: ECCV (2008)
Tamaazousti, M., Gay-Bellile, V., Naudet-Collette, S., Bourgeois, S., Dhome, M.: NonLinear refinement of structure from motion reconstruction by taking advantage of a partial knowledge of the environment. In: CVPR (2011)
Laneurit, J., Chapuis, R., Chausse, F.: Accurate vehicle positioning on a numerical map. Int. J. Control Autom. Syst. 3, 15–31 (2005)
Jo, K., Chu, K., Sunwoo, M.: GPS-bias correction for precise localization of autonomous vehicles. In: IV (2013)
Lee, D.D., Vernaza, P.: Robust GPS/INS-aided localization and mapping via GPS bias estimation. In: ISER (2006)
Arth, C., Wagner, D., Klopschitz, M., Irschara, A., Schmalstieg, D.: Wide area localization on mobile phones. In: ISMAR (2009)
Dong, Z., Zhang, G., Jia, J., Bao, H.: Keyframe-based real-time camera tracking. In: ICCV (2009)
Tong, G., Wu, Z., Weng, N., Hou, W.: An omni-directional vSLAM based on spherical camera model and 3D modeling. in: World Congress on Intelligent Control and Automation (2012)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Larnaout, D., Gay-Bellile, V., Bourgeois, S. et al. Fast and automatic city-scale environment modelling using hard and/or weak constrained bundle adjustments. Machine Vision and Applications 27, 943–962 (2016). https://doi.org/10.1007/s00138-016-0766-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00138-016-0766-6