Abstract
This paper presents a novel algorithm that enables the semi-automatic reconstruction of human-made structures (e.g., buildings) into piecewise planar 3D models from a single image. This allows the models to be readily used in virtual or augmented reality visual simulations or for data acquisition in 3D geographic information systems. Contrary to traditional labor-intensive but accurate single view reconstruction (SVR) solutions based purely on geometric constraints, and contrary to recent fully automatic albeit low-accuracy SVR algorithms based on statistical inference, the presented method achieves a compromise between speed and accuracy, leading to less user input and acceptable visual effects. The user input required in the presented approach is primarily a line drawing that represents an outline of the building to be reconstructed. Using this input, the developed method takes advantage of a newly proposed vanishing point (VP) detection algorithm that can simultaneously estimate multiple VPs in an image. With those VPs, the normal direction of planes—which are projected onto the image plane as polygons in the line drawing—can be automatically calculated. Following this step, a linear system similar to the traditional SVR solutions can be used to achieve 3D reconstruction. Experiments that demonstrate the efficacy and visual outcome of the developed method are also described, highlighting the method’s potential use for rapid geometric model building of surrounding structures in visual simulation of engineering processes.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Behzadan AH, Kamat VR (2009) Automated generation of operations level construction animations in outdoor augmented reality (special issue on Graphical 3D Visualization in Architecture, Engineering, and Construction, American Society of Civil Engineers, Reston, VA). J Comput Civil Eng 23(6):405–4417
Brooks FP (1999) What's real about virtual reality? IEEE Comput. Graph. Appl 19(6):16–27
Caprile B, Torre V (1990) Using vanishing points for camera calibration. Int J Comput Vision 4:127–139
Coughlan JM, Yuille AL (1999) Manhattan world: compass direction from a single image by Bayesian Inference. In: International conference on computer vision (ICCV), 1999
Criminisi A, Reid I, Zisserman A (2000) Single view metrology. Int J Comput Vision 40:123–148
Delage E, Lee H, Ng A (2006) A dynamic bayesian network model for autonomous 3d reconstruction from a single indoor image. Computer vision and pattern recognition (CVPR) 2:2418–2428
Delage E, Lee H, Ng A (2007) Automatic single-image 3d reconstructions of indoor manhattan world scenes. In: Robotics Research, vol 28, pp 305–321. ISBN: 978-3-540-48110-2
Denis P, Elder J, Estrada F (2008) Efficient edge-based methods for estimating manhattan frames in urban imagery. In: European conference on computer vision, 2008
Duda RO, Hart EP (1972) Use of the Hough transformation to detect lines and curves in pictures. Commun ACM 15(1):11–15
Fischler MA, Bolles RC (1981) Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun ACM 24:381–395
Grompone G, Jakubowicz J, Morel J, Randall G (2010) LSD: a fast line segment detector with a false detection control. IEEE Trans Pattern Anal Mach Intell 32:722
Grossmann E, Santos-Victor J (2005) Least-squares 3D reconstruction from one or more views and geometric clues. Comput Vis Image Underst 99:151–174
Hoiem D, Efros AA, Hebert M (2005) Automatic photo pop-up. ACM Trans Graph (TOG) 24:584
Kamat VR, Martinez JC, Fischer M, Golparvar-Fard M, Pena-Mora F, Savarese S (2011) Research in visualization techniques for field construction (American Society of Civil Engineers, Reston, VA). J Constr Eng Manage 137(10):853–862
Liebowitz D, Zisserman A (1999) Combining scene and auto-calibration constraints. In: The 7th international conference on computer vision, Kerkyra, Greece 1999
Min P, Halderman JA, Kazhdan M, Funkhouser TA (2003) Early experiences with a 3D model search engine. In: Proceeding of the eighth international conference on 3D Web technology, ACM Press, New York, pp 7–18
Saxena A, Chung S, Ng A (2006) Learning depth from single monocular images. Adv Neural Inf Process Syst 18:1161
Sturm P, Maybank SJ (1999) A method for interactive 3d reconstruction of piecewise planar objects from single images. In: British machine vision conference, Nottingham, England, 1999
Tardif JP (2009) Non-iterative approach for fast and accurate vanishing point detection. In: International conference on computer vision (ICCV), 2009
Toldo R, Fusiello A (2008). Robust multiple structures estimation with J-Linkage. In: European conference on computer vision (ECCV), 2008
Van Den Heuvel FA (1998) 3D reconstruction from a single image using geometric constraints. ISPRS J Photogramm Remote Sens 53:354–368
Youichi H, Ken-Ichi A, Kiyoshi A (1997) Tour into the picture: using a spidery mesh interface to make animation from a single image. In: Proceedings of the 24th annual conference on computer graphics and interactive techniques
Zhang H, Shi JJ, Tam CM (2002) Iconic animation for activity-based construction simulation. J Com Civil Engin 16(3):157-164
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Feng, C., Deng, F. & Kamat, V.R. Rapid geometric modeling for visual simulation using semi-automated reconstruction from single image. Engineering with Computers 30, 31–39 (2014). https://doi.org/10.1007/s00366-012-0283-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00366-012-0283-9