Three-dimensional building detection and modeling using a statistical approach

In this paper, we address the problem of building reconstruction in high-resolution stereoscopic aerial imagery. We present a hierarchical strategy to detect and model buildings in urban sites, based on a global focusing process, followed by a local modeling. During the first step, we extract the building regions by exploiting to the full extent the depth information obtained with a new adaptive correlation stereo matching. In the modeling step, we propose a statistical approach, which is competitive to the sequential methods using segmentation and modeling. This parametric method is based on a multiplane model of the data, interpreted as a mixture model. From a Bayesian point of view the so-called augmentation of the model with indicator variables allows using stochastic algorithms to achieve both model parameter estimation and plane segmentation. We then report a Monte Carlo study of the performance of the stochastic algorithm on synthetic data, before displaying results on real data.

[1]  N. Shephard.  Partial non-Gaussian state space , 1994 .

[2]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[3]  Andrew Zisserman,et al.  Automatic reconstruction of piecewise planar models from multiple views , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[4]  W. Wong,et al.  The calculation of posterior distributions by data augmentation , 1987 .

[5]  John F. Canny,et al.  A Computational Approach to Edge Detection , 1986, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  C. Brenner,et al.  AN INTEGRATED SYSTEM FOR URBAN MODEL GENERATION , 2000 .

[7]  Gérard Giraudon,et al.  Adaptive window algorithm for aerial image stereo , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[8]  Pascal Fua,et al.  Combining Stereo and Monocular Information to Compute Dense Depth Maps that Preserve Depth Discontinuities , 1991, IJCAI.

[9]  M. Tanner.  Tools for statistical inference: methods for the exploration of posterior distributions and likeliho , 1994 .

[10]  Luc Van Gool,et al.  Automatic Modeling and 3D Reconstruction of Urban House Roofs from High Resolution Aerial Imagery , 1998, ECCV.

[11]  E. Baltsavias,et al.  Automatic Extraction of Man-Made Objects from Aerial and Space Images (II) , 1995 .

[12]  C. Robert,et al.  Estimation of Finite Mixture Distributions Through Bayesian Sampling , 1994 .

[13]  M. J. Hannah.  A system for digital stereo image matching , 1989 .

[14]  E. Baltsavias,et al.  3-D Building Reconstruction with ARUBA: A Qualitative and Quantitative Evaluation , 1997 .

[15]  Matthieu Cord,et al.  Accurate Building Structure Recovery from High Resolution Aerial Imagery , 2001, Comput. Vis. Image Underst..

[16]  Wolfgang Förstner,et al.  Towards automatic building extraction from high-resolution digital elevation models , 1995 .

[17]  Wei Luo,et al.  Using Models to Improve Stereo Reconstruction , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[18]  Howard Schultz,et al.  Terrain reconstruction from widely separated images , 1995, Defense, Security, and Sensing.

[19]  Matthieu Cord,et al.  Building Detection and Reconstruction from Mid- and High-Resolution Aerial Imagery , 1998, Comput. Vis. Image Underst..

[20]  Ramakant Nevatia,et al.  Using Perceptual Organization to Extract 3-D Structures , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  G. Casella,et al.  Explaining the Gibbs Sampler , 1992 .

[22]  Thomas Labe,et al.  ROBUST TECHNIQUES FOR ESTIMATING PARAMETERS OF 3D BUILDING PRIMITIVES , 1998 .

[23]  Takeo Kanade,et al.  A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[24]  H. Maître,et al.  DENSE URBAN DEM WITH THREE OR MORE HIGH-RESOLUTION AERIAL IMAGES , 1998 .

[25]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[26]  Matthieu Cord,et al.  Automatic Extraction and Modelling of Urban Buildings from High Resolution Aerial Images , 1999 .

[27]  Wolfgang Eckstein,et al.  Extracting objects from digital terrain models , 1995, Optics & Photonics.

[28]  Olivier Jamet,et al.  Extraction and textural characterization of above-ground areas from aerial stereo pairs: a quality assessment , 1998 .

[29]  David Declercq,et al.  Bayesian model identification: Application to building reconstruction in aerial imagery , 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

[30]  Christoph Hug,et al.  Extracting Artificial Surface Objects from Airborne Laser Scanner Data , 1997 .