Abstract
In this paper we propose a new method for the extraction of roads from remotely sensed images. Under the assumption that roads form a thin network in the image, we approximate such a network by connected line segments.
To perform this task, we construct a point process able to simulate and detect thin networks. The segments have to be connected, in order to form a line-network. Aligned segments are favored whereas superposition is penalized. These constraints are enforced by the interaction model (called the Candy model). The specific properties of the road network in the image are described by the data term. This term is based on statistical hypothesis tests.
The proposed probabilistic model can be written within a Gibbs point process framework. The estimate for the network is found by minimizing an energy function. In order to avoid local minima, we use a simulated annealing algorithm, based on a Monte Carlo dynamics (RJMCMC) for finite point processes. Results are shown on SPOT, ERS and aerial images.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Baddeley, A.J. and van Lieshout, M.N.M. 1993. Stochastic geometry models in high-level vision. In Statistics and Images, Vol. 1, K.V. Mardia and G.K. Kanji (Eds.). Advances in Applied Statistics, a supplement to Journal of Applied Statistics 20:pp231–256. Abingdon: Carfax.
Barzohar, M. and Cooper, D.B. 1996. Automatic finding of main roads in aerial images by using geometric-stochastic models and estimation. IEEE Trans. on Pattern Analysis and Machine Intelligence, 18:707–721.
Bogess, J.E. 1994. Using artificial neural networks to indentify roads in satellite images. In Proceedings of the World Congress on Neural Networks, San Diego, pp. 410–415.
Fua, P. and Leclerc, Y.G. 1990. Model driven edge detection. Machine Vision and Applications, 3:45–56.
Fischler, M.A., Tenenbaum, J.M. and Wolf, H.C. 1981. Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique. Computer Graphics and Image Procesing, 15:201–223.
Garcin, L., Descombes, X., Zerubia, J. and Le Men, H. 2001. Building detection by Markov object processes and a MCMC algorithm. INRIA Research Report, 4206.
Geman, D. and Jedynak, B. 1996.Anactive testing model for tracking roads in satellite images. IEEE Trans. on Pattern Analysis and Machine Intelligence, 18:1–14.
Geyer, C. J. and Møller, J. 1994. Simulation and likelihood inference for spatial point process. Scandinavian Journal of Statistics, B, 21:359–373.
Geyer, C.J. 1998. Likelihood inference for spatial point processes. In Stochastic Geometry, Likelihood and Computation, O.E. Barndoff-Nielsen, W.S. Kendall and M.N.M. van Lieshout (Eds.), Chapmann and Hall: London.
Graffigne, C. and Herlin, I. 1989. Modélisation de réseaux pour l'Imagerie Satellite SPOT. AFCET, 7eme Congrés de Reconnaissance des Formes et Intelligence Artificielle (Paris), pp. 833– 842.
Green, P. 1995. Reversible jump MCMC computation and bayesian model determination. Biometrika, 82:711–732
Green, P. 1996. MCMC in image analysis In Markov Chain Monte Carlo in Practice, W.R. Gilks, S. Richardson, and D.J. Spiegelhalter (Eds.) pp. 381–399, Chapman and Hall: London.
van Lieshout, M.N.M. 1994. Stochastic annealing for nearestneighbour point processes with application to object recognition. Advances in Applied Probability, 26:281–300.
van Lieshout, M.N.M. 2000. Markov Point Processes and their Applications.Imperial College Press/World Scientific Publishing: London/Singapore.
Merlet, N. and Zerubia, J. 1996. New prospects in line detection by dynamic programming. IEEE Trans. on Pattern Analysis and Machine Intelligence, 18:426–431.
Meyn, S.P. and Tweedie, R.L. 1993. Markov Chains and Stochastic Stability Springer-Verlag: London.
Møller, J. 1998. Markov Chain Monte Carlo and spatial point processes. In Stochastic Geometry, Likelihood and Computation, O.E. Barndoff-Nielsen, W.S. Kendall and M.N.M. van Lieshout (Eds.) Chapmann and Hall: London.
Neuenschwander, W.M., Fua, P., Iverson, L., Szekely, G. and Kubler, O. 1997. Ziplock Snakes. International Journal of Computer Vision, 25(3):191–201.
Ortner, M., Descombes, X. and Zerubia, J. 2002. Building extraction from digital elevation models. INRIA Research Report, 4517.
Preston, C.J. 1977. Spatial birth-and-death processes. Bulletin of the International Statistical Institute, 46:371–391.
Refregier, P., Germain, O. and Gaidon, T. 1997. Optimal snake segmentation of target and background with independentGammadensity probabilities application to speckled and preprocessed images. Optics Communications, 137:382–388.
Robert, C. and Casella, G. 1999. Monte Carlo Statistical Methods Springer-Verlag.
Rue, H. and Syversveen, A.R. 1998. Bayesian object oecognition with Baddley's delta loss. Advances in Applied Probability (SGSA), 30(1):55–75.
Rue, H. and Hurn, M. 1999. Bayesian object identification. Biometrika, (3), 649–660.
Ruelle, D. 1969. Statistical Mechanics: Rigorous Results, W.A. Benjamin: Reading, Massachusetts.
Serendero, M.A. 1989. Extraction d'Informations Symboliques en Imagerie SPOT: Réseaux de Communication et Agglomerations. PhD Thesis (in French), Nice-Sophia Antipolis University.
Stoica, R. 2001. Processus ponctuels pour l'extraction des réseaux linéiques dans les images satellitaires et aériennes. PhD Thesis (in French), Nice Sophia-Antipolis University.
Stoyan, D., Kendall, W.S., and Mecke, J. 1987. Stochastic Geometry and its Applications. John Willey and Sons.
Tupin, F., Maître, H., Mangin, J.-F., Nicolas, J.-M. and Pechersky, E. 1998. Detection of linear features in SAR images: Application to road network extraction. IEEE Trans. Geoscience and Remote Sensing, 36(2):434–453.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Stoica, R., Descombes, X. & Zerubia, J. A Gibbs Point Process for Road Extraction from Remotely Sensed Images. International Journal of Computer Vision 57, 121–136 (2004). https://doi.org/10.1023/B:VISI.0000013086.45688.5d
Issue Date:
DOI: https://doi.org/10.1023/B:VISI.0000013086.45688.5d