Abstract
We propose a method to label roads in aerial images and extract a topologically correct road network. Three factors make road extraction difficult: (i) high intra-class variability due to clutter like cars, markings, shadows on the roads; (ii) low inter-class variability, because some non-road structures are made of similar materials; and (iii) most importantly, a complex structural prior: roads form a connected network of thin segments, with slowly changing width and curvature, often bordered by buildings, etc. We model this rich, but complicated contextual information at two levels. Locally, the context and layout of roads is learned implicitly, by including multi-scale appearance information from a large neighborhood in the per-pixel classifier. Globally, the network structure is enforced explicitly: we first detect promising stretches of road via shortest-path search on the per-pixel evidence, and then select pixels on an optimal subset of these paths by energy minimization in a CRF, where each putative path forms a higher-order clique. The model outperforms several baselines on two challenging data sets, both in terms of precision/recall and w.r.t. topological correctness.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
As often done in aerial imaging, when it is available we regard the height-field from dense matching as an additional image channel, and do not separately refer to it.
- 2.
In principle the two-stage classification could potentially be replaced by some form of structured prediction. This would require significantly more training data.
- 3.
If desired the \(P^N\)-Potts model would also allow for conventional pairwise potentials. We did not find them necessary, the context-based unaries are already locally smooth.
- 4.
Graz was kindly provided by Microsoft Photogrammetry. Vaihingen is part of the ISPRS benchmark http://www.itc.nl/ISPRS_WGIII4/tests_datasets.html.
- 5.
\(\kappa \) avoids biases due to uneven class distribution. E.g., for an image with 10 % road pixels a result without a single road pixel has 90 % overall accuracy, but \(\kappa \)=0 %.
References
Bajcsy, R., Tavakoli, M.: Computer recognition of roads from satellite pictures. IEEE Trans. Syst. Man Cybern. 6(9), 623–637 (1976)
Bas, E., Erdogmus, D.: Principal curves as skeletons of tubular objects. Neuroinformatics 9, 181–191 (2011)
Benmansour, F., Cohen, L.D.: Tubular structure segmentation based on minimal path method and anisotropic enhancement. IJCV 92, 192–210 (2011)
Chai, D., Förstner, W., Lafarge, F.: Recovering line-networks in Images by junction-point processes. In: CVPR (2013)
Deschamps, T., Cohen, L.D.: Fast extraction of minimal paths in 3d images and applications to virtual endoscopy. Med. Image Anal. 5(4), 281–299 (2001)
Doucette, P., Agouris, P., Stefanidis, A.: Automated road extraction from high resolution multispectral imagery. Photogram. Eng. Remote Sens. 70(12), 1405–1416 (2004)
Fischler, M., Tenenbaum, J., Wolf, H.: Detection of roads and linear structures in low-resolution aerial imagery using a multisource knowledge integration technique. Comput. Graph. Image Process. 15, 201–223 (1981)
van Gemert, J.C., Geusebroek, J.-M., Veenman, C.J., Smeulders, A.W.M.: Kernel codebooks for scene categorization. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part III. LNCS, vol. 5304, pp. 696–709. Springer, Heidelberg (2008)
Grote, A., Heipke, C., Rottensteiner, F.: Road network extraction in suburban areas. Photogram. Rec. 27(137), 8–28 (2012)
Heipke, C., Mayer, H., Wiedemann, C.: Evaluation of automatic road extraction. In: 3D Reconstruction and Modeling of Topographic Objects (1997)
Hinz, S., Baumgartner, A.: Automatic extraction of urban road networks from multi-view aerial imagery. ISPRS J. Photogram. Remote Sens. 58, 83–98 (2003)
Hu, J., Razdan, A., Femiani, J.C., Cui, M., Wonka, P.: Road network extraction and intersection detection from aerial images by tracking road footprints. IEEE TGRS 45(12), 4144–4157 (2007)
Hussain, S., Triggs, B.: Visual recognition using local quantized patterns. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 716–729. Springer, Heidelberg (2012)
Kohli, P., Ladicky, L., Torr, P.H.S.: Robust higher order potentials for enforcing label consistency. In: CVPR (2008)
Kohli, P., Ladicky, L., Torr, P.H.S.: Robust higher order potentials for enforcing label consistency. IJCV 82(3), 302–324 (2009)
Lacoste, C., Descombes, X., Zerubia, J.: Point processes for unsupervised line network extraction in remote sensing. PAMI 27(10), 1568–1579 (2005)
Ladicky, L., Russell, C., Kohli, P., Torr, P.H.S.: Associative hierarchical CRFs for object class image segmentation. In: ICCV (2009)
Lafarge, F., Gimel’farb, G., Descombes, X.: Geometric feature extraction by a multimarked point process. PAMI 32(9), 1597–1609 (2010)
Laptev, I., Mayer, H., Lindeberg, T., Eckstein, W., Steger, C., Baumgartner, A.: Automatic extraction of roads from aerial images based on scale space and snakes. MVA 12, 23–31 (2000)
Li, H., Yezzi, A.: Vessels as 4-D curves: global minimal 4-D paths to extract 3-D tubular surfaces and centerlines. IEEE TMI 26(9), 1213–1223 (2007)
Lindeberg, T.: Scale-space theory: A basic tool for analysing structures at different scales. J. Appl. Stat. 21(2), 224–270 (1994)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)
Malik, J., Belongie, S., Leung, T., Shi, J.: Contour and texture analysis for image segmentation. Int. J. Comput. Vis. 43(1), 7–27 (2001)
Mayer, H., Hinz, S., Bacher, U., Baltsavias, E.: A test of automatic road extraction approaches. IAPRS 36(3), 209–214 (2006)
Mena, J., Malpica, J.: An automatic method for road extraction in rural and semi-urban areas starting from high resolution satellite imagery. Pattern Recogn. Lett. 26, 1201–1220 (2005)
Miao, Z., Shi, W., Zhang, H., Wang, X.: Road centerline extraction from high-resolution imagery based on shape features and multivariate adaptive regression splines. IEEE GRSL 10(3), 583–587 (2013)
Mnih, V., Hinton, G.E.: Learning to detect roads in high-resolution aerial images. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010, Part VI. LNCS, vol. 6316, pp. 210–223. Springer, Heidelberg (2010)
Poullis, C., You, S.: Delineation and geometric modeling of road networks. ISPRS J. Photogram. Remote Sens. 65, 165–181 (2010)
Shechtman, E., Irani, M.: Matching local self-similarities across images and videos. In: Conference on Computer Vision and Pattern Recognition (2007)
Shotton, J., Winn, J.M., Rother, C., Criminisi, A.: TextonBoost: joint appearance, shape and context modeling for multi-class object recognition and segmentation. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 1–15. Springer, Heidelberg (2006)
Stoica, R., Descombes, X., Zerubia, J.: A Gibbs point process for road extraction from remotely sensed images. IJCV 57(2), 121–136 (2004)
Türetken, E., Benmansour, F., Andres, B., Pfister, H., Fua, P.: Reconstructing loopy curvilinear structures using integer programming. In: CVPR (2013)
Türetken, E., Benmansour, F., Fua, P.: Automated reconstruction of tree structures using path classifiers and mixed integer programming. In: CVPR (2012)
Türetken, E., González, G., Blum, C., Fua, P.: Automated reconstruction of dendritic and axonal trees by global optimization with geometric priors. Neuroinformatics 9, 279–302 (2011)
Ünsalan, C., Sirmacek, B.: Road network detection using probabilistic and graph theoretical methods. IEEE TGRS 50(11), 4441–4453 (2012)
Wegner, J.D., Montoya-Zegarra, J.A., Schindler, K.: A higher-order CRF model for road network extraction. In: CVPR (2013)
Wiedemann, C., Heipke, C., Mayer, H., Jamet, O.: Empirical evaluation of automatically extracted road axes. In: CVPR Workshops (1998)
Winn, J., Criminisi, A., Minka, T.: Object categorization by learned universal visual dictionary. In: CVPR (2005)
Zhao, T., Xie, J., Amat, F., Clack, N., Ahammad, P., Peng, H., Long, F., Myers, E.: Automated reconstruction of neuronal morphology based on local geometrical and global structural models. Neuroinformatics 9, 247–261 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Montoya-Zegarra, J.A., Wegner, J.D., Ladický, Ľ., Schindler, K. (2014). Mind the Gap: Modeling Local and Global Context in (Road) Networks. In: Jiang, X., Hornegger, J., Koch, R. (eds) Pattern Recognition. GCPR 2014. Lecture Notes in Computer Science(), vol 8753. Springer, Cham. https://doi.org/10.1007/978-3-319-11752-2_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-11752-2_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-11751-5
Online ISBN: 978-3-319-11752-2
eBook Packages: Computer ScienceComputer Science (R0)