Abstract
Through the application of new methods of digital restitution, photogrammetry applied to the urban domain has always contributed to the improvement of the knowledge and control of urban development especially in relation to rapidly changing spaces. In this study, we seek to develop a method of extracting road network from aerial photos at a scale of 1:25000, in the area of El Marsa, a northern suburb of Tunis, Tunisia. As it is generally known, from the intensity variations on the image, the one can make the segmentation, recognize the objects and the forms, and evaluate their spatial positions as well as the relations uniting them. In this context, the roads seem to be of particular interest in urban areas. Their automatic recognition makes them useful in various tasks, including mapping, recalling multisource images, urban planning and automatic navigation. However, despite the various works carried out on this field, none of the sophisticated road detection techniques is perfect. The difficulty of road extraction is seen while establishing a statistical test to know whether a given pixel of the image participates in the road network or not. In fact, this difficulty is accentuated in the urban environment as it is characterized by a strong heterogeneity of attributes. Compared to other cartographic themes such as buildings, contour lines, and vegetation, manual road entry is fast, and the road theme appears to be the easiest one to be automatically restituted. Our major concern, throughout this study, is to elaborate a methodological approach that enables us to replace manual photogrammetric capture by automatic or a semi-automatic captures from the Orthophoto of a 30 cm resolution. In relation to the current state of art, this photogrammetric capture is advantageous in time and material. This work on automatic interpretation of aerial images thus meets the need to optimize the productivity of photogrammetric capture strings without harming the quality of the final product. The problem raised however is related to the automatic extraction of roads in 2D and its transformation into 3D with validation. Our procedure is not limited to image processing, it rather extends to:
-
Road extraction from radiometry-based segmentation using the “eCognition” software.
-
Making a mask for buildings.
While the first step with “eCognition” allows the transformation of the buildings into vector format and polygon type, the second step with “ArcScene” contributes to the juxtaposition of the roads in a continuous way on the Orthophoto. The last step of our procedure consists in the layering of the roads on a Digital Terrain Model (DTM) using the “LPS” software, with a resolution of 1 m in planimetry. The results obtained are evaluated by quantitative statistical approach. In this perspective, it is important to further develop an automatic chain of quality control and validation of the restituted road network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Singh, P. P., & Garg, R. D. (2013). Automatic road extraction from high resolution satellite image using adaptive global thresholding and morphological operations. Journal of the Indian Society of Remote Sensing, 41(3), 631–640.
Richards, J. A. (2013). Remote sensing digital image analysis. Berlin: Springer.
Dosovitskiy, A., Fischer, P., Ilg, E., Hr̈usser, P., Hazırbas, C., Golkov, V., et al. (2015). FlowNet: Learning optical flow with convolutional networks. In IEEE International Conference on Computer Vision (ICCV).
Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for scene segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence.
Pinheiro, P., & Collobert, R. (2014). Recurrent convolutional neural networks for scenelabeling. In International Conference on Machine Learning (pp. 82–90).
Bajcsy, R., & Tavakoli, M. (1976). Computer recognition of roads from satellite pictures. IEEE Transactions on Systems, Man, and Cybernetics, 6(9), 623–637.
Farah, N. (1998). Extraction et évaluation du réseau routier urbain à partir des images satellitaires: développement d’algorithmes. Mémoire (M.Sc) Département de géographie et télédétection Faculté des lettres et sciences humaines Université de Sherbrooke (p. 95).
Mena, J. B. (2003). State of the art on automatic road extraction for GIS update: A novel classification. Pattern Recognition Letters, 24(16), 3037–3058.
Ruskoné, R., & Airault, S. (1997). Toward an automatic extraction of the road network by local interpretation of the scene. In 46th Photogrammetric Week, Stuttgart.
Yoon, H. S., Hackett, J., & Bhattacharya, D. (2002). Proceedings of the National Academy of Sciences of the USA, 99, 11724–11729.
Faber, A., & Förstner, W. (1999). Scale characteristics of local autocovariances for texture segmentation. International Archives of Photogrammetry and Remote Sensing, 32(7–4–3), Valladolid, Spain.
Fischler, M., Tenenbaum, J. M., & Wolf, H. C. (1981). Detection of roads and linear structures in low-resolution herid hagery using an mdtisource knowledge integration technique. Computer Graphics Image Process, 15, 201–223.
Amini, A. A., Weymouth, T. E., & Jain, R. C. (1990). Using dynamic programming for solving variational problems in vision. IEEE Transactions on Pattern Analysis & Machine Intelligence, 12, 855–867.
Stoica, R., Descombes, X., & Zérubia, J. (2000). A Markov point process for road extraction in remote sensed images. Technical Report 3923, Rapport de recherche de l’INRIA.
Dal Poz, A. P., Gyftakis, S., & Agouris, P. (2000). Semiautomatic road extraction: Comparison of methodologies and experiments. In 2000 ASPRS Annual Conference, Washington, DC, USA.
Dal Poz, A. P. & Vale, G. M. (2003). Dynamic programming approach for semi-automated road extraction from medium- and high-resolution images. ISPRS Archives, 34(3/W8), 87–91, Munich.
Lassalle, P. (2015). Étude du passage à l’échelle des algorithmes de segmentation et de classification en télédétection pour le traitement de volumes massifs de données, Doctorat de l’université de Toulouse.
Kass, M., & Witkin, A. (1988). Snakes: Active contours models. International Journal of Computer Vision, 1(4), 321–331.
Steger, C., Mayer, H., Eckstein, W., Heinrich, E., & Baumgartner, A. (1999). Automatic road extraction based on multi-scale, grouping, and context. Photogrammetric Engineering and Remote Sensing, 65(7), 777–785.
Laptev, I., Mayer, H., Lindeberg, T., Eckstein, W., Steger, C., & Baumgartner, A. (2000). Automatic extraction of roads from aerial images based on scale space and snakes. Machine Vision and Applications, 12, 23–31.
Krähenbühl, P., & Koltun, V. (2011). Efficient inference in fully connected CRFs with Gaussian edge potentials. In: Advances in neural information processing systems.
Chen, L. C., Barron, J. T., Papandreou, G., Murphy, K., & Yuille, A. L. (2016). Semantic image segmentation with task-specific edge detection using
Pinheiro, P. O., Lin, T. Y., Collobert, R., & Dollár, P. (2016). Learning to refine object segments. European Conference on Computer Vision (pp. 75–91). Berlin: Springer.
Wang, J., & Howarth, P. J. (1987). Autornated road network extraction from Landsat TM imagery. ASPRS-ACSM, Annual Convention, 1, 429–438.
Ton, J., Jain, A. K., Enslin, W. R., & Hudson, W. D. (1989). Automatic road identification and labelling in Landsat 4 TM images. Photogrammetria, 43, 276–357.
Wang, J., Treitz, P. M., & Howarth, P. J. (1992). Road network detection from SPOT imagery for updating geogaphical information systems in the rural- urban fringe. International Journal of Geographical Information Systems, 6(2), 141–157.
Wang, T.-Q, Liu, X.-W., & Yin, H.-S, (1994). A new species of Hymenopus (Mantodea Hymenopodidae: Hymenopodinae) from China. Entomotaxonomia, 16(2), 79–81.
Matheron, G. (1975). Random sets and integral geometry bull. American Mathematical Society, 81, 844–847.
Serra, J. (1983). Image analysis and mathematical morphology. \(\square \)Cytometry (pp. 184–185). https://doi.org/10.1002/cyto.990040213.
O’Brien, D. (1991). Computer assisted feature extraction (InterEx). In Proceeding of I4th. Canadian Symposium on Rernote Sensing (pp. 423–427).
Wang, D., He, D.-C, Wang, L., & et Morin, D. (1996). L’extraction du réseau routier urbain à partir d’images SPOT HRV. International Journal of Remote Sensing, 17(4), 827–833.
Wang, J., Song, J., Chen, M., & Yang, Z. (2015). Road network extraction: A neural dynamic framework based on deep learning and a finite state machine. International Journal of Remote Sensing, 36, 3144–3169.
Khesali, E., Zoej, M. J. V., Mokhtarzade, M., & Dehghani, M. (2016). Semi automatic road extraction by fusion of high resolution optical and radar image. Journal of the Indian Society of Remote Sensing, 44(1), 21–29.
Reza, H., Riahi, B., Abolfazl, A., Rezaeian, H. (2017). Semi automatic road extraction from digital images. The Egyptian Journal of Remote Sensing and Space Sciences, 20(2017), 117–123.
Zerubia, J., & et Merlet, N. (1993). Classical Mechanics and Roads Detection in SPOT Images. Rapport de Recherche no 1889, lnstitut National de Recherche en Informatique et en Automatique. France. 52 p.
Cleynenbreugel, J. V., Fierens, F., Suetens, P., & Oosterlink, A. (1990). Delineating road structure on satellite imagery by a GIS-guided technique. Photogrammetry and Remote Sensing, 56(6), 893–898.
Jedynak, B. (1995). Modèles stochastiques et méthodes déterministes pour extraire les routes des images de la terre vues du ciel”. Thèse de Doctorat: Université Paris-Sud, France (p. 186).
Vosselman, G., & De Knecht, J. (1995). Road tracking by profile matching and Kalman filtering. In Gruen A., Kuebler O., Agouris P. (Eds.), Workshop on Automatic Extraction of Man-Made Objects from Aerial and Space Images. Birkhauser, Basel (pp. 265–274).
Tamokoue, H. O. (2011). Etude exploratoire de méthodes d’extraction automatique du réseau routier à partir d’images satellites haute résolution. ENSG, 2011, 15–16.
Sehad, M. (2014). Segmentation d’images par une approche basée sur des caractéristiques texturales, temporelles et spectrales: Application aux images MSG. Thèse de doctorat en Télédétection: Université Mouloud Mammeri, Tizi Ouzou, Algérie (200 p.).
Bouziani, M., et al. (2010). Rule-based classification of very high resolution image. IEEE Transactions on Geoscience and Remote Sensing, 48(8), 3198–3211.
Croquerez, J. (1995). Analyse d’images - Filtrage Et Segmentation. Edition Masson.
Deriche, R. (1987). UsingCanny’s Creteria to derive a recursively implemented optimal edge detector. International Journal of Computer Vision, 1(2), 167–187.
Fortier, M. F. A., Ziou, D., Armenakis, C., & Xang, S. (1999). Nouvelles perspectives en détection de contour: textures et images multispectrales. Vision interface, trios rivière (pp. 19–21).
Xue, H., Géraud, T., & Duret-Lutz, A. (2003). Multi-band segmentation using morphological clustering and fusion- application to color image segmentation. In IEEE International Conference on Image Processing.
Martinez-Uso, A., Plat, F., & Garcia-Sevilla, P. (2005). Multispectral images segmentation by energy minimization for fruit quality estimation. In Pattern Recognition and Image Analysis (Vol. 3523, pp. 689–696).
Roussen, M., & Deriche, R. (2002). A variational framework for active and adaptive segmentation of vector valued images. In IEEE proceeding of the workshop on motion and video computing.
Roula, M. A., Bouridane, A., Kurugollo, F., & Amira, A. (2002). UN supervised segmentation of multispectral images using edge progression and cost function. In IEEE International Conference of Image Processing (Vol. 3, pp. 781–784).
Cheng, H. D., & Sun, Y. (2000). A hierarchical approach to color image segmentation using homogeneity. IEEE International Transactions on Image Processing, 9(12), 2071–2082.
Ikonomakis, N., Pataniotis, K. N., & Venetsanopoulos, A. N. (2000). Unsupervised seed determination for a region-based color image segmentation Scheme. In Proceedings of the international conference on image processing, 10–13 September, Vancouver, BC, Vol. 1, pp. 537–540.
Voisine, N. (2002). Approche adaptative de coopération hiérarchique de méthodes de segmentation, application aux images multicomposantes. Ph.D thesis, Université de Rennes 1, 250p.
Tremeau, A., Colantoni, P. (2000). Regions adjacency’s graph applied to color image segmentation. IEEE Transactions on Image Processing, 9(4), 735–744.
Li, P., & Xiao, X. (2007). Multispectral image segmentation by a multichannel Watershed-bases approach. International Journal of Remote Sensing, 28(19), 4429–4452.
Volpi, M., & Tuia, D. (2017). ense semantic labeling of subdecimeter resolution images with convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing, 55, 881–893.
Zhang, R., Sun, D., Yu, Y., & Goldberg, M. D. (2012). Mapping night time flood from MODIS observations using support vector machines. Photogrammetric Engineering and Remote Sensing, 78, 1151–1161.
Girard, M. C., & Girard, C. M. (2003). Processing of remote sensing data (487p). The Netherlands: Balkema.
Bou Kheir, R., Greve, M. H., Deroin, J. P., & Rebai, N. (2011). Implementing GIS regression trees for generating the spatial distribution of copper in Mediterranean environments: The case study of Lebanon. International Journal of Environmental Analytical Chemistry, 20. https://doi.org/10.1080/03067319.2011.603079.
Rebai, N., Slama, T., & Turki, M. M. (2007). Evaluation de différentes méthodes d’interpolation spatiale pour laproduction d’un MNT á partir des données topographiques dans un SIG. Revue XYZ, 110(1er trimester).
Kneale, P., See, L., & Smith, A. (2001). Towards defining measures for neural network forecasting models. In Proceeding of the 6th International Conference on Geocomputation, University of Queensland, 24–26 September 2001, Brisbane, Australia, pp. 61–72.
Nash, J. E., & Sutcliffe, J. V. (1970). River flow forecasting through conceptual models, I, A discussion of principals. Journal of Hydrology, 10(1970), 282–290.
Willmott, C. J. (1981). On the validation of models. Physical Geography, 2(1981), 148–194.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Mansouri, K., Rebai, N., Gaaloul, S., Salhi, M. (2020). Using Aerial Photography for Semi-automatic Extraction of Road Network at a Scale of 1:25000. In: Rebai, N., Mastere, M. (eds) Mapping and Spatial Analysis of Socio-economic and Environmental Indicators for Sustainable Development. Advances in Science, Technology & Innovation. Springer, Cham. https://doi.org/10.1007/978-3-030-21166-0_11
Download citation
DOI: https://doi.org/10.1007/978-3-030-21166-0_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-21165-3
Online ISBN: 978-3-030-21166-0
eBook Packages: Earth and Environmental ScienceEarth and Environmental Science (R0)