Abstract
Understanding cityscapes using remote sensing data has been an active research field for more than two decades. Meanwhile, machine learning provides generalization capabilities compared to hierarchical and rule-based methods. This paper evaluates several machine learning algorithms in order to fuse shadow detection and shadow compensation methods for building detection using high resolution aerial imagery. Three complex and real-life urban study areas were used as test datasets with various: (i) kinds of buildings structures of special architecture, (ii) pixel resolutions and, (iii) types of data. Objective evaluation metrics have been used for assessing the compared algorithms such recall, precision and F1-score as well as rates of completeness, correctness and quality. For both approaches, i.e., shadow detection and building detection, the computational complexity of each machine learning algorithm was examined. The results indicate that deep learning schemes, such a Convolutional Neural Network (CNN), provides the best classification performance in terms of shadow detection and building detection.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR, Seattle, WA, USA (2016)
Maltezos, Ε., Doulamis, Ν., Doulamis, A., Ioannidis, C.: Deep convolutional neural networks for building extraction from orthoimages and dense image matching point clouds. J. Appl. Remote Sens. 11(4), 042620-1–042620-22 (2017)
Rottensteiner, F., Sohn, G., Gerke, M., Wegner, J.D., Breitkopf, U., Jung, J.: Results of the ISPRS benchmark on urban object detection and 3D building reconstruction. ISPRS J. Photogramm. Remote Sens. 93, 256–271 (2014)
Doulamis, A., et al.: 5D modelling: an efficient approach for creating spatiotemporal predictive 3D maps of large-scale cultural resources. In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (PRSSIS), II5/W3, pp. 61–68 (2015)
Lorenzi, L., Melgani, F., Mercier, G.: A complete processing chain for shadow detection and reconstruction in VHR images. IEEE TGARS 50(9), 3440–3452 (2012)
Song, H., Huang, B., Zhang, K.: Shadow detection and reconstruction in high-resolution satellite images via morphological filtering and example-based learning. IEEE TGARS 52(5), 2545–2554 (2013)
Guislain, M., Digne, J., Chaine, R., Kudelski, D., Lefebvre-Albaret, P.: Detecting and correcting shadows in urban point clouds and image collections. In: 3DV, pp. 1–9 (2016)
Hosseinzadeh, S., Shakeri, M., Hong, Z.: Fast shadow detection from a single image using a patched convolutional neural network. In: CVPR, Seattle, Honolulu, Hawaii (2017)
Luo, L., et al.: Automated extraction of the archaeological tops of qanat shafts from VHR imagery in Google Earth. Remote Sensing 6, 11956–11976 (2014)
Doulamis, A., et al.: 4D reconstruction of the past. In: SPIE Proceedings, vol. 8795, pp. 1–11 (2013)
Kadhim, N., Mourshed, M., Bray, M.: Automatic extraction of urban structures based on shadow information from satellite imagery. In: 14th Conference of International Building Performance Simulation, pp. 2607–2614 (2015)
Cerra, D., Plank, S., Lysandrou, V., Tian, J.: Cultural heritage sites in danger-towards automatic damage detection from space. Remote Sens. 8(781), 1–15 (2016)
Zhou, K., Gorte, B.: Shadow detection from VHR aerial images in urban area by using 3D city models and a decision fusion approach. In: ISPRS Annals of the PRSSIS, XLII-2/W7, pp. 579–586 (2017)
Kadhim, N., Mourshed, M.: A shadow-overlapping algorithm for estimating building heights from VHR satellite images. IEEE GRSL 15(1), 8–12 (2018)
Llamas, J., Lerones, P.M., Medina, R., Zalama, E., Gómez-García-Bermejo, J.: Classification of architectural heritage images using deep learning techniques. Appl. Sci. 7(992), 1–25 (2017)
Yasser, A.M., Clawson, K., Bowerman, C., Lévêque, M.: Saving cultural heritage with digital make-believe: machine learning and digital techniques to the rescue. In: Proceedings of British HCI Conference, pp. 1–5 (2017)
Bassier, M., Vergauwen, M., Van Genechten, B.: Automated classification of heritage buildings for as-built BIM using machine learning techniques. In: ISPRS Annals of the PRSSIS, IV-2/W2, pp. 25–30 (2017)
Uhl, J., Leyk, S., Chiang, Y., Duan, W., Knoblock, C.: Exploring the potential of deep learning for settlement symbol extraction from historical map documents. In: UCGIS (2018)
Cheng, G., Han, J.: A survey on object detection in optical remote sensing images. ISPRS J. Photogramm. Remote Sens. 117, 11–28 (2016)
Bhatia, N., Vandana: Survey of nearest neighbor techniques. Int. J. Comput. Sci. Inf. Secur. 8(2), 302–305 (2010)
Rokach, L., Schclar, A., Itach, E.: Ensemble methods for multi-label classification. Expert Syst. Appl. 41(16), 7507–7523 (2014)
Farid, D.M., Zhang, L., Rahman, C.M., Hossain, M.A., Strachan, R.: Hybrid decision tree and naïve Bayes classifiers for multi-class classification tasks. Expert Syst. Appl. 41(4), 1937–1946 (2014)
Zhuang, F., et al.: Mining distinction and commonality across multiple domains using generative model for text classification. IEEE TKDE 24(11), 2025–2039 (2012)
Belgiu, M., Drăguţ, L.: Random forest in remote sensing: a review of applications and future directions. ISPRS J. Photogramm. Remote Sens. 114, 24–31 (2016)
Abe, S.: Support Vector Machines for Pattern Classification. Advances in Computer Vision and Pattern Recognition. Springer, London (2010). https://doi.org/10.1007/978-1-84996-098-4
Protopapadakis, E., et al.: A genetically optimized neural classifier applied to numerical pile integrity tests considering concrete piles. Comput. Struct. 162, 68–79 (2016)
Remondino, F., Spera, M.G., Nocerino, E., Menna, F., Nex., F., Barsanti, S.G.: Dense image matching: comparisons and analyses. In: Proceedings of Digital Heritage International Congress, pp. 47–54 (2013)
Rovithis, Ε., et al.: LiDAR-aided urban-scale assessment of soil-structure interaction effects: the case of Kalochori residential area (N. Greece). Bull. Earthq. Eng. 15(11), 4821–4850 (2017)
Singh, K.K., Pal, K., Nigam, M.J.: Shadow detection and removal from remote sensing images using NDI and morphological operators. Int. J. Comput. Appl. 42(10), 37–40 (2012)
Rottensteiner, F., Sohn, G., Gerke, M., Wegner, J.D.: ISPRS test project on urban classification and 3D building reconstruction, ISPRS—Commission III—Photogrammetric Computer Vision and Image Analysis Working Group III/4–3D Scene Analysis (2013)
Cramer, M.: The DGPF test on digital aerial camera evaluation – overview and test design. Photogrammetrie – Fernerkundung – Geoinformation 2, 73–82 (2010). http://www.ifp.uni-stuttgart.de/dgpf/DKEP-Allg.html
Rutzinger, M., Rottensteiner, F., Pfeifer, N.: A comparison of evaluation techniques for building extraction from airborne laser scanning. IEEE J-STARS 2(1), 11–20 (2009)
Acknowledgments
This research is supported by the European Funded Project of H2020, Terpsichore, under agreement no. 691218.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Maltezos, E., Protopapadakis, E., Doulamis, N., Doulamis, A., Ioannidis, C. (2018). Understanding Historical Cityscapes from Aerial Imagery Through Machine Learning. In: Ioannides, M., et al. Digital Heritage. Progress in Cultural Heritage: Documentation, Preservation, and Protection. EuroMed 2018. Lecture Notes in Computer Science(), vol 11196. Springer, Cham. https://doi.org/10.1007/978-3-030-01762-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-030-01762-0_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01761-3
Online ISBN: 978-3-030-01762-0
eBook Packages: Computer ScienceComputer Science (R0)