Performance analysis of rule-based classification and deep learning method for automatic road extraction

Year 2023, , 83 - 97, 15.02.2023

Zeynep Bayramoğlu , Melis Uzar

https://doi.org/10.26833/ijeg.1062250

Cited By: 11

Abstract

The need for accurate and up-to-date spatial data by decision-makers in public and private administrations is increasing gradually. In recent decades, in the management of disasters and smart cities, fast and accurate extraction of roads, especially in emergencies, is quite important in terms of transportation, logistics planning, and route determination. In this study, automatic road extraction analyses were carried out using the Unmanned Aerial Vehicle (UAV) data set, belonging to the Yildiz Technical University Davutpasa Campus road route. For this purpose, this paper presents a comparison between performance analysis of rule-based classification and U-Net deep learning method for solving automatic road extraction problems. Objects belonging to the road and road network were obtained with the rule-based classification method with overall accuracy of 95%, and with the deep learning method with an overall accuracy of 86%. On the other hand, the performance metrics including accuracy, recall, precision, and F1 score were utilized to evaluate the performance analysis of the two methods. These values were obtained from confusion matrices for 4 target classes consisting of road and road elements namely road, road line, sidewalk, and bicycle road. Finally, integration of classified image objects with ontology was realized. Ontology was developed by defining four target class results obtained as a result of the rule-based classification method, conceptual class definition and properties, rules, and axioms.

Keywords

Automatic road extraction, remote sensing, Deep Learning, Ontology, UAV

References

• Fetai, B., Ostir, K., Kosmatin, F. M. & Lisec, A. (2019). Extraction of visible boundaries for cadastral mapping based on UAV ımagery. Remote Sensing, 11(13), 2-20.
• Kavzoğlu, T., & Tombul, H. (2017). Nesne Tabanlı Sınıflandırmada Segmentasyon Kalitesinin Sınıflandırma Doğruluğu Üzerine Etkisinin İncelenmesi. Afyon Kocatepe Üniversitesi Fen ve Mühendislik Bilimleri Dergisi, 17(1), 118-125.
• Abdollahi, A., Pradhan, B., Shukla, N., Chakraborty, S. & Alamri, A. (2020). Deep Learning Approaches applied to remote sensing datasets for road extraction: A state of the art review. Remote Sensing, 12(9), 4-22.
• Lian, R., Wang, W., Mustafa, N., & Huang, L. (2020). Road Extraction Methods in High-Resolution Remote Sensing Images: A Comprehensive Review. IEEE journal of selected topics in applıed earth observations and remote sensing, 11(5), 552, 2-16.
• Yadav, D. P., Nagarajan, K., Pande, H., Tiwari, P., & Narawade, R. (2020). Automatic urban road extraction from high resolution satellite data using object based ımage analysis: a fuzzy classification approach. Journal of Remote Sensing & GIS, 9(1), 279, 1-8.
• Yiğit, A. Y., & Uysal, M. (2020). Automatic road detection from orthophoto images. Mersin Photogrammetry Journal, 2(1), 10-17.
• Zhang, X., Han, L., & Zhu, L. (2020). How well do deep learning based methods for land cover classification and object detection perform on high resolution remote sensing imagery. Remote Sensing, 12(3), 2-29.
• Senthilnath, J., Varia, N., Dokania, A., Anand, G., & Benediktsson, J. A. (2020). Deep TEC: Deep transfer learning with ensemble classifier for road extraction from UAV imagery. Remote Sensing, 12(2), 245-264.
• Zhang, Z., & Wang, Y. (2019). JointNet: A common neural network for road and building extraction. Remote Sensing, 11(6), 696-718.
• Gao, L., Song, W., Dai, J., & Chen, Y. (2019). Road extraction from high-resolution remote sensing imagery using refined deep residual convolutional neural network. Remote Sensing, 11(5), 552-568.
• Zhang, Z., Liu, Q., & Wang, Y. (2017). Road extraction by deep residual U-Net. IEEE Geoscience and Remote Sensing Letters, 5(15), 749-753.
• Huang, Z., Cheng, G., Wang, H., Li, H., Shi, L., & Pan, C. (2016). Building extraction from multi-source remote sensing images via deep deconvolution neural networks. IEEE International Geoscience and Remote Sensing Symposium, 1835-1838, Beijing, China.
• Abderrahim, N. Y. Q, Abderrahim, S. & Rida, A. (2020). Road segmentation using U-Net architecture. IEEE International Conference of Moroccan Geomatics, 1-4, Casablanca, Morocco.
• Emek, R., & Demir, N. (2020). Building detection from SAR images using U-Net deep learnıng method. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Volume XLIV-4/W3-2020, 5th International Conference on Smart City Applications, 215-218, Virtual Safranbolu, Turkey.
• Xiaoqiang, Lu, Gong, T., & Zheng, X. (2020). Multisource compensation network for remote sensing cross-domain scene classification, IEEE Trans. Geoscience Remote Sensing, 58(4), 2504-2515.
• Sarıturk, B., Bayram, B., Duran, Z., & Seker, D. Z. (2020). Feature extraction from satellite images using SEGNET and fully convolutional networks (FCN) International Journal of Engineering and Geosciences, 5(3), 138 - 143.
• Cheng, G, Xie, X., Han, J., Guo, L., & Xia, G. (2020). Remote sensing ımage scene classification meets deep learning: challenges, methods, benchmarks, and opportunities. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13(1), 3735-3756.
• Cira, C. I., Alcarria, R., Manso-Callejo, M. Á., & Serradilla, F. (2020). A deep learning-based solution for large-scale extraction of the secondary road network from high-resolution aerial orthoimagery. Applied Sciences, 10(20), 2-18.
• Filin, O., Zapara, A. & Panchenko, S. (2018). Road detection with EOSResUNet and post vectorizing algorithm. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 211-215, Salt Lake City, UT, USA.
• Zhang, L., Zhang, L., & Du, B. (2016). Deep learning for remote sensing data: a technical tutorial on the state of the art. IEEE Geoscience and Remote Sensing Magazine, 4(2), 22-40.
• Zhang, Z., Liu, Q., & Wang, Y. (2018). Road extraction by deep residual U-net. IEEE Geoscience and Remote Sensing Letters, 15(5), 749-753.
• Sener, Z. (2020). Ontology use and evaluation in spatial object extraction from multi sensor system data. Doctoral Thesis, Yıldız Technical University, Institute of Science, Istanbul, 159p
• Bouyerbou, H., Bechkoum, K., Benblidia, N., & Lepage, R. (2014). Ontology-based semantic classification of satellite images: Case of major disasters. IEEE Geoscience and Remote Sensing Symposium, 2347-2350, Quebec City, Canada.
• Smeulders, A. W. M., Worring, M., Santini, S., Gupta, A. & Jain, R. (2009). Content-based image retrieval at the end of the early years. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(12), 1349-1380
• Belgiu, M., & Thomas, J. (2013). Ontology based interpretation of very high-resolution imageries- grounding ontologies on visual interpretation keys AGILE Conference, 14-17, Leuven.
• Sener, Z., & Uzar, M. (2020). New trend in object oriented image analysis - ontology. Journal of the Faculty of Engineering and Architecture of Gazi University, 35(1), 479-493.
• Memduhoglu, A., & Basaraner, M. (2022). An approach for multi-scale urban building data integration and enrichment through geometric matching and semantic web. Cartography and Geographic Information Science, 49(1), 1-17.
• Ronneberger, O., Fischer, P., & Brox, T. (2015) U-Net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, Wells W, Frangi A. (eds) Medical Image Computing and Computer-Assisted Intervention MICCAI 2015. Lecture Notes in Computer Science, 234-241, Springer, Cham. ISBN 978-3-319-24574-4
• https://www.tmmob.org.tr/en
• Bayrak, O. C. (2020). Segmentation of liver and brain lesions by deep learning approach from medical images. Master’s Thesis, Yıldız Technical University, Institute of Science, Istanbul, 54p.
• Sørensen, T. (1948). A method of establishing groups of equal amplitude in plant sociology based on similarity of species, and its application to analyses of the vegetation on Danish Commons, Kongelige Danske Videnskabernes Selskab, Biologiske Skrifter, 5, 1-34.
• Savoy, J., Gaussier, E., Savoy, J., & Gaussier, E. (2010). Information retrieval. In N. Indurkhya & F. Damerau (Eds.), Handbook of natural language processing. Boca Raton Chapman; Hall/CRC, 455-484. ISBN: 1420085921
• Rutzinger, M., Rottensteiner, F., & Pfeifer, N. (2009). A comparison of evaluation techniques for building extraction from airborne laser scanning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2(1), 11-20.
• Benbahria, Z., Sebari, I., Hajji, H., & Smiej, M. F. (2021). Intelligent mapping of irrigated areas from Landsat 8 images using transfer learning. International Journal of Engineering and Geosciences, 6(1), 40 - 50.