Automatic classification of underground utilities in Urban Areas: A novel method combining ground penetrating radar and image processing

• Autorzy: Pasternak Klaudia , Fryśkowska-Skibniewska Anna

Identyfikatory

DOI

10.24425/ace.2024.149851

Warianty tytułu

PL

Automatyczna klasyfikacja podziemnych sieci uzbrojenia terenu na obszarach zurbanizowanych: nowatorska metoda klasyfikacji integrująca detekcję GPR i przetwarzanie obrazów

• Języki publikacji: EN

Abstrakty

EN

Precise determination of the location of underground utility networks is crucial in the field of civil engineering for: the planning and management of space with densely urbanized areas, infrastructure modernization, during construction and building renovations. In this way, damage to underground utilities can be avoided, damage risks to neighbouring buildings can be minimized, and human and material losses can be prevented. It is important to determine not only the location but also the type of underground utility network. Information about location and network types improves the process of land use design and supports the sustainable development of urban areas, especially in the context of construction works in build-up areas and areas planned for development. The authors were inspired to conduct research on this subject by the development of a methodology for classifying network types based on images obtained in a non-invasive way using a Leica DS2000 ground penetrating radar. The authors have proposed a new classification algorithm based on the geometrical properties of hyperboles that represent underground utility networks. Another aim of the research was to automate the classification process, which may support the user in selecting the type of network in images that are sometimes highly noise-laden. The developed algorithm shortens the time required for image interpretation and the selection of underground objects, which is particularly important for inexperienced operators. The classification results revealed that the average effectiveness of the classification of network types ranged from 42% to 70%, depending on the type of infrastructure.

PL

Precyzyjne określenie położenia podziemnych sieci uzbrojenia terenu jest kluczowe w dziedzinie inżynierii lądowej w zakresie prac modernizacyjnych infrastruktury, podczas budowy i remontów obiektów oraz przy planowaniu i zarządzaniu przestrzenią o gęstej urbanizacji. Wiele zadań administracji publicznej takich jak: pozyskiwanie gruntów, zarządzanie własnością i planowanie zależy od wiarygodności lokalizacji uzbrojenia podziemnego. Pozwala to uniknąć zniszczeń uzbrojenia podziemnego, zminimalizować ryzyko uszkodzeń sąsiednich budynków oraz zapobiec stratom ludzkim i materialnym. Ważne jest, aby określić nie tylko lokalizację, ale również rodzaj sieci uzbrojenia podziemnego. Informacja o lokalizacji i rodzajach sieci usprawnia proces projektowania zagospodarowania terenu i wspiera zrównoważony rozwój obszarów miejskich, zwłaszcza w kontekście prac budowlanych na terenach zabudowanych i planowanych do zabudowy w dziedzinie inżynierii lądowej. Motywacją autorów do podjęcia tematu badawczego było opracowanie metodyki klasyfikacji typów sieci na podstawie bezinwazyjnie pozyskanych obrazów georadarem Leica DS2000. Autorzy zaproponowali nowy algorytm klasyfikacji bazujący na cechach geometrycznych hiperbol reprezentujących sieci podziemne. Celem pracy była również automatyzacja procesu klasyfikacji, który może wspomóc użytkownika w wyborze typu sieci na czasami bardzo zaszumionych obrazach. Echogramy pozyskano w kilkunastu różnych lokalizacjach w Otwocku i na obszarze Wojskowej Akademii Technicznej w Warszawie. Opracowany algorytm pozwala na skrócenie czasu interpretacji obrazów i selekcji obiektów podziemnych, co jest szczególnie istotne dla niedoświadczonych operatorów. Wyniki klasyfikacji wykazały, że średnia skuteczność klasyfikacji typów sieci waha się w graniach od 42% do 70% w zależności od rodzaju infrastruktury podziemnej.

Słowa kluczowe

EN

classification; hyperbola; ground penetrating radar; land surveying; ring projection method; underground infrastructure; urban area

PL

georadar; klasyfikacja; sieć podziemna; uzbrojenie terenu; metoda projekcji pierścieniowej; pomiar geodezyjny; obszar zurbanizowany

• Wydawca: Komitet Inżynierii Lądowej i Wodnej PAN ; Politechnika Warszawska, Wydział Inżynierii Lądowej
• Czasopismo: Archives of Civil Engineering
• Rocznik: 2024
• Tom: Vol. 70, nr 2
• Strony: 59--77
• Opis fizyczny: Bibliogr. 40 poz., il., tab.

Twórcy

autor

Pasternak Klaudia

• Military University of Technology (WAT), Faculty of Civil Engineering and Geodesy, Department of Imagery Intelligence, Warsaw, Poland

• https://orcid.org/0000-0001-5794-0560

autor

Fryśkowska-Skibniewska Anna

• Military University of Technology (WAT), Faculty of Civil Engineering and Geodesy, Department of Imagery Intelligence, Warsaw, Poland

• https://orcid.org/0000-0001-5449-8092

Bibliografia

• [1] P. Stones and T.Y. Heng, “Underground space development key planning factors”, Procedia Engineering, vol. 165, pp. 343-354, 2016, doi: 10.1016/j.proeng.2016.11.709.
• [2] C. Akcay, A. Solt, and N.M. Korkmaz, “A proposal for the reconstruction of a historical masonry building constructed in Ottoman Era (Istanbul)”, Journal of Building Engineering, vol. 32, art. no. 101493, 2020, doi: 10.1016/j.jobe.2020.101493.
• [3] M. Metwaly, “Application of GPR technique for subsurface utility mapping: A case study from urban area of Holy Mecca, Saudi Arabia”, Measurement, vol. 60, pp. 139-145, 2015, doi: 10.1016/j.measurement.2014.09.064.
• [4] W. Nawrocki and Z. Piasek, “Experimental testing of-geo-radar resolving power for detection of underground installations”, Geodesy and Cartography, vol. 54, no. 3, pp. 119-130, 2005.
• [5] S. Cafiso, A. Di Graziano, D. Goulias, M. Mangiameli, and G. Mussumeci, “Implementation of GPR and TLS data for the assessment of thepp. bridge slab geometry and reinforcement”, Archives of Civil Engineering, vol. 66, no. 1, pp. 297-308, 2020, doi: 10.24425/ace.2020.131789.
• [6] A. Hoła, Ł. Sadowski, and J. Szymanowski, “Non-destructive testing and analysis of a XIX Century Brick Masonry Building”, Archives of Civil Engineering, vol. 66, no. 4, pp. 201-219, 2020, doi: 10.24425/ace.2020.135217.
• [7] S. Birkenfeld, “Automatic detection of reflexion hyperbolas in GPR data with neural networks”, in World Automation Congress. Kobe, Japan, 2010, pp. 1-6.
• [8] H. Liu, C. Lin, J. Cui, L. Fan, X. Xie, and B. F. Spencer, “Detection and localization of rebar in concrete by deep learning using ground penetrating radar”, Automation in Construction, vol. 118, art. no. 103279, 2020, doi: 10.1016/j.autcon.2020.103279.
• [9] W. Lei, F. Hou, J. Xi, Q. Tan, M. Xu, X. Jiang, G. Liu, and Q. Gu, “Automatic hyperbola detection and fitting in GPR B-scan image”, Automation in Construction, vol. 106, art. no. 102839, 2019, doi: 10.1016/j.autcon.2019.102839.
• [10] U.S. Khan, W. Al-Nuaimy, and F.E. Abd El-Samie, “Detection of landmines and underground utilities from acoustic and GPR images with a cepstral approach”, Journal of Visual Communication and Image Representation, vol. 21, no. 7, pp. 731-740, 2010, doi: 10.1016/j.jvcir.2010.05.007.
• [11] M.S. Kang, N. Kim, S.B. Im, J.-J. Lee, and Y.-K. An, “3D GPR image-based UcNet for enhancing underground cavity detectability”, Remote Sensing, vol. 11, no. 21, 2019, doi: 10.3390/rs11212545.
• [12] N. Kim, S. Kim, Y.K. An, and J.J. Lee, “Triplanar imagsubing of 3-D GPR data for deep-learning-based underground object detection”, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 11, pp. 4446-4456, 2019, doi: 10.1109/JSTARS.2019.2953505.
• [13] N. Kim, S. Kim, Y.K. An, and J.J. Lee, “A novel 3D GPR image arrangement for deep learning-based underground object classification”, International Journal of Pavement Engineering, vol. 22, no. 6, pp. 740-751, 2021, doi: 10.1080/10298436.2019.1645846.
• [14] R. Parrillo, R.L. Roberts, and A. Haggan, “Bridge deck condition assessment using ground penetrating radar”, presented at International Bridge Conference, Pittsburgh, PA, 2005.
• [15] L.L. olde Scholtenhuis, X. den Duijn, and S. Zlatanova, “Representing geographical uncertainties of utility location data in 3D”, Automation in Construction, vol. 96, pp. 483-493, 2018, doi: 10.1016/j.autcon.2018.09.012.
• [16] B. Jafrasteh and N. Fathianpour, “Automatic extraction of geometrical characteristics hidden in ground-penetrating radar sectional images using simultaneous perturbation artificial bee colony algorithm”, Geophysical Prospecting, vol. 65, no. 1, pp. 324-336, 2017, doi: 10.1111/1365-2478.12413.
• [17] J. Gocał, Ł. Ortyl, and M. Sołtys, “Processing of images recorded by the radar method, aimed at construction of metric 3D models of subsurface objects and structures”, Geodesy and Cartography, vol. 55, no. 1, pp. 47-56, 2006.
• [18] U. Ozkaya, F. Melgani, M. Belete, B. Levent, and S.M. Donelli, “GPR Bscan image analysis with deep learning methods”, Measurement, vol. 165, art. no. 107770, 2020, doi: 10.1016/j.measurement.2020.107770.
• [19] P. Gamba, “Neural detection of pipe signatures in GPR images”, IEEE Transactions on Geoscience and Remote Sensing, vol. 38, no. 2, pp. 790-797, 2000, doi: 10.1109/36.842008.
• [20] Z.J. Long, B.A. Xing, H. Liu, et al., “Hyperbola recognition from ground penetrating radar using deep convolutional neural networks”, in 2nd International Conference on Artificial Intelligence: Techniques and Applications. Shenzhen, China, 2017, pp. 11-13.
• [21] M. Wlodarczyk-Sielicka, J. Lubczonek, and A. Stateczny, “Comparison of selected clustering algorithms of raw data obtained by interferometric methods using artificial neural networks”, in Proceedings of the 17th International Radar Symposium. Krakow, Poland, 2016, pp. 1-5.
• [22] A. Czechowicz, P. Gryboś, J. Jachimski, S. Mikrut, Z. Mikrut, P. Pawlik, and R. Tadeusiewicz, Sieci neuronowe w procesach dopasowania zdjęc lotniczych, (Neural networks in aerial images matching process). AGH Krakow, 2010 (in Polish).
• [23] A. Sekrecka, M. Kedzierski, and D. Wierzbicki, “Pre-Processing of panchromatic images to improve object detection in pansharpened images”, Sensors, vol. 19, no. 23, 2019, sub doi: 10.3390/s19235146.
• [24] J. Lester and L.E. Bernold, “Innovative process to characterize buried utilities using Ground Penetrating Radar”, Automation in Construction, vol. 16, no. 4, pp. 546-555, 2007, doi: 10.1016/j.autcon.2006.09.004.
• [25] X. He, C. Wang, R. Zheng, and X. Li, “GPR image noise removal using Grey Wolf Optimisation in the NSST Domain”, Remote Sensing, vol. 13, no. 21, 2021, doi: 10.3390/rs13214416.
• [26] Z. Xiang, G. Ou, and A. Rashidi, “Robust cascaded frequency filters to recognize rebar in GPR data with complex signal interference”, Automation in Construction, vol. 124, art. no. 103593, 2021, doi: 10.1016/j.autcon.2021.103593.
• [27] X. He, H. Yan, C. Wang, R. Zheng, Y. Li, and X. Li, “Non-stationary random noise removal in ground-penetrating radar images subby using self-guided filtering”, Digital Signal Processing, vol. 129, art. no. 103690, 2022, doi: 10.1016/j.dsp.2022.103690.
• [28] L. Arévalo-Lomas, B. Biosca, D. Paredes-Palacios, and J. Díaz-Curiel, “Processing radargrams to obtain resistivity sections”, Remote Sensing, vol. 14, no. 11, 2022, doi: 10.3390/rs14112639.
• [29] L. Chen and Y. Wang, “Automatic key frame extraction in continuous videos from construction monitoring by using color, texture, and gradient features”, Automation in Construction, vol. 81, pp. 355-368, 2017, doi: 10.1016/j.autcon.2017.04.004.
• [30] Z. Hui-lin, T. Mao, and C. Xiao-li, “Feature extraction and classification of echo signal of ground penetrating radar”, Wuhan University Journal of Natural Sciences, vol. 10, pp. 1009-1012, 2005, doi: 10.1007/BF02832458.
• [31] U. Marmol and N. Borowiec, “Detection of line objects by means of Gabor Wavelets and Hough transform”, Archives of Civil Engineering, vol. 66, no. 3, pp. 339-363, 2020, doi: 10.24425/ace.2020.134401.
• [32] A. Lejzerowicz and M. Wutke, “GPR as a support tool in determining the causes of failure of objects built in the “White Box” technology”, Archives of Civil Engineering, vol. 66, no. 3, pp. 173-189, 2020, doi: 10.24425/ace.2020.134391.
• [33] S. Cafiso, A. Di Graziano, et al., “Implementation of GPR and TLS data for the assessment of the bridge slab geometry and reinforcement”, Archives of Civil Engineering, vol. 66, no. 1, pp. 297-308, 2020, doi: 10.24425/ace.2020.131789.
• [34] K. Onyszko and A. Fryśkowska-Skibniewska, “A new methodology for the detection and extraction of hyperbolas in GPR images”, Remote Sensing, vol. 13, no. 23, 2021, doi: 10.3390/rs13234892.
• [35] A. Zhang, K.C.P. Wang, E. Yang, J.Q. Li, C. Chen, and Y. Qiu, “Pavement lane marking detection using matched filter”, Measurement, vol. 130, pp. 105-117, 2018, doi: 10.1016/j.measurement.2018.07.089.
• [36] L.D. Sharma and R.K. Sunkaria, “A robust QRS detection using novel pre-processing techniques and kurtosis based enhanced efficiency”, Measurement, vol. 87, pp. 194-204, 2016, doi: 10.1016/j.measurement.2016.03.015.
• [37] K. Onyszko and A. Fryśkowska-Skibniewska, “Analysis of the possibility of classification the types of utilities networks on the GPR images”, presented at FIG Congress - Volunteering for the future - Geospatial excellence for a better living, 11-15 September 2022, Warsaw, Poland, 2022.
• [38] P. Guan-Chen, “A tutorial of wavelet for pattern recognition”, National Taiwan University, Taipei, Taiwan, 2011.
• [39] M. Łącka and J. Łubczonek, “Analysis of qualitative and quantitative assessment methods for shoreline extraction”, Zeszyty Naukowe Akademii Morskiej w Szczecinie, no. 69, pp. 9-19, 2022, doi: 10.17402/495.
• [40] W. Lu, J. Dong, et al., “Damage identification of bridge structure model based on empirical mode decomposition algorithm and Autoregressive Integrated Moving Average procedure”, Archives of Civil Engineering, vol. 68, no. 4, pp. 653-667, 2022, doi: 10.24425/ace.2022.143060.