{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T10:41:47Z","timestamp":1774435307650,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"21","license":[{"start":{"date-parts":[[2019,10,29]],"date-time":"2019-10-29T00:00:00Z","timestamp":1572307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2018R1A1A1A05078493"],"award-info":[{"award-number":["2018R1A1A1A05078493"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>This paper proposes a 3D ground penetrating radar (GPR) image-based underground cavity detection network (UcNet) for preventing sinkholes in complex urban roads. UcNet is developed based on convolutional neural network (CNN) incorporated with phase analysis of super-resolution (SR) GPR images. CNNs have been popularly used for automated GPR data classification, because expert-dependent data interpretation of massive GPR data obtained from urban roads is typically cumbersome and time consuming. However, the conventional CNNs often provide misclassification results due to similar GPR features automatically extracted from arbitrary underground objects such as cavities, manholes, gravels, subsoil backgrounds and so on. In particular, non-cavity features are often misclassified as real cavities, which degrades the CNNs\u2019 performance and reliability. UcNet improves underground cavity detectability by generating SR GPR images of the cavities extracted from CNN and analyzing their phase information. The proposed UcNet is experimentally validated using in-situ GPR data collected from complex urban roads in Seoul, South Korea. The validation test results reveal that the underground cavity misclassification is remarkably decreased compared to the conventional CNN ones.<\/jats:p>","DOI":"10.3390\/rs11212545","type":"journal-article","created":{"date-parts":[[2019,10,31]],"date-time":"2019-10-31T05:18:26Z","timestamp":1572499106000},"page":"2545","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":54,"title":["3D GPR Image-based UcNet for Enhancing Underground Cavity Detectability"],"prefix":"10.3390","volume":"11","author":[{"given":"Man-Sung","family":"Kang","sequence":"first","affiliation":[{"name":"Department of Architectural Engineering, Sejong University, Seoul 05006, Korea"}]},{"given":"Namgyu","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Sejong University, Seoul 05006, Korea"}]},{"given":"Seok Been","family":"Im","sequence":"additional","affiliation":[{"name":"Research Institute for Infrastructure Performance, KISTEC, Jinju 52856, Korea"}]},{"given":"Jong-Jae","family":"Lee","sequence":"additional","affiliation":[{"name":"Department of Civil and Environmental Engineering, Sejong University, Seoul 05006, Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3852-9025","authenticated-orcid":false,"given":"Yun-Kyu","family":"An","sequence":"additional","affiliation":[{"name":"Department of Architectural Engineering, Sejong University, Seoul 05006, Korea"}]}],"member":"1968","published-online":{"date-parts":[[2019,10,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1016\/j.enggeo.2007.11.020","article-title":"Sinkhole distribution in a rapidly developing urban environment: Hillsborough Country, Tampa Bay area, Florida","volume":"99","author":"Brinkmann","year":"2008","journal-title":"Eng. Geol."},{"key":"ref_2","unstructured":"(2019, April 05). Massive Sinkhole Nearly Swallows Home in Pennsylvania. Available online: https:\/\/philadelphia.cbslocal.com\/2017\/01\/25\/massive-sinkhole-opens-up-in-cheltenham-twp\/."},{"key":"ref_3","unstructured":"(2019, April 18). Huge Sinkholes Are Now Appearing in the Wrong Places. Available online: https:\/\/phys.org\/news\/2017-05-huge-sinkholes-wrong.html."},{"key":"ref_4","unstructured":"(2019, March 12). Watch: Four Killed after Massive Sinkhole Opens in Chinese City. Available online: https:\/\/www.newschannel5.com\/news\/world\/china-sinkhole-video."},{"key":"ref_5","unstructured":"(2019, April 04). Huge Sinkhole Opens up on a Busy Chinese Road and Engulfs a Tree and a Minivan. Available online: https:\/\/www.dailymail.co.uk\/news\/article-4593858\/Huge-sinkhole-opens-busy-Chinese-road.html."},{"key":"ref_6","unstructured":"(2019, April 05). Huge Sinkhole Swallows Street in Fukuoka, Japan. Available online: https:\/\/www.bbc.com\/news\/world-asia-37906065#."},{"key":"ref_7","unstructured":"(2019, April 05). Sinkhole in Seoul Forces 200 Residents to Evacuate. Available online: http:\/\/koreabizwire.com\/sinkhole-in-seoul-forces-200-residents-to-evacuate\/123512."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.geomorph.2015.04.018","article-title":"Sinkhole monitoring and early warning: An experimental and successful GB-InSAR application","volume":"241","author":"Intrieri","year":"2015","journal-title":"Geomorphology"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.enggeo.2017.10.009","article-title":"Sinkhole investigation in an urban area by trenching in combination with GPR, ERT and high-precision leveling. Mantled evaporate karst of Zaragoza city, NE Spain","volume":"231","author":"Sevil","year":"2017","journal-title":"Eng. Geol."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Sun, H., Pashoutani, S., and Zhu, J. (2018). Nondestructive evaluation of concrete bridge decks with automated acoustic scanning system and ground penetrating radar. Sensors, 18.","DOI":"10.3390\/s18061955"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1109\/TGRS.2003.817804","article-title":"Discrimination mode processing for EMI and GPR sensors for hand-held land mine detection","volume":"42","author":"Ho","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/S0926-9851(99)00070-1","article-title":"A ground-penetrating radar survey for archaeological investigations in an urban area (Lecce, Italy)","volume":"44","author":"Basile","year":"2000","journal-title":"J. Appl. Geophys."},{"key":"ref_13","unstructured":"Daniel, D.J. (2004). Ground Penetrating Radar, The Institution of Electrical Engineers. [2nd ed.]."},{"key":"ref_14","first-page":"387","article-title":"Data processing and imaging in GPR system dedicated for landmine detection","volume":"3","author":"Groenenboom","year":"2002","journal-title":"SSTA"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"559","DOI":"10.14429\/dsj.67.10048","article-title":"Critical analysis of background subtraction techniques on real GPR data","volume":"67","author":"Sharma","year":"2017","journal-title":"Def. Sci. J."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Park, B.J., Kim, J.G., Lee, J.S., Kang, M.S., and An, Y.K. (2018). Underground object classification for urban roads using instantaneous phase analysis of GPR data. Remote Sens., 10.","DOI":"10.3390\/rs10091417"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Simi, A., Bracciali, S., and Manacorda, G. (2008, January 26\u201330). Hough transform based automatic pipe detection for array GPR: Algorithm development and on-site tests. Proceedings of the IEEE Radar Conference, Rome, Italy.","DOI":"10.1109\/RADAR.2008.4720763"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Li, W., Cui, X., Guo, L., Chen, J., Chen, X., and Cao, X. (2016). Tree root automatic recognition in ground penetrating radar profiles based on randomized Hough transform. Remote Sens., 8.","DOI":"10.3390\/rs8050430"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Noreen, T., and Khan, U.S. (2017, January 21\u201323). Using pattern recognition with HOG to automatically detect reflection hyperbolas in ground penetrating radar data. Proceedings of the International Conference on Electrical and Computing Technologies and Applications, Ras Al Khaimah, UAE.","DOI":"10.1109\/ICECTA.2017.8252064"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1109\/TGRS.2013.2252016","article-title":"Histogram of oriented gradients for landmine detection in ground penetrating radar data","volume":"52","author":"Torrione","year":"2013","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"844","DOI":"10.1080\/08839514.2016.1274250","article-title":"Application of neural network enhanced ground penetrating radar to localization of burial sites","volume":"30","author":"Mazurkiewicz","year":"2016","journal-title":"Appl. Artif. Intell."},{"key":"ref_22","unstructured":"Travassos, X.L., Avila, S.L., and Ida, N. (2018). Artificial neural networks and machine learning techniques applied to ground penetrating radar: A review. Appl. Comput. Inform., in press."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Huston, D., and Xia, T. (2016, January 20\u201324). Underground object characterization based on neural networks for ground penetrating radar data. Proceedings of the SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring, Las Vegas, NV, USA.","DOI":"10.1117\/12.2219345"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/S0926-9851(99)00055-5","article-title":"Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern recognition","volume":"43","author":"Huang","year":"2000","journal-title":"J. Appl. Geophys."},{"key":"ref_25","unstructured":"Lameri, S., Lombardi, F., Bestagini, P., Lualdi, M., and Tubaro, S. (September, January 28). Landmine detection from GPR data using convolutional neural networks. Proceedings of the European Signal Processing Conference, Kos, Greece."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Kim, N.G., Kim, S.H., An, Y.K., and Lee, J.J. (2019). A novel 3D GPR image arrangement for deep learning-based underground object classification. Int. J. Pavement Eng.","DOI":"10.1080\/10298436.2019.1645846"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Kang, M.S., Kim, N.G., Lee, J.J., and An, Y.K. (2019). Deep learning-based automated underground cavity detection using three-dimensional ground penetrating radar. Struct. Health Monit., 1475921719838081.","DOI":"10.1177\/1475921719838081"},{"key":"ref_28","unstructured":"Kizhevsky, A., Sutskever, I., and Hilton, G. (2012, January 3\u20136). ImageNet classification with deep convolutional neural networks. Proceedings of the NIPS\u201912, Lake Tahoe, NV, USA."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., and Fu, Y. (2018, January 8\u201314). Image super-resolution using very deep residual channel attention networks. Proceedings of the European Conference on Computer Vision, Munich, Germany.","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"ref_30","unstructured":"Timofte, R., Gu, S., Gool, L.V., Zhang, L., and Yang, M.H. (2018, January 18\u201322). NTIRE 2018 challenge on single image super-resolution: Methods and results. Proceedings of the Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"163","DOI":"10.1016\/j.cpc.2016.08.020","article-title":"gprMax: Open source software to simulate electromagnetic wave propagation for ground penetrating radar","volume":"209","author":"Warren","year":"2016","journal-title":"Comput. Phys. Commun."},{"key":"ref_32","unstructured":"(2019, October 01). 3D-RADAR. Available online: http:\/\/3d-radar.com\/system\/."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/21\/2545\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:30:21Z","timestamp":1760189421000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/11\/21\/2545"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,29]]},"references-count":32,"journal-issue":{"issue":"21","published-online":{"date-parts":[[2019,11]]}},"alternative-id":["rs11212545"],"URL":"https:\/\/doi.org\/10.3390\/rs11212545","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,29]]}}}