Pontfelhők szegmentálása mesterséges intelligenciával
Point Cloud Segmentation with AI
Keywords:
point clouds, machine learning, deep learning, semantic segmentation / pontfelhő, gépi tanulás, mély tanulás, szemantikus szegmentációAbstract
We present a semantic segmentation method based on machine learning techniques for the automated detection of buildings from point clouds generated through photogrammetric processing. We employed Random Forest and neural network-based classification, combined with DBSCAN clustering. Processing two rural test areas, we successfully segmented more than 90% of the buildings.
Kivonat
Egy gépi tanulási módszereken alapuló szemantikus szegmentáló eljárást mutatunk be fotogrammetria feldolgozással előállított pontfelhőkből az épületek automatizált megtalálására. Random forest illetve neurális hálózat alapú osztályozást valamint DBSCAN csoportképzést alkalmaztunk. Két falusias mintaterület feldolgozása során az épületek több mint 90 százalékát sikerült szegmentálni.
References
[1] Bonaccorso G. Machine Learning Algorithms - Second Edition, 2018. Packt, ISBN 9781789347999
[2] Ditho T. P., Kurniawan A. W. Evaluation of Cloth Simulation Filter (CSF) forGround Filtering in UAV-Based DTM Generation toSupport Urban 3D Cadastre 2025 IOP Conf. Ser.: EarthEnviron. Sci. 1551 012011
[3] Grilli, E., Menna F., Remondino F. A review of point clouds segmentation and classification algorithms, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-2/W3, pp. 339–344, 2017.
[4] He G. B., Li L. L. Research and application of lidar technology in cadastral surveying and mapping. The In-ternational Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLIII-B1-2020, pp. 33–37, 2020. https://doi.org/10.5194/isprs-archives-XLIII-B1-2020-33-2020
[5] Holéczy E. Oláh R. Siki Z., Takács B., Tóth Z., Varga T. Módszertani útmutató az elavult ingatlan-nyilvántartási térképek korszerű technológiákkal végzett felújításához Magyar Mérnöki Kamara Kiadványsorozata 63., 82 p. (2020)
[6] Hrutka B. P., Siki Z., Takács B. VOXEL-BASED POINT CLOUD SEGMENTATION AND BUILDING DETECTION INTERNATIONAL ARCHIVES OF THE PHOTOGRAMMETRY REMOTE SENSING AND SPATIAL INFORMATION SCIENCES 48 : 4/W1-2022 pp. 209-215. , 7 p. (2022) https://doi.org/10.5194%2Fi sprs-archives-XLVIII-4-W1-2022-209-2022
[7] Hrutka B. P. Application of Machine Learning to Detect Building Points in Photogrammetry-based Point Clouds PERIODICA POLYTECHNICA-CIVIL ENGINEERING 68 : 4 pp. 1021-1030. , 10 p. (2024)
[8] Kedzierski M., Fryskowska A., Wierzbicki D., Nerc P. Chosen aspects of the production of the basic map using UAV imagery. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B1, pp. 873–877, 2016. https://doi.org/10.5194/isprsarchives-XLI-B1-873-2016
[9] Kurczynski Z., Bakuła K., Karabin M., Markiewicz J. S., Ostrowski W., Podlasiak P., Zawieska D. The Possibility of Using Images Obtained from the UAS in Cadastral Works. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI-B1, pp. 909–915, 2016. https://doi.org/10.5194/isprsarchives-XLI-B1-909-2016
[10] Li M., Rottensteiner F., Heipke C. Modelling of buildings from aerial LiDAR point clouds using TINs and label maps, ISPRS Journal of Photogrammetry and Remote Sensing, Volume 154,2019,Pages 127-138, ISSN 0924-2716, https://doi.org/10.1016/j.isprsjprs.2019.06.003
[11] Rijsdijk M., van Hinsbergh W. H. M., Witteveen W., tenBuuren G. H. M., Schakelaar G. A., Poppinga G., van Persie M., Ladiges R. Unmanned Aerial Systems in the Process of Juridical Verification of Cadastral Border. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XL-1/W2, pp. 325–331, 2013. https://doi.org/10.5194/isprsarchives-xl-1-w2-325-2013
[12] Šafář V., Potůčková M., Karas, J., Tlustý J., Štefanová E., Jančovič M., Žofková D. C. The use of UAV in Cadastral mapping of the Czech Republic. ISPRS International Journal of Geo-Information, 10(6), 380, 2021. https://doi.org/10.3390/ijgi10060380
[13] Zhang, W., Qi, J., Wan, P., Wang, H., Xie, D., Wang, X., Yan, G. 2016. An Easy-to-Use Airborne LiDAR Data Filtering Method Based on Cloth Simulation. Remote Sensing, 8(6), pp. 1–22. https://doi.org/10.3390/rs8060501
