[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123183-en":3,"doc-seo-123183-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},123183,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Application of Machine Learning to Detect Building Points in Photogrammetry-based Point Clouds","Modern point cloud acquisition for land surveying and geoinformatics—covering UAV photogrammetry, TLS, ALS, and MMS—enables efficient coverage of large areas with high resolution or accuracy. The main bottleneck is processing massive datasets with millions of points, where manual workflows are time-consuming and often extract only a small subset. An automated processing chain is presented to detect and separate building points from large-scale photogrammetry-based point clouds. The approach combines RANSAC with machine learning methods (DBSCAN and MLP), trained and evaluated on the Heissigheim 3D (H3D) dataset to separate roof and vegetation points with over 90% accuracy, improving building-point separation quality.","[https://doi.org/10.3311/PPci.22496](https://doi.org/10.3311/PPci.22496)  \nCreative Commons Attribution b  \n| 1021  \nPeriodica Polytechnica Civil Engineering, 68(4), pp. 1021–1030, 2024  \nApplication of Machine Learning to Detect Building Points in Photogrammetry-based Point Clouds  \nBence Péter Hrutka1*  \n1 Department of Geodesy and Surveying, Faculty of Civil Engineering, Budapest University of Technology and Economics, Műegyetem rkp. 3., H-1111 Budapest, Hungary  \n* Corresponding author, e-mail: [hrutka.bence@emk.bme.hu](hrutka.bence@emk.bme.hu)  \nReceived: 03 May 2023, Accepted: 29 March 2024, Published online: 29 May 2024  \nAbstract  \nDifferent point cloud technologies such as Terrestrial Laser Scanners (TLS), Airborne Laser Scanners (ALS), Mobile Mapping Systems (MMS), and Unmanned Aerial Vehicles (UAV) have become increasingly more common in land surveying and geoinformatics over recent years. Thanks to these modern tools, experts can survey large areas cost-effectively with either high resolution or high accuracy. However, processing the point cloud, which consists of millions of points, can be a massive challenge. Manual processing of these large datasets can often be very time-consuming and hardware-demanding, and most of the time, only a limited part of the point cloud is used to derive the final products. The solution can be to automate the process as much as possible. Several advanced mathematical methods, especially Machine Learning (ML) algorithms, allow efficient automated processing of point clouds. This paper presentsa processing chain to detect and separate building points from large-scale photogrammetry-based point clouds. The processing is based on the combination of Random Sample Consensus (RANSAC) and Machine Learning (ML) algorithms like Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and Multi-Layer Perceptron (MLP) . Presented methods were trained and tested on established and open available Heissigheim 3D (H3D) dataset to separate roof and vegetation points with over 90% accuracy in order to enhance the separation of building points on large-scale point clouds.  \nKeywords  \nUAV, point cloud, building reconstruction, classification, machine learning  \n1 Introduction  \nUnmanned Aerial Vehicle (UAV) photogrammetry-based measurements have become popular in the last two decades. There are several applications, from geoscience to engineering, where UAVs' utility has been firmly proven. With drones' flexibility and relatively low costs, experts can efficiently develop maps of large areas with high speed and resolution [1] . One of the many applications is updating land registry maps, where Unmanned Aerial Vehicles can supply fast and affordable solutions without entering private properties. In the literature, there are several examples where UAV photogrammetry-based point clouds were used to update old analog maps.  \nOne of the first attempts was in the Netherlands in 2013 [2], where UAV photogrammetry-based point clouds and true-orthophotos were derived from highresolution photos to identify property boundaries. As a result of the test, it was found that the required accuracy of land registry mapping is achievable. GNSS measurements  \nwere applied to check the reliability of the final product, and it proved to be below 10 cm. Similar studies were obtained in Albania [3] and Poland [4] to support land registration and improve the quality of existing maps. These studies have produced equivalent results.  \nWhile UAV-based photogrammetry is a prominent method for generating point clouds with the required accuracy, drones deployed with Light Detection and Ranging (LiDAR) are also increasingly prevalent in mapping applications. A study by He and Li [5] illustrated that LiDAR sensor-based campaigns could also be used in land registry mapping with 5–10 cm of accuracy. A comparable investigation was conducted in the Czech Republic [6], where an experiment was also carried out to compare the res","cbCaip7QYidEKJJq","https://ap.wps.com/l/cbCaip7QYidEKJJq","pdf",6168169,1,10,"English","en",105,"# Introduction\n## Motivation for automation in point cloud processing\n## Related work on UAV photogrammetry and LiDAR\n## Segmentation and classification methods\n## Prior building-point detection approaches","[{\"question\":\"Why is automated processing needed for photogrammetry-based point clouds?\",\"answer\":\"Point clouds contain millions of points, making manual processing slow and hardware-demanding. Automation helps efficiently extract the subset needed for final products.\"},{\"question\":\"What processing chain is proposed to detect building points?\",\"answer\":\"The method combines RANSAC with machine learning algorithms including DBSCAN and a Multi-Layer Perceptron (MLP) to detect and separate building-related points.\"},{\"question\":\"How was the method validated and with what performance?\",\"answer\":\"The approach was trained and tested on the Heissigheim 3D (H3D) dataset to separate roof and vegetation points, achieving over 90% accuracy.\"}]","Application of Machine Learning to Detect Building Points in Photogrammetry-based Point Clouds | PDF",1785815081,25,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"application-of-machine-learning-to-detect-building-points-in-photogrammetry-based-point-clouds","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/application-of-machine-learning-to-detect-building-points-in-photogrammetry-based-point-clouds/123183/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is automated processing needed for photogrammetry-based point clouds?","Question",{"text":75,"@type":76},"Point clouds contain millions of points, making manual processing slow and hardware-demanding. Automation helps efficiently extract the subset needed for final products.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What processing chain is proposed to detect building points?",{"text":80,"@type":76},"The method combines RANSAC with machine learning algorithms including DBSCAN and a Multi-Layer Perceptron (MLP) to detect and separate building-related points.",{"name":82,"@type":73,"acceptedAnswer":83},"How was the method validated and with what performance?",{"text":84,"@type":76},"The approach was trained and tested on the Heissigheim 3D (H3D) dataset to separate roof and vegetation points, achieving over 90% accuracy.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":21,"slug":133},"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]