Research Article
BibTex RIS Cite

Lidar Nokta Bulutundan Ransac-Tabanlı Bina Çatı Düzlemi Çıkarımı İçin Bir Yaklaşım

Year 2021, Volume: 2 Issue: 2, 76 - 95, 29.09.2021
https://doi.org/10.48123/rsgis.970893

Abstract

Son yıllarda önemi hızla artan 3B şehir modellerinde bina modellemesi LiDAR verisinin en yaygın uygulama alanları arasında yer almaktadır. Bu çalışmada, hava LiDAR verisinden 3B RANSAC (RANdom SAmple Consensus) algoritması ile çatı düzlemlerinin çıkarımı ve geriçatımı için veri odaklı bir yaklaşım önerilmiş ve iki farklı alanda (A1 ve A2) test edilmiştir. İlk olarak yer filtreleme yapılmıştır. Sonra, sınıflandırma ile tespit edilen bina sınıfı nokta bulutundan her bir binaya ait nokta kümesini çıkarmak için bölge büyüme bölütleme algoritması uygulanmıştır. Çıkarılan çatı düzlemsel yüzeylerde bulunan gürültü, DBSCAN (Density Based Spatial Clustering of Applications with Noise) algoritması kullanılarak tespit edilmiş ve silinmiştir. Doğruluk analizleri için, duyarlık (precision-p), bütünlük (recall-r) ve F-skor (F-score) değerleri hesaplanmıştır. A1 çalışma alanı için ortalama p, r ve F-skor değerleri sırasıyla, %86, %87 ve %85 olarak bulunmuştur. A2 çalışma alanı için bu değerler sırasıyla, %92, %93 ve %92 olarak bulunmuştur. Nokta yoğunluğunun daha yüksek olması ve bina çatı geometrisinin daha düzgün olması, A2 çalışma alanı sonuçlarını olumlu yönde etkilemiştir. Ayrıca, A2 çalışma alanında gürültünün daha başarılı bir şekilde tespiti sağlanmış ve dolayısıyla bu da doğruluk oranlarını artırmıştır.

References

  • Al-Zand, H. A. R. (2013). Bölümleyici kümeleme algoritmalarının farklı veri yoğunluklarında karşılaştırması (Yüksek Lisans Tezi), Gazi Üniversitesi Bilişim Enstitüsü, Ankara.
  • Awrangjeb, M., & Lu, G. (2013, November). Building roof plane extraction from LiDAR data. In International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2013. Proceedings. (pp. 1-8). IEEE.
  • Awrangjeb, M., & Fraser, C. S. (2013). Rule-based segmentation of LiDAR point cloud for automatic extraction of building roof planes. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, II-3/W3, 1-6. doi: 10.5194/isprsannals-II-3-W3-1-2013.
  • Axelsson, P. (2000). DEM generation from laser scanner data using adaptive TIN models. International Archives of Photogrammetry and Remote Sensing, 23(B4), 110–117.
  • Bilgin, T. T., & Çamurcu, Y. (2005). DBSCAN, OPTICS ve K-Means kümeleme algoritmalarının uygulamalı karşılaştırılması. Politeknik Dergisi, 8(2), 139–145.
  • Bretar, F. (2008). Feature extraction from LiDAR data in urban areas. J. Shan & C. K. Toth (Eds.), Topographic Laser Ranging and Scanning: Principles and Processing (pp. 403-418), CRC Press.
  • Canaz, S., Karsli, F., Guneroglu A., & Dihkan, M. (2015, Mayıs). LiDAR verileri kullanılarak göl sınırlarının otomatik olarak belirlenmesi. TUFUAB III. Teknik Sempozyumu, 2015. (pp. 287–293).
  • Carrilho, A., Ivanova, I., & Galo, M. (2017). Quality assessment for automatic LiDAR data classification methods. In XVIII SBSR–Simpósio Brasileiro de Sensoriamento Remoto, Santos–SP, Proceedings. (pp. 6772-6779).
  • Chen, B., Shi, S., Sun, J., Gong, W., Yang, J., Du, L., Guo, K., Wang, B., & Chen, B. (2019). Hyperspectral lidar point cloud segmentation based on geometric and spectral information. Optics Express, 27(17), 24043-24059. doi: 10.1364/OE.27.024043.
  • Chen, D., Zhang, L., Li, J., & Liu, R. (2012). Urban building roof segmentation from airborne LiDAR point clouds. International Journal of Remote Sensing, 33(20), 6497-6515. doi: 10.1080/01431161.2012.690083.
  • Costantino, D., & Angelini, M. G. (2011). Features and ground automatic extraction from airborne lidar data. ISPRS International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVIII-5/W12, 19–24. doi : 10.5194/isprsarchives-XXXVIII-5-W12-19-2011.
  • Çömert, R., & Avdan, U. (2014, Ekim). Yersel lazer tarayıcı verilerinden basit geometrik yüzeylerin otomatik olarak çıkarılması. 5. Uzaktan Algılama-CBS Sempozyumu (UZAL-CBS 2014). 14-17 Ekim, İstanbul.
  • Demir, N. (2016, Ekim). LiDAR Verisinden Çatı Düzlemlerinin Otomatik Çıkarılması. 6. Uzaktan Algılama-CBS Sempozyumu (UZAL-CBS 2016), Proceedings. (pp. 133-138).
  • Dorninger, P., & Nothegger, C. (2007). 3D Segmentation of unstructured point clouds for building modelling. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 36(3/W49A), 191–196.
  • DSM/DTM Filtering. (2021, June 6). International school on LiDAR Technology. Retrieved from http://home.iitk.ac.in/~blohani/LiDARSchool2008/Downloads/DTM_pfeifer.pdf
  • Fan, Y., Wang, M., Geng, N., Hu, S., Chang, J., & Zhang, J. J. (2018). A self-adaptive segmentation method for a point cloud. Visual Computer, 34(5), 659–673. doi: 10.1007/s00371-017-1405-6
  • Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Graphics and Image Processing, 24(6), 381-395.
  • Gönültaş, F., Atik, M. E., & Duran, Z . (2020). Extraction of roof planes from different point clouds using ransac algorithm. International Journal of Environment and Geoinformatics, 7(2), 165-171. doi:10.30897/ijegeo.715510
  • Karsli, F., & Pfeifer, N. (2012, Ekim). Ransac algoritması ile LiDAR verilerinden otomatik detay çıkarımı. IV. Uzaktan Algılama ve Coğrafi Bilgi Sistemleri Sempozyumu (UZAL-CBS 2012). 16-19 Ekim, Zonguldak.
  • Kayı, A., Erdoğan, M., & Eker, O. (2015). Optech HA-500 ve Riegl LMS- Q1560 ile gerçekleştirilen LiDAR test sonuçları. Harita Dergisi, 153, 42–46.
  • LAStools. (2021a, Haziran 6). ALS Filtering. Retrieved from http://lbi-archpro.org/als-filtering/lbi-project/results/lastools/filtering-algorithm-2
  • LAStools. (2021b, Haziran 6). ALS Filtering. Guidelines. Retrieved from http://lbi-archpro.org/als-filtering/lbiproject/results/lastools/guidelines-2
  • LAStools. (2021c, Haziran 6). Rapidlasso GmbH. lasground. Retrieved from https://rapidlasso.com/lastools/lasground/
  • LAStools. (2021d, Haziran 6). Rapidlasso GmbH. lasclassify. Retrieved from https://rapidlasso.com/lastools/lasclassify/
  • Maltezos, E., & Ioannidis, C. (2016). Automatic extraction of building roof planes from airborne lidar data applying an extended 3d randomized hough transform. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, III-3, 209-216. doi: 10.5194/isprs-annals-III-3-209-2016.
  • Morgan, M., & Tempfli, K. (2000). Automatic building extraction from airborne laser scanning data. International Archives of Photogrammetry and Remote Sensing, XXXIII-B3, 616–623.
  • Meng, X., Currit, N., & Zhao, K. (2010). Ground filtering algorithms for airborne LiDAR data: A review of critical issues. Remote Sensing, 2(3), 833–860. doi: 10.3390/rs2030833.
  • PCL. (2021a, Haziran 6). Point Cloud Library (PCL) tutorials. Region growing segmentation. Retrieved from https://pcl.readthedocs.io/projects/tutorials/en/latest/region_growing_segmentation.html#region-growing-segmentation
  • PCL. (2021b, Haziran 6). Point Cloud Library tutorials. Estimating Surface Normals in a PointCloud. Retrieved from https://pcl.readthedocs.io/projects/tutorials/en/latest/normal_estimation.html#normal-estimation
  • RANSAC. (2018, Ocak 22). RANdom SAmple Consensus (RANSAC). Retrieved from http://www.math-info.univparis5.fr/~lomn/Cours/CV/SeqVideo/Material/RANSAC-tutorial.pdf
  • Rusu, R. B. (2010). Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments. Künstl Intell, 24, 345–348. doi: 10.1007/s13218-010-0059-6.
  • Sithole, G., & Vosselman, G. (2003). Report: ISPRS Comparison of Filters. Retrieved from https://www.itc.nl/isprs/wgIII-3/filtertest/report05082003.pdf
  • Tarsha-Kurdi, F., Landes, T., & Grussenmeyer, P. (2007). Hough-transform and extended ransac algorithms for automatic detection of 3d building roof planes from LiDAR data. ISPRS International ‎Archives of Photogrammetry, Remote Sensing and Spatial Information Systems, XXXVI, ‎‎3/W52, 407-412.
  • Vosselman, G., & Dijkman, S. (2001). 3D building model reconstruction from point clouds and ground plans. International Archives of Photogrammetry and Remote Sensing, XXXIV-3/W4, 37-43.
  • Wei, S. (2008). Building boundary extraction base on LiDAR point clouds data. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVII-B3b, 157–161.
  • Yarpiz. (2021, Haziran 6). Implementation of Density-Based Spatial Clustering of Applications with Noise (DBSCAN) in MATLAB. Retrieved from https://www.mathworks.com/matlabcentral/fileexchange/52905-dbscan-clustering-algorithm
  • Zaman, T. (2018, Ocak 22). 3D RANSAC (get planes from point clouds). Retrieved from http://www.timzaman.com/2011/03/3d-ransacplanaire-oppervlakken-uit-puntwolken/

An Approach for Ransac-Based Building Roof Plane Extraction from Lidar Point Cloud

Year 2021, Volume: 2 Issue: 2, 76 - 95, 29.09.2021
https://doi.org/10.48123/rsgis.970893

Abstract

In 3D city modelling, the importance of which has increased rapidly in recent years, building modelling is among the most frequently used application areas of LiDAR data. In this study, a data-driven approach was proposed for the extraction and reconstruction of roof planes from aerial LiDAR data using 3D RANSAC (RANdom SAmple Consensus) algorithm and tested in two areas (A1 and A2). First, ground filtering was performed. Then, region growing segmentation algorithm was applied to extract point set of each building from the building class detected through classification. The noise that exists on the extracted planar surfaces were detected and removed using the DBSCAN (Density Based Spatial Clustering of Applications with Noise) algorithm. For accuracy assessment, precision (p), recall (r), and F-score values were calculated. For study area A1, the mean values for p, r and F-score were computed as 86%, 87% and 85%, respectively. For study area A2, these values were computed as 92%, 93% and 92%, respectively. The higher density of point cloud and smoother roof geometry appear to have affected the results positively in study area A2. Besides, the noise was more successfully detected in study area A2, which increased the accuracy rates.

References

  • Al-Zand, H. A. R. (2013). Bölümleyici kümeleme algoritmalarının farklı veri yoğunluklarında karşılaştırması (Yüksek Lisans Tezi), Gazi Üniversitesi Bilişim Enstitüsü, Ankara.
  • Awrangjeb, M., & Lu, G. (2013, November). Building roof plane extraction from LiDAR data. In International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2013. Proceedings. (pp. 1-8). IEEE.
  • Awrangjeb, M., & Fraser, C. S. (2013). Rule-based segmentation of LiDAR point cloud for automatic extraction of building roof planes. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, II-3/W3, 1-6. doi: 10.5194/isprsannals-II-3-W3-1-2013.
  • Axelsson, P. (2000). DEM generation from laser scanner data using adaptive TIN models. International Archives of Photogrammetry and Remote Sensing, 23(B4), 110–117.
  • Bilgin, T. T., & Çamurcu, Y. (2005). DBSCAN, OPTICS ve K-Means kümeleme algoritmalarının uygulamalı karşılaştırılması. Politeknik Dergisi, 8(2), 139–145.
  • Bretar, F. (2008). Feature extraction from LiDAR data in urban areas. J. Shan & C. K. Toth (Eds.), Topographic Laser Ranging and Scanning: Principles and Processing (pp. 403-418), CRC Press.
  • Canaz, S., Karsli, F., Guneroglu A., & Dihkan, M. (2015, Mayıs). LiDAR verileri kullanılarak göl sınırlarının otomatik olarak belirlenmesi. TUFUAB III. Teknik Sempozyumu, 2015. (pp. 287–293).
  • Carrilho, A., Ivanova, I., & Galo, M. (2017). Quality assessment for automatic LiDAR data classification methods. In XVIII SBSR–Simpósio Brasileiro de Sensoriamento Remoto, Santos–SP, Proceedings. (pp. 6772-6779).
  • Chen, B., Shi, S., Sun, J., Gong, W., Yang, J., Du, L., Guo, K., Wang, B., & Chen, B. (2019). Hyperspectral lidar point cloud segmentation based on geometric and spectral information. Optics Express, 27(17), 24043-24059. doi: 10.1364/OE.27.024043.
  • Chen, D., Zhang, L., Li, J., & Liu, R. (2012). Urban building roof segmentation from airborne LiDAR point clouds. International Journal of Remote Sensing, 33(20), 6497-6515. doi: 10.1080/01431161.2012.690083.
  • Costantino, D., & Angelini, M. G. (2011). Features and ground automatic extraction from airborne lidar data. ISPRS International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVIII-5/W12, 19–24. doi : 10.5194/isprsarchives-XXXVIII-5-W12-19-2011.
  • Çömert, R., & Avdan, U. (2014, Ekim). Yersel lazer tarayıcı verilerinden basit geometrik yüzeylerin otomatik olarak çıkarılması. 5. Uzaktan Algılama-CBS Sempozyumu (UZAL-CBS 2014). 14-17 Ekim, İstanbul.
  • Demir, N. (2016, Ekim). LiDAR Verisinden Çatı Düzlemlerinin Otomatik Çıkarılması. 6. Uzaktan Algılama-CBS Sempozyumu (UZAL-CBS 2016), Proceedings. (pp. 133-138).
  • Dorninger, P., & Nothegger, C. (2007). 3D Segmentation of unstructured point clouds for building modelling. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 36(3/W49A), 191–196.
  • DSM/DTM Filtering. (2021, June 6). International school on LiDAR Technology. Retrieved from http://home.iitk.ac.in/~blohani/LiDARSchool2008/Downloads/DTM_pfeifer.pdf
  • Fan, Y., Wang, M., Geng, N., Hu, S., Chang, J., & Zhang, J. J. (2018). A self-adaptive segmentation method for a point cloud. Visual Computer, 34(5), 659–673. doi: 10.1007/s00371-017-1405-6
  • Fischler, M. A., & Bolles, R. C. (1981). Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Graphics and Image Processing, 24(6), 381-395.
  • Gönültaş, F., Atik, M. E., & Duran, Z . (2020). Extraction of roof planes from different point clouds using ransac algorithm. International Journal of Environment and Geoinformatics, 7(2), 165-171. doi:10.30897/ijegeo.715510
  • Karsli, F., & Pfeifer, N. (2012, Ekim). Ransac algoritması ile LiDAR verilerinden otomatik detay çıkarımı. IV. Uzaktan Algılama ve Coğrafi Bilgi Sistemleri Sempozyumu (UZAL-CBS 2012). 16-19 Ekim, Zonguldak.
  • Kayı, A., Erdoğan, M., & Eker, O. (2015). Optech HA-500 ve Riegl LMS- Q1560 ile gerçekleştirilen LiDAR test sonuçları. Harita Dergisi, 153, 42–46.
  • LAStools. (2021a, Haziran 6). ALS Filtering. Retrieved from http://lbi-archpro.org/als-filtering/lbi-project/results/lastools/filtering-algorithm-2
  • LAStools. (2021b, Haziran 6). ALS Filtering. Guidelines. Retrieved from http://lbi-archpro.org/als-filtering/lbiproject/results/lastools/guidelines-2
  • LAStools. (2021c, Haziran 6). Rapidlasso GmbH. lasground. Retrieved from https://rapidlasso.com/lastools/lasground/
  • LAStools. (2021d, Haziran 6). Rapidlasso GmbH. lasclassify. Retrieved from https://rapidlasso.com/lastools/lasclassify/
  • Maltezos, E., & Ioannidis, C. (2016). Automatic extraction of building roof planes from airborne lidar data applying an extended 3d randomized hough transform. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, III-3, 209-216. doi: 10.5194/isprs-annals-III-3-209-2016.
  • Morgan, M., & Tempfli, K. (2000). Automatic building extraction from airborne laser scanning data. International Archives of Photogrammetry and Remote Sensing, XXXIII-B3, 616–623.
  • Meng, X., Currit, N., & Zhao, K. (2010). Ground filtering algorithms for airborne LiDAR data: A review of critical issues. Remote Sensing, 2(3), 833–860. doi: 10.3390/rs2030833.
  • PCL. (2021a, Haziran 6). Point Cloud Library (PCL) tutorials. Region growing segmentation. Retrieved from https://pcl.readthedocs.io/projects/tutorials/en/latest/region_growing_segmentation.html#region-growing-segmentation
  • PCL. (2021b, Haziran 6). Point Cloud Library tutorials. Estimating Surface Normals in a PointCloud. Retrieved from https://pcl.readthedocs.io/projects/tutorials/en/latest/normal_estimation.html#normal-estimation
  • RANSAC. (2018, Ocak 22). RANdom SAmple Consensus (RANSAC). Retrieved from http://www.math-info.univparis5.fr/~lomn/Cours/CV/SeqVideo/Material/RANSAC-tutorial.pdf
  • Rusu, R. B. (2010). Semantic 3D Object Maps for Everyday Manipulation in Human Living Environments. Künstl Intell, 24, 345–348. doi: 10.1007/s13218-010-0059-6.
  • Sithole, G., & Vosselman, G. (2003). Report: ISPRS Comparison of Filters. Retrieved from https://www.itc.nl/isprs/wgIII-3/filtertest/report05082003.pdf
  • Tarsha-Kurdi, F., Landes, T., & Grussenmeyer, P. (2007). Hough-transform and extended ransac algorithms for automatic detection of 3d building roof planes from LiDAR data. ISPRS International ‎Archives of Photogrammetry, Remote Sensing and Spatial Information Systems, XXXVI, ‎‎3/W52, 407-412.
  • Vosselman, G., & Dijkman, S. (2001). 3D building model reconstruction from point clouds and ground plans. International Archives of Photogrammetry and Remote Sensing, XXXIV-3/W4, 37-43.
  • Wei, S. (2008). Building boundary extraction base on LiDAR point clouds data. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXXVII-B3b, 157–161.
  • Yarpiz. (2021, Haziran 6). Implementation of Density-Based Spatial Clustering of Applications with Noise (DBSCAN) in MATLAB. Retrieved from https://www.mathworks.com/matlabcentral/fileexchange/52905-dbscan-clustering-algorithm
  • Zaman, T. (2018, Ocak 22). 3D RANSAC (get planes from point clouds). Retrieved from http://www.timzaman.com/2011/03/3d-ransacplanaire-oppervlakken-uit-puntwolken/
There are 37 citations in total.

Details

Primary Language Turkish
Subjects Photogrammetry and Remote Sensing
Journal Section Research Articles
Authors

Murat Güler 0000-0002-4212-5114

Mustafa Türker 0000-0001-5604-0472

Publication Date September 29, 2021
Submission Date July 13, 2021
Acceptance Date August 27, 2021
Published in Issue Year 2021 Volume: 2 Issue: 2

Cite

APA Güler, M., & Türker, M. (2021). Lidar Nokta Bulutundan Ransac-Tabanlı Bina Çatı Düzlemi Çıkarımı İçin Bir Yaklaşım. Türk Uzaktan Algılama Ve CBS Dergisi, 2(2), 76-95. https://doi.org/10.48123/rsgis.970893