Classification of UAV point clouds by random forest machine learning algorithm

Abstract

Today, unmanned aerial vehicle (UAV)-based images have become an important data sources for researchers who deals with mapping from various disciplines on photogrammetry and remote sensing. Reconstruction of an area with three-dimensional (3D) point clouds from UAV-based images are an essential process to be used for traditional 2D cadastral maps or to produce a topographic maps. Point clouds should be classified since they subjected to various analyses for extraction for further information from direct point cloud data. Due to the high density of point clouds, data processing and gathering information makes the classification of point clouds a challenging task and may take a long time. Therefore, the classification processing allows an optimal solution to acquire valuable information. In this study, random forest machine learning algorithm for classification processing is applied with radiometric features (Red band, Green band and Blue band) and geometric characteristics derived from covariance feature (curvature, omnivariance, flatness, linearity, surface variance, anisotropy and normalized terrain surface) of points. In addition, the case study is presented in order to test applicability of the proposed methodology to acquire an accuracy and performance of random forest method on the UAV based point cloud. After the classification processing, a class assigned each point from the model was compared with the reference data class. Lastly, the overall accuracy of the classification was achieved as 96% and the Kappa index was reached to 91% on data set.

Keywords

• Unmanned aerial vehicle
• Point cloud
• Classification
• Random forest

References

1. Akar Ö & Güngör O (2012). Classification of multispectral images using Random Forest algorithm. Journal of Geodesy and Geoinformation, 1(2), 105-112. DOI: 10.9733/jgg.241212.1
2. Akgül M, Yurtseven H, Demir M, Akay A E, Gülci S & Öztürk T (2016). Usage opportunities of generating digital elevation model with unmanned aerial vehicles on forestry. Journal of the Faculty of Forestry Istanbul University, 66(1), 104-118 DOI:10.17099/jffiu.23976 (in Turkish)
3. Arya S, Mount D, Kemp S E & Jefferis G (2019). RANN: Fast nearest neighbour search (wraps ANN library) using l2 metric. R package version 2.6, 1. Retrieved from: https://rdrr.io/cran/RANN/
4. ASPRS (2019). LAS Specification 1.4 - R14. American Society for Photogrammetry and Remote Sensing. Retrieved from http://www.asprs.org/wp-content/uploads/2019/03/LAS_1_4_r14.pdf
5. Bivand R S, Pebesma E & Gomez-Rubio V (2008). Applied spatial data analysis with R. ISBN: 978-1-4614-7618-4, Springer, New York.
6. Blomley R, Weinmann M, Leitloff J & Jutzi B (2014). Shape distribution features for point cloud analysis - A geometric histogram approach on multiple scales. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, II-3, 9-16. DOI: 10.5194/isprsannals-II-3-9-2014
7. Breiman L (2001). Random forests. Machine learning, 45(1), 5-32.
8. Chen B, Shi S, Gong W, Zhang Q, Yang J, Du L, Sun J, Zhang Z & Song S (2017). Multispectral liDAR point cloud classification: A two-Step approach. Remote Sensing, 9(4), 373. DOI: 10.3390/rs9040373

9. CloudCompare. (2013). Telecom ParisTech (version 2.4) [GPL software]. EDF R&D. Retrieved from http://www.danielgm.net/cc/
10. Cutler D R, Edwards Jr T C, Beard K H, Cutler A, Hess K T, Gibson J & Lawler J J (2007). Random forests for classification in ecology. Ecology, 88(11), 2783-2792. DOI:10.1890/07-0539.1
11. Çetinkaya B & Toz G (2007). Usage of error matrix in the accuracy assessment of geographic data selection results. İTÜDERGİSİ/d, 6(5-6), 59-68. (in Turkish)
12. Çömert R, Matci D K & Avdan, U. (2019). Object based burned area mapping with random forest algorithm. International Journal of Engineering and Geosciences, 4(2), 78-87. DOI:10.26833/ijeg.455595
13. de Almeida C T, Galvao L S, Aragao L E D E, Ometto J P H B, Jacon A D, Pereira F R D, et al. (2019). Combining LiDAR and hyperspectral data for aboveground biomass modeling in the Brazilian Amazon using different regression algorithms. Remote Sensing of Environment, 232. DOI:10.1016/j.rse.2019.111323
14. Demir N (2015). Various methods to detect buildings using image and lidar data. Havacılık ve Uzay Teknolojileri Dergisi, 8(1), 55-65. (in Turkish)
15. Guo L, Chehata N, Mallet C & Boukir S (2011). Relevance of airborne lidar and multispectral image data for urban scene classification using Random Forests. ISPRS Journal of Photogrammetry and Remote Sensing, 66(1), 56-66. doi:10.1016/j.isprsjprs.2010.08.007
16. Guyot A, Lennon M, Thomas N, Gueguen S, Petit T, Lorho T, Cassen S & Hubert-Moy L (2019). Airborne hyperspectral imaging for submerged archaeological mapping in shallow water environments. Remote Sensing, 11(19). DOI: 10.3390/rs11192237
17. Hackel T, Wegner J D & Schindler K (2017). Joint classification and contour extraction of large 3D point clouds. ISPRS Journal of Photogrammetry and Remote Sensing, 130, 231-245. DOI:10.1016/j.isprsjprs.2017.05.012
18. Karakaş G (2018). An approach for building extraction using lidar point cloud data and high resolution orthophotos. Master's Thesis, Hacettepe University, Ankara (in Turkish).
19. Kashani A G, Olsen M J, Parrish C E & Wilson N (2015). A review of LIDAR radiometric processing: From Ad Hoc intensity correction to rigorous radiometric calibration. Sensors, 15(11), 28099-28128. DOI: 10.3390/s151128099
20. Kim H B & Sohn G (2012). Random forests based multiple classifier system for power-Line scene classification. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 38(5), W12, 253-258. DOI: 10.5194/isprsarchives-XXXVIII-5-W12-253-2011
21. Kraus K & Pfeifer N (1998). Determination of terrain models in wooded areas with airborne laser scanner data. ISPRS Journal of Photogrammetry and Remote Sensing, 53(4), 193-203. DOI: 10.1016/S0924-2716(98)00009-4
22. Kuhn M (2008). Building predictive models in R using the caret package. Journal of Statistical Software, 28(5), 1-26.
23. Liaw A & Wiener M (2002). Classification and regression by randomForest. R news, 2(3), 18-22.
24. Lowe D G (2004). Distinctive image features from Scale-Invariant keypoints. International Journal of Computer Vision, 60(2), 91-110. DOI:10.1023/b:Visi.0000029664.99615.94
25. Luo L, Wang X, Guo H, Lasaponara R, Zong X, Masini N, et al. (2019). Airborne and spaceborne remote sensing for archaeological and cultural heritage applications: A review of the century (1907-2017). Remote Sensing of Environment, 232. DOI:10.1016/j.rse.2019.111280
26. Nevalainen O, Honkavaara E, Tuominen S, Viljanen N, Hakala T. et al. (2017). Individual tree detection and classification with UAV-Based photogrammetric point clouds and hyperspectral imaging. Remote Sensing, 9(3). DOI: 10.3390/rs9030185
27. Niemeyer J, Rottensteiner F & Soergel U (2014). Contextual classification of lidar data and building object detection in urban areas. ISPRS Journal of Photogrammetry and Remote Sensing, 87, 152-165. doi:10.1016/j.isprsjprs.2013.11.001
28. Niu Z, Xu Z, Sun G, Huang W, Wang L, Feng M, Li W, He W, Gao S (2015). Design of a new multispectral waveform LiDAR instrument to monitor vegetation. IEEE Geoscience and Remote Sensing Letters, 12(7), 1506-1510. DOI: 10.1109/LGRS.2015.2410788
29. Ok A Ö, Akar Ö & Güngör O (2011). Classification of crops in agricultural lands using random forest classifıcation method. TUFUAB VI. Teknik Sempozyumu, Antalya, Turkey (in Turkish).
30. Özbay E & Çınar A (2016). A metrical approach to classification of the object modelling with point cloud data. Afyon Kocatepe University Journal of Science and Engineering, 16, 128‐136 (in Turkish)
31. Özdemir E & Remondino F (2019) Classification of aerial point clouds with deep learning. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 42(2), 103-110. DOI: 10.5194/isprs-archives-XLII-2-W13-103-2019
32. Öztürk O, Bilgilioğlu B B, Çelik M F, Bilgilioğlu S S & Uluğ R (2017). The investigation of the height and the camera angle in the production of orthoimage with images of unmanned aerial vehicle (UAV). Geomatik, 2(3), 135-142. DOI:10.29128/geomatik.327049 (in Turkish).
33. Pan Y, Zhang X, Cervone G & Yang L (2018). Detection of asphalt pavement potholes and cracks based on the unmanned aerial vehicle multispectral imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(10), 3701-3712. DOI: 10.1109/JSTARS.2018.2865528
34. Pandey P C, Koutsias N, Petropoulos G P, Srivastava P K & Dor E B (2019). Land use/land cover in view of earth observation: data sources, input dimensions, and classifiers-a review of the state of the art. Geocarto International. DOI:10.1080/10106049.2019.1629647
35. Ramasubramanian K & Singh A (2017). Machine learning using R: Springer, Berkeley. ISBN: 978-1-4842-4215-5
36. Roussel J-R & Auty D (2017). lidR: Airborne LiDAR data manipulation and visualization for forestry applications. Retrieved from:https://github.com/Jean-Romain/lidR.
37. Sevgen S C (2019). Airborne lidar data classification in complex urban area using random forest: A case study of Bergama, Turkey. International Journal of Engineering and Geosciences, 4(1), 45-51. DOI:10.26833/ijeg.440828
38. Shan J & Toth C K (2018). Topographic Laser Ranging and Scanning. Taylor & Francis Group. ISBN:13-978-1-4987-7227-3
39. Sohn G, Jwa Y & Kim H B (2012). Automatic powerline scene classification and reconstruction using airborne lidar data. ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, I-3, 167-172. Doi: 10.5194/isprsannals-I-3-167-2012
40. Şahin B, Güzel C, Baş S & Türker M (2018). 3DETECTOR-LIDAR nokta bulutu verisinden otomatik ağaç konumu belirleme sistemi. VII. Uzaktan Algılama-CBS Sempozyumu, Eskisehir, 21 (in Turkish).
41. Taşcı A E & Onan A (2016). K-en yakın komşu algoritması parametrelerinin sınıflandırma performansı üzerine etkisinin incelenmesi. Akademik Bilişim (in Turkish).
42. Team R C (2019). R: A Language and Environment for Statistical Computing In R Foundation for Statistical Computing, Vienna, Austria.
43. Tóvári D & Pfeifer N (2005). Segmentation based robust interpolation-a new approach to laser data filtering. International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 36(3/19), 79-84.
44. Ulvi A (2018). Analysis of the utility of the unmanned aerial vehicle (UAV) in volume calculation by using photogrammetric techniques. International Journal of Engineering and Geosciences. 3(2), 43-49. DOI:10.26833/ijeg.377080
45. Ulvi A & Toprak A S (2016). Investigation of three-dimensional modelling availability taken photograph of the unmanned aerial vehicle: Sample of Kanlidivane Church. International Journal of Engineering and Geosciences, 1(1), 1-7. DOI: 10.26833/ijeg.285216
46. Ulvi A, Yakar M, Yiğit A Y & Kaya Y (2020). Production of 3 Dimensional Point Clouds and Models of Aksaray Kızıl Kilise by Using UAVs and Photogrammetric Techniques. Geomatik, 5(1), 19-26. DOI:10.29128/geomatik.560179 (in Turkish)
47. Vosselman G (2000). Slope based filtering of laser altimetry data. International Archives of Photogrammetry and Remote Sensing, 33, 935–942.
48. Wei G, Shalei S, Bo Z, Shuo S, Faquan L, Xuewu C (2012). Multi-wavelength canopy LiDAR for remote sensing of vegetation: Design and system performance. ISPRS Journal of Photogrammetry and Remote Sensing, 69, 1-9. DOI:10.1016/j.isprsjprs.2012.02.001
49. Wichmann V, Bremer M, Lindenberger J, Rutzinger M, Georges C, Petrini-Monteferri F (2015). Evaluating the potential of multispectral airborne lidar for topographic mapping and land cover classification. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2(3)(W5), 113-119. DOI:10.5194/isprsannals-II-3-W5-113-2015
50. Yadav M & Singh A K (2017). Rural road surface extraction using mobile LiDAR point cloud data. Journal of the Indian Society of Remote Sensing, 46,531-538. DOI: 10.1007/s12524-017-0732-4
51. Zeybek M & Şanlıoğlu İ (2019a). Point cloud filtering on UAV based point cloud. Measurement, 133, 99-111. DOI:10.1016/j.measurement.2018.10.013
52. Zeybek M & Şanlıoğlu İ (2019b). A study on determination of topographical surface changes by image processing techniques. Journal of Natural Hazards and Environment, 5(2), 350-367. DOI: 10.21324/dacd.531719
53. Zeybek M (2020) PCL-RandomForest-Classification Retrieved from: https://github.com/mzeybek583/PCL-RandomForest-Classification.
54. Zhang K, Chen S C, Whitman D, Shyu M L, Yan J, Zhang C (2003). A progressive morphological filter for removing nonground measurements from airborne LIDAR data. IEEE Transactions on Geoscience and Remote Sensing, 41(4), 872-882. DOI:10.1109/TGRS.2003.810682
55. 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), 501. DOI: 10.3390/rs8060501
56. Zou X, Cheng M, Wang C, Xia Y & Li J (2017). Tree classification in complex forest point clouds based on deep learning. IEEE Geoscience and Remote Sensing Letters, 14(12), 2360-2364. DOI: 10.1109/LGRS.2017.2764938