Comparison of point cloud filtering methods with data acquired by photogrammetric method and RGB-D sensors

Abstract

Point clouds (PCs) are inevitable sources to generate digital solid model-based applications such as reverse engineering, differential 3D modelling, 3D sensing and modelling of environments, scene reconstruction, augmented reality. Photogrammetric methods, Terrestrial Laser Scanners and RGB-D sensors are relatively common among the technologies used to capture PCs. Because of their structural characteristics, measuring systems produce large amounts of noise that cannot be precisely predicted in type and amplitude. Due to the noisy measurements, the spatial orientations of the differential surface particles and the spatial locations of the corner points have a certain degree of deformation. In order to increase visual, spatial and physical quality of the solid model, which is frequently used in reverse engineering, PCs must be filtered to discard noise and outlier. In this paper PC produced from different methods was filtering with Shepard Inverse Distance Weighting method, Gaussian Filtering method, Single Value Decomposition Based Plane Fitting method and Optimization Based Plane Fitting method. Backtracking Search Optimization Algorithm (BSA) was used to fitting plane. Experimental results were compared visually and statistical according to the number of neighborhoods. The results showed that Backtracking Search Optimization based filtering supplied better noise smoothing results than its competitors.

Keywords

• Point cloud
• Photogrammetry
• RGB-D Sensor
• Terrestrial Laser Scanners
• Backtracking Search
• Optimization Based Filter

References

1. Adams A, Gelfand N, Dolson J & Levoy M (2009). Gaussian kd-trees for fast high-dimensional filtering. ACM SIGGRAPH 2009. https://doi.org/10.1145/1576246.1531327
2. Aghababaee H, Ferraioli G, Schirinzi G & Pascazio V (2019). Regularization of SAR Tomography for 3-D Height Reconstruction in Urban Areas. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(2), 648-659.
3. Ahmadabadian A H, Karami A & Yazdan R (2019). An automatic 3D reconstruction system for texture-less objects. Robotics and Autonomous Systems, 117, 29-39.
4. Altuntas C (2015). Integration of point clouds originated from laser scanner and photogrammetric images for visualization of complex details of historical buildings. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 40(5), 431.
5. Amenta N (1999). The crust algorithm for 3 D surface reconstruction. Symposium on Computational geometry, 423-424.
6. Babak O & Deutsch C V (2009). Statistical approach to inverse distance interpolation. Stochastic Environmental Research and Risk Assessment, 23(5), 543-553.
7. Bellekens B, Spruyt V, Berkvens R & Weyn M (2014). A survey of rigid 3D point cloud registration algorithms. International Journal on Advances in Intelligent Systems, 8, 118-127.
8. Cai S, Zhang W, Liang X, Wan P, Qi J, Yu S & Shao J (2019). Filtering airborne LiDAR data through complementary cloth simulation and progressive TIN densification filters. Remote Sensing, 11(9), 1037.

9. Civicioglu P (2013). Backtracking search optimization algorithm for numerical optimization problems. Applied Mathematics and Computation, 219(15), 8121-8144.
10. Civicioglu P, Besdok E, Gunen M A & Atasever U H (2020). Weighted differential evolution algorithm for numerical function optimization: a comparative study with cuckoo search, artificial bee colony, adaptive differential evolution, and backtracking search optimization algorithms. Neural Computing and Applications, 32, 3923–3937.
11. Doğan Y & Yakar M (2018). GIS and three-dimensional modeling for cultural heritages. International Journal of Engineering and Geosciences, 3(2), 50-55.
12. Fleishman S, Drori I & Cohen-Or D (2003). Bilateral mesh denoising. ACM Transactions on Graphics (TOG), 950-953.
13. Garcia-Garcia A, Orts-Escolano S, Garcia-Rodriguez J & Cazorla M (2018). Interactive 3D object recognition pipeline on mobile GPGPU computing platforms using low-cost RGB-D sensors. Journal of Real-Time Image Processing, 14(3), 585-604.
14. Golub G H & Reinsch C (1971). Singular value decomposition and least squares solutions. In Linear Algebra (pp. 134-151): Springer, Berlin, Heidelberg
15. Gunen M A (2017). Comparison of point cloud filtering algorithms. Master’s Thesis, Erciyes University, Kayseri.
16. Gunen M A, Atasever Ü H, Taşkanat T & Besdok E (2019). Usage of unmanned aerial vehicles (UAVs) in determining drainage networks. Nature Sciences, 14(1), 1-10.
17. Gunen M A, Besdok E, Civicioglu P & Atasever U H (2020). Camera calibration by using weighted differential evolution algorithm: a comparative study with ABC, PSO, COBIDE, DE, CS, GWO, TLBO, MVMO, FOA, LSHADE, ZHANG and BOUGUET. Neural Computing and Applications.
18. Gunen M A, Çoruh L & Besdok E (2017). Oyun Dünyasında Model Ve Doku Üretiminde Fotogrametri Kullanımı. Geomatik, 2(2), 86-93.
19. Gunen M A, Kesikoglu A, Karkinli A E & Besdok E (2017). RGB-D sensörler ile iç mekan haritalamasi [Turkish-only]. International Artificial Intelligence and Data Processing Symposium (IDAP).
20. Han X-F, Jin J S, Wang M-J, Jiang W, Gao L & Xiao L (2017). A review of algorithms for filtering the 3D point cloud. Signal Processing: Image Communication, 57, 103-112.
21. Hoppe H, DeRose T, Duchamp T, McDonald J & Stuetzle W (1992). Surface reconstruction from unorganized points. Proceedings of the 19th annual conference on Computer graphics and interactive techniques (pp. 71-78).
22. Hou W, Chan T & Ding M (2012). Denoising point cloud. Inverse Problems in Science and Engineering, 20(3), 287-298.
23. Javernick L, Brasington J & Caruso B (2014). Modeling the topography of shallow braided rivers using Structure-from-Motion photogrammetry. Geomorphology, 213, 166-182.
24. Jia C, Yang T, Wang C, Fan B & He F (2019). A new fast filtering algorithm for a 3D point cloud based on RGB-D information. PloS one, 14(8).
25. Juan L & Gwon O (2009). A comparison of sift, pca-sift and surf. International Journal of Signal Processing, Image Processing and Pattern Recognition, 8(3), 169-176.
26. Kurban T (2014). 3 Boyutlu Nesnelerin Modellenmesi İçin Nokta Bulutlarının Sezgisel Optimizasyon Yöntemleri İle İşlenmesi. PhD Thesis, Erciyes Universitesi, Kayseri.
27. Li Y, Snavely N, Huttenlocher D & Fua P (2012). Worldwide pose estimation using 3d point clouds. European conference on computer vision.
28. Lu G Y & Wong D W (2008). An adaptive inverse-distance weighting spatial interpolation technique. Computers & Geosciences, 34(9), 1044-1055.
29. Narváez E A L & Narváez N E L (2006). Point cloud denoising using robust principal component analysis. GRAPP, 51-58.
30. Nyarko E K, Vidović I, Radočaj K & Cupec R (2018). A nearest neighbor approach for fruit recognition in RGB-D images based on detection of convex surfaces. Expert Systems with Applications, 114, 454-466.
31. Oliveira A, Oliveira J F, Pereira J M, De Araújo B R & Boavida J (2014). 3D modelling of laser scanned and photogrammetric data for digital documentation: the Mosteiro da Batalha case study. Journal of real-time image processing, 9(4), 673-688.
32. 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.
33. Stückler J, Waldvogel B, Schulz H & Behnke S (2015). Dense real-time mapping of object-class semantics from RGB-D video. Journal of real-time image processing, 10(4), 599-609.
34. Tercan E (2017). İnsansız hava aracı kullanılarak antik kent ve tarihi kervan yolunun fotogrametrik belgelenmesi: Sarıhacılar örneği. Mühendislik Bilimleri ve Tasarım Dergisi, 5(3), 633-642.
35. Tercan E (2018). Karayolu ölçmelerinde insansız hava araçlarının kullanılması: Okurcalar şehir merkezi örneği. Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, 7(2), 649-660.
36. Tercan E, Besdok E & Tapkın S (2020). Heuristic Modelling of traffic accident characteristics. Transportation Letters, 1-9. Tölgyessy M & Hubinský P (2011). The kinect sensor in robotics education. Proceedings of 2nd International Conference on Robotics in Education, 143-146.
37. Ulvi̇ 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.
38. URL https://faro.app.box.com/s/ou88y63qotb5cnid5610nc570z74cpsu/file/441669813395, Accessed on: 2 October 2019.
39. Vock R, Dieckmann A, Ochmann S & Klein R (2019). Fast template matching and pose estimation in 3D point clouds. Computers & Graphics, 79, 36-45.
40. Wirjadi O & Breuel T (2005). Approximate separable 3D anisotropic Gauss filter. IEEE International Conference on Image Processing, Genova, Italy.
41. Wolff K, Kim C, Zimmer H, Schroers C, Botsch M, Sorkine-Hornung O & Sorkine-Hornung A (2016). Point cloud noise and outlier removal for image-based 3D reconstruction. Fourth International Conference on 3D Vision (3DV), 118-127.
42. Xiang T & Cheong L-F (2003). Understanding the behavior of SFM algorithms: A geometric approach. International journal of computer vision, 51(2), 111-137.
43. Yu J, McMillan L & Gortler S (2004). Surface camera (scam) light field rendering. International Journal of Image and Graphics, 4(04), 605-625.