A Comparative Study for Indoor Planar Surface Segmentation via 3D Laser Point Cloud Data

Year 2020, , 128 - 137, 01.10.2020

Eyüp Eymen Eruyar , Metehan Yılmaz , Berat Yılmaz , Onur Akbulut , Kaya Turgut , Burak Kaleci

https://doi.org/10.34248/bsengineering.735705

Cited By: 1

Abstract

In recent years, point cloud data generated with RGB-D cameras, 3D lasers, and 3D LiDARs have been employed frequently in robotic applications. In indoor environments, RGB-D cameras, which have short-range and can only describe the vicinity of the robots, generally are opted due to their low cost. On the other hand, 3D lasers and LiDARs can capture long-range measurements and generally are used in outdoor applications. In this study, we deal with the segmentation of indoor planar surfaces such as wall, floor, and ceiling via point cloud data. The segmentation methods, which are situated in Point Cloud Library (PCL) were executed with 3D laser point cloud data. The experiments were conducted to evaluate the performance of these methods with the publicly available Fukuoka indoor laser dataset, which has point clouds with different noise levels. The test results were compared in terms of segmentation accuracy and the time elapsed for segmentation. Besides, the general characteristics of each method were discussed. In this way, we revealed the positive and negative aspects of these methods for researchers that plan to apply them to 3D laser point cloud data.

Keywords

3D laser, Segmentation, Planar surfaces, Indoor, Fukuoka indoor dataset, PCL

References

• Anil EB, Tang P, Akinci B, Huber D. 2013. Deviation analysis method for the assessment of the quality of the as-is Building Information Models generated from point cloud data. Aut in Construc, 35: 507-516.
• Besl PJ, Jain RC. 1988. Segmentation through variable-order surface fitting. IEEE Transact on Pat Analy Machine Intel, 10(2): 167-192.
• Cadena C, Košecka J. 2015. Semantic parsing for priming object detection in indoors RGB-D scenes. Int J Robotics Res, 34(4-5): 582-597.
• Egger J, Colen RR, Freisleben B, Nimsky C. 2012. Manual refinement system for graph-based segmentation results in the medical domain. J Medic Sys, 36(5): 2829-2839.
• Ferraz A, Bretar F, Jacquemoud S, Gonçalves G, Pereira L. 2010. 3D segmentation of forest structure using a mean-shift based algorithm. IEEE Int Conference on Image Processing, 1413-1416.
• Fischler MA, Bolles RC. 1981. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun of the ACM, 24(6): 381-395.
• Grilli E, Menna F, Remondino F. 2017. A review of point clouds segmentation and classification algorithms. The Intl Archives of Phot, Remote Sensing and Spatial Inf Sci, 42: 339.
• Himmelsbach M, Hundelshausen FV, Wuensche HJ. 2010. Fast segmentation of 3D point clouds for ground vehicles. IEEE Intelligent Vehicles Symposium, 560-565.
• Ioannou Y, Taati B, Harrap R, Greenspan M. 2012. Difference of normals as a multi-scale operator in unorganized point clouds. Second Int Conference on 3D Imaging, Modeling, Processing, Visualization & Transmission, 501-508.
• Jagannathan A, Miller EL. 2007. Three-dimensional surface mesh segmentation using curvedness-based region growing approach. IEEE Transactions on Pat Analy Machine Intel, 29(12): 2195-2204.
• Kim T, Yu W. 2009. Performance evaluation of ransac family. In Proceedings of the British Machine Vision Conference (BMVC), 1-12.
• Koppula HS, Anand A, Joachims T, Saxena A. 2011. Semantic labeling of 3d point clouds for indoor scenes. In Adv in Neural Inf Processing sys, 244-252.
• Lin Y, Wang C, Zhai D, Li W, Li J. 2018. Toward better boundary preserved supervoxel segmentation for 3D point clouds. ISPRS J Photogrammetry and remote sensing, 143: 39-47.
• Lu Y, Song D. 2015. Robustness to lighting variations: An RGB-D indoor visual odometry using line segments. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 688-694.
• Martinez Mozos O, Nakashima K, Jung H, Iwashita Y, Kurazume R. 2019. Fukuoka datasets for place categorization. Int J Robotics Res, 38(5): 507-517.
• Mattausch O, Panozzo D, Mura C, Sorkine‐Hornung O, Pajarola R. 2014. Object detection and classification from large‐scale cluttered indoor scans. Computer Graphics Forum, 33(2): 11-21.
• Monica R, Aleotti J, Zillich M, Vincze M. 2017. Multi-label point cloud annotation by selection of sparse control points. International Conference on 3D Vision (3DV), 301-308.
• Morsdorf F, Meier E, Kötz B, Itten KI, Dobbertin M, Allgöwer B. 2004. LIDAR-based geometric reconstruction of boreal type forest stands at single tree level for forest and wildland fire management. Remote Sensing of Envir, 92(3): 353-362.
• Mutlu B, Hacıömeroğlu M, Serdar GM, Dikmen M, Sever H. 2014. Silhouette extraction from street view images. Int J Advanced Robotic Sys, 11(7): 114.
• Nguyen A, Le B. 2013. 3D point cloud segmentation: A survey. 6th IEEE conference on robotics, automation and mechatronics (RAM), 225-230.
• Ning X, Zhang X, Wang Y, Jaeger M. 2009. Segmentation of architecture shape information from 3D point cloud. Proceedings of the 8th International Conference on Virtual Reality Continuum and its Applications in Industry, 127-132.
• Papon J, Abramov A, Schoeler M, Worgotter F. 2013. Voxel cloud connectivity segmentation-supervoxels for point clouds. Proceedings of the IEEE conference on computer vision and pattern recognition, 2027-2034.
• PCL-Color-Based Region Growing (PCL-CBRG). 2020. Point Cloud Library Color-Based Region Growing Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/region_growing_rgb_segmentation.html#region-growing-rgb-segmentation (access date: 01.05.2020)
• PCL- Conditional Euclidean Clustering (PCL-CEC). 2020. Point Cloud Library Conditional Euclidean Clustering Segmentation Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/ latest/conditional_euclidean_clustering.html#conditional-euclidean-clustering (access date: 01.05.2020).
• PCL- Conditional Removal Filtering (PCL-CRF). 2020. Point Cloud Library Conditional Removal Filtering Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/conditional_removal.html#conditional-removal (access date: 01.05.2020).
• PCL- Difference of Normal Based Segmentation (PCL-DONBS). 2020. Point Cloud Library Difference of Normal Based Segmentation Codes. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/don_segmentation.html#don-segmentation (access date: 01.05.2020).
• PCL-Euclidean Clustering Extraction (PCL-ECE). 2020. Point Cloud Library Euclidean Clustering Extraction Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/cluster_extraction.html#cluster-extraction (access date: 01.05.2020).
• PCL-Min-Cut Based Segmentation (PCL-MCBS). 2020. Point Cloud Library Min-Cut Based Segmentation Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/min_cut_segmentation.html#min-cut-segmentation (access date: 01.05.2020).
• PCL-Plane Segmentation (PCL-PS). 2020. Point Cloud Library Plane Segmentation Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/planar_segmentation.html#planar-segmentation (access date: 01.05.2020).
• PCL-Progressive Morphological Filter Segmentation (PCL-PMFS). 2020. Point Cloud Library Progressive Morphological Filter Segmentation Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/progressive_morphological_filtering.html#progressive- morphological-filtering (access date: 01.05.2020).
• PCL-Region Growing (PCL-RG). 2020. Point Cloud Library Region Growing Segmentation Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/region_growing_segmentation.html#region-growing-segmentation (access date: 01.05.2020).
• PCL-Segmentation (PCL-S). 2020. Point Cloud Library Segmentation Codes. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/index.html#segmentation (access date: 01.05.2020).
• PCL- Supervoksel Clustering (PCL-SC). 2020. Point Cloud Library Supervoksel Clustering Segmentation Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/supervoxel_clustering.html#supervoxel-clustering (access date: 28.04.2020).
• PCL-Surface Smoothing (PCL-SS). 2020. Point Cloud Library Surface Smoothing Code. URL: https://pcl.readthedocs.io/projects/tutorials/en/latest/resampling.html?highlight=resampling#smoothing-and-normal-estimation-based-on-polynomial-reconstruction (access date: 02.05.2020).
• Qu T, Coco J, Rönnäng M, Sun W. 2014. Challenges and trends of implementation of 3D point cloud technologies in building information modeling (BIM): case studies. Computing in Civil and Build Eng, 809-816.
• Rabbani T, Van Den Heuvel F, Vosselmann G. 2006. Segmentation of point clouds using smoothness constraint. Int archives of Photogrammetry, Remote Sens and spatial Inf Sci, 36(5): 248-253.
• Raguram R, Chum O, Pollefeys M, Matas J, Frahm JM. 2012. USAC: a universal framework for random sample consensus. IEEE Trans on Pattern Analy and Machine Int, 35(8): 2022-2038.
• Rusu RB, Cousins S. 2011. 3d is here: Point cloud library (pcl). IEEE international conference on robotics and automation, 1-4.
• Rusu RB, Marton ZC, Blodow N, Dolha M, Beetz M. 2008. Towards 3D point cloud based object maps for household environments. Robotics and Autonomous Sys, 56(11): 927-941.
• Schnabel R, Wahl R, Klein R. 2007. Efficient RANSAC for point‐cloud shape detection. Comp Graphics Forum, 26(2): 214-226.
• Su W, Zhang M, Liu J, Sun Z. 2018. Automated extraction of corn leaf points from unorganized terrestrial LiDAR point clouds. Int J Agri and Biol Eng, 11(3): 166-170.
• 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 Workshop on Laser Scanning 2007 and SilviLaser 2007, Sep 2007, Espoo, Finland, 407-412.
• Vo AV, Truong-Hong L, Laefer DF, Bertolotto M. 2015. Octree-based region growing for point cloud segmentation. ISPRS J Photoy and Remote Sensing, 104: 88-100.
• Wu G, Zhu Q, Huang M, Guo Y, Qin J. 2019. Automatic recognition of juicy peaches on trees based on 3D contour features and colour data. Biosystems Eng, 188: 1-13.
• Xie Y, Tian J, Zhu XX. 2019. A review of point cloud semantic segmentation. arXiv preprint arXiv:1908.08854.
• Xu B, Jiang W, Shan J, Zhang J, Li L. 2016. Investigation on the weighted ransac approaches for building roof plane segmentation from lidar point clouds. Remote Sens, 8(1): 5.
• Zermas D, Izzat I, Papanikolopoulos N. 2017. Fast segmentation of 3d point clouds: A paradigm on lidar data for autonomous vehicle applications. IEEE International Conference on Robotics and Automation (ICRA), 5067-5073.
• Zhou W, Peng R, Dong J, Wang T. 2018. Automated extraction of 3D vector topographic feature line from terrain point cloud. Geocarto Int, 33(10): 1036-1047.