AIRCC's International Journal of Computer Science and Information Technology

Open Access Open Access  Restricted Access Subscription Access

Lidar Point Cloud Classification using Expectation Maximization Algorithm


Affiliations
1 Department of Software Engineering, Faculty of Information Technology, Hanoi University of Mining and Geology, Hanoi, Viet Nam
 

EM algorithm is a common algorithm in data mining techniques. With the idea of using two iterations of E and M, the algorithm creates a model that can assign class labels to data points. In addition, EM not only optimizes the parameters of the model but also can predict device data during the iteration. Therefore, the paper focuses on researching and improving the EM algorithm to suit the LiDAR point cloud classification. Based on the idea of breaking point cloud and using the scheduling parameter for step E to help the algorithm converge faster with a shorter run time. The proposed algorithm is tested with measurement data set in Nghe An province, Vietnam for more than 92% accuracy and has faster runtime than the original EM algorithm.

Keywords

LiDAR, EM Algorithm, Scheduling Parameter, LiDAR Point Elevation, GMM Model.
User
Notifications
Font Size

  • Nallig Leal, Esmeide Leal, Sanchez Torres German A linear programming approach for 3D point cloud simplification.

  • Zhenyang Hui, Dajung Li, Shuanggen Jin, Yao Yevenyo Ziggah, Leyang Wang (2019) Automatic DTM extraction from Airborne LiDAR based on expectation - maximization, Optics and Laser Technology, vol.112, pp. 43-55

  • Kun Zhang, Weihong Bi, Xiaoming Zhang, Xinghu Fu, Kunpeng Zhu, Li Zhu (2015) A new kmeans clustering algorithm for point cloud, International Journal of Hybrid Information Technology, vol. vol. 8, no. 9, pp. 157-170.

  • Keng FanLin, Chi Pei Wang, Pai Hui Su (2012) Object-based classification for LiDAR point cloud.

  • Chao Luo, Gunho Sohn (2013) Line-based classification of terrestrial laser scanning data using conditional random field, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol XL-7/W2, ISPRS2013.

  • Xiao Liu, Congyin Han, Tiande Guo (2018) A robust point sets matching method [Online]. Available: https://arxiv.org/ftp/arxiv/papers/1411/1411.0791.pdf. [Accessed 9 10 2019].

  • Z.Hui, P.Cheng, Y.Y. Ziggah, Y.Nie (2018) A threshold-free filtering algorithm for airborne LiDAR point clouds based on Expectation Maximization, The International Archives of the Photogrammetry, RS and Spatial Information Sciences, vol. XLII-3.

  • Suresh Lodha, David P.Helmbold, Darren M.Fitzpatrick (2007) Aerial LiDAR data classification using expectation – maximization, Research Gate.

  • Yang HongLei, Peng JunHuan, Zhang DingXuan (2013) An Improved Em algorithm for remote sensing classification, Chinese Science Bullentin, vol. 58, no. 9, pp. 1060-1071.

  • Xiao Liu, Congying han, Tiande Guo (2014), "arXiv”. [Online]. Available: https://arxiv.org/ftp/arxiv/papers/1411/1411.0791.pdf. [Accessed 7 10 2019].

  • Yu-chuan Chang, Ayman F.habib, Dong Cheon Lee, Jae Hong Yom (2008) Automatic classification of LiDAR data into Ground and non-Ground points, The International Archives of the Photogrammetry, RS and Spatial Information Sciences, vol. XXXVII, no. B4, pp.457-46.

  • Borja Rodriguez - Cuenca, Silverio Garcia Cortes, Celestino Ordonez, Maria C.Alonso (2015) Automatic detection and classification of pole-like objects in urban point cloud data using an anomaly detection algorithm, Remote Sensing, vol. 7, pp.12680-12703.

  • Serez Kutluk, Koray Kayabol, Aydin Akan (2016) Classification of Hyperspectral Images using Mixture of Probabilistics PCA models, European signal processing conference, pp. 1568-1572.

  • Iftekhar Naim, Daniel Gildea (2012) Convergence of EM algorithm for GMM with unbalanced Mixing coefficients, International Conference on Machine Learning.

  • Lawrence H. Cox, Marco Better (2009). Sampling from discrete distributions: Application to an editing problem, Research Gate.

  • Naonori Ueda, Ryohei Nakano (1998) Deterministic Annealing Variant of the EM algorithm, [Online]. Available: https://papers.nips.cc/paper/941-deterministic-annealing-variant-of-the-em-algorithm.pdf. [Accessed 6 3 2020].

  • S. Borman (2006) The expectation maximization algorithm a short tutorial.


Abstract Views: 366

PDF Views: 150




  • Lidar Point Cloud Classification using Expectation Maximization Algorithm

Abstract Views: 366  |  PDF Views: 150

Authors

Nguyen Thi Huu Phuong
Department of Software Engineering, Faculty of Information Technology, Hanoi University of Mining and Geology, Hanoi, Viet Nam

Abstract


EM algorithm is a common algorithm in data mining techniques. With the idea of using two iterations of E and M, the algorithm creates a model that can assign class labels to data points. In addition, EM not only optimizes the parameters of the model but also can predict device data during the iteration. Therefore, the paper focuses on researching and improving the EM algorithm to suit the LiDAR point cloud classification. Based on the idea of breaking point cloud and using the scheduling parameter for step E to help the algorithm converge faster with a shorter run time. The proposed algorithm is tested with measurement data set in Nghe An province, Vietnam for more than 92% accuracy and has faster runtime than the original EM algorithm.

Keywords


LiDAR, EM Algorithm, Scheduling Parameter, LiDAR Point Elevation, GMM Model.

References