Abstract
Using depth sensor devices to obtain 3D reconstruction maps is widely used in robotics and UAVs technology. For instance, large-scale environments reconstruction usually requires multiple or multiple angles to construct local point cloud maps, and then use 3D point cloud fusion technology to obtain global maps. In this paper, we present a complete point cloud fusion system for 3D map reconstruction of indoor environment based on traditional method, including initial fusion and precise fusion. Furthermore, we adopt the method of kd-tree search to match the points in the cloud of two point clouds, and eliminate the wrong matching or the matching point pairs with large error to improve the fusion efficiency. Our experiments show that, the convergence speed of the iterative process is improved, and the time complexity of the whole fusion algorithm is reduced while the final fusion effect achieves the required accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
He, H., Wang, H., Sun, L.: Research on 3D point-cloud registration technology based on Kinect V2 sensor. In: 2018 Chinese Control and Decision Conference (CCDC). IEEE (2018)
Salvi, J., Matabosch, C., Fofi, D., Forest, J.: A review of recent range image registration methods with accuracy evaluation. Image Vis. Comput. 25(5), 578–596 (2007)
Qiu, S., Luo, Y.: Point cloud registration based on improved ICP algorithm. Henan Science and Technology (2017)
Besl, P.J., Mckay, N.D.: Method for registration of 3-D shapes. In: Sensor Fusion IV: Control Paradigms and Data Structures, pp. 239–256 (1992)
Jun, L., Wei, L., Donglai, D., Qiang, S.: Point cloud registration algorithm based on NDT with variable size voxel. In: Control Conference, pp. 3707–3712 (2015)
Sharp, G.C., Lee, S.W., Wehe, D.K.: ICP registration using invariant features. IEEE Trans. PAMI 24(1), 90–102 (2002)
Schmuck, P., Chli, M.: Multi-UAV collaborative monocular slam. In: IEEE International Conference on Robotics and Automation, pp. 3863–3870 (2017)
Zhong, Y.: Intrinsic shape signatures: a shape descriptor for 3D object recognition. In: IEEE International Conference on Computer Vision Workshops, pp. 689–696 (2010)
Mur-Artal, R., Tards, J.D.: ORB-SLAM2: an open-source slam system for monocular, stereo, and RGB-D cameras. IEEE Trans. Rob. 33(5), 1255–1262 (2017)
Rusu, R.B., Blodow, N., Beetz, M.: Fast point feature histograms (FPFH) for 3D registration. In: IEEE International Conference on Robotics and Automation, pp. 3212–3217 (2009)
Acknowledgments
The authors would like to express their high appreciations to the supports from the National Natural Science Foundation of China (61871426) and Basic Research Project of Shenzhen (JCYJ20170413110004682).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Li, H., Qi, X., Yang, Z. (2019). A ICP-Improved Point Cloud Maps Fusion Algorithm with Multi-UAV Collaboration. In: Jia, M., Guo, Q., Meng, W. (eds) Wireless and Satellite Systems. WiSATS 2019. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 280. Springer, Cham. https://doi.org/10.1007/978-3-030-19153-5_56
Download citation
DOI: https://doi.org/10.1007/978-3-030-19153-5_56
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19152-8
Online ISBN: 978-3-030-19153-5
eBook Packages: Computer ScienceComputer Science (R0)