Abstract
Typical convolution architectures require fairly conventional input data formats, such as image grids or three-dimensional pixels, to show shared weights and other kernel optimizations. Because point clouds and grids are not typical formats, most researchers usually convert these data into conventional three-dimensional pixel grids or picture sets before providing them to deep-net architectures. However, this data representation transformation presents unnecessary result data and introduces the natural invariance of quantified workpiece fuzzy data. For this reason, we focus on using a different simple point cloud input representation for three-dimensional geometry, and named our deep network as point network. Point cloud is a simple and unified structure, which avoids the combination of irregularity and complex grids, so it is easier to learn. This topic takes point cloud as input directly, and outputs the whole input classification label or every part label of each point input. In the basic settings, each point is represented by three coordinates (x, y, z), and additional dimensions can be added by calculating normals and other local or global characteristics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Qi CR, Su H, Niessner M, Dai A, Yan M, Guibas LJ (2016) Volumetric and multi-view CNNs for object classification on 3D data, arXiv
Gupta S, Girshick R, Arbelaez P, Malik J (2014) Learning rich features from RGB-D images for object detection and segmentation. In: ECCV
Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554
Jia Z, Chang Y-J, Chen T (2009) Active view selection for object and pose recognition. In: ICCV workshops
Qi CR, Su H, Mo K, Guibas LJ (2016) PointNet: deep learning on point sets for 3D classification and segmentation. arXiv preprint arXiv:1612.00593
Su H, Maji S, Kalogerakis E, Learned-Miller EG (2015) Multi-view convolutional neural networks for 3D shape recognition. In: Proceedings ICCV (to appear)
Vinyals O, Bengio S, Kudlur M (2015) Order matters: sequence to sequence for sets. arXiv preprint arXiv:1511.06391
Macrini D, Shokoufandeh A, Dickinson S, Siddiqi K, Zucker S (2002) View-based 3-D object recognition using shock graphs. In: Proceedings of ICPR, vol 3
Shi B, Bai S, Zhou Z, Bai X (2015) DeepPano: deep panoramic representation for 3-D shape recognition. IEEE Sig Process Lett 22:2339–2343
Sinha A, Bai J, Ramani K (2016) Deep learning 3D shape surfaces using geometry images. In: ECCV, pp 223–240
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Yu, F., Wei, Y., Yu, H. (2020). Research on 3-D Laser Point Cloud Recognition Based on Depth Neural Network. In: Xu, Z., Choo, KK., Dehghantanha, A., Parizi, R., Hammoudeh, M. (eds) Cyber Security Intelligence and Analytics. CSIA 2019. Advances in Intelligent Systems and Computing, vol 928. Springer, Cham. https://doi.org/10.1007/978-3-030-15235-2_197
Download citation
DOI: https://doi.org/10.1007/978-3-030-15235-2_197
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-15234-5
Online ISBN: 978-3-030-15235-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)