Classification Using 3D Point Cloud and 2D Image on Abstract Objects

Authors

  • Mark Yang The Quarry Lane School
  • Guillermo Goldsztein Mentor, Georgia Institute of Technology

DOI:

https://doi.org/10.47611/jsrhs.v10i3.2222

Keywords:

Classification, Point Cloud, Image, Abstract Design

Abstract

While classification using machine learning is exceptionally successful with 2D images, it is more challenging to classify 3D objects. However, 3D objects classification is critical because of its application in autonomous vehicles and robotics. This paper compared neural networks with similar structures using 3D point clouds and 2D images on the same objects. We also generated objects with abstract design and input them into the neural networks we created. We find clear disadvantages with classifying abstract objects compared to ordinary objects for both neural networks. We believe having contextual information will help to address this problem. We also observed that the neural network based on images performs worse than that based on point clouds. However, image based classification takes less time to train compared to point cloud based classification.

Downloads

Download data is not yet available.

References or Bibliography

Dawson-Haggerty et al. (n.d.). trimesh. Version 3.2.0. url: https://trimsh.org/

Feng, Yutong, Yifan Feng, Haoxuan You, Xibin Zhao, and Yue Gao (2018). MeshNet: Mesh Neural Network for 3D Shape Representation. arXiv: 1811.11424 [cs.CV]

Filgueira, A., H. González-Jorge, S. Lagüela, L. Díaz-Vilariño, and P. Arias (2017). “Quantifying the influence of rain in LiDAR performance”. In: Measurement 95, pp. 143–148.

Qi, Charles R., Hao Su, Kaichun Mo, and Leonidas J. Guibas (2017). Point-Net: Deep Learning on Point Sets for 3D Classification and Segmentation. arXiv: 1612.00593 [cs.CV]

Rusu, Radu Bogdan and Steve Cousins (2011). “3D is here: Point Cloud Library (PCL)”. In: 2011 IEEE International Conference on Robotics and Automation, pp. 1–4. doi: 10.1109/ICRA.2011.5980567

Sedaghat, N., Zolfaghari, M., Amiri, E., & Brox, T. (2016). Orientation-boosted voxel nets for 3d object recognition. arXiv preprint arXiv: 1604.03351[cs.CV]

Wandinger, Ulla (2005). Introduction to Lidar. Ed. by Claus Weitkamp. New York, NY: Springer New York, pp. 1–18. isbn: 978-0-387-25101-1. doi: 10.1007/0-387-25101-4_1. url: https://doi.org/10.1007/0-387-25101-4_1

Wu, Zhirong et al. (2015). 3D ShapeNets: A Deep Representation for Volu-metric Shapes. arXiv: 1406.5670 [cs.CV]

Xiao, Tong, Tian Xia, Yi Yang, Chang Huang, and Xiaogang Wang (2015). “Learning From Massive Noisy Labeled Data for Image Classification”. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Zhang, Feihu, Daniel Clarke, and Alois Knoll (2014). “Vehicle detection based on LiDAR and camera fusion”. In: 17th International IEEE Conference on Intelligent Transportation Systems (ITSC), pp. 1620–1625. doi: 10.1109/ITSC.2014.6957925

Published

11-04-2021

How to Cite

Yang, Z., & Goldsztein, G. (2021). Classification Using 3D Point Cloud and 2D Image on Abstract Objects. Journal of Student Research, 10(3). https://doi.org/10.47611/jsrhs.v10i3.2222

Issue

Section

HS Research Articles