Pointwise CNN for 3D Object Classification on Point Cloud


Wei Song, Zishu Liu, Yifei Tian, Simon Fong, Journal of Information Processing Systems Vol. 17, No. 4, pp. 787-800, Aug. 2021  

10.3745/JIPS.02.0160
Keywords: Point Clouds, Pointwise CNN, 3D Object Classification
Fulltext:

Abstract

Three-dimensional (3D) object classification tasks using point clouds are widely used in 3D modeling, face recognition, and robotic missions. However, processing raw point clouds directly is problematic for a traditional convolutional network due to the irregular data format of point clouds. This paper proposes a pointwise convolution neural network (CNN) structure that can process point cloud data directly without preprocessing. First, a 2D convolutional layer is introduced to percept coordinate information of each point. Then, multiple 2D convolutional layers and a global max pooling layer are applied to extract global features. Finally, based on the extracted features, fully connected layers predict the class labels of objects. We evaluated the proposed pointwise CNN structure on the ModelNet10 dataset. The proposed structure obtained higher accuracy compared to the existing methods. Experiments using the ModelNet10 dataset also prove that the difference in the point number of point clouds does not significantly influence on the proposed pointwise CNN structure.


Statistics
Show / Hide Statistics

Statistics (Cumulative Counts from November 1st, 2017)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.




Cite this article
[APA Style]
Wei Song, Zishu Liu, Yifei Tian, & Simon Fong (2021). Pointwise CNN for 3D Object Classification on Point Cloud. Journal of Information Processing Systems, 17(4), 787-800. DOI: 10.3745/JIPS.02.0160.

[IEEE Style]
W. Song, Z. Liu, Y. Tian and S. Fong, "Pointwise CNN for 3D Object Classification on Point Cloud," Journal of Information Processing Systems, vol. 17, no. 4, pp. 787-800, 2021. DOI: 10.3745/JIPS.02.0160.

[ACM Style]
Wei Song, Zishu Liu, Yifei Tian, and Simon Fong. 2021. Pointwise CNN for 3D Object Classification on Point Cloud. Journal of Information Processing Systems, 17, 4, (2021), 787-800. DOI: 10.3745/JIPS.02.0160.