Int J Performability Eng ›› 2018, Vol. 14 ›› Issue (7): 1503-1512.doi: 10.23940/ijpe.18.07.p14.15031512

• Original articles • Previous Articles     Next Articles

3D Convolutional Neural Network for Semantic Scene Segmentation based on Unstructured Point Clouds

Rui Zhanga, b, Yan Wangc, Guangyun Lib, Zhen Hana, Junpeng Lia, and Chunying Lia   

  1. aNorth China University of Water Resources and Electric Power, Zhengzhou, 450045, China
    bInformation Engineering University, Zhengzhou, 450052, China
    cZhengzhou Institute of Technology, Zhengzhou, 450044, China

Abstract:

The use of point cloud datasets is an inevitable trend in the analysis of natural scenes. In this paper, we propose a semantic segmentation network architecture that consumes 3D point clouds directly, which can efficiently avoid mapping 3D point clouds to 2D images. Experimental results indicate strong performance that is on par with or even better than state-of-the-art methods for semantic segmentation on the Stanford semantic parsing dataset.


Submitted on March 19, 2018; Revised on April 23, 2018; Accepted on June 13, 2018
References: 38