Share Email Print

Proceedings Paper

ATSGPN: adaptive threshold instance segmentation network in 3D point cloud
Author(s): Yu Sun; Zhicheng Wang; Jingjing Fei; Ling Chen; Gang Wei
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

We introduce an adaptive threshold instance segmentation network in point cloud based on similarity group proposal network(SGPN), named adaptive threshold similarity group proposal network(ATSGPN). SGPN learns the feature of point cloud to process similarity matrix and clusters. In our experiments, we find that we cannot always get the proper threshold by heuristic method to divide the points although the similarity matrix is good enough. Based on this idea, we introduce the Threshold Map to learn segmentation threshold. We also improve the feature extraction using edge convolution(EdgeConv). The point cloud first passes EdgeConv to extract features and learns the similarity matrix in feature space. The semantic label of each point and the segmentation threshold can help to generate groups and then calculates confidence to evaluate the group quality and backpropagation. ATSGPN has higher accuracy on Stanford Large- Scale 3D Indoor Spaces Dataset (S3SID) and fewer steps than SGPN, and there are some experiments can be shown in the paper for its good performance.

Paper Details

Date Published: 14 February 2020
PDF: 8 pages
Proc. SPIE 11430, MIPPR 2019: Pattern Recognition and Computer Vision, 114301O (14 February 2020); doi: 10.1117/12.2541582
Show Author Affiliations
Yu Sun, Tongji Univ. (China)
Zhicheng Wang, Tongji Univ. (China)
Jingjing Fei, Tongji Univ. (China)
Ling Chen, Tongji Univ. (China)
Gang Wei, Tongji Univ. (China)

Published in SPIE Proceedings Vol. 11430:
MIPPR 2019: Pattern Recognition and Computer Vision
Nong Sang; Jayaram K. Udupa; Yuehuan Wang; Zhenbing Liu, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?