P2Net: A Post-Processing Network for Refining Semantic Segmentation of LiDAR Point Cloud based on Consistency of Consecutive Frames

Yutaka Momma, Weimin Wang*, Edgar Simo-Serra, Satoshi Iizuka, Ryosuke Nakamura, Hiroshi Ishikawa

*この研究の対応する著者

研究成果: Conference contribution

抄録

We present a lightweight post-processing method to refine the semantic segmentation results of point cloud sequences. Most existing methods usually segment frame by frame and encounter the inherent ambiguity of the problem: based on a measurement in a single frame, labels are sometimes difficult to predict even for humans. To remedy this problem, we propose to explicitly train a network to refine these results predicted by an existing segmentation method. The network, which we call the P2Net, learns the consistency constraints between "coincident" points from consecutive frames after registration. We evaluate the proposed post-processing method both qualitatively and quantitatively on the SemanticKITTI dataset that consists of real outdoor scenes. The effectiveness of the proposed method is validated by comparing the results predicted by two representative networks with and without the refinement by the post-processing network. Specifically, qualitative visualization validates the key idea that labels of the points that are difficult to predict can be corrected with P2Net. Quantitatively, overall mIoU is improved from 10.5% to 11.7% for PointNet [1] and from 10.8% to 15.9% for PointNet++ [2].

本文言語English
ホスト出版物のタイトル2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
出版社Institute of Electrical and Electronics Engineers Inc.
ページ4110-4115
ページ数6
2020-October
ISBN(電子版)9781728185262
DOI
出版ステータスPublished - 2020 10 11
イベント2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020 - Toronto, Canada
継続期間: 2020 10 112020 10 14

Conference

Conference2020 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2020
国/地域Canada
CityToronto
Period20/10/1120/10/14

ASJC Scopus subject areas

  • ソフトウェア
  • 制御およびシステム工学
  • 人間とコンピュータの相互作用
  • コンピュータ サイエンスの応用
  • 電子工学および電気工学

フィンガープリント

「P<sup>2</sup>Net: A Post-Processing Network for Refining Semantic Segmentation of LiDAR Point Cloud based on Consistency of Consecutive Frames」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル