Improved Multistage Learning for Multibody Motion Segmentation

• Kanatani Kenichi

• Sugaya Yasuyuki

抄録

We present an improved version of the MSL method of Sugaya and Kanatani for multibody motion segmentation. We replace their initial segmentation based on heuristic clustering by an analytical computation based on GPCA, fitting two 2-D affine spaces in 3-D by the Taubin method. This initial segmentation alone can segment most of the motions in natural scenes fairly correctly, and the result is successively optimized by the EM algorithm in 3-D, 5-D, and 7-D. Using simulated and real videos, we demonstrate that our method outperforms the previous MSL and other existing methods. We also illustrate its mechanism by our visualization technique.

収録刊行物

• Memoirs of the Faculty of Engineering, Okayama University

  Memoirs of the Faculty of Engineering, Okayama University 44 24-31, 2010-01

  Faculty of Engineering, Okayama University

詳細情報

• CRID: 1390853649478684800
• NII論文ID: 120002309159
• NII書誌ID: AA12014085
• ISSN: 13496115
• DOI: 10.18926/19956
• Web Site: https://ousar.lib.okayama-u.ac.jp/19956
• 本文言語コード: en
• データソース種別:
  • JaLC
  • IRDB
  • CiNii Articles
  • KAKEN