Efficient monocular pose estimation for complex 3D models

A. Rubio, M. Villamizar, L. Ferraz, A. Penate-Sanchez, A. Ramisa, E. Simo-Serra, A. Sanfeliu, F. Moreno-Noguer

研究成果: Conference contribution

19 被引用数 (Scopus)

抄録

We propose a robust and efficient method to estimate the pose of a camera with respect to complex 3D textured models of the environment that can potentially contain more than 100; 000 points. To tackle this problem we follow a top down approach where we combine high-level deep network classifiers with low level geometric approaches to come up with a solution that is fast, robust and accurate. Given an input image, we initially use a pre-trained deep network to compute a rough estimation of the camera pose. This initial estimate constrains the number of 3D model points that can be seen from the camera viewpoint. We then establish 3D-to-2D correspondences between these potentially visible points of the model and the 2D detected image features. Accurate pose estimation is finally obtained from the 2D-to-3D correspondences using a novel PnP algorithm that rejects outliers without the need to use a RANSAC strategy, and which is between 10 and 100 times faster than other methods that use it. Two real experiments dealing with very large and complex 3D models demonstrate the effectiveness of the approach.

本文言語English
ホスト出版物のタイトル2015 IEEE International Conference on Robotics and Automation, ICRA 2015
出版社Institute of Electrical and Electronics Engineers Inc.
ページ1397-1402
ページ数6
June
ISBN(電子版)9781479969234
DOI
出版ステータスPublished - 2015 6月 29
外部発表はい
イベント2015 IEEE International Conference on Robotics and Automation, ICRA 2015 - Seattle, United States
継続期間: 2015 5月 262015 5月 30

出版物シリーズ

名前Proceedings - IEEE International Conference on Robotics and Automation
番号June
2015-June
ISSN(印刷版)1050-4729

Conference

Conference2015 IEEE International Conference on Robotics and Automation, ICRA 2015
国/地域United States
CitySeattle
Period15/5/2615/5/30

ASJC Scopus subject areas

  • ソフトウェア
  • 制御およびシステム工学
  • 人工知能
  • 電子工学および電気工学

フィンガープリント

「Efficient monocular pose estimation for complex 3D models」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