In-Plane Rotation-Aware Monocular Depth Estimation Using SLAM

Yuki Saito, Ryo Hachiuma, Masahiro Yamaguchi, Hideo Saito

研究成果: Conference contribution

2 被引用数 (Scopus)

抄録

Estimating accurate depth from an RGB image in any environment is challenging task in computer vision. Recent learning based method using deep Convolutional Neural Networks (CNNs) have driven plausible appearance, but these conventional methods are not good at estimating scenes that have a pure rotation of camera, such as in-plane rolling. This movement imposes perturbations on learning-based methods because gravity direction is considered to be strong prior to CNN depth estimation (i.e., the top region of an image has a relatively large depth, whereas bottom region tends to have a small depth). To overcome this crucial weakness in depth estimation with CNN, we propose a simple but effective refining method that incorporates in-plane roll alignment using camera poses of monocular Simultaneous Localization and Mapping (SLAM). For the experiment, we used public datasets and also created our own dataset composed of mostly in-plane roll camera movements. Evaluation results on these datasets show the effectiveness of our approach.

本文言語English
ホスト出版物のタイトルFrontiers of Computer Vision - 26th International Workshop, IW-FCV 2020, Revised Selected Papers
編集者Wataru Ohyama, Soon Ki Jung
出版社Springer
ページ305-317
ページ数13
ISBN(印刷版)9789811548178
DOI
出版ステータスPublished - 2020
イベントInternational Workshop on Frontiers of Computer Vision, IW-FCV 2020 - Ibusuki, Japan
継続期間: 2020 2 202020 2 22

出版物シリーズ

名前Communications in Computer and Information Science
1212 CCIS
ISSN(印刷版)1865-0929
ISSN(電子版)1865-0937

Conference

ConferenceInternational Workshop on Frontiers of Computer Vision, IW-FCV 2020
CountryJapan
CityIbusuki
Period20/2/2020/2/22

ASJC Scopus subject areas

  • Computer Science(all)
  • Mathematics(all)

フィンガープリント 「In-Plane Rotation-Aware Monocular Depth Estimation Using SLAM」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