Virtually augmenting hundreds of real pictures: An approach based on learning, retrieval, and tracking

Julien Pilet, Hideo Saito

研究成果: Conference contribution

27 引用 (Scopus)

抜粋

Tracking is a major issue of virtual and augmented reality applications. Single object tracking on monocular video streams is fairly well understood. However, when it comes to multiple objects, existing methods lack scalability and can recognize only a limited number of objects. Thanks to recent progress in feature matching, state-of-the-art image retrieval techniques can deal with millions of images. However, these methods do not focus on real-time video processing and can not track retrieved objects. In this paper, we present a method that combines the speed and accuracy of tracking with the scalability of image retrieval. At the heart of our approach is a bi-layer clustering process that allows our system to index and retrieve objects based on tracks of features, thereby effectively summarizing the information available on multiple video frames. As a result, our system is able to track in real-time multiple objects, recognized with low delay from a database of more than 300 entries.

元の言語English
ホスト出版物のタイトルVR 2010 - IEEE Virtual Reality 2010, Proceedings
ページ71-78
ページ数8
DOI
出版物ステータスPublished - 2010 5 31
イベントIEEE Virtual Reality 2010, VR 2010 - Waltham, MA, United States
継続期間: 2010 3 202010 3 24

出版物シリーズ

名前Proceedings - IEEE Virtual Reality

Other

OtherIEEE Virtual Reality 2010, VR 2010
United States
Waltham, MA
期間10/3/2010/3/24

ASJC Scopus subject areas

  • Engineering(all)

フィンガープリント Virtually augmenting hundreds of real pictures: An approach based on learning, retrieval, and tracking' の研究トピックを掘り下げます。これらはともに一意のフィンガープリントを構成します。

  • これを引用

    Pilet, J., & Saito, H. (2010). Virtually augmenting hundreds of real pictures: An approach based on learning, retrieval, and tracking. : VR 2010 - IEEE Virtual Reality 2010, Proceedings (pp. 71-78). [5444811] (Proceedings - IEEE Virtual Reality). https://doi.org/10.1109/VR.2010.5444811