Unified tracking and recognition with rotation-invariant fast features
Abstract/Contents
- Abstract
- Mobile Augmented Reality (MAR) systems overlay virtual content on a live video stream of real-world content. These systems rely on content recognition and tracking to generate this overlay. Typically, these two components use disjoint image processing pipelines, which complicates and slows the system. We propose a new keypoint detector and local feature descriptor that enables the unification of tracking and recognition. This Rotation-Invariant Fast Feature (RIFF) is fast enough to track in real-time on a mobile device, and accurate enough for large-scale image recognition. We propose a tracking algorithm that efficiently matches RIFF descriptors between consecutive frames. This tracker operates with state-of-the-art accuracy at 30 fps on a 1 GHz mobile phone. The same descriptors used for tracking can be matched against a database for image recognition without the need for a separate descriptor pipeline. We evaluate the retrieval performance of RIFF on a challenging, real-world database of 1 million images. By using the same features for largescale image retrieval and video tracking, we have shown that these two tasks can be unified, providing particular benefit to MAR applications.
Description
Type of resource | text |
---|---|
Form | electronic; electronic resource; remote |
Extent | 1 online resource. |
Publication date | 2012 |
Issuance | monographic |
Language | English |
Creators/Contributors
Associated with | Takacs, Gabriel |
---|---|
Associated with | Stanford University, Department of Electrical Engineering |
Primary advisor | Girod, Bernd |
Primary advisor | Guibas, Leonidas J |
Thesis advisor | Girod, Bernd |
Thesis advisor | Guibas, Leonidas J |
Thesis advisor | Grzeszczuk, Radek, 1967- |
Advisor | Grzeszczuk, Radek, 1967- |
Subjects
Genre | Theses |
---|
Bibliographic information
Statement of responsibility | Gabriel Takacs. |
---|---|
Note | Submitted to the Department of Electrical Engineering. |
Thesis | Thesis (Ph.D.)--Stanford University, 2012. |
Location | electronic resource |
Access conditions
- Copyright
- © 2012 by Gabriel Takacs
- License
- This work is licensed under a Creative Commons Attribution Non Commercial 3.0 Unported license (CC BY-NC).
Also listed in
Loading usage metrics...