Abstract

Feature matching is at the base of many computer vision problems, such as object recognition or structure from motion. Current methods rely on costly descriptors for detection and matching. In this paper, we propose a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise. We demonstrate through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations. The efficiency is tested on several real-world applications, including object detection and patch-tracking on a smart phone.

Keywords

Orb (optics)Scale-invariant feature transformComputer scienceArtificial intelligenceComputer visionObject detectionCognitive neuroscience of visual object recognitionMatching (statistics)Feature extractionRotation (mathematics)Feature (linguistics)Invariant (physics)Feature matchingObject (grammar)Pattern recognition (psychology)Image (mathematics)Mathematics

Affiliated Institutions

Related Publications

Publication Info

Year
2011
Type
article
Pages
2564-2571
Citations
9963
Access
Closed

External Links

View on DOI.org

Social Impact

Altmetric
PlumX Metrics

Social media, news, blog, policy document mentions

Citation Metrics

9963
OpenAlex

Cite This

Ethan Rublee, Vincent Rabaud, Kurt Konolige et al. (2011). ORB: An efficient alternative to SIFT or SURF. , 2564-2571. https://doi.org/10.1109/iccv.2011.6126544

Identifiers

DOI
10.1109/iccv.2011.6126544