Skip to Main content Skip to Navigation
Journal articles

Camera tracking by online learning of keypoint arrangements using LLAH in augmented reality applications

Abstract : We propose a camera tracking method by on-line learning of keypoint arrange- ments in augmented reality applications. As target objects, we deal with intersection maps from GIS and text documents, which are not dealt with by the popular SIFT and SURF descriptors. For keypoint matching by keypoint arrangement, we use locally likely arrange- ment hashing (LLAH), in which the descriptors of the arrangement in a viewpoint are not invariant to wide viewpoints because the arrangement is changeable with respect to viewpoints. In order to solve this problem, we propose online learning of descriptors using new configurations of keypoints at new viewpoints. The proposed method allows keypoint matching to proceed under new viewpoints. We evaluate the performance and robustness of our tracking method using view changes.
Complete list of metadatas

Cited literature [25 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01521143
Contributor : Myriam Servières <>
Submitted on : Thursday, May 11, 2017 - 3:58:27 PM
Last modification on : Tuesday, April 2, 2019 - 1:58:56 AM
Document(s) archivé(s) le : Saturday, August 12, 2017 - 1:31:34 PM

File

uchiyama.pdf
Files produced by the author(s)

Identifiers

Collections

CNRS | AAU | CERMA | UGA | UNAM

Citation

Hideaki Uchiyama, Hideo Saito, Myriam Servières, Guillaume Moreau. Camera tracking by online learning of keypoint arrangements using LLAH in augmented reality applications. Virtual Reality, Springer Verlag, 2011, 15, ⟨10.1007/s10055-010-0173-7⟩. ⟨hal-01521143⟩

Share

Metrics

Record views

305

Files downloads

231