Toward augmenting everything: Detecting and tracking geometrical features on planar objects

Hideaki Uchiyama, Eric Marchand

Research output: Chapter in Book/Report/Conference proceedingConference contribution

12 Citations (Scopus)

Abstract

This paper presents an approach for detecting and tracking various types of planar objects with geometrical features. We combine tra- ditional keypoint detectors with Locally Likely Arrangement Hash- ing (LLAH) [21] for geometrical feature based keypoint matching. Because the stability of keypoint extraction affects the accuracy of the keypoint matching, we set the criteria of keypoint selection on keypoint response and the distance between keypoints. In order to produce robustness to scale changes, we build a non-uniform im- age pyramid according to keypoint distribution at each scale. In the experiments, we evaluate the applicability of traditional keypoint detectors with LLAH for the detection. We also compare our ap- proach with SURF and finally demonstrate that it is possible to de- tect and track different types of textures including colorful pictures, binary fiducial markers and handwritings.

Original languageEnglish
Title of host publication2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011
Pages17-25
Number of pages9
DOIs
Publication statusPublished - Dec 26 2011
Event2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011 - Basel, Switzerland
Duration: Oct 26 2011Oct 29 2011

Publication series

Name2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011

Other

Other2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011
CountrySwitzerland
CityBasel
Period10/26/1110/29/11

Fingerprint

Detectors
Textures
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Uchiyama, H., & Marchand, E. (2011). Toward augmenting everything: Detecting and tracking geometrical features on planar objects. In 2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011 (pp. 17-25). [6092366] (2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011). https://doi.org/10.1109/ISMAR.2011.6092366

Toward augmenting everything : Detecting and tracking geometrical features on planar objects. / Uchiyama, Hideaki; Marchand, Eric.

2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011. 2011. p. 17-25 6092366 (2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Uchiyama, H & Marchand, E 2011, Toward augmenting everything: Detecting and tracking geometrical features on planar objects. in 2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011., 6092366, 2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011, pp. 17-25, 2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011, Basel, Switzerland, 10/26/11. https://doi.org/10.1109/ISMAR.2011.6092366
Uchiyama H, Marchand E. Toward augmenting everything: Detecting and tracking geometrical features on planar objects. In 2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011. 2011. p. 17-25. 6092366. (2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011). https://doi.org/10.1109/ISMAR.2011.6092366
Uchiyama, Hideaki ; Marchand, Eric. / Toward augmenting everything : Detecting and tracking geometrical features on planar objects. 2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011. 2011. pp. 17-25 (2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011).
@inproceedings{d3c55a39bd484ac482ee96a048854c25,
title = "Toward augmenting everything: Detecting and tracking geometrical features on planar objects",
abstract = "This paper presents an approach for detecting and tracking various types of planar objects with geometrical features. We combine tra- ditional keypoint detectors with Locally Likely Arrangement Hash- ing (LLAH) [21] for geometrical feature based keypoint matching. Because the stability of keypoint extraction affects the accuracy of the keypoint matching, we set the criteria of keypoint selection on keypoint response and the distance between keypoints. In order to produce robustness to scale changes, we build a non-uniform im- age pyramid according to keypoint distribution at each scale. In the experiments, we evaluate the applicability of traditional keypoint detectors with LLAH for the detection. We also compare our ap- proach with SURF and finally demonstrate that it is possible to de- tect and track different types of textures including colorful pictures, binary fiducial markers and handwritings.",
author = "Hideaki Uchiyama and Eric Marchand",
year = "2011",
month = "12",
day = "26",
doi = "10.1109/ISMAR.2011.6092366",
language = "English",
isbn = "9781457721830",
series = "2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011",
pages = "17--25",
booktitle = "2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011",

}

TY - GEN

T1 - Toward augmenting everything

T2 - Detecting and tracking geometrical features on planar objects

AU - Uchiyama, Hideaki

AU - Marchand, Eric

PY - 2011/12/26

Y1 - 2011/12/26

N2 - This paper presents an approach for detecting and tracking various types of planar objects with geometrical features. We combine tra- ditional keypoint detectors with Locally Likely Arrangement Hash- ing (LLAH) [21] for geometrical feature based keypoint matching. Because the stability of keypoint extraction affects the accuracy of the keypoint matching, we set the criteria of keypoint selection on keypoint response and the distance between keypoints. In order to produce robustness to scale changes, we build a non-uniform im- age pyramid according to keypoint distribution at each scale. In the experiments, we evaluate the applicability of traditional keypoint detectors with LLAH for the detection. We also compare our ap- proach with SURF and finally demonstrate that it is possible to de- tect and track different types of textures including colorful pictures, binary fiducial markers and handwritings.

AB - This paper presents an approach for detecting and tracking various types of planar objects with geometrical features. We combine tra- ditional keypoint detectors with Locally Likely Arrangement Hash- ing (LLAH) [21] for geometrical feature based keypoint matching. Because the stability of keypoint extraction affects the accuracy of the keypoint matching, we set the criteria of keypoint selection on keypoint response and the distance between keypoints. In order to produce robustness to scale changes, we build a non-uniform im- age pyramid according to keypoint distribution at each scale. In the experiments, we evaluate the applicability of traditional keypoint detectors with LLAH for the detection. We also compare our ap- proach with SURF and finally demonstrate that it is possible to de- tect and track different types of textures including colorful pictures, binary fiducial markers and handwritings.

UR - http://www.scopus.com/inward/record.url?scp=84055199670&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84055199670&partnerID=8YFLogxK

U2 - 10.1109/ISMAR.2011.6092366

DO - 10.1109/ISMAR.2011.6092366

M3 - Conference contribution

AN - SCOPUS:84055199670

SN - 9781457721830

T3 - 2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011

SP - 17

EP - 25

BT - 2011 10th IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2011

ER -