Region-based tracking using sequences of relevance measures

Sandy Martedi, Bruce Thomas, Hideo Saito

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

5 Citations (Scopus)

Abstract

We present the preliminary results of our proposal: a region-based detection and tracking method of arbitrary shapes. The method is designed to be robust against orientation and scale changes and also occlusions. In this work, we study the effectiveness of sequence of shape descriptors for matching purpose. We detect and track surfaces by matching the sequences of descriptor so called relevance measures with their correspondences in the database. First, we extract stable shapes as the detection target using Maximally Stable Extreme Region (MSER) method. The keypoints on the stable shapes are then extracted by simplifying the outline of the stable regions. The relevance measures that are composed by three keypoints are then computed and the sequences of them are composed as descriptors. During runtime, the sequences of relevance measures are extracted from the captured image and are matched with those in the database. When a particular region is matched with one in the database, the orientation of the region is then estimated and virtual annotations can be superimposed. We apply this approach in an interactive task support system that helps users for creating paper craft objects.

Original languageEnglish
Title of host publication2013 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2013
DOIs
Publication statusPublished - 2013
Event12th IEEE and ACM International Symposium on Mixed and Augmented Reality, ISMAR 2013 - Adelaide, NSW, Australia
Duration: 2013 Oct 12013 Oct 4

Other

Other12th IEEE and ACM International Symposium on Mixed and Augmented Reality, ISMAR 2013
CountryAustralia
CityAdelaide, NSW
Period13/10/113/10/4

Fingerprint

Target tracking

Keywords

  • Artificial
  • augmented
  • virtual realities

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Martedi, S., Thomas, B., & Saito, H. (2013). Region-based tracking using sequences of relevance measures. In 2013 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2013 [6671834] https://doi.org/10.1109/ISMAR.2013.6671834

Region-based tracking using sequences of relevance measures. / Martedi, Sandy; Thomas, Bruce; Saito, Hideo.

2013 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2013. 2013. 6671834.

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

Martedi, S, Thomas, B & Saito, H 2013, Region-based tracking using sequences of relevance measures. in 2013 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2013., 6671834, 12th IEEE and ACM International Symposium on Mixed and Augmented Reality, ISMAR 2013, Adelaide, NSW, Australia, 13/10/1. https://doi.org/10.1109/ISMAR.2013.6671834
Martedi S, Thomas B, Saito H. Region-based tracking using sequences of relevance measures. In 2013 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2013. 2013. 6671834 https://doi.org/10.1109/ISMAR.2013.6671834
Martedi, Sandy ; Thomas, Bruce ; Saito, Hideo. / Region-based tracking using sequences of relevance measures. 2013 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2013. 2013.
@inproceedings{09f7f02e25ff46e48348777d34a46be8,
title = "Region-based tracking using sequences of relevance measures",
abstract = "We present the preliminary results of our proposal: a region-based detection and tracking method of arbitrary shapes. The method is designed to be robust against orientation and scale changes and also occlusions. In this work, we study the effectiveness of sequence of shape descriptors for matching purpose. We detect and track surfaces by matching the sequences of descriptor so called relevance measures with their correspondences in the database. First, we extract stable shapes as the detection target using Maximally Stable Extreme Region (MSER) method. The keypoints on the stable shapes are then extracted by simplifying the outline of the stable regions. The relevance measures that are composed by three keypoints are then computed and the sequences of them are composed as descriptors. During runtime, the sequences of relevance measures are extracted from the captured image and are matched with those in the database. When a particular region is matched with one in the database, the orientation of the region is then estimated and virtual annotations can be superimposed. We apply this approach in an interactive task support system that helps users for creating paper craft objects.",
keywords = "Artificial, augmented, virtual realities",
author = "Sandy Martedi and Bruce Thomas and Hideo Saito",
year = "2013",
doi = "10.1109/ISMAR.2013.6671834",
language = "English",
isbn = "9781479928699",
booktitle = "2013 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2013",

}

TY - GEN

T1 - Region-based tracking using sequences of relevance measures

AU - Martedi, Sandy

AU - Thomas, Bruce

AU - Saito, Hideo

PY - 2013

Y1 - 2013

N2 - We present the preliminary results of our proposal: a region-based detection and tracking method of arbitrary shapes. The method is designed to be robust against orientation and scale changes and also occlusions. In this work, we study the effectiveness of sequence of shape descriptors for matching purpose. We detect and track surfaces by matching the sequences of descriptor so called relevance measures with their correspondences in the database. First, we extract stable shapes as the detection target using Maximally Stable Extreme Region (MSER) method. The keypoints on the stable shapes are then extracted by simplifying the outline of the stable regions. The relevance measures that are composed by three keypoints are then computed and the sequences of them are composed as descriptors. During runtime, the sequences of relevance measures are extracted from the captured image and are matched with those in the database. When a particular region is matched with one in the database, the orientation of the region is then estimated and virtual annotations can be superimposed. We apply this approach in an interactive task support system that helps users for creating paper craft objects.

AB - We present the preliminary results of our proposal: a region-based detection and tracking method of arbitrary shapes. The method is designed to be robust against orientation and scale changes and also occlusions. In this work, we study the effectiveness of sequence of shape descriptors for matching purpose. We detect and track surfaces by matching the sequences of descriptor so called relevance measures with their correspondences in the database. First, we extract stable shapes as the detection target using Maximally Stable Extreme Region (MSER) method. The keypoints on the stable shapes are then extracted by simplifying the outline of the stable regions. The relevance measures that are composed by three keypoints are then computed and the sequences of them are composed as descriptors. During runtime, the sequences of relevance measures are extracted from the captured image and are matched with those in the database. When a particular region is matched with one in the database, the orientation of the region is then estimated and virtual annotations can be superimposed. We apply this approach in an interactive task support system that helps users for creating paper craft objects.

KW - Artificial

KW - augmented

KW - virtual realities

UR - http://www.scopus.com/inward/record.url?scp=84893323777&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84893323777&partnerID=8YFLogxK

U2 - 10.1109/ISMAR.2013.6671834

DO - 10.1109/ISMAR.2013.6671834

M3 - Conference contribution

AN - SCOPUS:84893323777

SN - 9781479928699

BT - 2013 IEEE International Symposium on Mixed and Augmented Reality, ISMAR 2013

ER -