Estimation-correction scheme based articulated object tracking using SIFT features and mean shift algorithm

Ying Lu, Chengjiao Guo, Takeshi Ikenaga

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

7 Citations (Scopus)

Abstract

Object tracking plays an important role in video surveillance system. However, in the field of object tracking, complex object motion and object occlusions still remains challenging topics. This paper proposes a Estimation-Correction (EC) object tracking scheme in real scenarios, combining the strength of scale invariant feature transform (SIFT) and mean shift algorithm. The corresponding SIFT features are used to estimate the position of the target candidate by the scale and space relation between each pair of features. Then mean shift is applied to conduct the local similarity search so as to find a right position and size of estimated candidate with a maximum likelihood. Experiment results demonstrate that the proposed SIFT/mean shift strategy keeps the tracking error in average 8 pixels and improves the tracking performance compared with the traditional SIFT and mean shift algorithm when tracking objects with complex motion and full occlusion.

Original languageEnglish
Title of host publicationNISS2010 - 4th International Conference on New Trends in Information Science and Service Science
Pages275-280
Number of pages6
Publication statusPublished - 2010
Event4th International Conference on New Trends in Information Science and Service Science, NISS2010 - Gyeongju
Duration: 2010 May 112010 May 13

Other

Other4th International Conference on New Trends in Information Science and Service Science, NISS2010
CityGyeongju
Period10/5/1110/5/13

Fingerprint

Mean shift
Tracking error
Maximum likelihood
Surveillance
Similarity search
Experiment
Scenarios

Keywords

  • Articulated object tracking
  • Mean shift algorithm
  • Sift features

ASJC Scopus subject areas

  • Information Systems and Management

Cite this

Lu, Y., Guo, C., & Ikenaga, T. (2010). Estimation-correction scheme based articulated object tracking using SIFT features and mean shift algorithm. In NISS2010 - 4th International Conference on New Trends in Information Science and Service Science (pp. 275-280). [5488608]

Estimation-correction scheme based articulated object tracking using SIFT features and mean shift algorithm. / Lu, Ying; Guo, Chengjiao; Ikenaga, Takeshi.

NISS2010 - 4th International Conference on New Trends in Information Science and Service Science. 2010. p. 275-280 5488608.

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

Lu, Y, Guo, C & Ikenaga, T 2010, Estimation-correction scheme based articulated object tracking using SIFT features and mean shift algorithm. in NISS2010 - 4th International Conference on New Trends in Information Science and Service Science., 5488608, pp. 275-280, 4th International Conference on New Trends in Information Science and Service Science, NISS2010, Gyeongju, 10/5/11.
Lu Y, Guo C, Ikenaga T. Estimation-correction scheme based articulated object tracking using SIFT features and mean shift algorithm. In NISS2010 - 4th International Conference on New Trends in Information Science and Service Science. 2010. p. 275-280. 5488608
Lu, Ying ; Guo, Chengjiao ; Ikenaga, Takeshi. / Estimation-correction scheme based articulated object tracking using SIFT features and mean shift algorithm. NISS2010 - 4th International Conference on New Trends in Information Science and Service Science. 2010. pp. 275-280
@inproceedings{ab26bc5c70264004bc2e371f42e53273,
title = "Estimation-correction scheme based articulated object tracking using SIFT features and mean shift algorithm",
abstract = "Object tracking plays an important role in video surveillance system. However, in the field of object tracking, complex object motion and object occlusions still remains challenging topics. This paper proposes a Estimation-Correction (EC) object tracking scheme in real scenarios, combining the strength of scale invariant feature transform (SIFT) and mean shift algorithm. The corresponding SIFT features are used to estimate the position of the target candidate by the scale and space relation between each pair of features. Then mean shift is applied to conduct the local similarity search so as to find a right position and size of estimated candidate with a maximum likelihood. Experiment results demonstrate that the proposed SIFT/mean shift strategy keeps the tracking error in average 8 pixels and improves the tracking performance compared with the traditional SIFT and mean shift algorithm when tracking objects with complex motion and full occlusion.",
keywords = "Articulated object tracking, Mean shift algorithm, Sift features",
author = "Ying Lu and Chengjiao Guo and Takeshi Ikenaga",
year = "2010",
language = "English",
isbn = "9788988678183",
pages = "275--280",
booktitle = "NISS2010 - 4th International Conference on New Trends in Information Science and Service Science",

}

TY - GEN

T1 - Estimation-correction scheme based articulated object tracking using SIFT features and mean shift algorithm

AU - Lu, Ying

AU - Guo, Chengjiao

AU - Ikenaga, Takeshi

PY - 2010

Y1 - 2010

N2 - Object tracking plays an important role in video surveillance system. However, in the field of object tracking, complex object motion and object occlusions still remains challenging topics. This paper proposes a Estimation-Correction (EC) object tracking scheme in real scenarios, combining the strength of scale invariant feature transform (SIFT) and mean shift algorithm. The corresponding SIFT features are used to estimate the position of the target candidate by the scale and space relation between each pair of features. Then mean shift is applied to conduct the local similarity search so as to find a right position and size of estimated candidate with a maximum likelihood. Experiment results demonstrate that the proposed SIFT/mean shift strategy keeps the tracking error in average 8 pixels and improves the tracking performance compared with the traditional SIFT and mean shift algorithm when tracking objects with complex motion and full occlusion.

AB - Object tracking plays an important role in video surveillance system. However, in the field of object tracking, complex object motion and object occlusions still remains challenging topics. This paper proposes a Estimation-Correction (EC) object tracking scheme in real scenarios, combining the strength of scale invariant feature transform (SIFT) and mean shift algorithm. The corresponding SIFT features are used to estimate the position of the target candidate by the scale and space relation between each pair of features. Then mean shift is applied to conduct the local similarity search so as to find a right position and size of estimated candidate with a maximum likelihood. Experiment results demonstrate that the proposed SIFT/mean shift strategy keeps the tracking error in average 8 pixels and improves the tracking performance compared with the traditional SIFT and mean shift algorithm when tracking objects with complex motion and full occlusion.

KW - Articulated object tracking

KW - Mean shift algorithm

KW - Sift features

UR - http://www.scopus.com/inward/record.url?scp=77957854425&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77957854425&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:77957854425

SN - 9788988678183

SP - 275

EP - 280

BT - NISS2010 - 4th International Conference on New Trends in Information Science and Service Science

ER -