Real-time non-rigid object tracking using CAMShift with weighted back projection

Lei Sun, Bingrong Wang, Takeshi Ikenaga

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

2 Citations (Scopus)

Abstract

The Continuously Adaptive Mean Shift algorithm (CAMShift) is an adaptation of mean shift algorithm for object tracking especially for head and face tracking. Traditional CAMShift can not deal with multi-colored object tracking and situations when similar colors exist nearby. In this paper, a new approach towards these problems using CAMShift with weighted back projection is proposed. In our approach, multidimensional histogram with thresholding strategy is utilized. And a new back projection weighting strategy is proposed for situations when similar colors exist near the tracked object. Through experiments, the results show that the proposed method exceeds the traditional CAMShift in situations with multi-colored object or similar-colored background while keeping the processing speed real-time.

Original languageEnglish
Title of host publicationProceedings - 2010 10th International Conference on Computational Science and Its Applications, ICCSA 2010
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages86-91
Number of pages6
ISBN (Electronic)9780769539997
DOIs
Publication statusPublished - 2010 Jan 1
Event10th International Conference on Computational Science and Its Applications, ICCSA 2010 - Fukuoka, Japan
Duration: 2010 Mar 232010 Mar 26

Other

Other10th International Conference on Computational Science and Its Applications, ICCSA 2010
CountryJapan
CityFukuoka
Period10/3/2310/3/26

Fingerprint

Mean Shift
Object Tracking
Projection
Real-time
Face Tracking
Color
Thresholding
Histogram
Weighting
Exceed
Processing
Experiment
Experiments

Keywords

  • CAMShift
  • Mean shift
  • Object tracking
  • Weighted back projection

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Signal Processing
  • Computational Mechanics
  • Computational Mathematics
  • Numerical Analysis

Cite this

Sun, L., Wang, B., & Ikenaga, T. (2010). Real-time non-rigid object tracking using CAMShift with weighted back projection. In Proceedings - 2010 10th International Conference on Computational Science and Its Applications, ICCSA 2010 (pp. 86-91). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICCSA.2010.39

Real-time non-rigid object tracking using CAMShift with weighted back projection. / Sun, Lei; Wang, Bingrong; Ikenaga, Takeshi.

Proceedings - 2010 10th International Conference on Computational Science and Its Applications, ICCSA 2010. Institute of Electrical and Electronics Engineers Inc., 2010. p. 86-91.

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

Sun, L, Wang, B & Ikenaga, T 2010, Real-time non-rigid object tracking using CAMShift with weighted back projection. in Proceedings - 2010 10th International Conference on Computational Science and Its Applications, ICCSA 2010. Institute of Electrical and Electronics Engineers Inc., pp. 86-91, 10th International Conference on Computational Science and Its Applications, ICCSA 2010, Fukuoka, Japan, 10/3/23. https://doi.org/10.1109/ICCSA.2010.39
Sun L, Wang B, Ikenaga T. Real-time non-rigid object tracking using CAMShift with weighted back projection. In Proceedings - 2010 10th International Conference on Computational Science and Its Applications, ICCSA 2010. Institute of Electrical and Electronics Engineers Inc. 2010. p. 86-91 https://doi.org/10.1109/ICCSA.2010.39
Sun, Lei ; Wang, Bingrong ; Ikenaga, Takeshi. / Real-time non-rigid object tracking using CAMShift with weighted back projection. Proceedings - 2010 10th International Conference on Computational Science and Its Applications, ICCSA 2010. Institute of Electrical and Electronics Engineers Inc., 2010. pp. 86-91
@inproceedings{2dafffb065cf4827bfce524402fe3303,
title = "Real-time non-rigid object tracking using CAMShift with weighted back projection",
abstract = "The Continuously Adaptive Mean Shift algorithm (CAMShift) is an adaptation of mean shift algorithm for object tracking especially for head and face tracking. Traditional CAMShift can not deal with multi-colored object tracking and situations when similar colors exist nearby. In this paper, a new approach towards these problems using CAMShift with weighted back projection is proposed. In our approach, multidimensional histogram with thresholding strategy is utilized. And a new back projection weighting strategy is proposed for situations when similar colors exist near the tracked object. Through experiments, the results show that the proposed method exceeds the traditional CAMShift in situations with multi-colored object or similar-colored background while keeping the processing speed real-time.",
keywords = "CAMShift, Mean shift, Object tracking, Weighted back projection",
author = "Lei Sun and Bingrong Wang and Takeshi Ikenaga",
year = "2010",
month = "1",
day = "1",
doi = "10.1109/ICCSA.2010.39",
language = "English",
pages = "86--91",
booktitle = "Proceedings - 2010 10th International Conference on Computational Science and Its Applications, ICCSA 2010",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Real-time non-rigid object tracking using CAMShift with weighted back projection

AU - Sun, Lei

AU - Wang, Bingrong

AU - Ikenaga, Takeshi

PY - 2010/1/1

Y1 - 2010/1/1

N2 - The Continuously Adaptive Mean Shift algorithm (CAMShift) is an adaptation of mean shift algorithm for object tracking especially for head and face tracking. Traditional CAMShift can not deal with multi-colored object tracking and situations when similar colors exist nearby. In this paper, a new approach towards these problems using CAMShift with weighted back projection is proposed. In our approach, multidimensional histogram with thresholding strategy is utilized. And a new back projection weighting strategy is proposed for situations when similar colors exist near the tracked object. Through experiments, the results show that the proposed method exceeds the traditional CAMShift in situations with multi-colored object or similar-colored background while keeping the processing speed real-time.

AB - The Continuously Adaptive Mean Shift algorithm (CAMShift) is an adaptation of mean shift algorithm for object tracking especially for head and face tracking. Traditional CAMShift can not deal with multi-colored object tracking and situations when similar colors exist nearby. In this paper, a new approach towards these problems using CAMShift with weighted back projection is proposed. In our approach, multidimensional histogram with thresholding strategy is utilized. And a new back projection weighting strategy is proposed for situations when similar colors exist near the tracked object. Through experiments, the results show that the proposed method exceeds the traditional CAMShift in situations with multi-colored object or similar-colored background while keeping the processing speed real-time.

KW - CAMShift

KW - Mean shift

KW - Object tracking

KW - Weighted back projection

UR - http://www.scopus.com/inward/record.url?scp=80255128649&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80255128649&partnerID=8YFLogxK

U2 - 10.1109/ICCSA.2010.39

DO - 10.1109/ICCSA.2010.39

M3 - Conference contribution

AN - SCOPUS:80255128649

SP - 86

EP - 91

BT - Proceedings - 2010 10th International Conference on Computational Science and Its Applications, ICCSA 2010

PB - Institute of Electrical and Electronics Engineers Inc.

ER -