Spatial color histogram based center voting method for subsequent object tracking and segmentation

Suryanto, Dae Hwan Kim, Hyo Kak Kim, Sung-Jea Ko

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

In this paper, we introduce an algorithm for object tracking in video sequences. In order to represent the object to be tracked, we propose a new spatial color histogram model which encodes both the color distribution and spatial information. Using this spatial color histogram model, a voting method based on the generalized Hough transform is employed to estimate the object location from frame to frame. The proposed voting based method, called the center voting method, requests every pixel near the previous object center to cast a vote for locating the new object center in the new frame. Once the location of the object is obtained, the back projection method is used to segment the object from the background. Experiment results show successful tracking of the object even when the object being tracked changes in size and shares similar color with the background.

Original languageEnglish
Pages (from-to)850-860
Number of pages11
JournalImage and Vision Computing
Volume29
Issue number12
DOIs
Publication statusPublished - 2011 Nov 1

Fingerprint

Color
Hough transforms
Pixels
Experiments

Keywords

  • Back projection
  • Center voting
  • Generalized Hough transform
  • Histogram
  • Object tracking
  • Spatial color

ASJC Scopus subject areas

  • Electrical and Electronic Engineering

Cite this

Spatial color histogram based center voting method for subsequent object tracking and segmentation. / Suryanto; Kim, Dae Hwan; Kim, Hyo Kak; Ko, Sung-Jea.

In: Image and Vision Computing, Vol. 29, No. 12, 01.11.2011, p. 850-860.

Research output: Contribution to journalArticle

@article{fda893d7816d4724802ef4d285a7ed48,
title = "Spatial color histogram based center voting method for subsequent object tracking and segmentation",
abstract = "In this paper, we introduce an algorithm for object tracking in video sequences. In order to represent the object to be tracked, we propose a new spatial color histogram model which encodes both the color distribution and spatial information. Using this spatial color histogram model, a voting method based on the generalized Hough transform is employed to estimate the object location from frame to frame. The proposed voting based method, called the center voting method, requests every pixel near the previous object center to cast a vote for locating the new object center in the new frame. Once the location of the object is obtained, the back projection method is used to segment the object from the background. Experiment results show successful tracking of the object even when the object being tracked changes in size and shares similar color with the background.",
keywords = "Back projection, Center voting, Generalized Hough transform, Histogram, Object tracking, Spatial color",
author = "Suryanto and Kim, {Dae Hwan} and Kim, {Hyo Kak} and Sung-Jea Ko",
year = "2011",
month = "11",
day = "1",
doi = "10.1016/j.imavis.2011.09.008",
language = "English",
volume = "29",
pages = "850--860",
journal = "Image and Vision Computing",
issn = "0262-8856",
publisher = "Elsevier Limited",
number = "12",

}

TY - JOUR

T1 - Spatial color histogram based center voting method for subsequent object tracking and segmentation

AU - Suryanto,

AU - Kim, Dae Hwan

AU - Kim, Hyo Kak

AU - Ko, Sung-Jea

PY - 2011/11/1

Y1 - 2011/11/1

N2 - In this paper, we introduce an algorithm for object tracking in video sequences. In order to represent the object to be tracked, we propose a new spatial color histogram model which encodes both the color distribution and spatial information. Using this spatial color histogram model, a voting method based on the generalized Hough transform is employed to estimate the object location from frame to frame. The proposed voting based method, called the center voting method, requests every pixel near the previous object center to cast a vote for locating the new object center in the new frame. Once the location of the object is obtained, the back projection method is used to segment the object from the background. Experiment results show successful tracking of the object even when the object being tracked changes in size and shares similar color with the background.

AB - In this paper, we introduce an algorithm for object tracking in video sequences. In order to represent the object to be tracked, we propose a new spatial color histogram model which encodes both the color distribution and spatial information. Using this spatial color histogram model, a voting method based on the generalized Hough transform is employed to estimate the object location from frame to frame. The proposed voting based method, called the center voting method, requests every pixel near the previous object center to cast a vote for locating the new object center in the new frame. Once the location of the object is obtained, the back projection method is used to segment the object from the background. Experiment results show successful tracking of the object even when the object being tracked changes in size and shares similar color with the background.

KW - Back projection

KW - Center voting

KW - Generalized Hough transform

KW - Histogram

KW - Object tracking

KW - Spatial color

UR - http://www.scopus.com/inward/record.url?scp=82555168343&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=82555168343&partnerID=8YFLogxK

U2 - 10.1016/j.imavis.2011.09.008

DO - 10.1016/j.imavis.2011.09.008

M3 - Article

VL - 29

SP - 850

EP - 860

JO - Image and Vision Computing

JF - Image and Vision Computing

SN - 0262-8856

IS - 12

ER -