Real-time disparity estimation using foreground segmentation for stereo sequences

Hansung Kim, Dong Bo Min, Shinwoo Choi, Kwanghoon Sohn

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

We propose a fast disparity estimation algorithm using background registration and object segmentation for stereo sequences from fixed cameras. Dense background disparity information i calculated in an initialization step, so that only disparities of moving object regions are updated in the main process. We propose a real-time segmentation technique using background subtraction and interframe differences, and a hierarchical disparity estimation using a region-dividing technique and shape-adaptive matching windows. Experimental results show that the proposed algorithm provides accurate disparity vector fields with an average processing speed of 15 frames/s for x 320 × 240 stereo sequences on an ordinary PC.

Original languageEnglish
Article number037402
JournalOptical Engineering
Volume45
Issue number3
DOIs
Publication statusPublished - 2006 Mar 1

Fingerprint

subtraction
Cameras
cameras
Processing

All Science Journal Classification (ASJC) codes

  • Atomic and Molecular Physics, and Optics
  • Engineering(all)

Cite this

@article{16d708a639bd4098838dff42e86a3c85,
title = "Real-time disparity estimation using foreground segmentation for stereo sequences",
abstract = "We propose a fast disparity estimation algorithm using background registration and object segmentation for stereo sequences from fixed cameras. Dense background disparity information i calculated in an initialization step, so that only disparities of moving object regions are updated in the main process. We propose a real-time segmentation technique using background subtraction and interframe differences, and a hierarchical disparity estimation using a region-dividing technique and shape-adaptive matching windows. Experimental results show that the proposed algorithm provides accurate disparity vector fields with an average processing speed of 15 frames/s for x 320 × 240 stereo sequences on an ordinary PC.",
author = "Hansung Kim and Min, {Dong Bo} and Shinwoo Choi and Kwanghoon Sohn",
year = "2006",
month = "3",
day = "1",
doi = "10.1117/1.2183667",
language = "English",
volume = "45",
journal = "Optical Engineering",
issn = "0091-3286",
publisher = "SPIE",
number = "3",

}

Real-time disparity estimation using foreground segmentation for stereo sequences. / Kim, Hansung; Min, Dong Bo; Choi, Shinwoo; Sohn, Kwanghoon.

In: Optical Engineering, Vol. 45, No. 3, 037402, 01.03.2006.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Real-time disparity estimation using foreground segmentation for stereo sequences

AU - Kim, Hansung

AU - Min, Dong Bo

AU - Choi, Shinwoo

AU - Sohn, Kwanghoon

PY - 2006/3/1

Y1 - 2006/3/1

N2 - We propose a fast disparity estimation algorithm using background registration and object segmentation for stereo sequences from fixed cameras. Dense background disparity information i calculated in an initialization step, so that only disparities of moving object regions are updated in the main process. We propose a real-time segmentation technique using background subtraction and interframe differences, and a hierarchical disparity estimation using a region-dividing technique and shape-adaptive matching windows. Experimental results show that the proposed algorithm provides accurate disparity vector fields with an average processing speed of 15 frames/s for x 320 × 240 stereo sequences on an ordinary PC.

AB - We propose a fast disparity estimation algorithm using background registration and object segmentation for stereo sequences from fixed cameras. Dense background disparity information i calculated in an initialization step, so that only disparities of moving object regions are updated in the main process. We propose a real-time segmentation technique using background subtraction and interframe differences, and a hierarchical disparity estimation using a region-dividing technique and shape-adaptive matching windows. Experimental results show that the proposed algorithm provides accurate disparity vector fields with an average processing speed of 15 frames/s for x 320 × 240 stereo sequences on an ordinary PC.

UR - http://www.scopus.com/inward/record.url?scp=33748614303&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33748614303&partnerID=8YFLogxK

U2 - 10.1117/1.2183667

DO - 10.1117/1.2183667

M3 - Article

AN - SCOPUS:33748614303

VL - 45

JO - Optical Engineering

JF - Optical Engineering

SN - 0091-3286

IS - 3

M1 - 037402

ER -