Joint motion and disparity fields estimation for stereoscopic video sequences

W. Yang, K. Ngan, J. Lim, K. Sohn

Research output: Contribution to journalArticle

26 Citations (Scopus)

Abstract

In this paper, we present a separate edge-preserving regularization scheme to calculate disparity fields for a stereoscopic image pair and a joint disparity and motion estimation algorithm for stereoscopic video sequences. We aim at using the block-based joint estimation algorithm to calculate the displacement fields for stereoscopic and multiview video coding. In the proposed separate regularization scheme, an edge-preserving cost function is proposed for matching, the Sobel edge values are incorporated into the cost function as edge-preserving weights. The optimal Lagrange multiplier is determined using the convex hull bisection algorithm under the rate-distortion theory. A fast algorithm is then proposed where the textured regions and the homogeneous regions of the images are identified and regularized differently. In the joint regularization scheme, we calculate the two motion fields and the two disparity fields for two successive image pairs simultaneously. The four fields are regularized iteratively under the stereo-motion consistency constraint. Results are compared with existing algorithms and the superior performance of the proposed methods is confirmed.

Original languageEnglish
Pages (from-to)265-276
Number of pages12
JournalSignal Processing: Image Communication
Volume20
Issue number3
DOIs
Publication statusPublished - 2005 Mar 1

Fingerprint

Cost functions
Lagrange multipliers
Motion estimation
Image coding

All Science Journal Classification (ASJC) codes

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Electrical and Electronic Engineering

Cite this

@article{224147217bd14cd9b0f4525784fc5f95,
title = "Joint motion and disparity fields estimation for stereoscopic video sequences",
abstract = "In this paper, we present a separate edge-preserving regularization scheme to calculate disparity fields for a stereoscopic image pair and a joint disparity and motion estimation algorithm for stereoscopic video sequences. We aim at using the block-based joint estimation algorithm to calculate the displacement fields for stereoscopic and multiview video coding. In the proposed separate regularization scheme, an edge-preserving cost function is proposed for matching, the Sobel edge values are incorporated into the cost function as edge-preserving weights. The optimal Lagrange multiplier is determined using the convex hull bisection algorithm under the rate-distortion theory. A fast algorithm is then proposed where the textured regions and the homogeneous regions of the images are identified and regularized differently. In the joint regularization scheme, we calculate the two motion fields and the two disparity fields for two successive image pairs simultaneously. The four fields are regularized iteratively under the stereo-motion consistency constraint. Results are compared with existing algorithms and the superior performance of the proposed methods is confirmed.",
author = "W. Yang and K. Ngan and J. Lim and K. Sohn",
year = "2005",
month = "3",
day = "1",
doi = "10.1016/j.image.2004.12.003",
language = "English",
volume = "20",
pages = "265--276",
journal = "Signal Processing: Image Communication",
issn = "0923-5965",
publisher = "Elsevier",
number = "3",

}

Joint motion and disparity fields estimation for stereoscopic video sequences. / Yang, W.; Ngan, K.; Lim, J.; Sohn, K.

In: Signal Processing: Image Communication, Vol. 20, No. 3, 01.03.2005, p. 265-276.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Joint motion and disparity fields estimation for stereoscopic video sequences

AU - Yang, W.

AU - Ngan, K.

AU - Lim, J.

AU - Sohn, K.

PY - 2005/3/1

Y1 - 2005/3/1

N2 - In this paper, we present a separate edge-preserving regularization scheme to calculate disparity fields for a stereoscopic image pair and a joint disparity and motion estimation algorithm for stereoscopic video sequences. We aim at using the block-based joint estimation algorithm to calculate the displacement fields for stereoscopic and multiview video coding. In the proposed separate regularization scheme, an edge-preserving cost function is proposed for matching, the Sobel edge values are incorporated into the cost function as edge-preserving weights. The optimal Lagrange multiplier is determined using the convex hull bisection algorithm under the rate-distortion theory. A fast algorithm is then proposed where the textured regions and the homogeneous regions of the images are identified and regularized differently. In the joint regularization scheme, we calculate the two motion fields and the two disparity fields for two successive image pairs simultaneously. The four fields are regularized iteratively under the stereo-motion consistency constraint. Results are compared with existing algorithms and the superior performance of the proposed methods is confirmed.

AB - In this paper, we present a separate edge-preserving regularization scheme to calculate disparity fields for a stereoscopic image pair and a joint disparity and motion estimation algorithm for stereoscopic video sequences. We aim at using the block-based joint estimation algorithm to calculate the displacement fields for stereoscopic and multiview video coding. In the proposed separate regularization scheme, an edge-preserving cost function is proposed for matching, the Sobel edge values are incorporated into the cost function as edge-preserving weights. The optimal Lagrange multiplier is determined using the convex hull bisection algorithm under the rate-distortion theory. A fast algorithm is then proposed where the textured regions and the homogeneous regions of the images are identified and regularized differently. In the joint regularization scheme, we calculate the two motion fields and the two disparity fields for two successive image pairs simultaneously. The four fields are regularized iteratively under the stereo-motion consistency constraint. Results are compared with existing algorithms and the superior performance of the proposed methods is confirmed.

UR - http://www.scopus.com/inward/record.url?scp=13544256362&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13544256362&partnerID=8YFLogxK

U2 - 10.1016/j.image.2004.12.003

DO - 10.1016/j.image.2004.12.003

M3 - Article

AN - SCOPUS:13544256362

VL - 20

SP - 265

EP - 276

JO - Signal Processing: Image Communication

JF - Signal Processing: Image Communication

SN - 0923-5965

IS - 3

ER -