Real-time depth reconstruction from stereo sequences

Hansung Kim, Shinwoo Choi, Kwanghoon Sohn

Research output: Contribution to journalConference article

Abstract

We propose a fast depth reconstruction algorithm for stereo sequences using camera geometry and disparity estimation. In disparity estimation process, we calculate dense background disparity fields in an initialization step so that only disparities of moving object regions are updated in the main process using real-time segmentation and hierarchical disparity estimation techniques. The estimated dense disparity fields are converted into depth information by camera geometry. Experimental results show that the proposed algorithm provides accurate depth information with an average processing speed of 15 frames/sec for 320 × 240 stereo sequences on a common PC. We also verified the performance of the proposed algorithm by applying it to real applications.

Original languageEnglish
Article number60160E
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume6016
DOIs
Publication statusPublished - 2005 Dec 1
EventThree-Dimensional TV, Video, and Display IV - Boston, MA, United States
Duration: 2005 Oct 242005 Oct 26

Fingerprint

Real-time
Camera
Cameras
cameras
Geometry
Reconstruction Algorithm
geometry
Moving Objects
Initialization
Segmentation
Calculate
Experimental Results
Processing
Background

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

@article{ed6f18bc7e8e412b8164d870d7b0a003,
title = "Real-time depth reconstruction from stereo sequences",
abstract = "We propose a fast depth reconstruction algorithm for stereo sequences using camera geometry and disparity estimation. In disparity estimation process, we calculate dense background disparity fields in an initialization step so that only disparities of moving object regions are updated in the main process using real-time segmentation and hierarchical disparity estimation techniques. The estimated dense disparity fields are converted into depth information by camera geometry. Experimental results show that the proposed algorithm provides accurate depth information with an average processing speed of 15 frames/sec for 320 × 240 stereo sequences on a common PC. We also verified the performance of the proposed algorithm by applying it to real applications.",
author = "Hansung Kim and Shinwoo Choi and Kwanghoon Sohn",
year = "2005",
month = "12",
day = "1",
doi = "10.1117/12.630397",
language = "English",
volume = "6016",
journal = "Proceedings of SPIE - The International Society for Optical Engineering",
issn = "0277-786X",
publisher = "SPIE",

}

Real-time depth reconstruction from stereo sequences. / Kim, Hansung; Choi, Shinwoo; Sohn, Kwanghoon.

In: Proceedings of SPIE - The International Society for Optical Engineering, Vol. 6016, 60160E, 01.12.2005.

Research output: Contribution to journalConference article

TY - JOUR

T1 - Real-time depth reconstruction from stereo sequences

AU - Kim, Hansung

AU - Choi, Shinwoo

AU - Sohn, Kwanghoon

PY - 2005/12/1

Y1 - 2005/12/1

N2 - We propose a fast depth reconstruction algorithm for stereo sequences using camera geometry and disparity estimation. In disparity estimation process, we calculate dense background disparity fields in an initialization step so that only disparities of moving object regions are updated in the main process using real-time segmentation and hierarchical disparity estimation techniques. The estimated dense disparity fields are converted into depth information by camera geometry. Experimental results show that the proposed algorithm provides accurate depth information with an average processing speed of 15 frames/sec for 320 × 240 stereo sequences on a common PC. We also verified the performance of the proposed algorithm by applying it to real applications.

AB - We propose a fast depth reconstruction algorithm for stereo sequences using camera geometry and disparity estimation. In disparity estimation process, we calculate dense background disparity fields in an initialization step so that only disparities of moving object regions are updated in the main process using real-time segmentation and hierarchical disparity estimation techniques. The estimated dense disparity fields are converted into depth information by camera geometry. Experimental results show that the proposed algorithm provides accurate depth information with an average processing speed of 15 frames/sec for 320 × 240 stereo sequences on a common PC. We also verified the performance of the proposed algorithm by applying it to real applications.

UR - http://www.scopus.com/inward/record.url?scp=33644761673&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=33644761673&partnerID=8YFLogxK

U2 - 10.1117/12.630397

DO - 10.1117/12.630397

M3 - Conference article

VL - 6016

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

M1 - 60160E

ER -