A sparse-to-dense method for 3D optical flow estimation in 3D light-microscopy image sequences

Sandeep Manandhar, Patrick Bouthemy, Erik Welf, Philippe Roudot, Charles Kervrann

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

Abstract

We present a two-stage 3D optical flow estimation method for light microscopy image volumes. The method takes a pair of light microscopy image volumes as input, segments the 2D slices of the source volume in superpixels and sparsely estimates the 3D displacement vectors in the volume pair. A weighted interpolation is then introduced to get a dense 3D flow field. Edges and motion boundaries are considered during the interpolation. Our experimental results show good gain in execution speed, and accuracy evaluated in computer generated 3D data. Promising results on real 3D image sequences are reported.

Original languageEnglish (US)
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PublisherIEEE Computer Society
Pages952-956
Number of pages5
Volume2018-April
ISBN (Electronic)9781538636367
DOIs
StatePublished - May 23 2018
Event15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States
Duration: Apr 4 2018Apr 7 2018

Other

Other15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
CountryUnited States
CityWashington
Period4/4/184/7/18

Fingerprint

Optical flows
Optical microscopy
Microscopy
Interpolation
Light
Flow fields

Keywords

  • 3D Optical Flow
  • 3D PatchMatch
  • Fluorescence Microscopy
  • Interpolation

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Manandhar, S., Bouthemy, P., Welf, E., Roudot, P., & Kervrann, C. (2018). A sparse-to-dense method for 3D optical flow estimation in 3D light-microscopy image sequences. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (Vol. 2018-April, pp. 952-956). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363728

A sparse-to-dense method for 3D optical flow estimation in 3D light-microscopy image sequences. / Manandhar, Sandeep; Bouthemy, Patrick; Welf, Erik; Roudot, Philippe; Kervrann, Charles.

2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. p. 952-956.

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

Manandhar, S, Bouthemy, P, Welf, E, Roudot, P & Kervrann, C 2018, A sparse-to-dense method for 3D optical flow estimation in 3D light-microscopy image sequences. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. vol. 2018-April, IEEE Computer Society, pp. 952-956, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/4/18. https://doi.org/10.1109/ISBI.2018.8363728
Manandhar S, Bouthemy P, Welf E, Roudot P, Kervrann C. A sparse-to-dense method for 3D optical flow estimation in 3D light-microscopy image sequences. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April. IEEE Computer Society. 2018. p. 952-956 https://doi.org/10.1109/ISBI.2018.8363728
Manandhar, Sandeep ; Bouthemy, Patrick ; Welf, Erik ; Roudot, Philippe ; Kervrann, Charles. / A sparse-to-dense method for 3D optical flow estimation in 3D light-microscopy image sequences. 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April IEEE Computer Society, 2018. pp. 952-956
@inproceedings{1842a079cb414bc58af892f96c748d94,
title = "A sparse-to-dense method for 3D optical flow estimation in 3D light-microscopy image sequences",
abstract = "We present a two-stage 3D optical flow estimation method for light microscopy image volumes. The method takes a pair of light microscopy image volumes as input, segments the 2D slices of the source volume in superpixels and sparsely estimates the 3D displacement vectors in the volume pair. A weighted interpolation is then introduced to get a dense 3D flow field. Edges and motion boundaries are considered during the interpolation. Our experimental results show good gain in execution speed, and accuracy evaluated in computer generated 3D data. Promising results on real 3D image sequences are reported.",
keywords = "3D Optical Flow, 3D PatchMatch, Fluorescence Microscopy, Interpolation",
author = "Sandeep Manandhar and Patrick Bouthemy and Erik Welf and Philippe Roudot and Charles Kervrann",
year = "2018",
month = "5",
day = "23",
doi = "10.1109/ISBI.2018.8363728",
language = "English (US)",
volume = "2018-April",
pages = "952--956",
booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - A sparse-to-dense method for 3D optical flow estimation in 3D light-microscopy image sequences

AU - Manandhar, Sandeep

AU - Bouthemy, Patrick

AU - Welf, Erik

AU - Roudot, Philippe

AU - Kervrann, Charles

PY - 2018/5/23

Y1 - 2018/5/23

N2 - We present a two-stage 3D optical flow estimation method for light microscopy image volumes. The method takes a pair of light microscopy image volumes as input, segments the 2D slices of the source volume in superpixels and sparsely estimates the 3D displacement vectors in the volume pair. A weighted interpolation is then introduced to get a dense 3D flow field. Edges and motion boundaries are considered during the interpolation. Our experimental results show good gain in execution speed, and accuracy evaluated in computer generated 3D data. Promising results on real 3D image sequences are reported.

AB - We present a two-stage 3D optical flow estimation method for light microscopy image volumes. The method takes a pair of light microscopy image volumes as input, segments the 2D slices of the source volume in superpixels and sparsely estimates the 3D displacement vectors in the volume pair. A weighted interpolation is then introduced to get a dense 3D flow field. Edges and motion boundaries are considered during the interpolation. Our experimental results show good gain in execution speed, and accuracy evaluated in computer generated 3D data. Promising results on real 3D image sequences are reported.

KW - 3D Optical Flow

KW - 3D PatchMatch

KW - Fluorescence Microscopy

KW - Interpolation

UR - http://www.scopus.com/inward/record.url?scp=85048146351&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048146351&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363728

DO - 10.1109/ISBI.2018.8363728

M3 - Conference contribution

AN - SCOPUS:85048146351

VL - 2018-April

SP - 952

EP - 956

BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

PB - IEEE Computer Society

ER -