Direct global adjustment methods for endoscopic mosaicking

Sharmishtaa Seshamania, Michael D. Smith, Jason J. Corso, Marcus O. Filipovich, Ananth Natarajan, Gregory Hager

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

Abstract

Endoscopy is an invaluable tool for several surgical and diagnostic applications. It permits minimally invasive visualization of internal structures thus involving little or no injury to internal structures. This method of visualization however restricts the size of the imaging device and therefore compromises on the field of view captured in a single image. The problem of a narrow field of view can be solved by capturing video sequences and stitching them to generate a mosaic of the scene under consideration. Registration of images in the sequence is therefore a crucial step. Existing methods compute frame-to-frame registration estimates and use these to resample images in order to generate a mosaic. The complexity of the appearance of internal structures and accumulation of registration error in frame to frame estimates however can be large enough to cause a cumulative drift that can misrepresent the scene. These errors can be reduced by application of global adjustment schemes. In this paper, we present a set of techniques for overcoming this problem of drift for pixel based registration in order to achieve global consistency of mosaics. The algorithm uses the frame-to-frame estimate as an initialization and subsequently corrects these estimates by setting up a large scale optimization problem which simultaneously solves for all corrections of estimates. In addition we set up a graph and introduce loop closure constraints in order to ensure consistency of registration. We present our method and results in semi global and fully global graph based adjustment methods as well as validation of our results.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7261
DOIs
StatePublished - 2009
EventMedical Imaging 2009: Biomedical Applications in Molecular, Structural, and Functional Imaging - Lake Buena Vista, FL, United States
Duration: Feb 8 2009Feb 10 2009

Other

OtherMedical Imaging 2009: Biomedical Applications in Molecular, Structural, and Functional Imaging
CountryUnited States
CityLake Buena Vista, FL
Period2/8/092/10/09

Fingerprint

Visualization
adjusting
Endoscopy
estimates
Pixels
Imaging techniques
field of view
Equipment and Supplies
closures
Wounds and Injuries
pixels
optimization
causes

Keywords

  • Data integration for the clinic/or
  • Endoscopic procedures
  • Registration
  • Visualization

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Seshamania, S., Smith, M. D., Corso, J. J., Filipovich, M. O., Natarajan, A., & Hager, G. (2009). Direct global adjustment methods for endoscopic mosaicking. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7261). [72611D] https://doi.org/10.1117/12.812246

Direct global adjustment methods for endoscopic mosaicking. / Seshamania, Sharmishtaa; Smith, Michael D.; Corso, Jason J.; Filipovich, Marcus O.; Natarajan, Ananth; Hager, Gregory.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7261 2009. 72611D.

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

Seshamania, S, Smith, MD, Corso, JJ, Filipovich, MO, Natarajan, A & Hager, G 2009, Direct global adjustment methods for endoscopic mosaicking. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7261, 72611D, Medical Imaging 2009: Biomedical Applications in Molecular, Structural, and Functional Imaging, Lake Buena Vista, FL, United States, 2/8/09. https://doi.org/10.1117/12.812246
Seshamania S, Smith MD, Corso JJ, Filipovich MO, Natarajan A, Hager G. Direct global adjustment methods for endoscopic mosaicking. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7261. 2009. 72611D https://doi.org/10.1117/12.812246
Seshamania, Sharmishtaa ; Smith, Michael D. ; Corso, Jason J. ; Filipovich, Marcus O. ; Natarajan, Ananth ; Hager, Gregory. / Direct global adjustment methods for endoscopic mosaicking. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7261 2009.
@inproceedings{868555163ccd44008825d1eb8511118a,
title = "Direct global adjustment methods for endoscopic mosaicking",
abstract = "Endoscopy is an invaluable tool for several surgical and diagnostic applications. It permits minimally invasive visualization of internal structures thus involving little or no injury to internal structures. This method of visualization however restricts the size of the imaging device and therefore compromises on the field of view captured in a single image. The problem of a narrow field of view can be solved by capturing video sequences and stitching them to generate a mosaic of the scene under consideration. Registration of images in the sequence is therefore a crucial step. Existing methods compute frame-to-frame registration estimates and use these to resample images in order to generate a mosaic. The complexity of the appearance of internal structures and accumulation of registration error in frame to frame estimates however can be large enough to cause a cumulative drift that can misrepresent the scene. These errors can be reduced by application of global adjustment schemes. In this paper, we present a set of techniques for overcoming this problem of drift for pixel based registration in order to achieve global consistency of mosaics. The algorithm uses the frame-to-frame estimate as an initialization and subsequently corrects these estimates by setting up a large scale optimization problem which simultaneously solves for all corrections of estimates. In addition we set up a graph and introduce loop closure constraints in order to ensure consistency of registration. We present our method and results in semi global and fully global graph based adjustment methods as well as validation of our results.",
keywords = "Data integration for the clinic/or, Endoscopic procedures, Registration, Visualization",
author = "Sharmishtaa Seshamania and Smith, {Michael D.} and Corso, {Jason J.} and Filipovich, {Marcus O.} and Ananth Natarajan and Gregory Hager",
year = "2009",
doi = "10.1117/12.812246",
language = "English (US)",
isbn = "9780819475121",
volume = "7261",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Direct global adjustment methods for endoscopic mosaicking

AU - Seshamania, Sharmishtaa

AU - Smith, Michael D.

AU - Corso, Jason J.

AU - Filipovich, Marcus O.

AU - Natarajan, Ananth

AU - Hager, Gregory

PY - 2009

Y1 - 2009

N2 - Endoscopy is an invaluable tool for several surgical and diagnostic applications. It permits minimally invasive visualization of internal structures thus involving little or no injury to internal structures. This method of visualization however restricts the size of the imaging device and therefore compromises on the field of view captured in a single image. The problem of a narrow field of view can be solved by capturing video sequences and stitching them to generate a mosaic of the scene under consideration. Registration of images in the sequence is therefore a crucial step. Existing methods compute frame-to-frame registration estimates and use these to resample images in order to generate a mosaic. The complexity of the appearance of internal structures and accumulation of registration error in frame to frame estimates however can be large enough to cause a cumulative drift that can misrepresent the scene. These errors can be reduced by application of global adjustment schemes. In this paper, we present a set of techniques for overcoming this problem of drift for pixel based registration in order to achieve global consistency of mosaics. The algorithm uses the frame-to-frame estimate as an initialization and subsequently corrects these estimates by setting up a large scale optimization problem which simultaneously solves for all corrections of estimates. In addition we set up a graph and introduce loop closure constraints in order to ensure consistency of registration. We present our method and results in semi global and fully global graph based adjustment methods as well as validation of our results.

AB - Endoscopy is an invaluable tool for several surgical and diagnostic applications. It permits minimally invasive visualization of internal structures thus involving little or no injury to internal structures. This method of visualization however restricts the size of the imaging device and therefore compromises on the field of view captured in a single image. The problem of a narrow field of view can be solved by capturing video sequences and stitching them to generate a mosaic of the scene under consideration. Registration of images in the sequence is therefore a crucial step. Existing methods compute frame-to-frame registration estimates and use these to resample images in order to generate a mosaic. The complexity of the appearance of internal structures and accumulation of registration error in frame to frame estimates however can be large enough to cause a cumulative drift that can misrepresent the scene. These errors can be reduced by application of global adjustment schemes. In this paper, we present a set of techniques for overcoming this problem of drift for pixel based registration in order to achieve global consistency of mosaics. The algorithm uses the frame-to-frame estimate as an initialization and subsequently corrects these estimates by setting up a large scale optimization problem which simultaneously solves for all corrections of estimates. In addition we set up a graph and introduce loop closure constraints in order to ensure consistency of registration. We present our method and results in semi global and fully global graph based adjustment methods as well as validation of our results.

KW - Data integration for the clinic/or

KW - Endoscopic procedures

KW - Registration

KW - Visualization

UR - http://www.scopus.com/inward/record.url?scp=67149104214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67149104214&partnerID=8YFLogxK

U2 - 10.1117/12.812246

DO - 10.1117/12.812246

M3 - Conference contribution

AN - SCOPUS:67149104214

SN - 9780819475121

VL - 7261

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -