Robust real-time retinal tracking for ophthalmic applications

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Authors

Research Organisations

External Research Organisations

  • TH Köln - University of Applied Sciences
View graph of relations

Details

Original languageEnglish
Title of host publicationOphthalmic Technologies XXXV
EditorsDaniel X. Hammer, Derek Nankivil, Yuankai K. Tao
PublisherSPIE
ISBN (electronic)9781510683488
Publication statusPublished - 19 Mar 2025
EventSPIE Photonics West BiOS 2025 - San Francisco, United States
Duration: 25 Jan 202531 Jan 2025

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume13300
ISSN (Print)1605-7422

Abstract

This work presents a software-based approach for robust feature tracking of funduscopy images. In our specific application, it is utilized in a scannerless linear optical coherence tomography system, where both natural and directed eye movements are used to scan the retina. The approach developed includes a fast, contrast-enhancing video preprocessing step. Additional filtering highlights edges and details, enhancing the visibility of blood vessels and the optic disc. Reflections are removed, both those arising from the funduscopy setup itself and non-stationary reflections caused by the cornea or an intraocular lens. A state-of-the-art feature detector and descriptor is used to identify and characterize distinctive image regions. Subsequent feature matching and filtering include additional criteria to enhance robustness against outliers and false detections. From these final matches, homographies are calculated, allowing the derivation of relative movements and absolute positions. The results demonstrate real-time processing with high detection rates and minimal misdetections. This performance is maintained even in the presence of poor contrast and non-stationary reflections in the original video stream. While the tracking is optimized for our application, it is also applicable to other domains, such as optimizing the alignment of retinal images, generating wide-field panorama images from individual frames, or characterizing eye movements.

Keywords

    Computer Vision, Funduscopy, Image Enhancement, Motion Tracking, Ophthalmic Imaging, Retina, Video Processing

ASJC Scopus subject areas

Cite this

Robust real-time retinal tracking for ophthalmic applications. / Mendroch, Damian; Harings, David; Bauer, Niklas et al.
Ophthalmic Technologies XXXV. ed. / Daniel X. Hammer; Derek Nankivil; Yuankai K. Tao. SPIE, 2025. 133000L (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 13300).

Research output: Chapter in book/report/conference proceedingConference contributionResearchpeer review

Mendroch, D, Harings, D, Bauer, N, Altmeyer, S, Oberheide, U & Heisterkamp, A 2025, Robust real-time retinal tracking for ophthalmic applications. in DX Hammer, D Nankivil & YK Tao (eds), Ophthalmic Technologies XXXV., 133000L, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 13300, SPIE, SPIE Photonics West BiOS 2025, San Francisco, California, United States, 25 Jan 2025. https://doi.org/10.1117/12.3047657
Mendroch, D., Harings, D., Bauer, N., Altmeyer, S., Oberheide, U., & Heisterkamp, A. (2025). Robust real-time retinal tracking for ophthalmic applications. In D. X. Hammer, D. Nankivil, & Y. K. Tao (Eds.), Ophthalmic Technologies XXXV Article 133000L (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 13300). SPIE. https://doi.org/10.1117/12.3047657
Mendroch D, Harings D, Bauer N, Altmeyer S, Oberheide U, Heisterkamp A. Robust real-time retinal tracking for ophthalmic applications. In Hammer DX, Nankivil D, Tao YK, editors, Ophthalmic Technologies XXXV. SPIE. 2025. 133000L. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.3047657
Mendroch, Damian ; Harings, David ; Bauer, Niklas et al. / Robust real-time retinal tracking for ophthalmic applications. Ophthalmic Technologies XXXV. editor / Daniel X. Hammer ; Derek Nankivil ; Yuankai K. Tao. SPIE, 2025. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
Download
@inproceedings{0a302e35775e4bceaaa6e8036eb284f0,
title = "Robust real-time retinal tracking for ophthalmic applications",
abstract = "This work presents a software-based approach for robust feature tracking of funduscopy images. In our specific application, it is utilized in a scannerless linear optical coherence tomography system, where both natural and directed eye movements are used to scan the retina. The approach developed includes a fast, contrast-enhancing video preprocessing step. Additional filtering highlights edges and details, enhancing the visibility of blood vessels and the optic disc. Reflections are removed, both those arising from the funduscopy setup itself and non-stationary reflections caused by the cornea or an intraocular lens. A state-of-the-art feature detector and descriptor is used to identify and characterize distinctive image regions. Subsequent feature matching and filtering include additional criteria to enhance robustness against outliers and false detections. From these final matches, homographies are calculated, allowing the derivation of relative movements and absolute positions. The results demonstrate real-time processing with high detection rates and minimal misdetections. This performance is maintained even in the presence of poor contrast and non-stationary reflections in the original video stream. While the tracking is optimized for our application, it is also applicable to other domains, such as optimizing the alignment of retinal images, generating wide-field panorama images from individual frames, or characterizing eye movements.",
keywords = "Computer Vision, Funduscopy, Image Enhancement, Motion Tracking, Ophthalmic Imaging, Retina, Video Processing",
author = "Damian Mendroch and David Harings and Niklas Bauer and Stefan Altmeyer and Uwe Oberheide and Alexander Heisterkamp",
note = "Publisher Copyright: {\textcopyright} 2025 SPIE.; SPIE Photonics West BiOS 2025, BiOS 2025 ; Conference date: 25-01-2025 Through 31-01-2025",
year = "2025",
month = mar,
day = "19",
doi = "10.1117/12.3047657",
language = "English",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Hammer, {Daniel X.} and Derek Nankivil and Tao, {Yuankai K.}",
booktitle = "Ophthalmic Technologies XXXV",
address = "United States",

}

Download

TY - GEN

T1 - Robust real-time retinal tracking for ophthalmic applications

AU - Mendroch, Damian

AU - Harings, David

AU - Bauer, Niklas

AU - Altmeyer, Stefan

AU - Oberheide, Uwe

AU - Heisterkamp, Alexander

N1 - Publisher Copyright: © 2025 SPIE.

PY - 2025/3/19

Y1 - 2025/3/19

N2 - This work presents a software-based approach for robust feature tracking of funduscopy images. In our specific application, it is utilized in a scannerless linear optical coherence tomography system, where both natural and directed eye movements are used to scan the retina. The approach developed includes a fast, contrast-enhancing video preprocessing step. Additional filtering highlights edges and details, enhancing the visibility of blood vessels and the optic disc. Reflections are removed, both those arising from the funduscopy setup itself and non-stationary reflections caused by the cornea or an intraocular lens. A state-of-the-art feature detector and descriptor is used to identify and characterize distinctive image regions. Subsequent feature matching and filtering include additional criteria to enhance robustness against outliers and false detections. From these final matches, homographies are calculated, allowing the derivation of relative movements and absolute positions. The results demonstrate real-time processing with high detection rates and minimal misdetections. This performance is maintained even in the presence of poor contrast and non-stationary reflections in the original video stream. While the tracking is optimized for our application, it is also applicable to other domains, such as optimizing the alignment of retinal images, generating wide-field panorama images from individual frames, or characterizing eye movements.

AB - This work presents a software-based approach for robust feature tracking of funduscopy images. In our specific application, it is utilized in a scannerless linear optical coherence tomography system, where both natural and directed eye movements are used to scan the retina. The approach developed includes a fast, contrast-enhancing video preprocessing step. Additional filtering highlights edges and details, enhancing the visibility of blood vessels and the optic disc. Reflections are removed, both those arising from the funduscopy setup itself and non-stationary reflections caused by the cornea or an intraocular lens. A state-of-the-art feature detector and descriptor is used to identify and characterize distinctive image regions. Subsequent feature matching and filtering include additional criteria to enhance robustness against outliers and false detections. From these final matches, homographies are calculated, allowing the derivation of relative movements and absolute positions. The results demonstrate real-time processing with high detection rates and minimal misdetections. This performance is maintained even in the presence of poor contrast and non-stationary reflections in the original video stream. While the tracking is optimized for our application, it is also applicable to other domains, such as optimizing the alignment of retinal images, generating wide-field panorama images from individual frames, or characterizing eye movements.

KW - Computer Vision

KW - Funduscopy

KW - Image Enhancement

KW - Motion Tracking

KW - Ophthalmic Imaging

KW - Retina

KW - Video Processing

UR - http://www.scopus.com/inward/record.url?scp=105004219757&partnerID=8YFLogxK

U2 - 10.1117/12.3047657

DO - 10.1117/12.3047657

M3 - Conference contribution

AN - SCOPUS:105004219757

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Ophthalmic Technologies XXXV

A2 - Hammer, Daniel X.

A2 - Nankivil, Derek

A2 - Tao, Yuankai K.

PB - SPIE

T2 - SPIE Photonics West BiOS 2025

Y2 - 25 January 2025 through 31 January 2025

ER -

By the same author(s)