Saved in:
Bibliographic Details
Main Authors: Morlana, Javier, Tardós, Juan D., Montiel, J. M. M.
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2305.05546
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911949716979712
author Morlana, Javier
Tardós, Juan D.
Montiel, J. M. M.
author_facet Morlana, Javier
Tardós, Juan D.
Montiel, J. M. M.
contents We propose a topological mapping and localization system able to operate on real human colonoscopies, despite significant shape and illumination changes. The map is a graph where each node codes a colon location by a set of real images, while edges represent traversability between nodes. For close-in-time images, where scene changes are minor, place recognition can be successfully managed with the recent transformers-based local feature matching algorithms. However, under long-term changes -- such as different colonoscopies of the same patient -- feature-based matching fails. To address this, we train on real colonoscopies a deep global descriptor achieving high recall with significant changes in the scene. The addition of a Bayesian filter boosts the accuracy of long-term place recognition, enabling relocalization in a previously built map. Our experiments show that ColonMapper is able to autonomously build a map and localize against it in two important use cases: localization within the same colonoscopy or within different colonoscopies of the same patient. Code: https://github.com/jmorlana/ColonMapper.
format Preprint
id arxiv_https___arxiv_org_abs_2305_05546
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle ColonMapper: topological mapping and localization for colonoscopy
Morlana, Javier
Tardós, Juan D.
Montiel, J. M. M.
Computer Vision and Pattern Recognition
We propose a topological mapping and localization system able to operate on real human colonoscopies, despite significant shape and illumination changes. The map is a graph where each node codes a colon location by a set of real images, while edges represent traversability between nodes. For close-in-time images, where scene changes are minor, place recognition can be successfully managed with the recent transformers-based local feature matching algorithms. However, under long-term changes -- such as different colonoscopies of the same patient -- feature-based matching fails. To address this, we train on real colonoscopies a deep global descriptor achieving high recall with significant changes in the scene. The addition of a Bayesian filter boosts the accuracy of long-term place recognition, enabling relocalization in a previously built map. Our experiments show that ColonMapper is able to autonomously build a map and localize against it in two important use cases: localization within the same colonoscopy or within different colonoscopies of the same patient. Code: https://github.com/jmorlana/ColonMapper.
title ColonMapper: topological mapping and localization for colonoscopy
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2305.05546