KIT | KIT-Bibliothek | Impressum | Datenschutz

FootCapture: Towards an AR-based System for 3D Foot Object Acquisition through Photogrammetry

Khan-Blouki, Valentin 1; Seiz, Franziska 1; Walter, Nicolas 1; Jaus, Alexander 1; Marinov, Zdravko 1; Luijten, Gijs; Egger, Jan; Seibold, Constantin Marc ORCID iD icon 1; Solte, Dirk; Kleesiek, Jens
1 Institut für Anthropomatik und Robotik (IAR), Karlsruher Institut für Technologie (KIT)

Abstract:

The acquisition of accurate 3D models of feet is crucial in fields such as chronic foot wound monitoring, prosthetics design, and orthopedic surgery. However, obtaining precise models of patients' feet typically relies on manual measurements, which is both costly and prone to error. Addressing this need, we introduce FootCapture, a mobile application designed to facilitate the acquisition of precise photographic measurements. Our solution employs augmented reality to intuitively guide untrained users to capture comprehensive photographic data from the correct positions and angles, suitable to create a high-fidelity 3D model of the patient's foot using photogrammetry. To validate our application's utility, we compared FootCapture with Apple's Guided Capture application in a user study with n=7 participants. The results showed FootCapture’s intuitive use and high robustness marking it as a tool worth considering for medical personnel.


Verlagsausgabe §
DOI: 10.5445/IR/1000173750
Veröffentlicht am 27.08.2024
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Anthropomatik und Robotik (IAR)
Publikationstyp Proceedingsbeitrag
Publikationsjahr 2024
Sprache Englisch
Identifikator KITopen-ID: 1000173750
Erschienen in Medical Imaging with Deep Learning
Veranstaltung Conference on Medical Imaging with Deep Learning (MIDL 2024), Paris, Frankreich, 03.07.2024 – 05.07.2024
Serie Medical Imaging with Deep Learning 2024
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page