Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sun, Yung-Hong, Shen, Gefei, Chen, Jiangang, Fernandes, Jayer, Shada, Amber L., Heise, Charles P., Jiang, Hongrui, Hu, Yu Hen
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2412.16742
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866917981076848640
author Sun, Yung-Hong
Shen, Gefei
Chen, Jiangang
Fernandes, Jayer
Shada, Amber L.
Heise, Charles P.
Jiang, Hongrui
Hu, Yu Hen
author_facet Sun, Yung-Hong
Shen, Gefei
Chen, Jiangang
Fernandes, Jayer
Shada, Amber L.
Heise, Charles P.
Jiang, Hongrui
Hu, Yu Hen
contents EasyVis2 is a system designed to provide hands-free, real-time 3D visualization for laparoscopic surgery. It incorporates a surgical trocar equipped with an array of micro-cameras, which can be inserted into the body cavity to offer an enhanced field of view and a 3D perspective of the surgical procedure. A specialized deep neural network algorithm, YOLOv8-Pose, is utilized to estimate the position and orientation of surgical instruments in each individual camera view. These multi-view estimates enable the calculation of 3D poses of surgical tools, facilitating the rendering of a 3D surface model of the instruments, overlaid on the background scene, for real-time visualization. This study presents methods for adapting YOLOv8-Pose to the EasyVis2 system, including the development of a tailored training dataset. Experimental results demonstrate that, with an identical number of cameras, the new system improves 3D reconstruction accuracy and reduces computation time. Additionally, the adapted YOLOv8-Pose system shows high accuracy in 2D pose estimation.
format Preprint
id arxiv_https___arxiv_org_abs_2412_16742
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle EasyVis2: A Real Time Multi-view 3D Visualization System for Laparoscopic Surgery Training Enhanced by a Deep Neural Network YOLOv8-Pose
Sun, Yung-Hong
Shen, Gefei
Chen, Jiangang
Fernandes, Jayer
Shada, Amber L.
Heise, Charles P.
Jiang, Hongrui
Hu, Yu Hen
Computer Vision and Pattern Recognition
EasyVis2 is a system designed to provide hands-free, real-time 3D visualization for laparoscopic surgery. It incorporates a surgical trocar equipped with an array of micro-cameras, which can be inserted into the body cavity to offer an enhanced field of view and a 3D perspective of the surgical procedure. A specialized deep neural network algorithm, YOLOv8-Pose, is utilized to estimate the position and orientation of surgical instruments in each individual camera view. These multi-view estimates enable the calculation of 3D poses of surgical tools, facilitating the rendering of a 3D surface model of the instruments, overlaid on the background scene, for real-time visualization. This study presents methods for adapting YOLOv8-Pose to the EasyVis2 system, including the development of a tailored training dataset. Experimental results demonstrate that, with an identical number of cameras, the new system improves 3D reconstruction accuracy and reduces computation time. Additionally, the adapted YOLOv8-Pose system shows high accuracy in 2D pose estimation.
title EasyVis2: A Real Time Multi-view 3D Visualization System for Laparoscopic Surgery Training Enhanced by a Deep Neural Network YOLOv8-Pose
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.16742