Three-dimensional Reconstruction of Retinal Blood Vessels based on Binocular Vision

Due to the limited perception ability of the naked eye, it is difficult to accurately locate the micro scale retinal vessels, which is easy to cause organ damage in the process of surgery. Therefore, the retinal vascular reconstruction method based on binocular stereo vision is studied. Firstly, bui...

Full description

Saved in:
Bibliographic Details
Published in2022 14th International Conference on Computational Intelligence and Communication Networks (CICN) pp. 109 - 114
Main Authors Wu, Chao-liang, Lv, Zhi-jin, Liu, Hua-zhu, Zhao, Xiao-fang
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.12.2022
Subjects
binocular vision
Blood vessels
error energy function
Fundus vessels
Image segmentation
Machine vision
Point cloud compression
Solid modeling
Surgery
three dimensional reconstruction
Three-dimensional displays
Online AccessGet full text

Cover

More Information
Summary:Due to the limited perception ability of the naked eye, it is difficult to accurately locate the micro scale retinal vessels, which is easy to cause organ damage in the process of surgery. Therefore, the retinal vascular reconstruction method based on binocular stereo vision is studied. Firstly, build a binocular vision detection system and then calibrate and correct the system. Secondly, filter and segment the collected 3D printed eyeball blood vessel model image, and calculate the parallax and depth map by constructing the error energy function. After that, the high-precision 3D point cloud model can be obtained. Finally, the error analysis of three-dimensional point cloud is carried out by binocular parallax principle. The experimental results show that this method can control the error within 0.5 mm and meet the requirements of retinal vascular surgery.
ISSN:2472-7555
DOI:10.1109/CICN56167.2022.10008256