{"title":"Three-dimensional Reconstruction of Retinal Blood Vessels based on Binocular Vision","authors":"Chao-liang Wu, Zhiming Lv, Hua-zhu Liu, Xiaoqing Zhao","doi":"10.1109/CICN56167.2022.10008256","DOIUrl":null,"url":null,"abstract":"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.","PeriodicalId":287589,"journal":{"name":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","volume":"10 2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 14th International Conference on Computational Intelligence and Communication Networks (CICN)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CICN56167.2022.10008256","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
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.