{"title":"The Background Role in 3D Object Reconstruction","authors":"I. Enesi, A. Kuqi, Ambra Korra","doi":"10.1109/MECO58584.2023.10155095","DOIUrl":null,"url":null,"abstract":"Photogrammetry is a continuously growing 3D reconstruction technique, due to the simplicity and low costs of hardware and software parts. It is defined as the collection of physical information from 2D photos to generate 3D reconstructions. There are various software options available to perform this task, each with its own specifications in terms of quality, performance, and price. In 3D reconstruction, one of the most determining factors is the accuracy of dimensions, especially when it comes to the field of spare parts or prostheses in medicine. Undoubtedly there are many concurrent factors that establish the final precision, present in both hardware and software. Determining the dimensions of the reconstructed object, especially when the object in focus is small and has a complex geometric shape, is one of the main tasks. To achieve the 3D reconstruction, we will utilize open-source software such as Meshroom combined with measurements taken using MeshLab, along with proprietary software like Agisoft. Experimental results show that Agisoft performs better than Meshroom&Meshlab, offering more optimization techniques, reducing processing time and a higher visual quality in the reconstructed 3D object as well as a higher accuracy in size measurement.","PeriodicalId":187825,"journal":{"name":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 12th Mediterranean Conference on Embedded Computing (MECO)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/MECO58584.2023.10155095","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
Photogrammetry is a continuously growing 3D reconstruction technique, due to the simplicity and low costs of hardware and software parts. It is defined as the collection of physical information from 2D photos to generate 3D reconstructions. There are various software options available to perform this task, each with its own specifications in terms of quality, performance, and price. In 3D reconstruction, one of the most determining factors is the accuracy of dimensions, especially when it comes to the field of spare parts or prostheses in medicine. Undoubtedly there are many concurrent factors that establish the final precision, present in both hardware and software. Determining the dimensions of the reconstructed object, especially when the object in focus is small and has a complex geometric shape, is one of the main tasks. To achieve the 3D reconstruction, we will utilize open-source software such as Meshroom combined with measurements taken using MeshLab, along with proprietary software like Agisoft. Experimental results show that Agisoft performs better than Meshroom&Meshlab, offering more optimization techniques, reducing processing time and a higher visual quality in the reconstructed 3D object as well as a higher accuracy in size measurement.