Web service for automatic generation of 3D models through video

Abstract

This thesis aims to create a scalable web service capable of generating 3D models through video. In order to improve usability and reduce costs, it is expected that the video is acquired through a monocular aquisition system. In order to make this tool as simple and flexible as possible, a web service is going to be developed. This allows developers to create other applications that can be accessed in lesser powerful devices, such as smartphones, provided that they have an Internet connection. The major contribution of this thesis is the creation of the cloud's system architecture, adapting the existing 3D reconstruction algorithms to this new reality, since the majority of the computer vision algorithms are not distributed.