An Interactive platform for low-cost 3D building modeling from VGI data using convolutional neural network

The applications of 3D building models are limited as producing them requires massive labor and time costs well expensive devices. In this paper, we aim to propose a novel web-based interactive platform, VGI3D, overcome these challenges. platform is designed reconstruct by using free images from internet users or volunteered geographic information (VGI) even though not all high quality. Our can effectively obtain each model in 30 seconds, with the help user interaction module convolutional neural network (CNN). provides boundary facades for modeling. And CNN detect facade elements multiple architectural styles complex scenes within images. Moreover, simple possible make it easier use both expert non-expert users. Meanwhile, conducted usability testing collected feedback participants better optimize experience. general, usage VGI data reduces device costs, simplifies process extraction Hence, our proposed offers promising solution modeling community.