Three-Dimensional Human Head Reconstruction Using Smartphone-Based Close-Range Video Photogrammetry

Dalius Matuzevičius,Artūras Serackis

doi:10.3390/app12010229

Dalius Matuzevičius, Artūras Serackis

Open Access

https://doi.org/10.3390/app12010229

Copy DOI

Journal: Applied sciences	Publication Date: Dec 27, 2021
Citations: 18	License type: CC BY 4.0

Affiliation: Vilnius Gediminas Technical University

Abstract

Creation of head 3D models from videos or pictures of the head by using close-range photogrammetry techniques has many applications in clinical, commercial, industrial, artistic, and entertainment areas. This work aims to create a methodology for improving 3D head reconstruction, with a focus on using selfie videos as the data source. Then, using this methodology, we seek to propose changes for the general-purpose 3D reconstruction algorithm to improve the head reconstruction process. We define the improvement of the 3D head reconstruction as an increase of reconstruction quality (which is lowering reconstruction errors of the head and amount of semantic noise) and reduction of computational load. We proposed algorithm improvements that increase reconstruction quality by removing image backgrounds and by selecting diverse and high-quality frames. Algorithm modifications were evaluated on videos of the mannequin head. Evaluation results show that baseline reconstruction is improved 12 times due to the reduction of semantic noise and reconstruction errors of the head. The reduction of computational demand was achieved by reducing the frame number needed to process, reducing the number of image matches required to perform, reducing an average number of feature points in images, and still being able to provide the highest precision of the head reconstruction.

Highlights

Academic Editor: Mauro Lo BruttoThree-dimensional modeling of the human head has a wide range of applications.Three-dimensional data of the head, with extension to the whole body, are widely used in clinical, industrial, anthropological, forensic, sports, commercial, and entertainment areas
The methodology is created keeping in mind that 3D reconstruction algorithms are intended for use in creating head models from selfie videos, and the models will most likely be used to make head measurements in order to select a suitable size of head wearables
Semantic noise is reduced by minimizing non-head points in the reconstructed model, so the reconstructed scene includes only head points

Summary

Introduction

Three-dimensional modeling of the human head has a wide range of applications. Three-dimensional data of the head, with extension to the whole body, are widely used in clinical, industrial, anthropological, forensic, sports, commercial, and entertainment areas. The first branch of the baseline algorithm is created by adding image background elimination and is labeled as Pipeline 2 with sub-branches {a|b} (Figure 1). Initial feature point selection following the 6. Feature point detection step of the generalized 3D reconstruction pipeline. The initial feature point selection (or elimination of unnecessary points) process requires information about the bounds of the main object, i.e., the head.

Objectives

Methods

Results

Conclusion