On Structure-From-Motion Application Challenges: Good Practices

On Structure-From-Motion Application Challenges: Good Practices

George Ioannakis (Faculty of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece), Anestis Koutsoudis (Xanthi's Division, Multimedia Research Group, Athena Research and Innovation Center, Xanthi, Greece), Fotis Arnaoutoglou (Xanthi's Division, Multimedia Research Group, Athena Research and Innovation Center, Xanthi, Greece), Chairi Kiourt (Xanthi's Division, Multimedia Research Group, Athena Research and Innovation Center, Xanthi, Greece) and Christodoulos Chamzas (Faculty of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece)
DOI: 10.4018/IJCMHS.2017070103
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Numerous software solutions that implement the Structure-from-Motion/Multi-View Stereo (SfM/MVS) 3D reconstruction approach have been made available during the last decade. These allow the production of high quality in terms of geometry and colour information 3D models with the use of unordered image collections that depict a static scene or object from arbitrary viewpoints. Nowadays SfM/MVS-based 3D reconstruction approaches constitute a popular solution in a variety of applications within the cultural heritage domain. As with all 3D reconstruction approaches it has its limitations and application challenges. In this work, the authors attempt to compose a set of guidelines that are based on the important outcomes of important published works that propose solutions that overcome the various challenges introduced by non-friendly surface types.
Article Preview

2. Overcoming Sfm/Mvs Challenges

Numerous software solutions that implement the Structure-from-Motion/Multi-View Stereo (SfM/MVS) 3D reconstruction approach have been made available during the last decade. It is a fact that the image collection phase, that provides the input data for the SfM/MVS, should be performed under specific and controlled environment conditions. Moreover, the surface properties of the object being captured have to be method-friendly. The latter prerequisite is fulfilled when the object’s surface exploits high-frequency changes in terms of colours or intensities while being non-reflective. In all other cases, it is most probable that the application of the SfM/MVS will produce 3D models that reflect errors in terms of geometric accuracy (noisy surfaces).

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 1: 2 Issues (2017)
View Complete Journal Contents Listing