Scene Understanding and 3D Imagination: A Comparison between Machine Learning and Human Cognition

Michael Schoosleitner, Torsten Ullrich, Torsten Ullrich

2020

Abstract

Spatial perception and three-dimensional imagination are important characteristics for many construction tasks in civil engineering. In order to support people in these tasks, worldwide research is being carried out on assistance systems based on machine learning and augmented reality. In this paper, we examine the machine learning component and compare it to human performance. The test scenario is to recognize a partly-assembled model, identify its current status, i.e. the current instruction step, and to return the next step. Thus, we created a database of 2D images containing the complete set of instruction steps of the corresponding 3D model. Afterwards, we trained the deep neural network RotationNet with these images. Usually, the machine learning approaches are compared to each other; our contribution evaluates the machine learning results with human performance tested in a survey: in a clean-room setting the survey and RotationNet results are comparable and neither is significantly better. The real-world results show that the machine learning approaches need further improvements.

Paper Citation

in Harvard Style

Schoosleitner M. and Ullrich T. (2020). Scene Understanding and 3D Imagination: A Comparison between Machine Learning and Human Cognition. In Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 2: HUCAPP; ISBN 978-989-758-402-2, SciTePress, pages 231-238. DOI: 10.5220/0009350002310238

in Bibtex Style

@conference{hucapp20,
author={Michael Schoosleitner and Torsten Ullrich},
title={Scene Understanding and 3D Imagination: A Comparison between Machine Learning and Human Cognition},
booktitle={Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 2: HUCAPP},
year={2020},
pages={231-238},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009350002310238},
isbn={978-989-758-402-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2020) - Volume 2: HUCAPP
TI - Scene Understanding and 3D Imagination: A Comparison between Machine Learning and Human Cognition
SN - 978-989-758-402-2
AU - Schoosleitner M.
AU - Ullrich T.
PY - 2020
SP - 231
EP - 238
DO - 10.5220/0009350002310238
PB - SciTePress