1-s2.0-S2667305322000199-main.pdf (2.99 MB)
Download file

Investigating the optimisation of real-world and synthetic object detection training datasets through the consideration of environmental and simulation factors

Download (2.99 MB)
Computer vision is used for many industrial applications involving automation, especially those related to efficiency and safety. Computer vision techniques which use machine learning, such as object detectors, need a dataset of images for training and testing. Publicly available datasets or new dataset can be used. However, these datasets rarely consider whether the dataset is leading to optimal performance. Environmental factors, such as lighting and occlusion, will alter the appearance of the images and so images taken under certain condition may have different effects on training. A knowledge gap has formed as to how the test performance of deep neural networks can be improved by considering the effect and interactions of factors where either real or synthetic images are used. The following research illustrates that the different factors can have a significant impact on the test performance and demonstrates a process that can be used on real-world and synthetic images to identify the effect of each factor and discusses how this information may be used to create an optimal training dataset.

Funding

Loughborough University NPIF 2018

Engineering and Physical Sciences Research Council

Find out more...

History

School

  • Mechanical, Electrical and Manufacturing Engineering

Published in

Intelligent Systems with Applications

Volume

14

Publisher

Elsevier

Version

VoR (Version of Record)

Rights holder

© The Authors

Publisher statement

This is an Open Access Article. It is published by Elsevier under the Creative Commons Attribution 4.0 International Licence (CC BY 4.0). Full details of this licence are available at: https://creativecommons.org/licenses/by/4.0/

Acceptance date

11/04/2022

Publication date

2022-04-12

Copyright date

2022

ISSN

2667-3053

Language

en

Depositor

Dr Jon Petzing. Deposit date: 25 April 2022

Article number

200079