loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Author: Ivan Nikolov

Affiliation: Computer Graphics Group, Department of Architecture, Design and Media Technology, Aalborg University, Aalborg, Denmark

Keyword(s): Synthetic Data, Variational Autoencoders, Object Detection, Dataset Augmentation, Surveillance.

Abstract: The requirements for more and more data for training deep learning surveillance and object detection models have resulted in slower deployment and more costs connected to dataset gathering, annotation, and testing. One way to help with this is the use of synthetic data giving more varied scenarios and not requiring manual annotation. We present our initial exploratory work in generating synthetic pedestrian augmentations for an existing dataset through the use of variational autoencoders. Our method consists of creating a large number of backgrounds and training a variational autoencoder on a small subset of annotated pedestrians. We then interpolate the latent space of the autoencoder to generate variations of these pedestrians, calculate their positions on the backgrounds, and blend them to create new images. We show that even though we do not achieve as good results as just adding more real images, we can boost the performance and robustness of a YoloV5 model trained on a mix of r eal and small amounts of synthetic images. As part of this paper, we also propose the next steps to expand this approach and make it much more useful for a wider array of datasets. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 18.118.226.105

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Nikolov, I. (2024). Variational Autoencoders for Pedestrian Synthetic Data Augmentation of Existing Datasets: A Preliminary Investigation. In Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP; ISBN 978-989-758-679-8; ISSN 2184-4321, SciTePress, pages 829-836. DOI: 10.5220/0012570700003660

@conference{visapp24,
author={Ivan Nikolov.},
title={Variational Autoencoders for Pedestrian Synthetic Data Augmentation of Existing Datasets: A Preliminary Investigation},
booktitle={Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP},
year={2024},
pages={829-836},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012570700003660},
isbn={978-989-758-679-8},
issn={2184-4321},
}

TY - CONF

JO - Proceedings of the 19th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications - Volume 2: VISAPP
TI - Variational Autoencoders for Pedestrian Synthetic Data Augmentation of Existing Datasets: A Preliminary Investigation
SN - 978-989-758-679-8
IS - 2184-4321
AU - Nikolov, I.
PY - 2024
SP - 829
EP - 836
DO - 10.5220/0012570700003660
PB - SciTePress

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic