Exploring Segnet Architectures for iGPU Embedded Devices

Jean-Baptiste Chaudron, Alfonso Mascarenas-Gonzalez

2023

Abstract

Image segmentation is an important topic in computer vision which encompasses a variety of techniques to divide image into multiple areas or sub-regions in order to extract meaningful information. Artificial Neural Networks (ANNs), biologically inspired algorithms, are nowadays widely used to perform such tasks and popular models are usually based on encoder-decoder architectures. Segnet was one of the first proposed model of this kind in the literature and, despite its efficiency, it has several drawbacks for embedded systems especially due to the huge amount of arithmetic operations and memory used in the original version. However, its simple sequential based architecture offers interesting properties for optimization and real-time analysis. In this paper, we deeply investigate how to tune and adapt original Segnet architecture to allow efficient run-time execution on embedded targets equipped with an iGPU. We propose our own implementation design which is experimented and validated on iGPU embedded devices for two state of the art datasets from Unmanned Aerial Vehicle (UAV) applications.

Paper Citation

in Harvard Style

Chaudron J. and Mascarenas-Gonzalez A. (2023). Exploring Segnet Architectures for iGPU Embedded Devices. In Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA; ISBN 978-989-758-674-3, SciTePress, pages 419-430. DOI: 10.5220/0012185100003595

in Bibtex Style

@conference{ncta23,
author={Jean-Baptiste Chaudron and Alfonso Mascarenas-Gonzalez},
title={Exploring Segnet Architectures for iGPU Embedded Devices},
booktitle={Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA},
year={2023},
pages={419-430},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012185100003595},
isbn={978-989-758-674-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Computational Intelligence - Volume 1: NCTA
TI - Exploring Segnet Architectures for iGPU Embedded Devices
SN - 978-989-758-674-3
AU - Chaudron J.
AU - Mascarenas-Gonzalez A.
PY - 2023
SP - 419
EP - 430
DO - 10.5220/0012185100003595
PB - SciTePress