Multichannel Analysis in Weed Detection

Hericles Ferraz, Jocival Dias Junior, André Backes, Daniel Abdala, Mauricio Escarpinati

2023

Abstract

In this paper a new classification scheme is investigated aiming to improve the current classification models used in weed detection based on UAV imaging data. The premise is that the investigation regarding the relevance of a given color space channel regarding its classification power of important features could lead to a better selection of training data. Consequently it could culminate on a superior classification result. An hybrid image is constructed using only the channels which least overlapping regarding their contribution to represent the weed and soil data. It is then fed to a deep neural net in which a process of transfer learning takes place incorporating the previously trained knowledge with the new data provided by the hybrid images. Three publicly available datasets were used both in training and testing. Preliminary results seems to indicate the feasibility of the proposed methodology.

Paper Citation

in Harvard Style

Ferraz H., Dias Junior J., Backes A., Abdala D. and Escarpinati M. (2023). Multichannel Analysis in Weed Detection. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 419-426. DOI: 10.5220/0011780900003417

in Bibtex Style

@conference{visapp23,
author={Hericles Ferraz and Jocival Dias Junior and André Backes and Daniel Abdala and Mauricio Escarpinati},
title={Multichannel Analysis in Weed Detection},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP},
year={2023},
pages={419-426},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011780900003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 4: VISAPP
TI - Multichannel Analysis in Weed Detection
SN - 978-989-758-634-7
AU - Ferraz H.
AU - Dias Junior J.
AU - Backes A.
AU - Abdala D.
AU - Escarpinati M.
PY - 2023
SP - 419
EP - 426
DO - 10.5220/0011780900003417
PB - SciTePress