Semantic Segmentation of Weeds and Crops in Multispectral Images by Using a Convolutional Neural Networks Based on U-Net

Miguel Ángel Chicchón Apaza, Héctor Manuel Bedón Monzón, Ramón Pablo Alcarria Garrido

Research output: Chapter in Book/Report/Conference proceedingPaper (Conference contribution)

Abstract

A first step in the process of automating weed removal in precision agriculture is the semantic segmentation of crops, weeds and soil. Deep learning techniques based on convolutional neural networks are successfully applied today and one of the most popular network architectures in semantic segmentation problems is U-Net. In this article, the variants in the U-Net architecture were evaluated based on the aggregation of residual and recurring blocks to improve their performance. For training and testing, a set of data available on the Internet was used, consisting of 60 multispectral images with unbalanced pixels, so techniques were applied to increase and balance the data. Experimental results show a slight increase in quality metrics compared to the classic U-Net architecture.

Original languageEnglish
Title of host publicationApplied Technologies - 1st International Conference, ICAT 2019, Proceedings
EditorsMiguel Botto-Tobar, Marcelo Zambrano Vizuete, Pablo Torres-Carrión, Sergio Montes León, Guillermo Pizarro Vásquez, Benjamin Durakovic
PublisherSpringer
Pages473-485
Number of pages13
ISBN (Print)9783030425197
DOIs
StatePublished - 1 Jan 2020
Event1st International Conference on Applied Technologies, ICAT 2019 - Quito, Ecuador
Duration: 3 Dec 20195 Dec 2019

Publication series

NameCommunications in Computer and Information Science
Volume1194 CCIS
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

Conference1st International Conference on Applied Technologies, ICAT 2019
CountryEcuador
CityQuito
Period3/12/195/12/19

Keywords

  • Convolutional neural network
  • Deep learning
  • Precision agriculture
  • Semantic segmentation
  • U-Net

Fingerprint Dive into the research topics of 'Semantic Segmentation of Weeds and Crops in Multispectral Images by Using a Convolutional Neural Networks Based on U-Net'. Together they form a unique fingerprint.

  • Projects

    Cite this

    Chicchón Apaza, M. Á., Monzón, H. M. B., & Garrido, R. P. A. (2020). Semantic Segmentation of Weeds and Crops in Multispectral Images by Using a Convolutional Neural Networks Based on U-Net. In M. Botto-Tobar, M. Zambrano Vizuete, P. Torres-Carrión, S. Montes León, G. Pizarro Vásquez, & B. Durakovic (Eds.), Applied Technologies - 1st International Conference, ICAT 2019, Proceedings (pp. 473-485). (Communications in Computer and Information Science; Vol. 1194 CCIS). Springer. https://doi.org/10.1007/978-3-030-42520-3_38