Assessment of Texture Features for Bermudagrass (<i>Cynodon dactylon</i>) Detection in Sugarcane Plantations
Sugarcane products contribute significantly to the Brazilian economy, generating U.S. $12.2 billion in revenue in 2018. Identifying and monitoring factors that induce yield reduction, such as weed occurrence, is thus imperative. The detection of Bermudagrass in sugarcane crops using remote sensing d...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-04-01
|
Series: | Drones |
Subjects: | |
Online Access: | https://www.mdpi.com/2504-446X/3/2/36 |
id |
doaj-caf8bbbb88bc4e9aaee73767f1c0eb4c |
---|---|
record_format |
Article |
spelling |
doaj-caf8bbbb88bc4e9aaee73767f1c0eb4c2020-11-25T01:06:04ZengMDPI AGDrones2504-446X2019-04-01323610.3390/drones3020036drones3020036Assessment of Texture Features for Bermudagrass (<i>Cynodon dactylon</i>) Detection in Sugarcane PlantationsCesare Di Girolamo-Neto0Ieda Del’Arco Sanches1Alana Kasahara Neves2Victor Hugo Rohden Prudente3Thales Sehn Körting4Michelle Cristina Araujo Picoli5Luiz Eduardo Oliveira e Cruz de Aragão6National Institute for Space Research–Remote Sensing Division, São José dos Campos, São Paulo 12227-010, BrazilNational Institute for Space Research–Remote Sensing Division, São José dos Campos, São Paulo 12227-010, BrazilNational Institute for Space Research–Image Processing Division, São José dos Campos, São Paulo 12227-010, BrazilNational Institute for Space Research–Remote Sensing Division, São José dos Campos, São Paulo 12227-010, BrazilNational Institute for Space Research–Image Processing Division, São José dos Campos, São Paulo 12227-010, BrazilNational Institute for Space Research–Remote Sensing Division, São José dos Campos, São Paulo 12227-010, BrazilNational Institute for Space Research–Remote Sensing Division, São José dos Campos, São Paulo 12227-010, BrazilSugarcane products contribute significantly to the Brazilian economy, generating U.S. $12.2 billion in revenue in 2018. Identifying and monitoring factors that induce yield reduction, such as weed occurrence, is thus imperative. The detection of Bermudagrass in sugarcane crops using remote sensing data, however, is a challenge considering their spectral similarity. To overcome this limitation, this paper aims to explore the potential of texture features derived from images acquired by an optical sensor onboard anunmanned aerial vehicle (UAV) to detect Bermudagrass in sugarcane. Aerial images with a spatial resolution of 2 cm were acquired from a sugarcane field in Brazil. The Green-Red Vegetation Index and several texture metrics derived from the gray-level co-occurrence matrix were calculated to perform an automatic classification using arandom forest algorithm. Adding texture metrics to the classification process improved the overall accuracy from 83.00% to 92.54%, and this improvement was greater considering larger window sizes, since they representeda texture transition between two targets. Production losses induced by Bermudagrass presence reached 12.1 tons × ha<sup>−1</sup> in the study site. This study not only demonstrated the capacity of UAV images to overcome the well-known limitation of detecting Bermudagrass in sugarcane crops, but also highlighted the importance of texture for high-accuracy quantification of weed invasion in sugarcane crops.https://www.mdpi.com/2504-446X/3/2/36remote sensingclassificationagricultureweed detectionUAV images |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Cesare Di Girolamo-Neto Ieda Del’Arco Sanches Alana Kasahara Neves Victor Hugo Rohden Prudente Thales Sehn Körting Michelle Cristina Araujo Picoli Luiz Eduardo Oliveira e Cruz de Aragão |
spellingShingle |
Cesare Di Girolamo-Neto Ieda Del’Arco Sanches Alana Kasahara Neves Victor Hugo Rohden Prudente Thales Sehn Körting Michelle Cristina Araujo Picoli Luiz Eduardo Oliveira e Cruz de Aragão Assessment of Texture Features for Bermudagrass (<i>Cynodon dactylon</i>) Detection in Sugarcane Plantations Drones remote sensing classification agriculture weed detection UAV images |
author_facet |
Cesare Di Girolamo-Neto Ieda Del’Arco Sanches Alana Kasahara Neves Victor Hugo Rohden Prudente Thales Sehn Körting Michelle Cristina Araujo Picoli Luiz Eduardo Oliveira e Cruz de Aragão |
author_sort |
Cesare Di Girolamo-Neto |
title |
Assessment of Texture Features for Bermudagrass (<i>Cynodon dactylon</i>) Detection in Sugarcane Plantations |
title_short |
Assessment of Texture Features for Bermudagrass (<i>Cynodon dactylon</i>) Detection in Sugarcane Plantations |
title_full |
Assessment of Texture Features for Bermudagrass (<i>Cynodon dactylon</i>) Detection in Sugarcane Plantations |
title_fullStr |
Assessment of Texture Features for Bermudagrass (<i>Cynodon dactylon</i>) Detection in Sugarcane Plantations |
title_full_unstemmed |
Assessment of Texture Features for Bermudagrass (<i>Cynodon dactylon</i>) Detection in Sugarcane Plantations |
title_sort |
assessment of texture features for bermudagrass (<i>cynodon dactylon</i>) detection in sugarcane plantations |
publisher |
MDPI AG |
series |
Drones |
issn |
2504-446X |
publishDate |
2019-04-01 |
description |
Sugarcane products contribute significantly to the Brazilian economy, generating U.S. $12.2 billion in revenue in 2018. Identifying and monitoring factors that induce yield reduction, such as weed occurrence, is thus imperative. The detection of Bermudagrass in sugarcane crops using remote sensing data, however, is a challenge considering their spectral similarity. To overcome this limitation, this paper aims to explore the potential of texture features derived from images acquired by an optical sensor onboard anunmanned aerial vehicle (UAV) to detect Bermudagrass in sugarcane. Aerial images with a spatial resolution of 2 cm were acquired from a sugarcane field in Brazil. The Green-Red Vegetation Index and several texture metrics derived from the gray-level co-occurrence matrix were calculated to perform an automatic classification using arandom forest algorithm. Adding texture metrics to the classification process improved the overall accuracy from 83.00% to 92.54%, and this improvement was greater considering larger window sizes, since they representeda texture transition between two targets. Production losses induced by Bermudagrass presence reached 12.1 tons × ha<sup>−1</sup> in the study site. This study not only demonstrated the capacity of UAV images to overcome the well-known limitation of detecting Bermudagrass in sugarcane crops, but also highlighted the importance of texture for high-accuracy quantification of weed invasion in sugarcane crops. |
topic |
remote sensing classification agriculture weed detection UAV images |
url |
https://www.mdpi.com/2504-446X/3/2/36 |
work_keys_str_mv |
AT cesaredigirolamoneto assessmentoftexturefeaturesforbermudagrassicynodondactylonidetectioninsugarcaneplantations AT iedadelarcosanches assessmentoftexturefeaturesforbermudagrassicynodondactylonidetectioninsugarcaneplantations AT alanakasaharaneves assessmentoftexturefeaturesforbermudagrassicynodondactylonidetectioninsugarcaneplantations AT victorhugorohdenprudente assessmentoftexturefeaturesforbermudagrassicynodondactylonidetectioninsugarcaneplantations AT thalessehnkorting assessmentoftexturefeaturesforbermudagrassicynodondactylonidetectioninsugarcaneplantations AT michellecristinaaraujopicoli assessmentoftexturefeaturesforbermudagrassicynodondactylonidetectioninsugarcaneplantations AT luizeduardooliveiraecruzdearagao assessmentoftexturefeaturesforbermudagrassicynodondactylonidetectioninsugarcaneplantations |
_version_ |
1725191672015355904 |