A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method
This paper presents a system for weed mapping, using imagery provided by unmanned aerial vehicles (UAVs). Weed control in precision agriculture is based on the design of site-specific control treatments according to weed coverage. A key component is precise and timely weed maps, and one of the crucial steps is weed monitoring, by ground sampling or remote detection. Traditional remote platforms, such as piloted planes and satellites, are not suitable for early weed mapping, given their low spatial and temporal resolutions. Nonetheless, the ultra-high spatial resolution provided by UAVs can be an efficient alternative. The proposed method for weed mapping partitions the image and complements the spectral information with other sources of information. Apart from the well-known vegetation indexes, which are commonly used in precision agriculture, a method for crop row detection is proposed. Given that crops are always organised in rows, this kind of information simplifies the separation between weeds and crops. Finally, the system incorporates classification techniques for the characterisation of pixels as crop, soil and weed. Different machine learning paradigms are compared to identify the best performing strategies, including unsupervised, semi-supervised and supervised techniques. The experiments study the effect of the flight altitude and the sensor used. Our results show that an excellent performance is obtained using very few labelled data complemented with unlabelled data (semi-supervised approach), which motivates the use of weed maps to design site-specific weed control strategies just when farmers implement the early post-emergence weed control.
Main Authors: | , , , , , |
---|---|
Other Authors: | |
Format: | artículo biblioteca |
Language: | English |
Published: |
Elsevier
2015-12
|
Subjects: | Remote sensing, Unmanned aerial vehicles (UAV), Weed detection, Machine learning, Hough transform, Support vector machine, |
Online Access: | http://hdl.handle.net/10261/158758 http://dx.doi.org/10.13039/501100000780 http://dx.doi.org/10.13039/501100003339 http://dx.doi.org/10.13039/501100003329 http://dx.doi.org/10.13039/501100011011 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
id |
dig-ias-es-10261-158758 |
---|---|
record_format |
koha |
spelling |
dig-ias-es-10261-1587582020-05-27T13:50:25Z A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method Pérez-Ortiz, María Peña Barragán, José Manuel Gutiérrez, Pedro Antonio Torres-Sánchez, Jorge Hervás-Martínez, César López Granados, Francisca Consejo Superior de Investigaciones Científicas (España) Ministerio de Economía y Competitividad (España) European Commission Junta de Andalucía Remote sensing Unmanned aerial vehicles (UAV) Weed detection Machine learning Hough transform Support vector machine This paper presents a system for weed mapping, using imagery provided by unmanned aerial vehicles (UAVs). Weed control in precision agriculture is based on the design of site-specific control treatments according to weed coverage. A key component is precise and timely weed maps, and one of the crucial steps is weed monitoring, by ground sampling or remote detection. Traditional remote platforms, such as piloted planes and satellites, are not suitable for early weed mapping, given their low spatial and temporal resolutions. Nonetheless, the ultra-high spatial resolution provided by UAVs can be an efficient alternative. The proposed method for weed mapping partitions the image and complements the spectral information with other sources of information. Apart from the well-known vegetation indexes, which are commonly used in precision agriculture, a method for crop row detection is proposed. Given that crops are always organised in rows, this kind of information simplifies the separation between weeds and crops. Finally, the system incorporates classification techniques for the characterisation of pixels as crop, soil and weed. Different machine learning paradigms are compared to identify the best performing strategies, including unsupervised, semi-supervised and supervised techniques. The experiments study the effect of the flight altitude and the sensor used. Our results show that an excellent performance is obtained using very few labelled data complemented with unlabelled data (semi-supervised approach), which motivates the use of weed maps to design site-specific weed control strategies just when farmers implement the early post-emergence weed control. This work was financed by the Recupera 2020 Project (an agreement between CSIC and Spanish MINECO, EU-FEDER funds). Research of Mr. Torres-Sánchez and Dr. Peña was financed by the FPI and Ramón y Cajal Programs, respectively. Research of Dr. Gutiérrez and Dr. Hervás-Martínez has been subsidised by the TIN2014-54583-C2-1-R project of the Spanish Ministerial Commission of Science and Technology (MICYT), FEDER funds and the P11-TIC-7508 project of the “Junta de Andalucía” (Spain). Peer reviewed 2018-01-03T08:52:27Z 2018-01-03T08:52:27Z 2015-12 artículo http://purl.org/coar/resource_type/c_6501 Applied Soft Computing Journal 37: 533-544 (2015) 1568-4946 http://hdl.handle.net/10261/158758 10.1016/j.asoc.2015.08.027 http://dx.doi.org/10.13039/501100000780 http://dx.doi.org/10.13039/501100003339 http://dx.doi.org/10.13039/501100003329 http://dx.doi.org/10.13039/501100011011 en #PLACEHOLDER_PARENT_METADATA_VALUE# info:eu-repo/grantAgreement/MINECO/Plan Estatal de Investigación Científica y Técnica y de Innovación 2013-2016/TIN2014-54583-C2-1-R http://doi.org/10.1016/j.asoc.2015.08.027 Sí none Elsevier |
institution |
IAS ES |
collection |
DSpace |
country |
España |
countrycode |
ES |
component |
Bibliográfico |
access |
En linea |
databasecode |
dig-ias-es |
tag |
biblioteca |
region |
Europa del Sur |
libraryname |
Biblioteca del IAS España |
language |
English |
topic |
Remote sensing Unmanned aerial vehicles (UAV) Weed detection Machine learning Hough transform Support vector machine Remote sensing Unmanned aerial vehicles (UAV) Weed detection Machine learning Hough transform Support vector machine |
spellingShingle |
Remote sensing Unmanned aerial vehicles (UAV) Weed detection Machine learning Hough transform Support vector machine Remote sensing Unmanned aerial vehicles (UAV) Weed detection Machine learning Hough transform Support vector machine Pérez-Ortiz, María Peña Barragán, José Manuel Gutiérrez, Pedro Antonio Torres-Sánchez, Jorge Hervás-Martínez, César López Granados, Francisca A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method |
description |
This paper presents a system for weed mapping, using imagery provided by unmanned aerial vehicles (UAVs). Weed control in precision agriculture is based on the design of site-specific control treatments according to weed coverage. A key component is precise and timely weed maps, and one of the crucial steps is weed monitoring, by ground sampling or remote detection. Traditional remote platforms, such as piloted planes and satellites, are not suitable for early weed mapping, given their low spatial and temporal resolutions. Nonetheless, the ultra-high spatial resolution provided by UAVs can be an efficient alternative. The proposed method for weed mapping partitions the image and complements the spectral information with other sources of information. Apart from the well-known vegetation indexes, which are commonly used in precision agriculture, a method for crop row detection is proposed. Given that crops are always organised in rows, this kind of information simplifies the separation between weeds and crops. Finally, the system incorporates classification techniques for the characterisation of pixels as crop, soil and weed. Different machine learning paradigms are compared to identify the best performing strategies, including unsupervised, semi-supervised and supervised techniques. The experiments study the effect of the flight altitude and the sensor used. Our results show that an excellent performance is obtained using very few labelled data complemented with unlabelled data (semi-supervised approach), which motivates the use of weed maps to design site-specific weed control strategies just when farmers implement the early post-emergence weed control. |
author2 |
Consejo Superior de Investigaciones Científicas (España) |
author_facet |
Consejo Superior de Investigaciones Científicas (España) Pérez-Ortiz, María Peña Barragán, José Manuel Gutiérrez, Pedro Antonio Torres-Sánchez, Jorge Hervás-Martínez, César López Granados, Francisca |
format |
artículo |
topic_facet |
Remote sensing Unmanned aerial vehicles (UAV) Weed detection Machine learning Hough transform Support vector machine |
author |
Pérez-Ortiz, María Peña Barragán, José Manuel Gutiérrez, Pedro Antonio Torres-Sánchez, Jorge Hervás-Martínez, César López Granados, Francisca |
author_sort |
Pérez-Ortiz, María |
title |
A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method |
title_short |
A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method |
title_full |
A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method |
title_fullStr |
A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method |
title_full_unstemmed |
A semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method |
title_sort |
semi-supervised system for weed mapping in sunflower crops using unmanned aerial vehicles and a crop row detection method |
publisher |
Elsevier |
publishDate |
2015-12 |
url |
http://hdl.handle.net/10261/158758 http://dx.doi.org/10.13039/501100000780 http://dx.doi.org/10.13039/501100003339 http://dx.doi.org/10.13039/501100003329 http://dx.doi.org/10.13039/501100011011 |
work_keys_str_mv |
AT perezortizmaria asemisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT penabarraganjosemanuel asemisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT gutierrezpedroantonio asemisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT torressanchezjorge asemisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT hervasmartinezcesar asemisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT lopezgranadosfrancisca asemisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT perezortizmaria semisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT penabarraganjosemanuel semisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT gutierrezpedroantonio semisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT torressanchezjorge semisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT hervasmartinezcesar semisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod AT lopezgranadosfrancisca semisupervisedsystemforweedmappinginsunflowercropsusingunmannedaerialvehiclesandacroprowdetectionmethod |
_version_ |
1777663138166996992 |