Automation solutions for the evaluation of plant health in corn fields

Dimitris Zermas, Da Teng, Panagiotis Stanitsas, Mike E Bazakos, Daniel Kaiser, Vassilios Morellas, D J Mulla, Nikolaos P Papanikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Citations (Scopus)

Abstract

The continuously growing need for increasing the production of food and reducing the degradation of water supplies, has led to the development of several precision agriculture systems over the past decade so as to meet the needs of modern societies. The present study describes a methodology for the detection and characterization of Nitrogen (N) deficiencies in corn fields. Current methods of field surveillance are either completed manually or with the assistance of satellite imaging, which offer infrequent and costly information to the farmers about the state of their fields. The proposed methodology promotes the use of small-scale Unmanned Aerial Vehicles (UAVs) and Computer Vision algorithms that operate with information in the visual (RGB) spectrum. Through this implementation, a lower cost solution for identifying N deficiencies is promoted. We provide extensive results on the use of commercial RGB sensors for delivering the essential information to farmers regarding the condition of their field, targeting the reduction of N fertilizers and the increase of the crop performance. Data is first collected by a UAV that hovers over a stressed area and collects high resolution RGB images at a low altitude. A recommendation algorithm identifies potential segments of the images that are candidates exhibiting N deficiency. Based on the feedback from experts in the area a training set is constructed utilizing the initial suggestions of the recommendation algorithm. Supervised learning methods are then used to characterize crop leaves that exhibit signs of N deficiency. The performance of 84.2% strongly supports the potential of this scheme to identify N-deficient leaves even in the case of images where the unhealthy leaves are heavily occluded by other healthy or stressed leaves.

Original languageEnglish (US)
Title of host publicationIROS Hamburg 2015 - Conference Digest
Subtitle of host publicationIEEE/RSJ International Conference on Intelligent Robots and Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages6521-6527
Number of pages7
ISBN (Electronic)9781479999941
DOIs
StatePublished - Dec 11 2015
EventIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015 - Hamburg, Germany
Duration: Sep 28 2015Oct 2 2015

Publication series

NameIEEE International Conference on Intelligent Robots and Systems
Volume2015-December
ISSN (Print)2153-0858
ISSN (Electronic)2153-0866

Other

OtherIEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015
CountryGermany
CityHamburg
Period9/28/1510/2/15

Fingerprint

Automation
Health
Unmanned aerial vehicles (UAV)
Crops
Supervised learning
Fertilizers
Image resolution
Water supply
Agriculture
Computer vision
Satellites
Nitrogen
Feedback
Imaging techniques
Degradation
Sensors
Costs

Keywords

  • Machine Learning
  • Precision Agriculture
  • UAV

Cite this

Zermas, D., Teng, D., Stanitsas, P., Bazakos, M. E., Kaiser, D., Morellas, V., ... Papanikolopoulos, N. P. (2015). Automation solutions for the evaluation of plant health in corn fields. In IROS Hamburg 2015 - Conference Digest: IEEE/RSJ International Conference on Intelligent Robots and Systems (pp. 6521-6527). [7354309] (IEEE International Conference on Intelligent Robots and Systems; Vol. 2015-December). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IROS.2015.7354309

Automation solutions for the evaluation of plant health in corn fields. / Zermas, Dimitris; Teng, Da; Stanitsas, Panagiotis; Bazakos, Mike E; Kaiser, Daniel; Morellas, Vassilios; Mulla, D J; Papanikolopoulos, Nikolaos P.

IROS Hamburg 2015 - Conference Digest: IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc., 2015. p. 6521-6527 7354309 (IEEE International Conference on Intelligent Robots and Systems; Vol. 2015-December).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Zermas, D, Teng, D, Stanitsas, P, Bazakos, ME, Kaiser, D, Morellas, V, Mulla, DJ & Papanikolopoulos, NP 2015, Automation solutions for the evaluation of plant health in corn fields. in IROS Hamburg 2015 - Conference Digest: IEEE/RSJ International Conference on Intelligent Robots and Systems., 7354309, IEEE International Conference on Intelligent Robots and Systems, vol. 2015-December, Institute of Electrical and Electronics Engineers Inc., pp. 6521-6527, IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015, Hamburg, Germany, 9/28/15. https://doi.org/10.1109/IROS.2015.7354309
Zermas D, Teng D, Stanitsas P, Bazakos ME, Kaiser D, Morellas V et al. Automation solutions for the evaluation of plant health in corn fields. In IROS Hamburg 2015 - Conference Digest: IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc. 2015. p. 6521-6527. 7354309. (IEEE International Conference on Intelligent Robots and Systems). https://doi.org/10.1109/IROS.2015.7354309
Zermas, Dimitris ; Teng, Da ; Stanitsas, Panagiotis ; Bazakos, Mike E ; Kaiser, Daniel ; Morellas, Vassilios ; Mulla, D J ; Papanikolopoulos, Nikolaos P. / Automation solutions for the evaluation of plant health in corn fields. IROS Hamburg 2015 - Conference Digest: IEEE/RSJ International Conference on Intelligent Robots and Systems. Institute of Electrical and Electronics Engineers Inc., 2015. pp. 6521-6527 (IEEE International Conference on Intelligent Robots and Systems).
@inproceedings{f75866152c0a4b95bd5e59a8d9b87525,
title = "Automation solutions for the evaluation of plant health in corn fields",
abstract = "The continuously growing need for increasing the production of food and reducing the degradation of water supplies, has led to the development of several precision agriculture systems over the past decade so as to meet the needs of modern societies. The present study describes a methodology for the detection and characterization of Nitrogen (N) deficiencies in corn fields. Current methods of field surveillance are either completed manually or with the assistance of satellite imaging, which offer infrequent and costly information to the farmers about the state of their fields. The proposed methodology promotes the use of small-scale Unmanned Aerial Vehicles (UAVs) and Computer Vision algorithms that operate with information in the visual (RGB) spectrum. Through this implementation, a lower cost solution for identifying N deficiencies is promoted. We provide extensive results on the use of commercial RGB sensors for delivering the essential information to farmers regarding the condition of their field, targeting the reduction of N fertilizers and the increase of the crop performance. Data is first collected by a UAV that hovers over a stressed area and collects high resolution RGB images at a low altitude. A recommendation algorithm identifies potential segments of the images that are candidates exhibiting N deficiency. Based on the feedback from experts in the area a training set is constructed utilizing the initial suggestions of the recommendation algorithm. Supervised learning methods are then used to characterize crop leaves that exhibit signs of N deficiency. The performance of 84.2{\%} strongly supports the potential of this scheme to identify N-deficient leaves even in the case of images where the unhealthy leaves are heavily occluded by other healthy or stressed leaves.",
keywords = "Machine Learning, Precision Agriculture, UAV",
author = "Dimitris Zermas and Da Teng and Panagiotis Stanitsas and Bazakos, {Mike E} and Daniel Kaiser and Vassilios Morellas and Mulla, {D J} and Papanikolopoulos, {Nikolaos P}",
year = "2015",
month = "12",
day = "11",
doi = "10.1109/IROS.2015.7354309",
language = "English (US)",
series = "IEEE International Conference on Intelligent Robots and Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "6521--6527",
booktitle = "IROS Hamburg 2015 - Conference Digest",

}

TY - GEN

T1 - Automation solutions for the evaluation of plant health in corn fields

AU - Zermas, Dimitris

AU - Teng, Da

AU - Stanitsas, Panagiotis

AU - Bazakos, Mike E

AU - Kaiser, Daniel

AU - Morellas, Vassilios

AU - Mulla, D J

AU - Papanikolopoulos, Nikolaos P

PY - 2015/12/11

Y1 - 2015/12/11

N2 - The continuously growing need for increasing the production of food and reducing the degradation of water supplies, has led to the development of several precision agriculture systems over the past decade so as to meet the needs of modern societies. The present study describes a methodology for the detection and characterization of Nitrogen (N) deficiencies in corn fields. Current methods of field surveillance are either completed manually or with the assistance of satellite imaging, which offer infrequent and costly information to the farmers about the state of their fields. The proposed methodology promotes the use of small-scale Unmanned Aerial Vehicles (UAVs) and Computer Vision algorithms that operate with information in the visual (RGB) spectrum. Through this implementation, a lower cost solution for identifying N deficiencies is promoted. We provide extensive results on the use of commercial RGB sensors for delivering the essential information to farmers regarding the condition of their field, targeting the reduction of N fertilizers and the increase of the crop performance. Data is first collected by a UAV that hovers over a stressed area and collects high resolution RGB images at a low altitude. A recommendation algorithm identifies potential segments of the images that are candidates exhibiting N deficiency. Based on the feedback from experts in the area a training set is constructed utilizing the initial suggestions of the recommendation algorithm. Supervised learning methods are then used to characterize crop leaves that exhibit signs of N deficiency. The performance of 84.2% strongly supports the potential of this scheme to identify N-deficient leaves even in the case of images where the unhealthy leaves are heavily occluded by other healthy or stressed leaves.

AB - The continuously growing need for increasing the production of food and reducing the degradation of water supplies, has led to the development of several precision agriculture systems over the past decade so as to meet the needs of modern societies. The present study describes a methodology for the detection and characterization of Nitrogen (N) deficiencies in corn fields. Current methods of field surveillance are either completed manually or with the assistance of satellite imaging, which offer infrequent and costly information to the farmers about the state of their fields. The proposed methodology promotes the use of small-scale Unmanned Aerial Vehicles (UAVs) and Computer Vision algorithms that operate with information in the visual (RGB) spectrum. Through this implementation, a lower cost solution for identifying N deficiencies is promoted. We provide extensive results on the use of commercial RGB sensors for delivering the essential information to farmers regarding the condition of their field, targeting the reduction of N fertilizers and the increase of the crop performance. Data is first collected by a UAV that hovers over a stressed area and collects high resolution RGB images at a low altitude. A recommendation algorithm identifies potential segments of the images that are candidates exhibiting N deficiency. Based on the feedback from experts in the area a training set is constructed utilizing the initial suggestions of the recommendation algorithm. Supervised learning methods are then used to characterize crop leaves that exhibit signs of N deficiency. The performance of 84.2% strongly supports the potential of this scheme to identify N-deficient leaves even in the case of images where the unhealthy leaves are heavily occluded by other healthy or stressed leaves.

KW - Machine Learning

KW - Precision Agriculture

KW - UAV

UR - http://www.scopus.com/inward/record.url?scp=84958225371&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958225371&partnerID=8YFLogxK

U2 - 10.1109/IROS.2015.7354309

DO - 10.1109/IROS.2015.7354309

M3 - Conference contribution

T3 - IEEE International Conference on Intelligent Robots and Systems

SP - 6521

EP - 6527

BT - IROS Hamburg 2015 - Conference Digest

PB - Institute of Electrical and Electronics Engineers Inc.

ER -