Authors:
C. Devia
1
;
J. Rojas
2
;
E. Petro
3
;
C. Martinez
1
;
I. Mondragon
1
;
D. Patino
1
;
C. Rebolledo
4
and
J. Colorado
1
Affiliations:
1
School of Engineering, Pontificia Universidad Javeriana, Bogota and Colombia
;
2
School of Engineering, Pontificia Universidad Javeriana, Bogota, Colombia, CIRAD, AGAP-Pam, Montpellier and France
;
3
The International Center for Tropical Agriculture -CIAT, Agrodiversity, Palmira and Colombia
;
4
The International Center for Tropical Agriculture -CIAT, Agrodiversity, Palmira, Colombia, CIRAD, AGAP-Pam, Montpellier and France
Keyword(s):
UAV, Precision Agriculture, Image Processing, Vegetative Indices, Multispectral Imagery, Machine Learning.
Related
Ontology
Subjects/Areas/Topics:
Image Processing
;
Informatics in Control, Automation and Robotics
;
Modeling, Simulation and Architectures
;
Robotics and Automation
Abstract:
This paper presents the integration of an UAV for the autonomous monitoring of rice crops. The system integrates image processing and machine learning algorithms to analyze multispectral aerial imagery. Our approach calculates 8 vegetation indices from the images at each stage of rice growth: vegetative, reproductive and ripening. Multivariable regressions and artificial neural networks have been implemented to model the relationship of these vegetation indices against two crop variables: biomass accumulation and leaf nitrogen concentration. Comprehensive experimental tests have been conducted to validate the setup. The results indicate that our system is capable of estimating biomass and nitrogen with an average correlation of 80% and 78% respectively.