Characterizing corn growth and development using computer vision
Tarbell, Kenneth Alvin
This item is only available for download by members of the University of Illinois community. Students, faculty, and staff at the U of I may log in with your NetID and password to view the item. If you are trying to access an Illinois-restricted dissertation or thesis, you can request a copy through your library's Inter-Library Loan office or purchase a copy directly from ProQuest.
Permalink
https://hdl.handle.net/2142/20757
Description
Title
Characterizing corn growth and development using computer vision
Author(s)
Tarbell, Kenneth Alvin
Issue Date
1990
Doctoral Committee Chair(s)
Reid, John F.
Department of Study
Agricultural and Biological Engineering
Discipline
Agricultural Engineering
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Agriculture, General
Engineering, Agricultural
Artificial Intelligence
Biology, Plant Physiology
Language
eng
Abstract
Efficient utilization of agricultural resources requires a better understanding of crop growth and development. Current modeling efforts aimed at predicting the response of plants to environmental conditions lack the ability to relate results to basic characteristics observed in the field. The ability to reliably evaluate both photometric and morphometric parameters for individual plants would not only improve existing models, but also create a database from which new models may be generated.
A vision-based data collection system was developed to study the growth and development of corn plants. Slide photographs were taken of field specimens at given intervals throughout the 1989 growing season. These images were scanned into the system and processed using software developed for this project. From 64 to 320 attributes were obtained for each plant and later combined with associated meteorological information to form a developmental database. A relationship between leaf area and length was derived and yielded a correlation coefficient (r$\sp2$) of 0.98. Also, a high correlation between measured and actual leaf length allowed the use of lengths measured from plant from views in leaf area estimations with an r$\sp2$ of 0.95. Given the average color for a leaf, it could be classified as either senesced or living using the green or red chromaticity values. Both classifiers had prediction confidences of about 95%.
Using a prototype model building software package (AIMS) which combined inductive learning and optimization techniques, mathematical models were generated for plant leaf area, individual leaf areas, leaf physiology, leaf node heights, and overall plant dimensions as a function of time and temperature. All models performed well, with r$\sp2$ values ranging from 0.63 to 0.98 for leaf area models and 0.90 to 0.99 for all others. These models were combined to form a single growth and development model describing the canopy dynamics of the sampled crop.
Use this login method if you
don't
have an
@illinois.edu
email address.
(Oops, I do have one)
IDEALS migrated to a new platform on June 23, 2022. If you created
your account prior to this date, you will have to reset your password
using the forgot-password link below.
