IDEALS Home University of Illinois at Urbana-Champaign logo The Alma Mater The Main Quad

Characterizing corn growth and development using computer vision

Show full item record

Bookmark or cite this item: http://hdl.handle.net/2142/20757

Files in this item

File Description Format
PDF 9114433.pdf (5MB) Restricted to U of Illinois (no description provided) PDF
Title: Characterizing corn growth and development using computer vision
Author(s): Tarbell, Kenneth Alvin
Doctoral Committee Chair(s): Reid, John F.
Department / Program: Agricultural and Biological Engineering
Discipline: Agricultural Engineering
Degree Granting Institution: University of Illinois at Urbana-Champaign
Degree: Ph.D.
Genre: Dissertation
Subject(s): Agriculture, General Engineering, Agricultural Artificial Intelligence Biology, Plant Physiology
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.
Issue Date: 1990
Type: Text
Language: English
URI: http://hdl.handle.net/2142/20757
Rights Information: Copyright 1990 Tarbell, Kenneth Alvin
Date Available in IDEALS: 2011-05-07
Identifier in Online Catalog: AAI9114433
OCLC Identifier: (UMI)AAI9114433
 

This item appears in the following Collection(s)

Show full item record

Item Statistics

  • Total Downloads: 0
  • Downloads this Month: 0
  • Downloads Today: 0

Browse

My Account

Information

Access Key