A machine vision system for quantification of citrus fruit dropped on the ground under the canopy

Daeun Choi, Won Suk Lee, Reza Ehsani, Fritz M. Roka

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

The overall goal of this study was to develop a machine vision system to quantify dropped citrus fruits on the ground. Specific objectives were: (1) to build a machine vision system suitable for citrus grove field conditions, (2) to develop an image enhancement algorithm for varying illumination conditions, and (3) to develop an image processing algorithm to estimate citrus fruit drop count and mass. The image processing algorithm consisted of (1) illumination enhancement using a retinex algorithm, (2) classification, (3) segmentation using a watershed algorithm with h-minima transform, and (4) ellipse fitting for mass estimation. Performances of the algorithms were evaluated in terms of correct identification and false positive errors. The average correct identification rate was 88.1%, 83.6%, and 82.9% for logistic regression, k-nearest neighbor (kNN), and Bayesian classifiers, respectively. False positive errors were 13.7%, 40.9%, and 17.9% for logistic regression, kNN, Bayesian classifiers, respectively. The results demonstrate the system's ability to quantify dropped fruits with specific geo-referenced location information. Spatially varied fruit drop maps plotted from the results can assist growers in finding problematic areas in their citrus groves more efficiently while reducing inspection and treatment costs. Such maps can also facilitate treatment of citrus Huanglongbing (HLB) disease in combination with HLB intensity data, psyllid counts, fertilization programs, and other block-specific management practices.

Original languageEnglish (US)
Pages (from-to)933-946
Number of pages14
JournalTransactions of the ASABE
Volume58
Issue number4
DOIs
StatePublished - Jan 1 2015

Fingerprint

Citrus fruits
Citrus
computer vision
citrus fruits
Computer vision
fruit
canopy
greening disease
fruit drop
Fruits
Lighting
image processing
lighting
Logistics
Fruit
logistics
Image processing
orchards
Classifiers
Logistic Models

All Science Journal Classification (ASJC) codes

  • Forestry
  • Food Science
  • Biomedical Engineering
  • Agronomy and Crop Science
  • Soil Science

Cite this

Choi, Daeun ; Lee, Won Suk ; Ehsani, Reza ; Roka, Fritz M. / A machine vision system for quantification of citrus fruit dropped on the ground under the canopy. In: Transactions of the ASABE. 2015 ; Vol. 58, No. 4. pp. 933-946.
@article{b515570053554fd188dc399aa9cbf095,
title = "A machine vision system for quantification of citrus fruit dropped on the ground under the canopy",
abstract = "The overall goal of this study was to develop a machine vision system to quantify dropped citrus fruits on the ground. Specific objectives were: (1) to build a machine vision system suitable for citrus grove field conditions, (2) to develop an image enhancement algorithm for varying illumination conditions, and (3) to develop an image processing algorithm to estimate citrus fruit drop count and mass. The image processing algorithm consisted of (1) illumination enhancement using a retinex algorithm, (2) classification, (3) segmentation using a watershed algorithm with h-minima transform, and (4) ellipse fitting for mass estimation. Performances of the algorithms were evaluated in terms of correct identification and false positive errors. The average correct identification rate was 88.1{\%}, 83.6{\%}, and 82.9{\%} for logistic regression, k-nearest neighbor (kNN), and Bayesian classifiers, respectively. False positive errors were 13.7{\%}, 40.9{\%}, and 17.9{\%} for logistic regression, kNN, Bayesian classifiers, respectively. The results demonstrate the system's ability to quantify dropped fruits with specific geo-referenced location information. Spatially varied fruit drop maps plotted from the results can assist growers in finding problematic areas in their citrus groves more efficiently while reducing inspection and treatment costs. Such maps can also facilitate treatment of citrus Huanglongbing (HLB) disease in combination with HLB intensity data, psyllid counts, fertilization programs, and other block-specific management practices.",
author = "Daeun Choi and Lee, {Won Suk} and Reza Ehsani and Roka, {Fritz M.}",
year = "2015",
month = "1",
day = "1",
doi = "10.13031/trans.58.10688",
language = "English (US)",
volume = "58",
pages = "933--946",
journal = "Transactions of the ASABE",
issn = "2151-0032",
publisher = "American Society of Agricultural and Biological Engineers",
number = "4",

}

A machine vision system for quantification of citrus fruit dropped on the ground under the canopy. / Choi, Daeun; Lee, Won Suk; Ehsani, Reza; Roka, Fritz M.

In: Transactions of the ASABE, Vol. 58, No. 4, 01.01.2015, p. 933-946.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A machine vision system for quantification of citrus fruit dropped on the ground under the canopy

AU - Choi, Daeun

AU - Lee, Won Suk

AU - Ehsani, Reza

AU - Roka, Fritz M.

PY - 2015/1/1

Y1 - 2015/1/1

N2 - The overall goal of this study was to develop a machine vision system to quantify dropped citrus fruits on the ground. Specific objectives were: (1) to build a machine vision system suitable for citrus grove field conditions, (2) to develop an image enhancement algorithm for varying illumination conditions, and (3) to develop an image processing algorithm to estimate citrus fruit drop count and mass. The image processing algorithm consisted of (1) illumination enhancement using a retinex algorithm, (2) classification, (3) segmentation using a watershed algorithm with h-minima transform, and (4) ellipse fitting for mass estimation. Performances of the algorithms were evaluated in terms of correct identification and false positive errors. The average correct identification rate was 88.1%, 83.6%, and 82.9% for logistic regression, k-nearest neighbor (kNN), and Bayesian classifiers, respectively. False positive errors were 13.7%, 40.9%, and 17.9% for logistic regression, kNN, Bayesian classifiers, respectively. The results demonstrate the system's ability to quantify dropped fruits with specific geo-referenced location information. Spatially varied fruit drop maps plotted from the results can assist growers in finding problematic areas in their citrus groves more efficiently while reducing inspection and treatment costs. Such maps can also facilitate treatment of citrus Huanglongbing (HLB) disease in combination with HLB intensity data, psyllid counts, fertilization programs, and other block-specific management practices.

AB - The overall goal of this study was to develop a machine vision system to quantify dropped citrus fruits on the ground. Specific objectives were: (1) to build a machine vision system suitable for citrus grove field conditions, (2) to develop an image enhancement algorithm for varying illumination conditions, and (3) to develop an image processing algorithm to estimate citrus fruit drop count and mass. The image processing algorithm consisted of (1) illumination enhancement using a retinex algorithm, (2) classification, (3) segmentation using a watershed algorithm with h-minima transform, and (4) ellipse fitting for mass estimation. Performances of the algorithms were evaluated in terms of correct identification and false positive errors. The average correct identification rate was 88.1%, 83.6%, and 82.9% for logistic regression, k-nearest neighbor (kNN), and Bayesian classifiers, respectively. False positive errors were 13.7%, 40.9%, and 17.9% for logistic regression, kNN, Bayesian classifiers, respectively. The results demonstrate the system's ability to quantify dropped fruits with specific geo-referenced location information. Spatially varied fruit drop maps plotted from the results can assist growers in finding problematic areas in their citrus groves more efficiently while reducing inspection and treatment costs. Such maps can also facilitate treatment of citrus Huanglongbing (HLB) disease in combination with HLB intensity data, psyllid counts, fertilization programs, and other block-specific management practices.

UR - http://www.scopus.com/inward/record.url?scp=84941563482&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84941563482&partnerID=8YFLogxK

U2 - 10.13031/trans.58.10688

DO - 10.13031/trans.58.10688

M3 - Article

AN - SCOPUS:84941563482

VL - 58

SP - 933

EP - 946

JO - Transactions of the ASABE

JF - Transactions of the ASABE

SN - 2151-0032

IS - 4

ER -