Estimation of prematurely dropped citrus count on the ground before harvesting

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

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

Abstract

Excessive amount of premature fruit drops can reach up to 25% of the entire production of the year. However, it is difficult to tell exact reasons of the premature drop due to the lack of a scientific diagnosis system. In this research, a machine vision system was developed to find where excessive fruit drop occurs in a citrus grove and to decide fruit dropping period by estimating that citrus was recently dropped or decayed due to being dropped. A hardware system was developed to facilitate automatic image acquisition in a citrus grove and reduce significant change in illumination in outdoor environment. A machine vision algorithm included thresholding and K-mean clustering to remove background and classification using a Random forest classifier. The result of this research shows that the correct identification was high (91.9%) for recently dropped citrus and relatively low (61.9%) for decayed fruit. Also, in-field spatial variability of the estimated amount of the dropped fruit by the algorithm was visualized on a map. This information can help growers to find potential causes of the fruit drop by correlating with other factors such as diseases, nutrition and soil types.

Original languageEnglish (US)
Title of host publicationAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014
PublisherAmerican Society of Agricultural and Biological Engineers
Pages467-474
Number of pages8
Volume1
ISBN (Electronic)9781632668455
StatePublished - Jan 1 2014
EventAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014 - Montreal, Canada
Duration: Jul 13 2014Jul 16 2014

Other

OtherAmerican Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014
CountryCanada
CityMontreal
Period7/13/147/16/14

Fingerprint

fruit drop
Citrus
Fruits
Fruit
computer vision
fruits
orchards
Computer vision
lighting
soil types
growers
nutrition
taxonomy
Image acquisition
Nutrition
Lighting
Research
Cluster Analysis
Classifiers
Soil

All Science Journal Classification (ASJC) codes

  • Agricultural and Biological Sciences(all)
  • Mechanical Engineering

Cite this

Choi, D., Lee, W. S., Ehsani, R., & Roka, F. (2014). Estimation of prematurely dropped citrus count on the ground before harvesting. In American Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014 (Vol. 1, pp. 467-474). American Society of Agricultural and Biological Engineers.
Choi, Daeun ; Lee, Won Suk ; Ehsani, Reza ; Roka, Fritz. / Estimation of prematurely dropped citrus count on the ground before harvesting. American Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014. Vol. 1 American Society of Agricultural and Biological Engineers, 2014. pp. 467-474
@inproceedings{762acb272d554a49994f11aa3717d1e8,
title = "Estimation of prematurely dropped citrus count on the ground before harvesting",
abstract = "Excessive amount of premature fruit drops can reach up to 25{\%} of the entire production of the year. However, it is difficult to tell exact reasons of the premature drop due to the lack of a scientific diagnosis system. In this research, a machine vision system was developed to find where excessive fruit drop occurs in a citrus grove and to decide fruit dropping period by estimating that citrus was recently dropped or decayed due to being dropped. A hardware system was developed to facilitate automatic image acquisition in a citrus grove and reduce significant change in illumination in outdoor environment. A machine vision algorithm included thresholding and K-mean clustering to remove background and classification using a Random forest classifier. The result of this research shows that the correct identification was high (91.9{\%}) for recently dropped citrus and relatively low (61.9{\%}) for decayed fruit. Also, in-field spatial variability of the estimated amount of the dropped fruit by the algorithm was visualized on a map. This information can help growers to find potential causes of the fruit drop by correlating with other factors such as diseases, nutrition and soil types.",
author = "Daeun Choi and Lee, {Won Suk} and Reza Ehsani and Fritz Roka",
year = "2014",
month = "1",
day = "1",
language = "English (US)",
volume = "1",
pages = "467--474",
booktitle = "American Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014",
publisher = "American Society of Agricultural and Biological Engineers",
address = "United States",

}

Choi, D, Lee, WS, Ehsani, R & Roka, F 2014, Estimation of prematurely dropped citrus count on the ground before harvesting. in American Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014. vol. 1, American Society of Agricultural and Biological Engineers, pp. 467-474, American Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014, Montreal, Canada, 7/13/14.

Estimation of prematurely dropped citrus count on the ground before harvesting. / Choi, Daeun; Lee, Won Suk; Ehsani, Reza; Roka, Fritz.

American Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014. Vol. 1 American Society of Agricultural and Biological Engineers, 2014. p. 467-474.

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

TY - GEN

T1 - Estimation of prematurely dropped citrus count on the ground before harvesting

AU - Choi, Daeun

AU - Lee, Won Suk

AU - Ehsani, Reza

AU - Roka, Fritz

PY - 2014/1/1

Y1 - 2014/1/1

N2 - Excessive amount of premature fruit drops can reach up to 25% of the entire production of the year. However, it is difficult to tell exact reasons of the premature drop due to the lack of a scientific diagnosis system. In this research, a machine vision system was developed to find where excessive fruit drop occurs in a citrus grove and to decide fruit dropping period by estimating that citrus was recently dropped or decayed due to being dropped. A hardware system was developed to facilitate automatic image acquisition in a citrus grove and reduce significant change in illumination in outdoor environment. A machine vision algorithm included thresholding and K-mean clustering to remove background and classification using a Random forest classifier. The result of this research shows that the correct identification was high (91.9%) for recently dropped citrus and relatively low (61.9%) for decayed fruit. Also, in-field spatial variability of the estimated amount of the dropped fruit by the algorithm was visualized on a map. This information can help growers to find potential causes of the fruit drop by correlating with other factors such as diseases, nutrition and soil types.

AB - Excessive amount of premature fruit drops can reach up to 25% of the entire production of the year. However, it is difficult to tell exact reasons of the premature drop due to the lack of a scientific diagnosis system. In this research, a machine vision system was developed to find where excessive fruit drop occurs in a citrus grove and to decide fruit dropping period by estimating that citrus was recently dropped or decayed due to being dropped. A hardware system was developed to facilitate automatic image acquisition in a citrus grove and reduce significant change in illumination in outdoor environment. A machine vision algorithm included thresholding and K-mean clustering to remove background and classification using a Random forest classifier. The result of this research shows that the correct identification was high (91.9%) for recently dropped citrus and relatively low (61.9%) for decayed fruit. Also, in-field spatial variability of the estimated amount of the dropped fruit by the algorithm was visualized on a map. This information can help growers to find potential causes of the fruit drop by correlating with other factors such as diseases, nutrition and soil types.

UR - http://www.scopus.com/inward/record.url?scp=84911890900&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84911890900&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84911890900

VL - 1

SP - 467

EP - 474

BT - American Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014

PB - American Society of Agricultural and Biological Engineers

ER -

Choi D, Lee WS, Ehsani R, Roka F. Estimation of prematurely dropped citrus count on the ground before harvesting. In American Society of Agricultural and Biological Engineers Annual International Meeting 2014, ASABE 2014. Vol. 1. American Society of Agricultural and Biological Engineers. 2014. p. 467-474