Development of a mushroom harvesting assistance system using computer vision

Research output: Contribution to conferencePaper

Abstract

Conventional mushroom harvesting relies on manual labors, which is one of the major reasons for increased production costs. Different maturation speed among individual mushrooms promotes farm workers' efforts in selective harvesting. To assist in robotic harvesting of mushrooms, a computer vision system was developed to detect an individual mushroom from mushroom clusters and evaluate maturity of the mushroom. Specific objectives of this study were to (1) solve the overlapping problem and differentiate each mushroom from a mushroom cluster, and (2) develop a machine vision algorithm to identify maturity using the size and shape of mushrooms. For mushroom identification, faster R-CNN model was developed to distinguish mushrooms from substrate. A 3D pointcloud of mushroom was acquired by a depth camera and used to segment an individual crop among the overlapped mushrooms in clusters. After the segmentation, the size of mushroom caps was calculated using the pointcloud and the shape of mushroom caps was quantified using normal vectors. The accuracy of maturity recognition reached 70.93 %. The results of this study can be extended to a commercial scale and enhance mushroom harvesting efficiency by reducing the overall cost of mushroom production.

Original languageEnglish (US)
DOIs
StatePublished - Jan 1 2019
Event2019 ASABE Annual International Meeting - Boston, United States
Duration: Jul 7 2019Jul 10 2019

Conference

Conference2019 ASABE Annual International Meeting
CountryUnited States
CityBoston
Period7/7/197/10/19

Fingerprint

computer vision
mushrooms
Computer vision
Farms
Crops
Costs
Identification (control systems)
Robotics
Cameras
Personnel
Substrates
mushroom growing
farm labor
production costs
cameras

All Science Journal Classification (ASJC) codes

  • Agronomy and Crop Science
  • Bioengineering

Cite this

Lee, Cheng Hao ; Choi, Daeun ; Pecchia, John ; He, Long ; Heinemann, Paul. / Development of a mushroom harvesting assistance system using computer vision. Paper presented at 2019 ASABE Annual International Meeting, Boston, United States.
@conference{21e818ea7aaa4e7e8bf1425fe3d9f330,
title = "Development of a mushroom harvesting assistance system using computer vision",
abstract = "Conventional mushroom harvesting relies on manual labors, which is one of the major reasons for increased production costs. Different maturation speed among individual mushrooms promotes farm workers' efforts in selective harvesting. To assist in robotic harvesting of mushrooms, a computer vision system was developed to detect an individual mushroom from mushroom clusters and evaluate maturity of the mushroom. Specific objectives of this study were to (1) solve the overlapping problem and differentiate each mushroom from a mushroom cluster, and (2) develop a machine vision algorithm to identify maturity using the size and shape of mushrooms. For mushroom identification, faster R-CNN model was developed to distinguish mushrooms from substrate. A 3D pointcloud of mushroom was acquired by a depth camera and used to segment an individual crop among the overlapped mushrooms in clusters. After the segmentation, the size of mushroom caps was calculated using the pointcloud and the shape of mushroom caps was quantified using normal vectors. The accuracy of maturity recognition reached 70.93 {\%}. The results of this study can be extended to a commercial scale and enhance mushroom harvesting efficiency by reducing the overall cost of mushroom production.",
author = "Lee, {Cheng Hao} and Daeun Choi and John Pecchia and Long He and Paul Heinemann",
year = "2019",
month = "1",
day = "1",
doi = "10.13031/aim.201900505",
language = "English (US)",
note = "2019 ASABE Annual International Meeting ; Conference date: 07-07-2019 Through 10-07-2019",

}

Lee, CH, Choi, D, Pecchia, J, He, L & Heinemann, P 2019, 'Development of a mushroom harvesting assistance system using computer vision', Paper presented at 2019 ASABE Annual International Meeting, Boston, United States, 7/7/19 - 7/10/19. https://doi.org/10.13031/aim.201900505

Development of a mushroom harvesting assistance system using computer vision. / Lee, Cheng Hao; Choi, Daeun; Pecchia, John; He, Long; Heinemann, Paul.

2019. Paper presented at 2019 ASABE Annual International Meeting, Boston, United States.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Development of a mushroom harvesting assistance system using computer vision

AU - Lee, Cheng Hao

AU - Choi, Daeun

AU - Pecchia, John

AU - He, Long

AU - Heinemann, Paul

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Conventional mushroom harvesting relies on manual labors, which is one of the major reasons for increased production costs. Different maturation speed among individual mushrooms promotes farm workers' efforts in selective harvesting. To assist in robotic harvesting of mushrooms, a computer vision system was developed to detect an individual mushroom from mushroom clusters and evaluate maturity of the mushroom. Specific objectives of this study were to (1) solve the overlapping problem and differentiate each mushroom from a mushroom cluster, and (2) develop a machine vision algorithm to identify maturity using the size and shape of mushrooms. For mushroom identification, faster R-CNN model was developed to distinguish mushrooms from substrate. A 3D pointcloud of mushroom was acquired by a depth camera and used to segment an individual crop among the overlapped mushrooms in clusters. After the segmentation, the size of mushroom caps was calculated using the pointcloud and the shape of mushroom caps was quantified using normal vectors. The accuracy of maturity recognition reached 70.93 %. The results of this study can be extended to a commercial scale and enhance mushroom harvesting efficiency by reducing the overall cost of mushroom production.

AB - Conventional mushroom harvesting relies on manual labors, which is one of the major reasons for increased production costs. Different maturation speed among individual mushrooms promotes farm workers' efforts in selective harvesting. To assist in robotic harvesting of mushrooms, a computer vision system was developed to detect an individual mushroom from mushroom clusters and evaluate maturity of the mushroom. Specific objectives of this study were to (1) solve the overlapping problem and differentiate each mushroom from a mushroom cluster, and (2) develop a machine vision algorithm to identify maturity using the size and shape of mushrooms. For mushroom identification, faster R-CNN model was developed to distinguish mushrooms from substrate. A 3D pointcloud of mushroom was acquired by a depth camera and used to segment an individual crop among the overlapped mushrooms in clusters. After the segmentation, the size of mushroom caps was calculated using the pointcloud and the shape of mushroom caps was quantified using normal vectors. The accuracy of maturity recognition reached 70.93 %. The results of this study can be extended to a commercial scale and enhance mushroom harvesting efficiency by reducing the overall cost of mushroom production.

UR - http://www.scopus.com/inward/record.url?scp=85072922775&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85072922775&partnerID=8YFLogxK

U2 - 10.13031/aim.201900505

DO - 10.13031/aim.201900505

M3 - Paper

AN - SCOPUS:85072922775

ER -