A Preliminary Method for Tracking In-Season Grapevine Cluster Closure Using Image Segmentation and Image Thresholding
Mapping and monitoring cluster morphology provides insights for disease risk assessment, quality control in wine production, and understanding environmental influences on cluster shape. During the progression of grapevine morphology, cluster closure (CC) (also called bunch closure) is the stage when...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi-Wiley
2023-01-01
|
Series: | Australian Journal of Grape and Wine Research |
Online Access: | http://dx.doi.org/10.1155/2023/3923839 |
_version_ | 1797663724118474752 |
---|---|
author | Manushi Trivedi Yuwei Zhou Jonathan Hyun Moon James Meyers Yu Jiang Guoyu Lu Justine Vanden Heuvel |
author_facet | Manushi Trivedi Yuwei Zhou Jonathan Hyun Moon James Meyers Yu Jiang Guoyu Lu Justine Vanden Heuvel |
author_sort | Manushi Trivedi |
collection | DOAJ |
description | Mapping and monitoring cluster morphology provides insights for disease risk assessment, quality control in wine production, and understanding environmental influences on cluster shape. During the progression of grapevine morphology, cluster closure (CC) (also called bunch closure) is the stage when berries touch one another. This study used mobile phone images to develop a direct quantification method for tracking CC in three grapevine cultivars (Riesling, Pinot gris, and Cabernet Franc). A total of 809 cluster images from fruit set to veraison were analyzed using two image segmentation methods: (i) a Pyramid Scene Parsing Network (PSPNet) to extract cluster boundaries and (ii) Otsu’s image thresholding method to calculate % CC based on gaps between the berries. PSPNet produced high accuracy (mean accuracy = 0.98, mean intersection over union (mIoU) = 0.95) with mIoU > 0.90 for both cluster and noncluster classes. Otsu’s thresholding method resulted in <2% falsely classified gap and berry pixels affecting quantified % CC. The progression of CC was described using basic statistics (mean and standard deviation) and using a curve fit. The CC curve showed an asymptotic trend, with a higher rate of progression observed in the first three weeks, followed by a gradual approach towards an asymptote. We propose that the X value (in this example, number of weeks past berry set) at which the CC progression curve reaches the asymptote be considered as the official phenological stage of CC. The developed method provides a continuous scale of CC throughout the season, potentially serving as a valuable open-source research tool for studying grapevine cluster phenology and factors affecting CC. |
first_indexed | 2024-03-11T19:18:54Z |
format | Article |
id | doaj.art-2af08b1233fa424da8dc9ee18836a520 |
institution | Directory Open Access Journal |
issn | 1755-0238 |
language | English |
last_indexed | 2024-03-11T19:18:54Z |
publishDate | 2023-01-01 |
publisher | Hindawi-Wiley |
record_format | Article |
series | Australian Journal of Grape and Wine Research |
spelling | doaj.art-2af08b1233fa424da8dc9ee18836a5202023-10-08T00:00:03ZengHindawi-WileyAustralian Journal of Grape and Wine Research1755-02382023-01-01202310.1155/2023/3923839A Preliminary Method for Tracking In-Season Grapevine Cluster Closure Using Image Segmentation and Image ThresholdingManushi Trivedi0Yuwei Zhou1Jonathan Hyun Moon2James Meyers3Yu Jiang4Guoyu Lu5Justine Vanden Heuvel6Horticulture SectionElectrical and Computer EngineeringDepartment of Computer ScienceFormerlyHorticulture SectionElectrical and Computer EngineeringHorticulture SectionMapping and monitoring cluster morphology provides insights for disease risk assessment, quality control in wine production, and understanding environmental influences on cluster shape. During the progression of grapevine morphology, cluster closure (CC) (also called bunch closure) is the stage when berries touch one another. This study used mobile phone images to develop a direct quantification method for tracking CC in three grapevine cultivars (Riesling, Pinot gris, and Cabernet Franc). A total of 809 cluster images from fruit set to veraison were analyzed using two image segmentation methods: (i) a Pyramid Scene Parsing Network (PSPNet) to extract cluster boundaries and (ii) Otsu’s image thresholding method to calculate % CC based on gaps between the berries. PSPNet produced high accuracy (mean accuracy = 0.98, mean intersection over union (mIoU) = 0.95) with mIoU > 0.90 for both cluster and noncluster classes. Otsu’s thresholding method resulted in <2% falsely classified gap and berry pixels affecting quantified % CC. The progression of CC was described using basic statistics (mean and standard deviation) and using a curve fit. The CC curve showed an asymptotic trend, with a higher rate of progression observed in the first three weeks, followed by a gradual approach towards an asymptote. We propose that the X value (in this example, number of weeks past berry set) at which the CC progression curve reaches the asymptote be considered as the official phenological stage of CC. The developed method provides a continuous scale of CC throughout the season, potentially serving as a valuable open-source research tool for studying grapevine cluster phenology and factors affecting CC.http://dx.doi.org/10.1155/2023/3923839 |
spellingShingle | Manushi Trivedi Yuwei Zhou Jonathan Hyun Moon James Meyers Yu Jiang Guoyu Lu Justine Vanden Heuvel A Preliminary Method for Tracking In-Season Grapevine Cluster Closure Using Image Segmentation and Image Thresholding Australian Journal of Grape and Wine Research |
title | A Preliminary Method for Tracking In-Season Grapevine Cluster Closure Using Image Segmentation and Image Thresholding |
title_full | A Preliminary Method for Tracking In-Season Grapevine Cluster Closure Using Image Segmentation and Image Thresholding |
title_fullStr | A Preliminary Method for Tracking In-Season Grapevine Cluster Closure Using Image Segmentation and Image Thresholding |
title_full_unstemmed | A Preliminary Method for Tracking In-Season Grapevine Cluster Closure Using Image Segmentation and Image Thresholding |
title_short | A Preliminary Method for Tracking In-Season Grapevine Cluster Closure Using Image Segmentation and Image Thresholding |
title_sort | preliminary method for tracking in season grapevine cluster closure using image segmentation and image thresholding |
url | http://dx.doi.org/10.1155/2023/3923839 |
work_keys_str_mv | AT manushitrivedi apreliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT yuweizhou apreliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT jonathanhyunmoon apreliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT jamesmeyers apreliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT yujiang apreliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT guoyulu apreliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT justinevandenheuvel apreliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT manushitrivedi preliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT yuweizhou preliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT jonathanhyunmoon preliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT jamesmeyers preliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT yujiang preliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT guoyulu preliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding AT justinevandenheuvel preliminarymethodfortrackinginseasongrapevineclusterclosureusingimagesegmentationandimagethresholding |