Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method

Accurately extracting the grape cluster at the front of overlapping grape clusters is the primary problem of the grape-harvesting robot. To solve the difficult problem of identifying and segmenting the overlapping grape clusters in the cultivation environment of a trellis, a simple method based on t...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Yun Peng, Shengyi Zhao, Jizhan Liu
Formato: article
Lenguaje:EN
Publicado: MDPI AG 2021
Materias:
Acceso en línea:https://doaj.org/article/7e7381277b52491ea55063a92b3f76a9
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:7e7381277b52491ea55063a92b3f76a9
record_format dspace
spelling oai:doaj.org-article:7e7381277b52491ea55063a92b3f76a92021-11-25T17:24:52ZSegmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method10.3390/electronics102228132079-9292https://doaj.org/article/7e7381277b52491ea55063a92b3f76a92021-11-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/22/2813https://doaj.org/toc/2079-9292Accurately extracting the grape cluster at the front of overlapping grape clusters is the primary problem of the grape-harvesting robot. To solve the difficult problem of identifying and segmenting the overlapping grape clusters in the cultivation environment of a trellis, a simple method based on the deep learning network and the idea of region growing is proposed. Firstly, the region of grape in an RGB image was obtained by the finely trained DeepLabV3+ model. The idea of transfer learning was adopted when training the network with a limited number of training sets. Then, the corresponding region of the grape in the depth image captured by RealSense D435 was processed by the proposed depth region growing algorithm (DRG) to extract the front cluster. The depth region growing method uses the depth value instead of gray value to achieve clustering. Finally, it fils the holes in the clustered region of interest, extracts the contours, and maps the obtained contours to the RGB image. The images captured by RealSense D435 in a natural trellis environment were adopted to evaluate the performance of the proposed method. The experimental results showed that the recall and precision of the proposed method were 89.2% and 87.5%, respectively. The demonstrated performance indicated that the proposed method could satisfy the requirements of practical application for robotic grape harvesting.Yun PengShengyi ZhaoJizhan LiuMDPI AGarticlegrape segmentationDeepLabV3+deep learningregion growingElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2813, p 2813 (2021)
institution DOAJ
collection DOAJ
language EN
topic grape segmentation
DeepLabV3+
deep learning
region growing
Electronics
TK7800-8360
spellingShingle grape segmentation
DeepLabV3+
deep learning
region growing
Electronics
TK7800-8360
Yun Peng
Shengyi Zhao
Jizhan Liu
Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method
description Accurately extracting the grape cluster at the front of overlapping grape clusters is the primary problem of the grape-harvesting robot. To solve the difficult problem of identifying and segmenting the overlapping grape clusters in the cultivation environment of a trellis, a simple method based on the deep learning network and the idea of region growing is proposed. Firstly, the region of grape in an RGB image was obtained by the finely trained DeepLabV3+ model. The idea of transfer learning was adopted when training the network with a limited number of training sets. Then, the corresponding region of the grape in the depth image captured by RealSense D435 was processed by the proposed depth region growing algorithm (DRG) to extract the front cluster. The depth region growing method uses the depth value instead of gray value to achieve clustering. Finally, it fils the holes in the clustered region of interest, extracts the contours, and maps the obtained contours to the RGB image. The images captured by RealSense D435 in a natural trellis environment were adopted to evaluate the performance of the proposed method. The experimental results showed that the recall and precision of the proposed method were 89.2% and 87.5%, respectively. The demonstrated performance indicated that the proposed method could satisfy the requirements of practical application for robotic grape harvesting.
format article
author Yun Peng
Shengyi Zhao
Jizhan Liu
author_facet Yun Peng
Shengyi Zhao
Jizhan Liu
author_sort Yun Peng
title Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method
title_short Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method
title_full Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method
title_fullStr Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method
title_full_unstemmed Segmentation of Overlapping Grape Clusters Based on the Depth Region Growing Method
title_sort segmentation of overlapping grape clusters based on the depth region growing method
publisher MDPI AG
publishDate 2021
url https://doaj.org/article/7e7381277b52491ea55063a92b3f76a9
work_keys_str_mv AT yunpeng segmentationofoverlappinggrapeclustersbasedonthedepthregiongrowingmethod
AT shengyizhao segmentationofoverlappinggrapeclustersbasedonthedepthregiongrowingmethod
AT jizhanliu segmentationofoverlappinggrapeclustersbasedonthedepthregiongrowingmethod
_version_ 1718412417562574848