2023
DOI: 10.1016/j.dib.2023.109100
|View full text |Cite
|
Sign up to set email alerts
|

GrapesNet: Indian RGB & RGB-D vineyard image datasets for deep learning applications

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
6

Relationship

0
6

Authors

Journals

citations
Cited by 9 publications
(2 citation statements)
references
References 6 publications
0
2
0
Order By: Relevance
“…The wGrapeUNIPD-DL dataset [46], available since 2022, comprises 373 images of various grape varieties captured at different phenological stages across six Italian vineyard locations. GrapesNet [47], published in 2023, offers four datasets containing RGB and RGB-D images of grape bunches, facilitating tasks such as grape segmentation and weight prediction. Representative examples of images appearing in the aforementioned datasets are presented in Figure 1.…”
Section: Available Datasetsmentioning
confidence: 99%
“…The wGrapeUNIPD-DL dataset [46], available since 2022, comprises 373 images of various grape varieties captured at different phenological stages across six Italian vineyard locations. GrapesNet [47], published in 2023, offers four datasets containing RGB and RGB-D images of grape bunches, facilitating tasks such as grape segmentation and weight prediction. Representative examples of images appearing in the aforementioned datasets are presented in Figure 1.…”
Section: Available Datasetsmentioning
confidence: 99%
“…They help in the identification and classification of diseases [8] , as well as in the detailed analysis of yield factors [9] . Following the idea of [10] , where they introduced the concept of different angles with a handheld camera to avoid occlusions and provided 11000+ images, this dataset offers Unmanned Aerial Vehicles (UAV) videos with grape bunch annotations recorded in a commercial vineyard under challenging conditions, such as occlusion. This endeavour aims not just at enriching the repository of data available for precision agriculture but also at overcoming specific hurdles not only for object detection within viticulture, similar to [11] where they provided instances to locate the bunches in the images but including tracking, by adding the same ID of each grape bunch along frames.…”
Section: Introductionmentioning
confidence: 99%