2021
DOI: 10.1051/e3sconf/202127001021
|View full text |Cite
|
Sign up to set email alerts
|

Neural network for identifying apple fruits on the crown of a tree

Abstract: To identify the fruits on the crowns of trees and count their number, a software and hardware complex (PAC) based on a technical vision system and a recurrent neural network of deep learning has been developed. The created neural network and class allocation algorithms allow the software and hardware complex to function stably in the conditions of industrial horticultural plantings, regardless of the size and interference of foliage, to determine the color of the fruit surface, to identify the presence of dise… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
4
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
1
1

Relationship

2
5

Authors

Journals

citations
Cited by 11 publications
(4 citation statements)
references
References 11 publications
0
4
0
Order By: Relevance
“…In our subsequent research on navigation, we also plan to use convolutional neural networks to refine the route. We used this toolkit to identify an apple when it was picked from a tree [16,17].…”
Section: Comparison Of Laboratory and Field Research Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…In our subsequent research on navigation, we also plan to use convolutional neural networks to refine the route. We used this toolkit to identify an apple when it was picked from a tree [16,17].…”
Section: Comparison Of Laboratory and Field Research Resultsmentioning
confidence: 99%
“…In an industrial garden, signals such as laser (clouds of points, 3D matrices and digital twins), ultrasonic and radio signals are used to determine the location and movement of an autonomous vehicle [14,15]. Speed, acceleration and changes in the position of the grippers and other working parts when the manipulator is operating under field conditions are controlled using accelerometers, gyroscopes and global satellite systems [16,17]. In this study, we will consider the use of a LiDAR (Light Detection and Ranging) sensor to construct maps of the obstacles and trajectories of an autonomous vehicle under the field conditions of an industrial garden.…”
Section: Introductionmentioning
confidence: 99%
“…These models demonstrate high efficiency in processing visual data, including images of biological objects. They have the ability to extract essential features and provide high accuracy in classification tasks [14,15]. Among various neural network models, modern YOLO convolutional models stand out as the most efficient.…”
Section: Methodsmentioning
confidence: 99%
“…Accelerometers, gyroscopes, and global satellite systems are used to control acceleration, movement speed and position changes in the working bodies in space. To recognize fruits on a tree, various computer vision methods are used, including neural networks (Smirnov et al, 2021;Khort et al, 2020).…”
Section: Sensorsmentioning
confidence: 99%