Agricultural picked object recognition algorithm based on database

A recognition algorithm and database technology, applied in the field of image recognition, can solve problems such as affecting users' experience of fruit tasting, small size differences, etc., to improve the quality of sales products, reduce losses, and reduce the risk of virus transmission.

Pending Publication Date: 2022-05-03
UNIV OF SCI & TECH LIAONING
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At this time, according to the first-in-first-out warehouse management, it will undoubtedly affect the user's experience of tasting fruit
[0004] In modern three-dimensional strawberry greenhouses, strawberries have slight color differences and small size differences. Therefore, it is necessary to develop an artificial intelligence fruit state recognition and detection system that can detect and judge the maturity of fruits during the picking process. The time difference between the refrigeration and transportation process assists the warehouse staff in the operation of entering and leaving the warehouse, and improves the precision and accuracy of the management of the warehouse entering and leaving the warehouse. At present, there are few reports in the relevant literature

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Agricultural picked object recognition algorithm based on database
  • Agricultural picked object recognition algorithm based on database
  • Agricultural picked object recognition algorithm based on database

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0033] The technical solutions of the present invention will be clearly and completely described below in conjunction with specific embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0034] Terminology in this article: Convolutional Neural Networks (CNN) is a class of roll product Computational and deeply structured feedforward neural network (Feedforward Neural Networks), yes deep learning (deep learning) one of the representative algorithms. Convolutional neural networks have representation learning (representation learning) ability, which can perform shift-invariant classification (shift-invariant classification) on input information according to its hierarc...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention belongs to the technical field of image recognition, and particularly relates to an agricultural picked object recognition algorithm based on a database, which is characterized in that a computer sets a maturity index according to a plurality of indexes such as colors, sizes and wrinkles of fruits to be picked and characteristics associated with maturity height, and establishes a model for the maturity degree and storage time of the fruits; the computer carries out artificial intelligence recognition on fruit pictures collected by the picking robot and transmits fruit types and coordinate information to a motion control unit of the picking robot, and finally grabbing, sorting and obstacle-avoiding walking are achieved. Compared with the prior art, the method has the beneficial effects that the maturity of strawberries can be divided into multiple grades according to market requirements, the maturity of picked strawberries with long storage time or long transportation distance is slightly lower, so that the distance of mailing and selling areas can be selected according to the maturity, the loss of the strawberries in transportation is reduced, and the economic benefit is increased. Sales areas are expanded, and economic benefits are improved.

Description

technical field [0001] The invention belongs to the technical field of image recognition, and in particular relates to a recognition algorithm of agricultural picking objects based on a database. Background technique [0002] There are many precautions for fruit picking, and the picking steps are cumbersome. However, in many areas of our country, fruit picking is still mainly done manually, and production mechanization and modelization have not been realized to a large extent. Simply relying on labor is not only inefficient, but also the quality of finished fruit products cannot be guaranteed. This picking method is time-consuming and labor-intensive, and requires the cooperation of multiple people to complete. Most of the picking machines in the prior art cannot be sorted and packed according to the maturity and size of the fruit during the picking process. They are usually picked in the orchard and transported to the sorting site by car, and then sorted manually or mechan...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06Q10/06G06F16/25G06Q10/10G06Q50/02
CPCG06Q10/06311G06Q10/06315G06Q10/06316G06Q10/0633G06Q10/06393G06Q10/06395G06Q10/103G06Q50/02G06F16/252
Inventor 李桐郑思侬陆鑫焱魏英新梁璐王立东高云吴玉娟宗洪凤陈壹刘敬墨白
Owner UNIV OF SCI & TECH LIAONING
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products