Candidatus Liberibacter spp. online rapid detection system and method based on deep learning

A technology of citrus huanglongbing and deep learning, applied in the field of citrus huanglongbing online rapid detection system, can solve the problems of difficult promotion, high detection cost, cumbersome process, etc., to promote precision agriculture and agricultural informatization, improve diagnostic efficiency and accuracy efficiency, and the effect of simplifying the diagnostic process

Inactive Publication Date: 2018-11-30
SOUTH CHINA AGRI UNIV
View PDF6 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the most reliable detection method for HLB is PCR detection technology, but the detection process of this method is cumbersome, the cycle is long, the detection cost is high, and the detection environment and operation requirements are high, which limits the applicatio...

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
  • Candidatus Liberibacter spp. online rapid detection system and method based on deep learning
  • Candidatus Liberibacter spp. online rapid detection system and method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0023] An online rapid detection method for citrus huanglongbing based on deep learning. This method takes citrus leaves and fruits as the research object, analyzes the images of infected citrus leaves and fruits, determines and extracts the image features of infected citrus leaves and fruits, and then The server establishes an accurate HLB diagnosis model through deep learning; farmers collect images of citrus leaves and fruits in the orchard through the mobile client and upload the images to the server. Farmers can quickly know whether the citrus trees in the orchard are infected with HLB.

[0024] The online detection of HLB by using the mobile phone client is more time-saving than traditional methods, and can find diseased strains more conveniently. Compared with PCR technology, it greatly shortens the detection cycle. In practical applications, identify...

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

A Candidatus Liberibacter spp. online rapid detection system based on deep learning includes a mobile phone client and a server end; the server end includes a data transmission module, a leaf and fruit detection module, a Candidatus Liberibacter spp. diagnosis module, and a sample database; a model of the leaf and fruit detection module is trained by using the data with instance annotations in a sample database to obtain the optimal model; a model of the Candidatus Liberibacter spp. diagnosis module is trained by using the data with diagnostic annotations in the sample database to obtain the optimal model; the leaf and fruit detection module transmits the output and detected single leaf and single fruit images to the Candidatus Liberibacter spp. diagnosis module. A Candidatus Liberibacterspp. online rapid detection method based on deep learning adopts the Candidatus Liberibacter spp. online rapid detection system based on deep learning. The invention belongs to the technical field ofintelligent identification of Candidatus Liberibacter spp., and has the advantages of rapid, efficient and reliable detection.

Description

technical field [0001] The invention belongs to the technical field of intelligent identification of citrus huanglongbing, and in particular relates to an online rapid detection system and method for citrus huanglongbing based on deep learning. Background technique [0002] Citrus is one of the fruits with the largest production volume in the world, and it is also one of the largest fruit varieties planted in southern my country. It plays a very important role in the agricultural economy. And citrus Huanglongbing (HLB) is destructive to the production of citrus. The disease causes citrus trees to show symptoms such as mottled leaves, yellow leaves, weak tree vigor, red-nosed fruit or green fruit that does not turn color, etc., and has the potential to spread. The characteristics of fast speed and great harm. Once the citrus trees are infected with the disease, the light ones will seriously affect the fruit yield and quality, and the severe ones will cause the citrus plants ...

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): G06T7/00G06K9/62G01N21/88
CPCG06T7/0002G01N21/8851G01N2021/8887G01N2021/8854G06T2207/30188G06T2207/10004G06T2207/20084G06T2207/20081G06F18/24
Inventor 邓小玲朱梓豪麦晓春兰玉彬谢昌栩练碧桢黄敬易黄梓效
Owner SOUTH CHINA AGRI UNIV
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap