Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intelligent pest and disease identification method and system based on CNN and LSTM

An identification method and technology for pests and diseases, applied in the field of intelligent pest identification methods and systems, can solve the problems of errors, time-consuming and laborious, affecting the efficiency of crop disease prevention and control, and achieve the effect of reducing manual labor intensity and improving treatment efficiency.

Pending Publication Date: 2022-01-11
SHANDONG INSPUR SCI RES INST CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Pests and diseases are one of the important factors leading to crop yield reduction. The traditional identification methods of crop diseases and insect pests basically rely on the professional knowledge and work experience of relevant experts to identify them, which is time-consuming, laborious, inefficient, and prone to human error, which seriously affects the control of crop diseases and insect pests. work efficiency

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
  • Intelligent pest and disease identification method and system based on CNN and LSTM
  • Intelligent pest and disease identification method and system based on CNN and LSTM
  • Intelligent pest and disease identification method and system based on CNN and LSTM

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] as attached figure 1 As shown, the intelligent pest identification method based on CNN and LSTM of the present invention is to use the convolutional neural network to judge the pest situation on the crops, and then match the treatment plan for the pest situation through LSTM to achieve the purpose of discovering and solving the pest; specifically as follows:

[0069] S1. Constructing a data set of crop diseases and insect pests;

[0070] S2. Construct and train the pest and disease model;

[0071] S3. Deploy and use the pest model.

[0072] The data set of crop diseases and insect pests in step S1 in this embodiment includes pictures of diseases and insect pests, the name of each picture of disease and insect pests, and the corresponding treatment plan for diseases and insect pests;

[0073] For example: a picture with wheat scab, then name it "wheat scab", and then enter the treatment plan for the related wheat scab.

[0074] The ratio of the training set to the te...

Embodiment 2

[0107] The intelligent disease and pest identification system based on CNN and LSTM of the present invention, this system comprises,

[0108] The construction unit is used to construct a data set of crop diseases and insect pests; wherein, the data set of agricultural diseases and insect pests includes pictures of diseases and insect pests, the name of each picture of diseases and insect pests and the treatment plan of corresponding diseases and insect pests; the ratio of the training set and the test set in the data set of agricultural diseases and insect pests is 4:1;

[0109] Construction and training unit, used to construct and train pest and disease models;

[0110] The deployment unit is used to deploy and use the pest model; specifically: deploy the pest model to the server, use the drone to take pictures of the crops, and upload the photos to the server, the server calls the pest model to identify the types of pests, and then Input the identification results of the pes...

Embodiment 3

[0123] The embodiment of the present invention also provides an electronic device, including: a memory and a processor;

[0124]Wherein, the memory stores computer-executable instructions;

[0125] The processor executes the computer-executed instructions stored in the memory, so that the processor executes the intelligent disease and pest identification method based on CNN and LSTM in any embodiment of the present invention.

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 discloses an intelligent pest and disease identification method and system based on CNN and LSTM, belongs to the technical field of artificial intelligence computer vision, and aims to solve the technical problems of how to identify crops by using the CNN and the LSTM and match corresponding treatment measures after identification so as to achieve the purposes of discovering pest and disease damage and radically treating the pest and disease damage. According to the adopted technical scheme, the method uses a convolutional neural network to judge the pest and disease damage conditions of crops, and then LSTM is used for matching a treatment scheme for the pest and disease damage conditions to achieve the purpose of discovering and solving the pest and disease damage. The method comprises the following steps: constructing a crop pest data set, constructing and training a pest and disease damage model, and deploying and using a pest model.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence computer vision, in particular to an intelligent pest identification method and system based on CNN and LSTM. Background technique [0002] Neural networks are part of the field of artificial intelligence research. Currently, the most popular neural network is deep convolutional neural networks (CNNs). Although convolutional networks also have shallow structures, due to the accuracy and It is rarely used for reasons such as expressiveness. At present, when referring to CNNs and convolutional neural networks, academia and industry no longer make a special distinction. They generally refer to convolutional neural networks with deep structures, and the number of layers varies from "several layers" to "tens or hundreds". CNNs have achieved great success in many, many research fields, such as: speech recognition, image recognition, image segmentation, natural language processing, etc. ...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06V20/10G06V10/764G06N3/04G06N3/08
CPCG06N3/08G06N3/044G06N3/045G06F18/22
Inventor 戴鸿君
Owner SHANDONG INSPUR SCI RES INST CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com