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

Crop disease image recognition method based on convolutional neural network

A convolutional neural network and image recognition technology, applied in the field of image recognition, can solve real-time, poor accuracy, time-consuming and labor-intensive problems, and achieve the effect of improving early warning of crop diseases

Inactive Publication Date: 2020-07-14
JILIN AGRICULTURAL UNIV
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, the traditional identification of crop diseases mainly relies on the experience accumulated by farmers in the past dynasties in the agricultural production process to make judgments, which is time-consuming and laborious, and the real-time and accuracy are poor.

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
  • Crop disease image recognition method based on convolutional neural network
  • Crop disease image recognition method based on convolutional neural network
  • Crop disease image recognition method based on convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] A method for image recognition of crop diseases based on a convolutional neural network, comprising the steps of:

[0026] S1. Acquisition of crop images at fixed points based on the UAV according to the established cruise route; each crop image will carry supporting POS data, the POS data includes latitude, longitude, elevation, heading angle (Phi), and pitch angle (Omega) and roll angle (Kappa);

[0027] S2. Read the POS data contained in the crop image, and adjust the angle of the image of the diseased area according to the POS data. The angle adjustment includes flipping left and right, flipping up and down, and flipping diagonally, and based on the Faster R-CNN model. Detecting and positioning, generating a diseased area image set; the images in the diseased area image set all carry the hyperlink marks of their corresponding POS data;

[0028] S3. Based on the DSSD_Xception_coco model, the detection and identification of holes, spots, and pest tracks in the image ...

Embodiment 2

[0032] A method for image recognition of crop diseases based on a convolutional neural network, comprising the steps of:

[0033] S1. Acquisition of crop images at fixed points based on the UAV according to the established cruise route; each crop image will carry supporting POS data, the POS data includes latitude, longitude, elevation, heading angle (Phi), and pitch angle (Omega) and roll angle (Kappa);

[0034] S2. Read the POS data contained in the crop image, and adjust the angle of the image of the diseased area according to the POS data. The angle adjustment includes flipping left and right, flipping up and down, and flipping diagonally, and based on the Faster R-CNN model. Detecting and positioning, generating a diseased area image set; the images in the diseased area image set all carry the hyperlink marks of their corresponding POS data;

[0035] S3. Based on the DSSD_Xception_coco model, the detection and identification of holes, spots, and pest tracks in the image ...

Embodiment 3

[0040] A method for image recognition of crop diseases based on a convolutional neural network, comprising the steps of:

[0041] S1. Acquisition of crop images at fixed points based on the UAV according to the established cruise route; each crop image will carry supporting POS data, the POS data includes latitude, longitude, elevation, heading angle (Phi), and pitch angle (Omega) and roll angle (Kappa);

[0042] S2. Read the POS data contained in the crop image, and adjust the angle of the image of the diseased area according to the POS data. The angle adjustment includes flipping left and right, flipping up and down, and flipping diagonally, and based on the Faster R-CNN model. Detecting and positioning, generating a diseased area image set; the images in the diseased area image set all carry the hyperlink marks of their corresponding POS data;

[0043] S3. Based on the DSSD_Xception_coco model, the detection and identification of holes, spots, and pest tracks in the image ...

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 a crop disease image recognition method based on a convolutional neural network. The method comprises the following steps: S1, collecting crop images at fixed time and fixed point based on an unmanned aerial vehicle; S2, reading POS data carried in the crop image, realizing detection and positioning of a disease area in the crop image based on a Faster R-CNN model, and generating a disease area image set; S3, realizing detection and recognition of holes, spots, pest tracks and the like in the disease area image based on a DSSD_Xception_coco model; and S4, outputting a disease recognition result based on the detection recognition result of the holes, the spots, the pest tracks and the like and the POS data of the corresponding disease area image, and completing disease condition statistics of each area. According to the invention, automatic detection, recognition and statistical analysis of crop diseases are realized, a corresponding control scheme is further provided, and a foundation is laid for improving crop disease early warning.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method for image recognition of crop diseases based on a convolutional neural network. Background technique [0002] Crop disease is one of the main agricultural disasters in my country. It has the characteristics of various types, great impact and frequent outbreaks. It not only causes losses to crop production, but also poses a threat to food safety. Therefore, the diagnosis and identification of crop diseases play an important role in ensuring crop yield and preventing food safety. At the same time, realizing accurate detection of crop diseases and the determination of the degree of disease is the key to the prevention and control of crop diseases. At present, the traditional crop disease identification mainly relies on the experience accumulated by farmers in the agricultural production process to make judgments, which is time-consuming and labor-intensive, and the real-t...

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): G06K9/00G06K9/32G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V20/188G06V10/242G06N3/045G06F18/241
Inventor 曹丽英李博于合龙李东明刘鹤马丽
Owner JILIN AGRICULTURAL UNIV
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