Method and system for detecting rice panicle blast based on deep convolutional neural network

A deep convolution and neural network technology, applied in the field of intelligent detection of rice blast disease, can solve problems such as limitations, and achieve the effect of increasing the number of samples, improving the prediction accuracy of ear blast, and increasing the diversity of samples

Active Publication Date: 2018-01-12
SOUTH CHINA UNIV OF TECH
View PDF11 Cites 38 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The research work is limited to a sample size of hundreds of orders, and is limited to the hyperspectral image acquisition process operated by a laboratory light box under the condition of a fixed light source, which is still far from the actual production application.

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
  • Method and system for detecting rice panicle blast based on deep convolutional neural network
  • Method and system for detecting rice panicle blast based on deep convolutional neural network
  • Method and system for detecting rice panicle blast based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0057] This example provides a rice blast detection method based on a deep convolutional neural network, which can provide technical support for outdoor rice blast disease prediction, and can also be used for the rational and precise application of agricultural resources such as water, fertilizer or pesticides in the production process Management, etc. have a guiding role.

[0058] Such as figure 1 Shown, the rice panicle blast detection method based on depth convolutional neural network of the present embodiment comprises the following steps:

[0059] S1. Collecting hyperspectral images of outdoor rice panicle plants and calibrating panicle blast disease

[0060] Rice samples at the early stage of yellow maturity were collected from the natural disease area induced by rice blast, covering multiple rice varieties. After simple muddy water cleaning, the hyperspectral images of rice spikes were collected.

[0061] According to the description of panicle blast disease by multip...

Embodiment 2

[0082] Such as Figure 7 As shown, the present embodiment provides a rice blast detection system based on a deep convolutional neural network, which is set up outdoors and includes a hyperspectral camera 1, a computer 2, a tripod 3 and a reflector 4, and the reflector 4 Paddy rice ear strain 5 is hung on it, and described hyperspectral camera 1 is fixed on the tripod 3, and is connected with computer 2, and the lens of hyperspectral camera 1 is aimed at the rice ear strain 5 on reflective plate 4, and in the present embodiment, The distance between the hyperspectral camera 1 and the reflection plate 4 is 80 cm, the width of the reflection plate is 40 cm, and the height is 60 cm.

[0083] The hyperspectral camera is used to collect hyperspectral images of rice ears and plants under any illumination (including the daytime under different sunlight conditions and the night of incandescent lighting), which uses the GaiaField-F-V10 of Sichuan Shuangli Hepu Technology Co., Ltd. Port...

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 method and a system for detecting rice panicle blast based on a deep convolutional neural network. The method comprises the following steps: acquiring a hyperspectral image of outdoor rice panicles and performing panicle blast disease calibration; performing data preprocessing and data enhancement on the hyperspectral image of the rice panicles; establishing a deep convolutional neural network model and optimizing model parameters with a stochastic gradient descent algorithm; detecting the hyperspectral image of the rice panicles to be tested with the trained deep convolutional neural network model, and judging whether the rice panicles are infected by the panicle blast disease or not. The system comprises a hyperspectral camera, a computer, a tripod and a reflection board, wherein the rice panicles are hung on the reflection board; the hyperspectral camera is fixed on the tripod, is connected with the computer, and has a lens aiming at the rice panicles on the reflection board. The method and the system provided by the invention can provide technical support for predicting the outdoor rice panicle blast disease and can also play an instructive role in rational and precise application and management of water and fertilizer, pesticide or other agricultural resources in a production process.

Description

technical field [0001] The invention relates to a rice blast blast detection method and system, in particular to a rice blast blast detection method and system based on a deep convolutional neural network, belonging to the technical field of intelligent detection of rice blast blast. Background technique [0002] Rice is the most important food crop in my country. my country's rice planting area reaches 30 million hectares, and its output accounts for 40% of the total grain output. Rice production is responsible for ensuring my country's food security. However, rice is often attacked by diseases and insect pests during its growth process, which affects the yield and quality. Rice blast is a fungal disease in the world, and it is one of the most serious rice diseases in the northern and southern rice-growing regions of my country. Rice blast occurs in all major rice areas in my country, with an average annual area of ​​more than 3.8 million hectares, and the annual loss of ...

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): G01N21/25
Inventor 黄双萍
Owner SOUTH CHINA UNIV OF TECH
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