Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A method for detecting diseases and pests of field crops based on an SSD convolution network

A convolutional network and field crop technology, applied in the field of deep learning and pattern recognition, can solve the problems of long detection time and low detection accuracy, and achieve the effects of fast operation speed, accelerated detection speed, and reduced quantity

Inactive Publication Date: 2019-01-11
XIJING UNIV +1
View PDF4 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problems of long detection time and low detection accuracy in the traditional crop pest detection method, provide a field crop pest detection method based on SSD convolution network, and provide the necessary information for the intelligent monitoring system of crop leaf pests. technical support

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
  • A method for detecting diseases and pests of field crops based on an SSD convolution network
  • A method for detecting diseases and pests of field crops based on an SSD convolution network
  • A method for detecting diseases and pests of field crops based on an SSD convolution network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In order to make the purpose of the present invention and technical scheme clearer, below in conjunction with figure 1 , figure 2 and Fig. 3 describe the implementation steps in the present invention in detail.

[0037] see figure 1 , the SSD convolutional network used in the present invention consists of a VGG deep convolutional neural network and a multi-scale feature detection network, and extracts the feature maps of 7 different convolutional layers for detection.

[0038] The field crop disease and insect pest detection method based on SSD convolutional network provided by the present invention comprises the following operations:

[0039] 1) Use smart phones or Internet of Things devices to collect images of crop leaves and pests in the field, and build a database of crop leaves and pest images;

[0040] 2) Use the SSD convolutional network to detect disease spots and pests of various shapes and sizes from each image in the database. The SSD convolutional netwo...

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 for detecting diseases and pests of field crops based on an SSD convolution network. At first, the VGG deep convolution neural network is used to extract the primary features of the image of the disease and insect pests, then multi-scale feature extraction is carried out to evaluate different aspect ratios of plaque and pest detection frames at each position in several feature images output from different convolution layers and to detect plaque and pest in various shapes and sizes of leaf images. The invention can learn the multi-level characteristics from lowto high, quickly realizes the detection of diseases and pests with high precision, greatly improves the detection capability of small lesions and pests, and is particularly suitable for the detectionof diseases and pests of crop leaves based on the video leaf image of the Internet of Things.

Description

technical field [0001] The invention belongs to the technical field of deep learning and pattern recognition, and relates to a field crop pest detection method based on an SSD convolution network. Background technique [0002] Crop pest control is an important task in crop production management, and the premise of control is to detect the occurrence of plant diseases and insect pests in time. At present, the detection of field diseases and insect pests is still mainly manual detection. This detection method is a time-consuming, low-accuracy work that can only be completed by long-term trained plant protection personnel and experienced agricultural managers. [0003] The automatic detection of crop leaf diseases and insect pests based on machine learning is an efficient inspection method to detect the occurrence of diseases and insect pests and judge their development trend from leaf images. It is an important research topic in the fields of computer vision, image processing ...

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): G06T7/00
CPCG06T7/0012G06T2207/20081G06T2207/20084G06T2207/30188
Inventor 张善文黄文准赵保平周美丽林东王振
Owner XIJING 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
Eureka Blog
Learn More
PatSnap group products