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

A method for detecting red beetles based on deep learning

A deep learning, silverfish technology, applied in the direction of instrument, calculation, character and pattern recognition, etc., can solve the problems of high cost, strong subjectivity, high labor intensity, etc.

Active Publication Date: 2021-04-30
BEIJING FORESTRY UNIVERSITY
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Manual monitoring has problems such as high labor intensity, high cost, low efficiency, and strong subjectivity. It is urgent to reduce the labor intensity of grassroots personnel through automatic counting methods, and improve the accuracy and timeliness of pest monitoring and forecasting.

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 red beetles based on deep learning
  • A method for detecting red beetles based on deep learning
  • A method for detecting red beetles based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] In recent years, deep learning has performed well in the field of target detection, which can simultaneously realize target positioning and recognition. The current relatively successful deep learning target detection networks include Faster R-CNN, SSD (Single Shot Multibox Detector), RetinaNet, Mask R-CNN, etc. in:

[0037] Faster R-CNN is a Region-Based NeuralNetwork based on RPN (region proposal network), which is a typical two-stage model. In the first stage of the image, a 2-class RPN is used to extract its region of interest (RoI), and in the second stage, Fast R-CNN is used to perform refine operations such as subdivision and position regression of the region of interest.

[0038] SSD is a typical single-stage model. An additional network structure is added after the truncated basic network, and feature maps with different resolutions are generated step by step (the deeper the network layer, the lower the resolution, and the stronger the semantic interpretation ...

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 is a method for detecting the red beetle based on deep learning. It first transmits the image of bark beetles collected from the modified trap to the server for image preprocessing, and then inputs the Faster R-CNN target detection model that uses the k-means method to optimize the default box for the silverfish dataset for detection, and finally The detection results are plotted on the input image after a series of post-processing. The invention can realize real-time collection and remote online identification of on-site image data in forest farms, reduces manpower expenditure, and realizes automation of forestry pest monitoring.

Description

technical field [0001] The invention relates to a method for detecting the red beetle, in particular to a method for detecting the red beetle based on deep learning. Background technique [0002] The ruby ​​beetle (RTB) is a stem-boring pest of more than 35 species of Pinaceae. After the insect was first discovered in Shanxi Province of my country in 1998, the damage area expanded rapidly. In 2004, the red beetle spread to Shanxi, Shaanxi, Hebei, and Henan provinces, and there were more than 6 million dead pine trees. In 2005, it spread to Mentougou District, Beijing. [0003] Accurate and timely monitoring and early warning of insect infestation can guide early control and avoid major economic and ecological losses. The monitoring of beetle beetle population is an important part of forest pest control. During the flying period of the red beetle adults, the staff hang traps according to the distribution of the pine forest. The traditional monitoring method is the manual...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/40G06K9/62
CPCG06V20/46G06V20/52G06V10/30G06F18/23213G06F18/241
Inventor 孙钰袁明帅任利利刘文萍张海燕
Owner BEIJING FORESTRY UNIVERSITY
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