Supercharge Your Innovation With Domain-Expert AI Agents!

Soybean inter-plant weed automatic identification device and method based on computer vision

A computer vision and automatic identification technology, applied in the field of weeding, can solve problems such as the inability to prevent marker sprinkler irrigation or natural precipitation removal, and the time-consuming and cumbersome marker marking process, achieving the effect of strong practicability, elimination of interference, and simplified algorithm.

Pending Publication Date: 2022-01-25
CHINA AGRI UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The labeling process of the markers applied by the existing crop signal transduction technology is time-consuming and cumbersome, and it is impossible to prevent the markers from being cleared by sprinkler irrigation or natural precipitation.

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
  • Soybean inter-plant weed automatic identification device and method based on computer vision
  • Soybean inter-plant weed automatic identification device and method based on computer vision
  • Soybean inter-plant weed automatic identification device and method based on computer vision

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0054]A computer vision-based soybean / inter-plant weed automatic identification device according to an embodiment of the present invention includes a darkroom system 1 constructed of profiles, the outside of the darkroom system 1 is covered with a black light-absorbing curtain 2, and the darkroom system A grayscale camera 3 is fixed on the inner top of 1, and the grayscale camera 3 is connected with a computer 4. Six blue LED lights 5 are fixed in the middle of the darkroom system 1, and the blue LED lights 5 are connected to a transformer. 6, and the inner bottom of the darkroom system 1 is fixed with six mirrors 7 with suitable tilt angle adjustments.

[0055] Through the above scheme of the present invention, the inclination angle of the blue LED light 5 is adjusted so that the light can be evenly directed to the soybean seedlings 8 without reflecting light with the mirror 7, and the voltage value of the transformer 6 is adjusted to an appropriate value, and the blue The br...

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 soybean inter-plant weed automatic identification device and method based on computer vision. The device comprises a darkroom system built by section bars; the dark room system is covered by a black light absorption curtain; a gray-scale camera is fixed at the top end in the darkroom system, and is connected with a computer; six blue LED lamps are fixed in the middle of the interior of the darkroom system, and the blue LED lamps are connected with the transformer; and six mirrors with proper inclination angles are fixed at the bottom end in the darkroom system. Through a series of improvements, a systematic crop signal transduction technology is adopted, information, such as fluorescent images of soybean crops and weeds, captured from seven perspectives at the same time is analyzed, a new computer vision real-time identification method based on the three-dimensional geometric appearance of the soybean marker is established, the position of a soybean stem in a field is accurately identified, and the weeding device can be combined to realize automatic weeding operation.

Description

technical field [0001] The invention relates to the field of weeding, in particular to a device and method for automatically identifying weeds among soybean plants based on computer vision. Background technique [0002] Weed damage is one of the main biological disasters after soybean emergence, and inter-row weeds are more harmful to soybean seedlings. The number of weeds emerging within 3 weeks after soybean sowing can account for about 95.00% of the total number of weeds emerging, so the early control of weeds in soybean fields is particularly important. [0003] At present, measures such as herbicides, manual weeding and mechanical intertillage weeding are often used in weed control. Herbicide weed control is currently the main means of controlling weeds in soybean fields, but herbicide application is likely to cause problems such as agricultural product quality and safety and environmental pollution. Manual weeding is a flexible and precise inter-row weeding method, b...

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): G06V20/10G06V10/26G06V10/25
CPCY02P60/14
Inventor 苏文浩黄青阳盛基
Owner CHINA AGRI UNIV
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More