Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and device for automatically identifying the growth period of rice seedlings

A technology for automatic identification and seedlings, applied in character and pattern recognition, instruments, calculations, etc., can solve the problem of not being able to obtain edge features of seedlings

Active Publication Date: 2021-10-29
JIANGSU POLYTECHNIC COLLEGE OF AGRI & FORESTRY
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, the traditional leaf contour extraction uses the leaf contour edge extraction algorithm. Due to the influence of light, there will be more overlapping areas in the leaf contour edge extraction of seedlings in different periods, and it is impossible to obtain accurate seedling edge features.

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 and device for automatically identifying the growth period of rice seedlings
  • A method and device for automatically identifying the growth period of rice seedlings
  • A method and device for automatically identifying the growth period of rice seedlings

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0082] The technical solutions of the present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0083] The method for automatically identifying the growth period of rice seedlings in the present invention first adopts image subtraction and color clustering methods to remove the background of the rice seedlings.

[0084] 1) Subtract the image of the identified area, the objects are the collected image and the background image.

[0085] G(x i ,y i ) = f 1 (x i ,y i )-f 0 (x i ,y i )

[0086] where G(x i ,y i ) is the image pixel after subtraction, f 1 (x i ,y i ) and f 0 (x i ,y i ) are the pixels corresponding to the seedling image to be recognized and the matrix background image respectively, f(x i ,y i ) = [x r x g x b ],x r 、x g 、x b represent f respectively 1 (x i ,y i ) and f 0 (x i ,y i ) pixel red, green and blue color component values. The subtraction is for the subtraction of RGB ...

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 automatically identifying the growth period of rice seedlings. The method first uses image subtraction and color clustering to perform background removal on the images of rice seedlings to be recognized; secondly, performs image segmentation on the rice seedling images after background removal; The edge is extracted from the image, and the edge area is colored by the four-color method; finally, the growth characteristics of the seedling in the four-color gamut are identified, and the growth stage of the seedling is judged. The present invention also provides an automatic identification device for rice seedling growth period based on the above automatic identification method. The invention solves the problem of difficult and inaccurate extraction of traditional leaf outline features, can accurately identify the key growth period state of seedling development, and lays a good foundation for precise water and fertilizer control of seedlings.

Description

technical field [0001] The invention relates to a crop growth stage recognition method, in particular to an automatic rice seedling growth stage recognition method. Background technique [0002] The automatic recognition method of rice seedlings based on machine vision is a key technology in the automation of rice seedling raising. Rice seedling recognition using image segmentation is affected by light, shadow, matrix, etc., and the extracted image features will appear fragmented, making it difficult to accurately extract the shape of rice seedlings. feature. The prior knowledge information of the seedlings is extracted by color clustering, and then the distance judgment is performed on the seedlings to extract the seedling information. Due to the influence of light, the prior clustering information of seedlings will not change with the change of light, and there will be deviations, especially when there is shadow in the matrix, the error is large, and the error of the segm...

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): G06K9/00G06K9/34G06K9/46G06K9/62
CPCG06V20/00G06V10/267G06V10/44G06F18/23
Inventor 薛小松严方刘晓宇余甜甜吴刚山冯祥陈仕雄范位龙董志茹
Owner JIANGSU POLYTECHNIC COLLEGE OF AGRI & FORESTRY