Automatic leaf area index observation system and method

A technology of leaf area index and automatic observation, applied in the field of agricultural observation, can solve the problems of no leaf area index, manual operation, and inability to achieve complete automation.

Inactive Publication Date: 2012-07-04
BEIJING NORMAL UNIVERSITY
View PDF5 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Because of these difficulties, the existing instruments for indirectly measuring leaf area index all need manual operation and cannot be fully automated.
There is no automatic observation system for leaf area index

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
  • Automatic leaf area index observation system and method
  • Automatic leaf area index observation system and method
  • Automatic leaf area index observation system and method

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0041] first embodiment : Improved K-means classification method

[0042] This method is implemented by the improved K-means classification module in the binary image generation module.

[0043] The improved K-means classification method uses the cluster analysis method, which needs to select the required number of classifications in the data, randomly find the cluster centers, and then reconfigure them iteratively until the optimal classification is achieved. The improved K-means classification method is first automatically divided into multiple categories according to the selected number of categories, and then thresholded according to the mean values ​​of various bands, and merged into two categories: green vegetation, soil and background. The processing flow of the improved method is:

[0044] 1) Calculating K initial category mean values ​​uniformly distributed on the image data space;

[0045] 2) Calculate the distance from the pixel to each initial category, and use...

no. 2 example

[0049] second embodiment : Automatic Threshold Classification Method

[0050] The method is implemented by the automatic threshold classification module in the binary image generation module.

[0051] For images with small winter wheat and corn leaves, four band threshold classification methods are provided. R, G, and B respectively represent the red, green, and blue bands of the RGB color space, and their value ranges are 0-255. H represents the chromaticity in the HSL color space, and its value range is 0°- 360°, the principle of classification is to distinguish between green leaves and soil background by setting the range of four variables R, G, B and H, so define four thresholds t1, t2, t3, t4 for setting R, G, B The scope of the four variables H and H, the variables limited by the four thresholds in each method are not fixed, and are only used for assigning values ​​to the four variables. The following four methods provide recommended thresholds. In the application, a...

no. 3 example

[0060] third embodiment : block threshold classification method

[0061] The method is implemented by the block threshold classification module in the binary image generation module.

[0062] Preferably, block processing is performed on the image of larger corn leaves or the original image of other crops with larger leaves, and the original image becomes a uniform patch classification result, which is more accurate, and then binarized by band thresholding. The block diameter determines the size of the block image, and the user needs to set it according to the image.

[0063] The processing flow of this method is:

[0064] 1) Image segmentation. Image segmentation requires the user to input the diameter of the segmentation block and the number of iterations. After the segmentation is completed, the image generates a uniform patch, and there are often unassigned pixels at the boundary of the patch. After segmentation, the image is more uniform and the classification is more ...

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 an automatic leaf area index observation system and an automatic leaf area index observation method. The system comprises a data acquisition device and an automatic leaf area index observation server which comprises a binary image generation module, a parameter extraction module and a leaf area index calculation module; the binary image generation module is used for classifying a crop canopy digital image acquired by the data acquisition device into a binary image; the parameter extraction module is used for extracting parameters such as gap rate, a gap size, and an aggregation index from the binary image; and the leaf area index calculation module is used for calculating the leaf area index according to the extracted information parameters. The system realizes a method for indirectly measuring the leaf area index. Compared with the prior art, the invention has the advantages that the method can be used for remotely acquiring images outdoor and meeting the image classification under outdoor complex conditions, classification accuracy is reliable and a classification result is accurate. Information such as the gap rate, the gap size, the aggregation index and the like are acquired from the binary image, so deeper analysis can be performed, and the leaf area index can be calculated.

Description

technical field [0001] The invention relates to the field of agricultural observation, and more specifically relates to a leaf area index automatic observation system and a method thereof. Background technique [0002] Leaf Area Index (LAI, Leaf Area Index), as one of the most basic and commonly used agricultural ecological environment parameters, has become one of the important indicators in the fields of plant ecology, forestry and agricultural yield estimation. At present, there are ready-made sensors for parameters such as temperature, humidity, and soil moisture, but there is no LAI sensor, which is due to the particularity of LAI measurement. Generally speaking, it is difficult to directly measure the leaf area index without damaging the crops. If an indirect measurement method is used, it is necessary to solve the representative problem of sampling, automatically distinguish between leaves and background, and interfere with leaf angles and mutual occlusions. Make cor...

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): G01B11/28G06K9/60
Inventor 李秀红夏江周刘强程晓严科杨细方
Owner BEIJING NORMAL UNIVERSITY
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