CN113222925A - ImagePy-based water-sensitive paper fog drop parameter measuring device and measuring method thereof - Google Patents

ImagePy-based water-sensitive paper fog drop parameter measuring device and measuring method thereof Download PDF

Info

Publication number
CN113222925A
CN113222925A CN202110485867.0A CN202110485867A CN113222925A CN 113222925 A CN113222925 A CN 113222925A CN 202110485867 A CN202110485867 A CN 202110485867A CN 113222925 A CN113222925 A CN 113222925A
Authority
CN
China
Prior art keywords
water
sensitive paper
image
imagepy
module
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202110485867.0A
Other languages
Chinese (zh)
Other versions
CN113222925B (en
Inventor
亢洁
刘港
冯树杰
郭国法
田野
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shaanxi University of Science and Technology
Original Assignee
Shaanxi University of Science and Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shaanxi University of Science and Technology filed Critical Shaanxi University of Science and Technology
Priority to CN202110485867.0A priority Critical patent/CN113222925B/en
Publication of CN113222925A publication Critical patent/CN113222925A/en
Application granted granted Critical
Publication of CN113222925B publication Critical patent/CN113222925B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/02—Investigating particle size or size distribution
    • G01N15/0205—Investigating particle size or size distribution by optical means
    • G01N15/0211—Investigating a scatter or diffraction pattern
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N15/00—Investigating characteristics of particles; Investigating permeability, pore-volume or surface-area of porous materials
    • G01N15/04—Investigating sedimentation of particle suspensions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
    • G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformations in the plane of the image
    • G06T3/60—Rotation of whole images or parts thereof
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/11—Region-based segmentation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/10—Segmentation; Edge detection
    • G06T7/136—Segmentation; Edge detection involving thresholding
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/20—Special algorithmic details
    • G06T2207/20112—Image segmentation details
    • G06T2207/20132—Image cropping
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30242—Counting objects in image

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Chemical & Material Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Dispersion Chemistry (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Quality & Reliability (AREA)
  • Image Processing (AREA)

Abstract

A water-sensitive paper fog droplet parameter measuring device based on ImagePy and a measuring method thereof comprise a water-sensitive paper image acquisition module, an image processing module and a fog droplet parameter statistical module; the image processing module comprises an image automatic rotating and cutting module based on ImagePy, an image splicing module and a color image segmentation module; and the fog drop parameter statistic module comprises six parameters of a maximum value, a minimum value, an average value, a median value, a fog drop coverage rate and a fog drop number. The fog drop coverage rate and the fog drop median function are added on the basis of the original function of ImagePy by writing a program; automatically cutting the water-sensitive paper image in a rotating manner through an image acquisition module and image processing software ImagePy, then carrying out image splicing and color image segmentation on the water-sensitive paper image, and further carrying out statistics on fog drop parameters such as the size of fog drops, the total fog drop number, the fog drop coverage rate and the like by using a fog drop parameter statistics module; the invention has the advantages of simple structure, convenient operation, accurate and quick measurement and wide application prospect.

Description

ImagePy-based water-sensitive paper fog drop parameter measuring device and measuring method thereof
Technical Field
The invention relates to the technical field of image processing, in particular to a device and a method for measuring fog drop parameters of water-sensitive paper based on ImagePy.
Background
The pesticide has the characteristics of low cost, effectiveness and rapidness in the aspect of controlling crop diseases and insect pests, and is the most powerful method for controlling the crop diseases and insect pests. However, the pesticide is wasted due to a large amount of spraying, and the environment and the health of people are seriously harmed. Therefore, how to improve the utilization rate of the pesticide and reduce the using amount of the pesticide becomes an urgent problem to be solved. The information such as the spray amount of the deposited fog drops on the target, the size of the fog drops, the coverage uniformity of the fog drops on the target and the like after the pesticide is applied can be quickly and effectively obtained, the pesticide application effect can be quantitatively evaluated, and a reference is provided for further optimizing the pesticide spraying technology.
At present, various water-Sensitive test paper image processing software is developed abroad, wherein R.D.Fox provides a result of a WSP (Water Sensitive paper) visual grading spray covering method; pannton developed a camera/illumination system that measures the percentage of spot coverage on a WSP; cunha M evaluated the ability of several water-sensitive paper image processing software to analyze spray quality; zhu Heping developed a portable fog drop parameter measurement system based on a PC and a scanner. Although the start is late in China, a good research result is obtained, and Guo Na, Wu Asia base, Qili jun, Qibaijing, Zheng strengthening, Jiang Tao, Chun Jiang, Lianping and the like research fog drop detection methods based on image processing, when a digital image of the water-sensitive paper is obtained, the water-sensitive paper image is inclined, the software cannot automatically detect the inclination angle of the water-sensitive paper, the automatic rotation operation of the water-sensitive paper image is lacked, the region of interest of the water-sensitive paper cannot be automatically obtained, the preprocessing operation of the water-sensitive paper needs to be performed by other software, and meanwhile, when the water-sensitive paper image is segmented, the water-sensitive paper is converted into a gray image and then segmented, so that some useful information is lost in the conversion process, and the detection accuracy is not high.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention aims to provide a device and a method for measuring fog drop parameters of water-sensitive paper based on ImagePy.
In order to achieve the purpose, the invention adopts the technical scheme that:
a water-sensitive paper fog droplet parameter measuring device based on ImagePy comprises a water-sensitive paper image acquisition module, an image processing module and a fog droplet parameter statistical module;
the image processing module comprises an image automatic rotating and cutting module based on ImagePy, an image splicing module and a color image segmentation module;
the fog drop parameter statistic module comprises fog drop maximum value, minimum value, average value, median, fog drop coverage rate and fog drop number parameter statistics; wherein, the fog drop coverage rate and the fog drop median function are added on the basis of the original function of ImagePy by writing a program.
The image automatic rotary cutting module realizes automatic rotary cutting of the water-sensitive paper image through a minimum external rectangular function (minAreaRect) and a vertical boundary minimum positive rectangular function (bounding) and comprises a cutting module, a cutting module and a cutting module, wherein the cutting module is used for cutting the water-sensitive paper image; and obtaining a minimum positive rectangle wrapping the outline of the water-sensitive paper image by using boundingRect (), and obtaining a minimum oblique rectangle wrapping the outline of the water-sensitive paper image by using minAreaRect ().
The image splicing module defines img _ center as a middle 1/2 area, img [1] as a left 1/4 area, img [2] as a right 1/4 area and img [3] as an image spliced by the img [1] and the img [2] by programming for the water-sensitive paper acquired by the water-sensitive paper image acquisition module, and outputs the img [3] and the img _ center.
The color image segmentation module adopts an RGB color space model.
A measuring method of a water-sensitive paper fog droplet parameter measuring device based on ImagePy specifically comprises the following steps:
step one, acquiring a water-sensitive paper image:
1) winding and fixing the water-sensitive paper on a vertical rod which is at the same height and level with the wheat seedlings to form a cylinder, wherein an 1/2 area in the middle of the water-sensitive paper faces the direction of spraying pesticides on agricultural machinery, and a 1/4 area on the left side and a 1/4 area on the right side of the water-sensitive paper are adhered together and are places where the agricultural machinery cannot directly spray, namely the back side;
2) by changing the type of a nozzle for spraying the pesticide and the spraying pressure, the agricultural machine carrying the pesticide respectively carries out multiple spraying experiments in the test wheat field, and multiple pieces of water-sensitive paper with sequential numbers can be obtained at different positions driven by the agricultural machine in each spraying experiment;
3) pasting the water-sensitive paper obtained in the last step on the same paper, and acquiring a group of experimentally collected water-sensitive paper images through an image acquisition module;
step two, the water sensitive paper image processing process:
1) collecting the water-sensitive paper image obtained in the step 3) by using an image collection module, importing the water-sensitive paper image into a computer, and opening the water-sensitive paper image to be processed by using ImagePy software;
2) firstly, graying, binaryzation, negation, corrosion and filtering operations are carried out on the water-sensitive paper image by ImagePy software, interference of useless information is eliminated, then area analysis operation is carried out, area screening is carried out on the water-sensitive paper image, and noise which does not belong to the water-sensitive paper is filtered by an area threshold value; because each water-sensitive paper image is of a fixed size, the value is taken as a threshold value, if the value is smaller than the threshold value, the water-sensitive paper image is determined to be unnecessary noise, and the noise is filtered out, so that an area only containing the water-sensitive paper image is obtained;
3) through the automatic rotary cutting module of the water-sensitive paper image, with the help of a minimum external rectangular function (minAreaRect) and a perpendicular boundary minimum positive rectangular function (boundingRect), the automatic rotary cutting of the water-sensitive paper image area obtained in the step 2) is realized: determining the angle of the water-sensitive paper image needing to be rotated by adopting a minimum circumscribed rectangular function (minAreaRect), and realizing rotation to enable the inclined water-sensitive paper image to be corrected; obtaining an interested area by adopting a smallest bounding rectangle function (bounding rectangle) to realize cutting of the water-sensitive paper area;
4) according to the real situation of pesticide spraying in the field, an image splicing module named montage img is added into open source software ImagePy image processing software, collected water-sensitive paper images are cut into a left 1/4 area, a middle 1/2 area and a right 1/4 area of the images, and then the left 1/4 and the right 1/4 are spliced together to serve as the back of crops;
5) the water-sensitive paper image is further segmented by a color image segmentation module by adopting a color image segmentation method, and threshold values of R, G, B colors are set: r, G, B, setting a threshold value according to the color, and displaying an area in which the RGB three-channel color value in the image is smaller than the threshold value, namely a fog drop area, as white, and other areas, namely a background, as black according to the set threshold value, so as to obtain the required fog drop area;
step three, a droplet parameter measuring method:
counting fog drop parameters of the water-sensitive paper image obtained in the second step and the 5) through a fog drop parameter counting module, wherein the fog drop parameters comprise the maximum value, the minimum value, the average value, the median value, the fog drop coverage rate and the fog drop number parameter; wherein, the fog drop coverage rate and the fog drop median function are added on the basis of the original function of ImagePy by writing a program: writing a fog drop coverage program according to a formula (1); the fog drop median program calculates according to the odd number and the even number of the fog drop number, all the numbers are sorted from small to large, if the numbers are odd, the median value is directly taken, and if the numbers are even, the two numbers positioned in the middle are added and divided by 2 to obtain the median value; automatic statistics of fog droplet parameters can be realized in ImagePy software;
the droplet coverage was calculated as the percentage of the droplet coverage area to the total area of the statistic:
Figure BDA0003050214040000041
in the formula: c is the fog drop coverage rate; a. thesThe number of pixels in a fog drop area is shown; a. thepThe total pixel number of the test paper area is shown.
The area threshold value in the second step 2) is 1000000.
Compared with the prior art, the invention has the beneficial effects that:
the device integrates an image acquisition module and image processing software ImagePy, the software is composed of a set of self-defined modules, automatic detection and rotation can be carried out on a water-sensitive paper image, then color image segmentation is carried out on the water-sensitive paper image, and then the modules are used for counting and measuring fog drop parameters such as fog drop size, total fog drop number and fog drop coverage rate, so that the problems that the existing water-sensitive paper image processing software lacks preprocessing operations such as rotation of the water-sensitive paper image and the detection precision is low due to the fact that the water-sensitive paper image is firstly converted into a gray image and then segmented are solved; the method can accurately and quickly count and measure the fog drop parameters, and provides a theoretical basis for researching the model of the agricultural mechanical nozzle and the influence of the spraying pressure on the pesticide spraying system.
Drawings
FIG. 1 is a flow chart of the water-sensitive paper image processing of the present invention.
FIG. 2 is a schematic diagram of the automatic rotary cutting of water-sensitive paper images according to the present invention.
FIG. 3 is a block diagram of the water-sensitive paper image stitching process of the present invention.
FIG. 4 is a diagram showing the cutting and splicing results of the water-sensitive paper of the present invention.
Fig. 5 is a droplet parameter dialog of the present invention.
FIG. 6 is a schematic view showing the fixing of the water-sensitive paper in the experiment of the present invention.
FIG. 7 is a schematic view of the operation of the agricultural machine during the experiment of the present invention.
Detailed Description
The invention is explained in more detail below with reference to the figures and examples:
referring to fig. 1, a device for measuring fog drop parameters of water-sensitive paper based on ImagePy comprises a water-sensitive paper image acquisition module, an image processing module and a fog drop parameter statistic module;
the image acquisition module adopts a scanner.
The image processing module comprises an image automatic rotating and cutting module based on ImagePy, an image splicing module and a color image segmentation module;
the fog drop parameter statistic module comprises fog drop maximum value, minimum value, average value, median, fog drop coverage rate and fog drop number parameter statistics; wherein, the fog drop coverage rate and the fog drop median function are added on the basis of the original function of ImagePy by writing a program.
The ImagePy software is an extensible image processing framework written by Python language; and the user carries out secondary development of the software according to the requirement, writes and names a corresponding function script, runs the software, and generates a corresponding plug-in after being loaded by a loader.
Referring to fig. 2, the image automatic rotation cropping module implements automatic rotation cropping of the water-sensitive paper image through a minimum circumscribed rectangle function (minAreaRect) and a vertical boundary minimum positive rectangle function (bounding rectangle); and obtaining a minimum positive rectangle wrapping the outline of the water-sensitive paper image by using boundingRect (), and obtaining a minimum oblique rectangle wrapping the outline of the water-sensitive paper image by using minAreaRect ().
Referring to fig. 3 and 4, the image stitching module defines img _ center as a middle 1/2 area, img [1] as a left 1/4 area, img [2] as a right 1/4 area, and img [3] as an image in which img [1] and img [2] are stitched, and outputs img [3] and img _ center, for the collected water-sensitive paper.
Referring to fig. 5, the droplet parameter statistics module is to program a program for calculating droplet coverage and a droplet size intermediate value on the basis of ImagePy, and after image processing is completed, statistically measure various parameters of the droplets, including statistics of a droplet maximum value, a minimum value, an average value, a median value, a droplet coverage and a droplet number. The color image segmentation plug-in adopts an RGB color space model.
A measuring method of a water-sensitive paper fog droplet parameter measuring device based on ImagePy specifically comprises the following steps:
step one, acquiring a water-sensitive paper image:
1) winding and fixing the water-sensitive paper on a vertical rod which is at the same height and level with the wheat seedlings to form a cylinder, wherein an 1/2 area in the middle of the water-sensitive paper faces the direction of spraying pesticides on agricultural machinery, and a left 1/4 area and a right 1/4 area of the water-sensitive paper are adhered together and are places where the agricultural machinery cannot directly spray, namely the back, as shown in fig. 6;
2) by changing the type of a nozzle for spraying the pesticide and the spraying pressure, the agricultural machine carrying the pesticide carries out 15 spraying experiments in the test wheat field according to the experimental requirements, and four pieces of water-sensitive paper with the sequential reference number of A, B, C, D can be obtained at different positions driven by the agricultural machine in each spraying experiment, as shown in figure 7;
3) pasting the water-sensitive paper obtained in the last step on the same paper, and acquiring a group of experimentally collected water-sensitive paper images through an image acquisition module;
step two, the water sensitive paper image processing process:
1) collecting the water-sensitive paper image obtained in the step 3) by using an image collection module, importing the water-sensitive paper image into a computer, and opening the water-sensitive paper image to be processed by using ImagePy software;
2) firstly, graying, binaryzation, negation, corrosion and filtering operations are carried out on the water-sensitive paper image by ImagePy software, interference of useless information is eliminated, then area analysis operation is carried out, area screening is carried out on the water-sensitive paper image, and noise which does not belong to the water-sensitive paper is filtered by an area threshold value; because each water-sensitive paper image is of a fixed size, the value is taken as a threshold value, if the value is smaller than the threshold value, the water-sensitive paper image is determined to be unnecessary noise, and the noise is filtered out, so that an area only containing the water-sensitive paper image is obtained;
3) through the automatic rotary cutting module of the water-sensitive paper image, with the help of a minimum external rectangular function (minAreaRect) and a perpendicular boundary minimum positive rectangular function (boundingRect), the automatic rotary cutting of the area of the water-sensitive paper image obtained in the step 2) is realized: determining the angle of the water-sensitive paper image needing to be rotated by adopting a minimum circumscribed rectangular function (minAreaRect), and realizing rotation to enable the inclined water-sensitive paper image to be corrected; obtaining an interested area by adopting a smallest bounding rectangle function (bounding rectangle) to realize cutting of the water-sensitive paper area;
4) according to the real situation of pesticide spraying in the field, an image splicing module named montage img is added in an open source software ImagePy image processing module, collected water-sensitive paper images are cut into a left 1/4 area, a middle 1/2 area and a right 1/4 area of the images, and then the left 1/4 and the right 1/4 are spliced together to serve as the back of crops;
5) the water-sensitive paper image is further segmented by a color image segmentation module by adopting a color image segmentation method, and threshold values of R, G, B colors are set: r, G, B, setting a threshold value according to the color, and displaying an area in which the RGB three-channel color value in the image is smaller than the threshold value, namely a fog drop area, as white, and other areas, namely a background, as black according to the set threshold value, so as to obtain the required fog drop area;
step three, a droplet parameter measuring method:
counting fog drop parameters of the water-sensitive paper image obtained in the second step and the 5) through a fog drop parameter counting module, wherein the fog drop parameters comprise the maximum value, the minimum value, the average value, the median value, the fog drop coverage rate and the fog drop number; wherein, the fog drop coverage rate and the fog drop median function are added on the basis of the original function of ImagePy by writing a program: the fog drop coverage rate program is written according to a formula (1), the fog drop median program is calculated according to the odd number and the even number of the fog drop numbers, all the numbers are sequenced from small to large, if the numbers are odd numbers, the median value is directly taken, and if the numbers are even numbers, the median value is obtained by dividing the sum of the two numbers positioned in the middle by 2; the two functions are loaded into software, so that automatic statistics of fog drop parameters can be realized in ImagePy software;
the droplet coverage was calculated as the percentage of the droplet coverage area to the total area of the statistic:
Figure BDA0003050214040000081
in the formula: c is the fog drop coverage rate; a. thesThe number of pixels in a fog drop area is shown; a. thepThe total pixel number of the test paper area is shown.
The area threshold value in the second step 2) is 1000000.
The water-sensitive paper (WSP) is a simple mechanical method providing rapid assessment of spray coverage, is a yellow-surfaced coated paper that turns dark blue upon contact with liquid droplets, has the characteristics of significant color development, and is easy for image processing and storage, and is currently the most commonly used collector for mist droplets. The water sensitive paper can be used to check the droplet distribution, the density of the spray and the droplet size.
The image acquisition module adopts a scanner, the model of the scanner is preferably Epson DS-570w, the scanning breadth is A4 paper size, the scanning speed is 35 pages/70 surfaces per minute, and the WIFI function is supported; the scanner is connected with a computer, four pieces of water-sensitive paper are pasted on the same A4 paper, and the scanner scans to obtain the water-sensitive paper image collected in one experiment.
The working principle of the invention is as follows:
the method comprises the steps of automatically rotating and cutting a water-sensitive paper image through an image acquisition module and image processing software ImagePy, then carrying out image splicing and color image segmentation on the water-sensitive paper image, and further carrying out statistics on fog drop parameters such as the size of fog drops, the total fog drop number, the fog drop coverage rate and the like by using a fog drop parameter statistics module.

Claims (7)

1.一种基于ImagePy的水敏纸雾滴参数测量装置，包括水敏纸图像采集模块、图像处理模块及雾滴参数统计模块；1. A water-sensitive paper droplet parameter measurement device based on ImagePy, comprising a water-sensitive paper image acquisition module, an image processing module and a droplet parameter statistics module; 所述图像处理模块包括基于ImagePy的图像自动旋转裁剪模块、图像拼接模块、彩色图像分割模块；The image processing module includes an ImagePy-based automatic image rotation and cropping module, an image splicing module, and a color image segmentation module; 所述雾滴参数统计模块，包括雾滴最大值、最小值、平均值、中值、雾滴覆盖率以及雾滴个数参数统计；其中，雾滴覆盖率和雾滴中值功能通过编写程序在ImagePy原有功能基础上添加此两项功能。The droplet parameter statistics module includes parameter statistics of the maximum value, minimum value, average value, median value, droplet coverage, and the number of droplets; wherein, the droplet coverage and the median function of droplets are programmed by programming These two functions are added on the basis of the original functions of ImagePy. 2.根据权利要求1所述的一种基于ImagePy的水敏纸雾滴参数测量装置，其特征在于：所述图像自动旋转裁剪模块，通过最小外接矩形函数(minAreaRect)和垂直边界最小正矩形函数(boundingRect)实现水敏纸图像的自动旋转裁剪；用boundingRect()得到包裹水敏纸图像轮廓的最小正矩形，minAreaRect()得到包裹水敏纸图像轮廓的最小斜矩形。2. a kind of water-sensitive paper fog drop parameter measuring device based on ImagePy according to claim 1, is characterized in that: described image automatic rotation cropping module, by minimum circumscribed rectangle function (minAreaRect) and vertical boundary minimum regular rectangle function (boundingRect) realizes the automatic rotation and cropping of the water-sensitive paper image; use boundingRect() to get the minimum regular rectangle that wraps the outline of the water-sensitive paper image, and minAreaRect() to get the minimum oblique rectangle that wraps the outline of the water-sensitive paper image. 3.根据权利要求1所述的一种基于ImagePy的水敏纸雾滴参数测量装置，其特征在于：所述图像拼接模块，对于采集到的水敏纸，通过编程，定义img_center为中间1/2区域，img[1]为左1/4区域，img[2]为右1/4区域，img[3]为img[1]与img[2]拼接的图像，输出img[3]和img_center。3. a kind of water-sensitive paper droplet parameter measuring device based on ImagePy according to claim 1, is characterized in that: described image splicing module, for the water-sensitive paper that collects, by programming, define img_center as middle 1/ 2 area, img[1] is the left 1/4 area, img[2] is the right 1/4 area, img[3] is the image spliced with img[1] and img[2], output img[3] and img_center . 4.根据权利要求1所述的一种基于ImagePy的水敏纸雾滴参数测量装置，其特征在于：所述彩色图像分割模块，采用的是RGB颜色空间模型。4 . The device for measuring the parameters of water-sensitive paper mist droplets based on ImagePy according to claim 1 , wherein the color image segmentation module adopts an RGB color space model. 5 . 5.根据权利要求1所述的一种基于ImagePy的水敏纸雾滴参数测量装置，其特征在于：所述雾滴参数统计模块为，通过编程，在ImagePy原有基础上，编写了雾滴覆盖率及雾滴尺寸中间值的程序，在完成图像处理后，统计测量雾滴各项参数，包括雾滴最大值、最小值、平均值、中值、雾滴覆盖率以及雾滴个数的统计。5. a kind of water sensitive paper fog drop parameter measuring device based on ImagePy according to claim 1, is characterized in that: described fog drop parameter statistics module is, by programming, on the original basis of ImagePy, has written fog drop The program of the coverage ratio and the median value of the droplet size, after the image processing is completed, the parameters of the droplets are statistically measured, including the maximum value, the minimum value, the average value, the median value, the droplet coverage ratio and the number of droplets. statistics. 6.一种基于ImagePy的水敏纸雾滴参数测量装置的测量方法，具体包括以下步骤：6. a measuring method based on the ImagePy water-sensitive paper droplet parameter measuring device, specifically comprises the following steps: 步骤一、水敏纸图像的采集：Step 1. Collection of water-sensitive paper images: 1)将水敏纸缠绕固定在与麦苗同一高度水平的竖杆上形成一个圆柱体，水敏纸中间的1/2区域面向农用机械喷洒农药的方向，水敏纸左侧1/4区域和右侧1/4区域粘贴在一起，为农用机械不能直接喷洒到的地方，即背面；1) Wind and fix the water-sensitive paper on a vertical pole at the same height as the wheat seedlings to form a cylinder. The middle 1/2 area of the water-sensitive paper faces the direction of agricultural machinery spraying pesticides, and the left 1/4 area of the water-sensitive paper and the The right 1/4 area is pasted together, which is the place that agricultural machinery cannot spray directly, that is, the back; 2)通过改变喷洒农药的喷嘴型号和喷药的压力，携带农药的农用机械在试验麦田中分别进行多次喷洒实验，每次喷洒实验在农用机械驶过的不同位置可获得顺序编号的多张水敏纸；2) By changing the type of spraying nozzles and the pressure of spraying, the agricultural machinery carrying pesticides will carry out multiple spraying experiments in the experimental wheat field, and in each spraying experiment, multiple water sensitive sheets of sequential numbers can be obtained at different positions where the agricultural machinery passes by. Paper; 3)将上一步所得到的水敏纸粘贴在同一张纸上，通过图像采集模块采集得到一组实验收集的水敏纸图像；3) Paste the water-sensitive paper obtained in the previous step on the same piece of paper, and acquire a group of water-sensitive paper images collected by the experiment through the image acquisition module; 步骤二、水敏纸图像处理过程：Step 2. Image processing process of water-sensitive paper: 1)用图像采集模块采集步骤一第3)步得到的水敏纸图像，并导入到电脑中，使用ImagePy软件打开要处理的水敏纸图像；1) use the image acquisition module to collect the water-sensitive paper image obtained in step 1 and 3), and import it into a computer, and use ImagePy software to open the water-sensitive paper image to be processed; 2)利用ImagePy软件首先对水敏纸图像进行灰度化、二值化、取反、腐蚀、滤波操作，消除无用信息的干扰，再进行区域分析操作，对水敏纸图像进行区域筛选，利用area阈值滤除不属于水敏纸的噪声；由于每一张水敏纸图像都是固定大小，将此值作为阈值，小于这个值则被认定为是不需要的噪声，将其滤除，从而得到仅含有水敏纸图像的区域；2) Use ImagePy software to first perform grayscale, binarization, inversion, corrosion, and filtering operations on the water-sensitive paper image to eliminate the interference of useless information, and then perform regional analysis operations to screen the water-sensitive paper image. The area threshold filters out the noise that does not belong to the water-sensitive paper; since each water-sensitive paper image is of a fixed size, this value is used as the threshold, and if it is smaller than this value, it is considered as unnecessary noise, and it is filtered out, so as to obtain only areas containing water-sensitive paper images; 3)通过水敏纸图像自动旋转裁剪模块，借助最小外接矩形函数(minAreaRect)和垂直边界最小正矩形函数(boundingRect)，实现步骤二第2)步得到的水敏纸图像的区域自动旋转裁剪：采用最小外接矩形函数(minAreaRect)确定水敏纸图像需要旋转的角度，实现旋转，使倾斜水敏纸图像归正；采用垂直边界最小正矩形函数(boundingRect)来获取感兴趣区域，实现水敏纸区域的裁剪；3) Through the water-sensitive paper image automatic rotation and cropping module, with the help of the minimum circumscribed rectangle function (minAreaRect) and the vertical boundary minimum regular rectangle function (boundingRect), realize the automatic rotation and cropping of the area of the water-sensitive paper image obtained in step 2 (2) step: The minimum circumscribed rectangle function (minAreaRect) is used to determine the angle that the water-sensitive paper image needs to be rotated, and the rotation is realized to normalize the inclined water-sensitive paper image; cropping of the area; 4)根据田间喷施农药的真实情况，通过在开源软件ImagePy图像处理软件中添加名为montageimg的图像拼接模块，将采集到的水敏纸图像，裁剪为图像的左侧1/4区域，中间1/2区域，右侧1/4区域，再将左侧1/4与右侧1/4拼接在一起，作为农作物的背面；4) According to the real situation of pesticide spraying in the field, by adding an image stitching module named montageimg in the open source software ImagePy image processing software, the collected water sensitive paper image is cropped into the left 1/4 area of the image, and the middle 1/2 area, 1/4 area on the right, and then splicing the left 1/4 and the right 1/4 together as the back of the crop; 5)通过彩色图像分割模块，采用彩色图像分割法进一步对水敏纸图像进行分割，设置R、G、B三种颜色的阈值：R、G、B三种颜色的数值范围为0～255，根据颜色来设置阈值，并根据设置的阈值，将图像中RGB三通道颜色数值小于阈值的区域，也就是雾滴区域显示成白色，其它区域也就是背景显示成黑色，从而得到需要的雾滴区域；5) Through the color image segmentation module, the water-sensitive paper image is further segmented by the color image segmentation method, and the thresholds of the three colors of R, G, and B are set: the numerical range of the three colors of R, G, and B is 0-255, The threshold is set according to the color, and according to the set threshold, the area where the RGB three-channel color value is less than the threshold in the image, that is, the fog drop area, is displayed as white, and the other areas, that is, the background, is displayed as black, so as to obtain the required fog drop area. ; 步骤三、雾滴参数测量方法：Step 3. Droplet parameter measurement method: 将步骤二第5)步得到的水敏纸图像通过雾滴参数统计模块统计雾滴参数，包括雾滴最大值、最小值、平均值、中值、雾滴覆盖率以及雾滴个数参数统计；其中，雾滴覆盖率和雾滴中值功能通过编写程序，在ImagePy原有功能基础上添加：雾滴覆盖率程序根据公式(1)编写；雾滴中值程序则根据雾滴个数的奇偶数来计算，将所有的数按从小到大顺序排序，若为奇数则直接取中间的值，若为偶数，则把位于中间位置的两数相加除以2得到中值；即可在ImagePy软件中实现雾滴参数的自动统计；The water-sensitive paper image obtained in step 2 (5) step is used to count the fog drop parameters through the fog drop parameter statistics module, including the maximum value, minimum value, average value, median value, fog drop coverage rate and fog drop number parameter statistics of the fog drop ; Among them, the functions of fog droplet coverage and fog droplet median value are added on the basis of the original functions of ImagePy through programming: the fog droplet coverage ratio program is written according to formula (1); the fog droplet median value program is based on the number of fog droplets. Calculate the odd and even numbers, sort all the numbers in ascending order, if it is an odd number, take the middle value directly, if it is an even number, add the two numbers in the middle position and divide by 2 to get the median value; Automatic statistics of droplet parameters in ImagePy software; 雾滴覆盖率通过雾滴覆盖区域面积占统计总面积的百分比计算：The droplet coverage is calculated by the percentage of the area covered by the droplets to the total statistical area:
Figure FDA0003050214030000041
Figure FDA0003050214030000041
 式中：C为雾滴覆盖率；As为雾滴区域像素数；Ap为试纸区域总像素数。In the formula: C is the droplet coverage; As is the number of pixels in the droplet area; Ap is the total number of pixels in the test paper area. 7.根据权利要求6所述的一种基于ImagePy的水敏纸雾滴参数测量装置的测量方法，其特征在于：所述步骤二第2)步中area阈值＝1000000。7 . The measurement method of an ImagePy-based device for measuring mist droplet parameters of water-sensitive paper according to claim 6 , wherein the area threshold=1,000,000 in the second step (2) of the step 2. 8 .
CN202110485867.0A 2021-04-30 2021-04-30 A water-sensitive paper droplet parameter measurement device and its measurement method based on ImagePy Active CN113222925B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110485867.0A CN113222925B (en) 2021-04-30 2021-04-30 A water-sensitive paper droplet parameter measurement device and its measurement method based on ImagePy

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110485867.0A CN113222925B (en) 2021-04-30 2021-04-30 A water-sensitive paper droplet parameter measurement device and its measurement method based on ImagePy

Publications (2)

Publication Number Publication Date
CN113222925A true CN113222925A (en) 2021-08-06
CN113222925B CN113222925B (en) 2023-01-31

Family

ID=77091107

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110485867.0A Active CN113222925B (en) 2021-04-30 2021-04-30 A water-sensitive paper droplet parameter measurement device and its measurement method based on ImagePy

Country Status (1)

Country Link
CN (1) CN113222925B (en)

Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103460017A (en) * 2011-02-04 2013-12-18 塞通诺米/St有限责任公司 Fluid stream imaging apparatus
CN105300854A (en) * 2015-10-27 2016-02-03 潍坊学院 Fog drop parameter measurement device and fog drop parameter measurement analysis method using device
CN105753509A (en) * 2016-02-01 2016-07-13 浙江大学 Humidity sensing ceramic, and preparation method and application thereof
WO2017063128A1 (en) * 2015-10-12 2017-04-20 深圳市大疆创新科技有限公司 Ejection quality testing system, method and sampling auxiliary device
CN108197534A (en) * 2017-12-19 2018-06-22 迈巨（深圳）科技有限公司 A kind of head part's attitude detecting method, electronic equipment and storage medium
CN108717706A (en) * 2018-04-28 2018-10-30 江南大学 Semi-automatic bunchy yarn process parameter identification method based on bunchy yarn fabric
CN109470604A (en) * 2018-11-02 2019-03-15 吉林大学 Droplet distribution detection sensor and detection method with bionic surface structure
CN109946204A (en) * 2019-04-25 2019-06-28 济南大学 A fog drop collection method using the principle of camera shutter
CN110567958A (en) * 2019-09-05 2019-12-13 中国民用航空总局第二研究所 A smart phone-based fog droplet image acquisition device and method
CN110689519A (en) * 2019-08-21 2020-01-14 华南农业大学 Fog drop deposition image detection system and method based on yolo network
CN110736687A (en) * 2019-10-25 2020-01-31 华南农业大学 A portable water-sensitive test paper droplet parameter analysis equipment and analysis method thereof
CN110951833A (en) * 2018-09-26 2020-04-03 中国农业大学 A detection kit and detection method for simultaneously detecting the drift or deposition of multiple spray droplets
CN111481212A (en) * 2020-03-25 2020-08-04 北京微纳灵动科技有限公司 Robot draws blood
CN112381819A (en) * 2020-12-07 2021-02-19 云南省烟草公司昆明市公司 HSV color model-based plant protection droplet detection method

Patent Citations (14)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103460017A (en) * 2011-02-04 2013-12-18 塞通诺米/St有限责任公司 Fluid stream imaging apparatus
WO2017063128A1 (en) * 2015-10-12 2017-04-20 深圳市大疆创新科技有限公司 Ejection quality testing system, method and sampling auxiliary device
CN105300854A (en) * 2015-10-27 2016-02-03 潍坊学院 Fog drop parameter measurement device and fog drop parameter measurement analysis method using device
CN105753509A (en) * 2016-02-01 2016-07-13 浙江大学 Humidity sensing ceramic, and preparation method and application thereof
CN108197534A (en) * 2017-12-19 2018-06-22 迈巨（深圳）科技有限公司 A kind of head part's attitude detecting method, electronic equipment and storage medium
CN108717706A (en) * 2018-04-28 2018-10-30 江南大学 Semi-automatic bunchy yarn process parameter identification method based on bunchy yarn fabric
CN110951833A (en) * 2018-09-26 2020-04-03 中国农业大学 A detection kit and detection method for simultaneously detecting the drift or deposition of multiple spray droplets
CN109470604A (en) * 2018-11-02 2019-03-15 吉林大学 Droplet distribution detection sensor and detection method with bionic surface structure
CN109946204A (en) * 2019-04-25 2019-06-28 济南大学 A fog drop collection method using the principle of camera shutter
CN110689519A (en) * 2019-08-21 2020-01-14 华南农业大学 Fog drop deposition image detection system and method based on yolo network
CN110567958A (en) * 2019-09-05 2019-12-13 中国民用航空总局第二研究所 A smart phone-based fog droplet image acquisition device and method
CN110736687A (en) * 2019-10-25 2020-01-31 华南农业大学 A portable water-sensitive test paper droplet parameter analysis equipment and analysis method thereof
CN111481212A (en) * 2020-03-25 2020-08-04 北京微纳灵动科技有限公司 Robot draws blood
CN112381819A (en) * 2020-12-07 2021-02-19 云南省烟草公司昆明市公司 HSV color model-based plant protection droplet detection method

Non-Patent Citations (5)

* Cited by examiner, † Cited by third party
Title
ANLIANG WANG 等: "ImagePy: an open-source, Python-based and platform-independent software package for bioimage analysis", 《BIOIMAGE INFORMATICS》 *
CURTIS T RUEDEN 等: "ImageJ2: ImageJ for the next generation of scientic image data", 《ARXIV:1701.05940V4》 *
王浩祺 等: "白菜田不同药械的雾滴分布与农药利用率", 《调查研究》 *
郭娜 等: "基于图像处理的雾滴粒径检测方法", 《沈阳农业大学学报》 *
郭娜 等: "雾滴沉积特性参数的图像检测算法改进", 《农业工程学报》 *

Also Published As

Publication number Publication date
CN113222925B (en) 2023-01-31

Similar Documents

Publication Publication Date Title
CN102506772B (en) Method and device for quickly detecting area of leaf blade based on mobile phone
CN103190224B (en) Computer vision technique-based corn ear species test method, system and device
CN104132897B (en) A kind of nitrogenous measuring method of plant leaf blade based on handheld device and device
JP5020444B2 (en) Crop growth measuring device, crop growth measuring method, crop growth measuring program, and computer-readable recording medium recording the crop growth measuring program
CN107110754B (en) Spray quality detection device, system, method and sampling auxiliary device
CN104813993B (en) Small agricultural pests automated watch-keeping facility and method based on machine vision
CN110689519B (en) Fog drop deposition image detection system and method based on yolo network
CN101226108A (en) A detection method of droplet distribution uniformity
Marçal et al. Image processing of artificial targets for automatic evaluation of spray quality
CN106969708A (en) A kind of detection means and method of aggregate quality morphology
CN101713641A (en) Digital graphic technology-based method and device for analyzing leaf area
CN110689533B (en) Method, system and device for detecting edge covering defects of plates
CN110490826B (en) Fog drop sample image processing method in camera
CN113362276A (en) Visual detection method and system for plate
CN109886954A (en) A method for detecting defects in printed matter
CN202267464U (en) Mobile phone based device for rapidly detecting blade area
CN115687850A (en) Method and device for calculating irrigation water demand of farmland
CN114594533A (en) A method and device for video rainfall monitoring based on adaptive Gaussian mixture algorithm
CN113222925A (en) ImagePy-based water-sensitive paper fog drop parameter measuring device and measuring method thereof
CN115439763A (en) Water engineering surface crack detection method based on YOLOv5 model
Peng et al. Weed recognition using image blur information
CN200996939Y (en) Early diagnostic device for plant leaf and canopy botrytis
CN110490868B (en) Nondestructive counting method based on computer vision corn cob grain number
CN217542750U (en) Device for counting particles in liquid and measuring and analyzing morphology
CN114774253A (en) Portable spore capturing and detecting device and detecting method thereof

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant