A production monitoring image processing method for mixed fertilizer

By collecting overall monitoring images in the production of mixed fertilizers, removing background areas and using pixel point screening models to identify unqualified particles, the problem of monitoring unqualified particles in the production of mixed fertilizers is solved, and production quality and accuracy are improved.

CN117935148BActive Publication Date: 2024-11-15青岛宇慧绿色工贸有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410012253.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-01-04
Publication Date
2024-11-15
Estimated Expiration
2044-01-04

AI Technical Summary

Technical Problem

In the production process of mixed fertilizers, it is difficult for the existing technology to effectively monitor and analyze unqualified particles, resulting in poor fertilizer work and reducing controlled release effect.

Method used

A hybrid fertilizer production monitoring image processing method is adopted. By collecting the overall monitoring image, removing the background area, determining the unqualified particle area, and using the pixel point screening model to determine the unqualified particle interval, and uploading it to the user terminal. The method includes calculating pixel change value of rectangular area and paperform area, constructing background pixel criteria, and simplifying the process of removing background noise.

Benefits of technology

The accuracy and quality of mixed fertilizer production monitoring is improved, the impact of background noise on image quality is reduced, and the accurate identification and monitoring of unqualified particles in the production process is ensured.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117935148B_ABST
    Figure CN117935148B_ABST
Patent Text Reader

Abstract

The invention discloses a method for processing production monitoring images of mixed fertilizers, belongs to the field of image processing technology, and comprises the following steps: S1, collecting an overall monitoring image of mixed fertilizers on a production line; S2, generating a local monitoring image of mixed fertilizers; S3, determining an unqualified mixed fertilizer particle area in the local monitoring image of the mixed fertilizers, and uploading the unqualified mixed fertilizer particle area to a user terminal. The invention performs pixel point analysis and processing on the local monitoring image with the background area removed, determines the unqualified mixed fertilizer particle area in the local monitoring image, provides a basis for users to monitor the production of mixed fertilizers, and improves the production quality of mixed fertilizers.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention belongs to the technical field of image processing, and in particular relates to an image processing method for production monitoring of mixed fertilizer. Background Art

[0002] Production is the core of manufacturing enterprises. All aspects of life are inseparable from production. Every industry must monitor and analyze products during product production. In the production process of mixed fertilizers and the preparation process of controlled-release fertilizers, the quality of mixed fertilizers, especially the degree of qualification, is an important indicator. Unqualified mixed fertilizers produced will lead to poor fertilizer working effects and reduce the controlled-release effect. Therefore, it is necessary to collect production images of mixed fertilizers for observation and analysis, determine the unqualified particles of mixed fertilizers, and ensure the production quality of mixed fertilizers. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes an image processing method for production monitoring of mixed fertilizer.

[0004] The technical solution of the present invention is: a method for processing images for monitoring production of mixed fertilizer comprises the following steps:

[0005] S1. Collect the overall monitoring image of the mixed fertilizer on the production line;

[0006] S2, removing the background area of ​​the overall monitoring image of the mixed fertilizer to generate a local monitoring image of the mixed fertilizer;

[0007] S3. Determine an unqualified mixed fertilizer particle area in the local monitoring image of the mixed fertilizer, and upload the unqualified mixed fertilizer particle area to the user terminal.

[0008] Furthermore, S2 includes the following sub-steps:

[0009] S21, in the overall monitoring image of the mixed fertilizer, determining a rectangular area and a round-shaped area;

[0010] S22, determining a pixel change value between the rectangular area and the round-shaped area according to the pixel points of the rectangular area and the pixel points of the round-shaped area;

[0011] S23, determine whether the pixel change value of the rectangular area and the circular area is greater than or equal to 0.5, if so, proceed to S24, otherwise proceed to S25;

[0012] S24, draw a first background pixel criterion, take the pixel point area in the round-shaped area that meets the first background pixel criterion as the background area, and proceed to S26;

[0013] S25, drawing a second background pixel criterion, taking a pixel point area in the overall monitoring image that meets the second background pixel criterion as a background area, and proceeding to S26;

[0014] S26, removing the background area of ​​the overall monitoring image of the mixed fertilizer to generate a local monitoring image of the mixed fertilizer.

[0015] The beneficial effect of the above further scheme is: in the present invention, when removing the background noise of the overall monitoring image, the overall monitoring image is first split into a rectangular area at the center position and a round-shaped area at the edge position, and the pixel point changes between the rectangular area and the round-shaped area, that is, the pixel change value, are calculated. If the pixel change value is large, it means that there is a large change in the pixel points between the rectangular area and the round-shaped area, and the background area only exists in the round-shaped area. Therefore, a first background pixel criterion is constructed, and the pixel points that meet the first background pixel criterion are selected in the round-shaped area as the background area; on the contrary, if the pixel change value is small, it means that both the rectangular area and the round-shaped area may have background noise, so a second background pixel criterion is constructed to filter the background area from the overall monitoring image. Such a background screening process can avoid directly calculating all the pixels of the overall monitoring image and simplify the algorithm flow.

[0016] Further, in S21, the specific method for determining the rectangular area and the round-shaped area is: taking the centroid of the overall monitoring image of the mixed fertilizer as the center of the rectangular area, drawing a circle with a length of And the width is The rectangular area of ​​the overall monitoring image is taken as the round-shaped area except the rectangular area; wherein L represents the length of the overall monitoring image, and W represents the width of the overall monitoring image.

[0017] Furthermore, in S22, the calculation formula of the pixel change value C between the rectangular area and the round-shaped area is: Where H m Represents the hue value of the mth pixel in the rectangular area, S m Indicates the saturation of the mth pixel in the rectangular area, V m Indicates the brightness of the mth pixel in the rectangular area, H n Indicates the hue value of the nth pixel in the round-shaped area, S n Indicates the saturation of the nth pixel in the round-shaped area, V n represents the brightness of the nth pixel in the circular area, M represents the number of pixels in the rectangular area, N represents the number of pixels in the circular area, max(·) represents the maximum value operation, min(·) represents the minimum value operation, and exp(·) represents the exponential operation.

[0018] Further, in S24, the expression of the first background pixel criterion is: Where H n Indicates the hue value of the nth pixel in the round-shaped area, S nIndicates the saturation of the nth pixel in the round-shaped area, V n Indicates the brightness of the nth pixel in the circular area, max(·) indicates the maximum value operation, and min(·) indicates the minimum value operation.

[0019] Further, in S25, the expression of the second background pixel criterion is: Where H k represents the hue value of the kth pixel in the overall monitoring image, S k Indicates the saturation of the kth pixel in the overall monitoring image, V k represents the brightness of the kth pixel in the overall monitoring image, K represents the number of pixels in the overall monitoring image, max(·) represents the maximum value operation, and min(·) represents the minimum value operation.

[0020] Furthermore, S3 includes the following sub-steps:

[0021] S31, constructing a pixel point screening model;

[0022] S32, determining an unqualified pixel interval according to a pixel screening model;

[0023] S33, taking the pixel points whose pixel values ​​in the local monitoring image belong to the unqualified pixel point interval as the unqualified mixed fertilizer particle area.

[0024] The beneficial effect of the above further scheme is: in the present invention, the pixel point screening model calculates the pixel values ​​of all pixels in the local monitoring image, and then uses the pixel point screening model to determine an interval to screen the area where unqualified mixed particles are located. Such a process can traverse each pixel point, and the determined unqualified pixel point interval is also accurate.

[0025] Furthermore, in S31, the expression of the pixel point screening model F is: ; In the formula, x l represents the pixel value of the lth pixel in the local monitoring image, L represents the number of pixels in the local monitoring image, and min(·) represents the minimum value operation.

[0026] Furthermore, in S32, the calculation formula of the left endpoint a of the unqualified pixel point interval is: ; Where F represents the pixel screening model, τ represents the standard deviation between all pixels in the local monitoring image, and c represents a constant;

[0027] In S32, the calculation formula of the right endpoint b of the unqualified pixel point interval is: .

[0028] The beneficial effects of the present invention are as follows: the present invention discloses a method for processing production monitoring images of mixed fertilizers. Since the particles of mixed fertilizers are relatively small, if there are background noise points in the collected overall monitoring image, it will have a great impact on the processing results of the production monitoring images. Therefore, the background of the production monitoring images of the mixed fertilizers is removed to reduce the impact of the background noise points on the image quality and improve the processing accuracy of the production monitoring images. In addition, the present invention also performs pixel point analysis and processing on the local monitoring images with the background removed to determine the area of ​​unqualified mixed fertilizer particles in the local monitoring images, thereby providing a basis for users to monitor the production of mixed fertilizers and improving the quality of mixed fertilizer production. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Figure 1 Flowchart of the image processing method for monitoring the production of mixed fertilizers. DETAILED DESCRIPTION

[0030] The embodiments of the present invention will be further described below in conjunction with the accompanying drawings.

[0031] like Figure 1 As shown, the present invention provides a method for processing images for monitoring production of mixed fertilizer, comprising the following steps:

[0032] S1. Collect the overall monitoring image of the mixed fertilizer on the production line;

[0033] S2, removing the background area of ​​the overall monitoring image of the mixed fertilizer to generate a local monitoring image of the mixed fertilizer;

[0034] S3. Determine an unqualified mixed fertilizer particle area in the local monitoring image of the mixed fertilizer, and upload the unqualified mixed fertilizer particle area to the user terminal.

[0035] In this embodiment of the present invention, S2 includes the following sub-steps:

[0036] S21, in the overall monitoring image of the mixed fertilizer, determining a rectangular area and a round-shaped area;

[0037] S22, determining a pixel change value between the rectangular area and the round-shaped area according to the pixel points of the rectangular area and the pixel points of the round-shaped area;

[0038] S23, determine whether the pixel change value of the rectangular area and the circular area is greater than or equal to 0.5, if so, proceed to S24, otherwise proceed to S25;

[0039] S24, draw a first background pixel criterion, take the pixel point area in the round-shaped area that meets the first background pixel criterion as the background area, and proceed to S26;

[0040] S25, drawing a second background pixel criterion, taking a pixel point area in the overall monitoring image that meets the second background pixel criterion as a background area, and proceeding to S26;

[0041] S26, removing the background area of ​​the overall monitoring image of the mixed fertilizer to generate a local monitoring image of the mixed fertilizer.

[0042] In the present invention, when removing the background noise of the overall monitoring image, the overall monitoring image is first split into a rectangular area at the center and a round-shaped area at the edge, and the pixel change between the rectangular area and the round-shaped area, that is, the pixel change value, is calculated. If the pixel change value is large, it means that the pixel points between the rectangular area and the round-shaped area have changed greatly, and the background area only exists in the round-shaped area. Therefore, a first background pixel criterion is constructed, and the pixels that meet the first background pixel criterion are selected in the round-shaped area as the background area; on the contrary, if the pixel change value is small, it means that both the rectangular area and the round-shaped area may have background noise, so a second background pixel criterion is constructed to filter the background area from the overall monitoring image. Such a background screening process can avoid directly calculating all the pixels of the overall monitoring image and simplify the algorithm flow.

[0043] In the embodiment of the present invention, in S21, the specific method for determining the rectangular area and the round-shaped area is: taking the centroid of the overall monitoring image of the mixed fertilizer as the center of the rectangular area, drawing a rectangular area with a length of And the width is The rectangular area of ​​the overall monitoring image is taken as the round-shaped area except the rectangular area; wherein L represents the length of the overall monitoring image, and W represents the width of the overall monitoring image.

[0044] In the embodiment of the present invention, in S22, the calculation formula of the pixel change value C between the rectangular area and the round-shaped area is: Where H m Represents the hue value of the mth pixel in the rectangular area, S m Indicates the saturation of the mth pixel in the rectangular area, V m Indicates the brightness of the mth pixel in the rectangular area, H n Indicates the hue value of the nth pixel in the round-shaped area, S n Indicates the saturation of the nth pixel in the round-shaped area, V n represents the brightness of the nth pixel in the circular area, M represents the number of pixels in the rectangular area, N represents the number of pixels in the circular area, max(·) represents the maximum value operation, min(·) represents the minimum value operation, and exp(·) represents the exponential operation.

[0045] In the embodiment of the present invention, in S24, the expression of the first background pixel criterion is: Where Hn Indicates the hue value of the nth pixel in the round-shaped area, S n Indicates the saturation of the nth pixel in the round-shaped area, V n Indicates the brightness of the nth pixel in the circular area, max(·) indicates the maximum value operation, and min(·) indicates the minimum value operation.

[0046] In the embodiment of the present invention, in S25, the expression of the second background pixel criterion is: Where H k represents the hue value of the kth pixel in the overall monitoring image, S k Indicates the saturation of the kth pixel in the overall monitoring image, V k represents the brightness of the kth pixel in the overall monitoring image, K represents the number of pixels in the overall monitoring image, max(·) represents the maximum value operation, and min(·) represents the minimum value operation.

[0047] In this embodiment of the present invention, S3 includes the following sub-steps:

[0048] S31, constructing a pixel point screening model;

[0049] S32, determining an unqualified pixel interval according to a pixel screening model;

[0050] S33, taking the pixel points whose pixel values ​​in the local monitoring image belong to the unqualified pixel point interval as the unqualified mixed fertilizer particle area.

[0051] In the present invention, the pixel point screening model calculates the pixel values ​​of all pixels in the local monitoring image, and then uses the pixel point screening model to determine an interval to screen the area where unqualified mixed particles are located. This process can traverse each pixel point, and the determined unqualified pixel point interval is also accurate.

[0052] In the embodiment of the present invention, in S31, the expression of the pixel point screening model F is: ; In the formula, x l represents the pixel value of the lth pixel in the local monitoring image, L represents the number of pixels in the local monitoring image, and min(·) represents the minimum value operation.

[0053] In the embodiment of the present invention, in S32, the calculation formula of the left endpoint a of the unqualified pixel point interval is: ; Where F represents the pixel screening model, τ represents the standard deviation between all pixels in the local monitoring image, and c represents a constant;

[0054] In S32, the calculation formula of the right endpoint b of the unqualified pixel point interval is: .

[0055] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and should be understood that the protection scope of the present invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific variations and combinations that do not deviate from the essence of the present invention based on the technical revelations disclosed by the present invention, and these variations and combinations are still within the protection scope of the present invention.

Claims

1. A method for image processing of production monitoring of mixed fertilizer, characterized in that: The following steps are involved: S1. Collect the overall monitoring image of the mixed fertilizer on the production line; S2, removing the background area of ​​the overall monitoring image of the mixed fertilizer to generate a local monitoring image of the mixed fertilizer; S3, determining the unqualified mixed fertilizer particle area of ​​the local monitoring image of the mixed fertilizer, and uploading the unqualified mixed fertilizer particle area to the user terminal; The S2 comprises the following sub-steps: S21, in the overall monitoring image of the mixed fertilizer, determining a rectangular area and a round-shaped area; S22, determining a pixel change value between the rectangular area and the round-shaped area according to the pixel points of the rectangular area and the pixel points of the round-shaped area; S23, determine whether the pixel change value of the rectangular area and the circular area is greater than or equal to 0.5, if so, proceed to S24, otherwise proceed to S25; S24, draw a first background pixel criterion, take the pixel point area in the round-shaped area that meets the first background pixel criterion as the background area, and proceed to S26; S25, drawing a second background pixel criterion, taking a pixel point area in the overall monitoring image that meets the second background pixel criterion as a background area, and proceeding to S26; S26, removing the background area of ​​the overall monitoring image of the mixed fertilizer to generate a local monitoring image of the mixed fertilizer; The S3 comprises the following sub-steps: S31, constructing a pixel point screening model; S32, determining an unqualified pixel interval according to a pixel screening model; S33, taking the pixel points whose pixel values ​​in the local monitoring image belong to the unqualified pixel point interval as the unqualified mixed fertilizer particle area; In S24, the expression of the first background pixel criterion is: Where H n Indicates the hue value of the nth pixel in the round-shaped area, S n Indicates the saturation of the nth pixel in the round-shaped area, V n represents the brightness of the nth pixel in the circular area, max(·) represents the maximum value operation, min(·) represents the minimum value operation, and N represents the number of pixels in the circular area; In S25, the expression of the second background pixel criterion is: Where H k represents the hue value of the kth pixel in the overall monitoring image, S k Indicates the saturation of the kth pixel in the overall monitoring image, V k represents the brightness of the kth pixel in the overall monitoring image, K represents the number of pixels in the overall monitoring image, max(·) represents the maximum value operation, and min(·) represents the minimum value operation; In S31, the expression of the pixel point screening model F is: ; In the formula, x l represents the pixel value of the lth pixel in the local monitoring image, L represents the number of pixels in the local monitoring image, and min(·) represents the minimum value operation.

2. The method for monitoring the production of mixed fertilizer according to claim 1, characterized in that: In the step S21, the specific method for determining the rectangular area and the round-shaped area is as follows: taking the centroid of the overall monitoring image of the mixed fertilizer as the center of the rectangular area, drawing a rectangular area with a length of And the width is The rectangular area of ​​the overall monitoring image is taken as the round-shaped area except the rectangular area; wherein L represents the length of the overall monitoring image, and W represents the width of the overall monitoring image.

3. The production monitoring image processing method of mixed fertilizer according to claim 1 is characterized in that, In S22, the calculation formula of the pixel change value C between the rectangular area and the round-shaped area is: ; In the formula, H m Represents the hue value of the mth pixel in the rectangular area, S m Indicates the saturation of the mth pixel in the rectangular area, V m Indicates the brightness of the mth pixel in the rectangular area, H n Indicates the hue value of the nth pixel in the round-shaped area, S n Indicates the saturation of the nth pixel in the round-shaped area, V n represents the brightness of the nth pixel in the circular area, M represents the number of pixels in the rectangular area, N represents the number of pixels in the circular area, max(·) represents the maximum value operation, min(·) represents the minimum value operation, and exp(·) represents the exponential operation.

4. The production monitoring image processing method of mixed fertilizer according to claim 1, characterized in that: In the above S32, the calculation formula of the left endpoint a of the unqualified pixel point interval is: ; Where F represents the pixel screening model, τ represents the standard deviation between all pixels in the local monitoring image, and c represents a constant; In the above S32, the calculation formula of the right endpoint b of the unqualified pixel point interval is: .