CN117036346A - Silica gel sewage treatment intelligent monitoring method based on computer vision - Google Patents
Silica gel sewage treatment intelligent monitoring method based on computer vision Download PDFInfo
- Publication number
- CN117036346A CN117036346A CN202311286294.4A CN202311286294A CN117036346A CN 117036346 A CN117036346 A CN 117036346A CN 202311286294 A CN202311286294 A CN 202311286294A CN 117036346 A CN117036346 A CN 117036346A
- Authority
- CN
- China
- Prior art keywords
- local minimum
- minimum point
- silica gel
- sewage
- top view
- 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
Links
- 239000010865 sewage Substances 0.000 title claims abstract description 170
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 title claims abstract description 143
- 239000000741 silica gel Substances 0.000 title claims abstract description 143
- 229910002027 silica gel Inorganic materials 0.000 title claims abstract description 143
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000012544 monitoring process Methods 0.000 title claims abstract description 33
- 238000011156 evaluation Methods 0.000 claims abstract description 24
- 230000011218 segmentation Effects 0.000 claims abstract description 18
- 230000009466 transformation Effects 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000009792 diffusion process Methods 0.000 claims description 22
- 230000008859 change Effects 0.000 claims description 15
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000009826 distribution Methods 0.000 claims description 14
- 238000005516 engineering process Methods 0.000 claims description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 8
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 5
- 238000003709 image segmentation Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 239000002351 wastewater Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 239000004566 building material Substances 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 229920002379 silicone rubber Polymers 0.000 description 1
- 238000003900 soil pollution Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 description 1
- 238000004065 wastewater treatment Methods 0.000 description 1
- 238000003911 water pollution Methods 0.000 description 1
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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
- G06T2207/20036—Morphological image processing
-
- 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
- G06T2207/20152—Watershed segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image data processing, and provides a silica gel sewage treatment intelligent monitoring method based on computer vision, which comprises the following steps: acquiring image data; acquiring a distance transformation graph based on the position information of the local minimum point, acquiring a binary image of the silica gel sewage top view based on the distance transformation graph, and acquiring a sewage texture coefficient of the local minimum point based on the binary image; acquiring a contour edge distance sequence of a local minimum point based on the binary image, acquiring a fuzzy evaluation index of the local minimum point based on the contour edge distance sequence of the local minimum point, acquiring a viscosity index of the local minimum point based on the sewage texture coefficient and the fuzzy evaluation index, and merging the local minimum points based on the viscosity index to acquire an optimized local minimum point; and acquiring a silica gel sewage index based on the segmentation result of the image, and monitoring the silica gel sewage treatment condition in real time. The invention avoids the phenomenon of over-segmentation of images and improves the accuracy of silica gel sewage treatment monitoring.
Description
Technical Field
The invention relates to the technical field of image data processing, in particular to an intelligent monitoring method for silica gel sewage treatment based on computer vision.
Background
The silica gel is a gel-like substance containing silicon rubber, has the characteristics of good thermal stability, high insulating property and the like, and has wide application in industries such as building materials, electronics, medical treatment and the like. With the development of society, the yield and the usage amount of silica gel are continuously increased, and correspondingly, with the expansion of the production scale of silica gel, silica gel wastewater is continuously increased, and if the silica gel wastewater is directly discharged, chemical substances and physical substances in the silica gel wastewater possibly pollute the environment, such as water pollution, soil pollution and the like. Therefore, the silica gel wastewater treatment link is very important, so that not only can the pollution to the environment be reduced and the water resource be protected, but also the green production of the industry can be promoted, and the sustainable development of the silica gel industry is promoted.
At present, a common image segmentation technology in a sewage monitoring method based on computer vision is used for completing the segmentation task of a silica gel sewage image, and the silica gel sewage treatment condition is monitored in real time. For example, a common watershed algorithm is widely applied in the field of image segmentation. However, the conventional watershed algorithm is applied to the segmentation task of the silica gel sewage image, so that the over-segmentation phenomenon is easy to occur, the accuracy of the segmentation result of the silica gel sewage area is low, and the follow-up silica gel sewage monitoring result is inaccurate.
Disclosure of Invention
The invention provides an intelligent monitoring method for silica gel sewage treatment based on computer vision, which aims to solve the problem of inaccurate silica gel sewage monitoring results, and adopts the following specific technical scheme:
the invention relates to a silica gel sewage treatment intelligent monitoring method based on computer vision, which comprises the following steps:
acquiring image data of a silica gel sewage top view;
obtaining a distance change graph of the silica gel sewage top view according to each local minimum point in the silica gel sewage top view, obtaining a binary image of the silica gel sewage top view according to a neighborhood distribution rule of each local minimum point in the distance change graph, obtaining a maximum inscribed rectangular area of each local minimum point according to an area window of each local minimum point in the binary image of the silica gel sewage top view, and obtaining a sewage texture coefficient of each local minimum point according to the maximum inscribed rectangular area of each local minimum point;
acquiring a contour edge distance sequence of each local minimum point according to a region window of each local minimum point in a binary image of the silica gel sewage top view, acquiring a fuzzy evaluation index of each local minimum point according to the contour edge distance sequence of each local minimum point, acquiring a viscosity index of each minimum point according to a sewage texture coefficient and the fuzzy evaluation index of each local minimum point, and merging the local minimum points according to the viscosity indexes to acquire optimized local minimum points;
and obtaining a segmentation result of the watershed algorithm according to the optimized local minimum point, obtaining a silica gel sewage index according to the segmentation result of the watershed algorithm, and monitoring the silica gel sewage treatment condition in real time.
Preferably, the method for obtaining the distance change map of the silica gel sewage top view according to each local minimum point in the silica gel sewage top view comprises the following steps:
the method comprises the steps of taking a distance value of each local minimum point obtained by using a watershed algorithm in a silica gel sewage top view as a first preset parameter value of each local minimum point, setting distance values of all pixel points except all local minimum points as a second preset parameter value, and replacing gray values of the pixel points with the distance value of each pixel point to obtain a distance binary image;
calculating Euclidean distance between each pixel point with the distance value of the second preset parameter value and the nearest local minimum value point in the distance binary image, replacing and updating the distance value of the pixel point by the Euclidean distance, traversing all the pixel points with the distance values of the second preset parameter value in the whole distance binary image, and marking the replaced and updated result as a distance change image of the silica gel sewage top view.
Preferably, the method for obtaining the binary image of the silica gel sewage top view according to the neighborhood distribution rule of each local minimum point in the distance change graph comprises the following steps:
taking each local minimum point in the distance change graph as a center, diffusing the pixel points in each direction until the distance value of the pixel points in each direction cannot be increased continuously, and finally, judging the pixel points stopping diffusing as diffusion boundary points;
setting the distance values of all the diffusion boundary points as a third preset parameter value, setting the distance values of the rest pixel points as a fourth preset parameter value, and recording the result after setting the distance values of all the pixel points in the image as a binary image of the silica gel sewage top view.
Preferably, the method for obtaining the maximum inscribed rectangular area of each local minimum point according to the area window to which each local minimum point belongs in the binary image of the silica gel sewage top view comprises the following steps:
obtaining a processing result of a binary image of a silica gel sewage top view by using a morphological closing operation technology, and taking the outline of a region to which each minimum point in the processing result belongs as a region window to which each local minimum point belongs;
and acquiring a maximum inscribed rectangular area of each local minimum point according to the maximum inscribed rectangle in the area where each local minimum point is located for the area window where each local minimum point is located in the binary image of the silica gel sewage top view.
Preferably, the method for obtaining the sewage texture coefficient of each local minimum point according to the largest inscribed rectangular region of each local minimum point comprises the following steps:
and acquiring a gray level co-occurrence matrix of each local minimum point according to the maximum inscribed rectangular area of each local minimum point, and taking the product of the first moment and the second moment of the gray level co-occurrence matrix of each local minimum point as the sewage texture coefficient of each local minimum point.
Preferably, the method for obtaining the contour edge distance sequence of each local minimum point according to the region window to which each local minimum point belongs in the binary image of the silica gel sewage top view comprises the following steps:
and for a region window of each local minimum point in the binary image of the silica gel sewage top view, acquiring Euclidean distances between all diffusion boundary points and the local minimum points in the region window of each local minimum point, and acquiring a contour edge distance sequence of each local minimum value according to the Euclidean distances between all diffusion boundary points and the local minimum points in a random arrangement.
Preferably, the method for obtaining the fuzzy evaluation index of each local minimum point according to the contour edge distance sequence of each local minimum point comprises the following steps:
for each local minimum point, taking the product of the square sum of low-frequency coefficients contained in a low-frequency region after discrete cosine transformation in a region window to which the local minimum point belongs and the variance of elements in a profile edge distance sequence of the local minimum point as a numerator, taking the sum of gradient amplitudes of all diffusion boundary points in the region window to which the local minimum point belongs as a denominator, and taking the ratio of the numerator to the denominator as a fuzzy evaluation index of the local minimum point.
Preferably, the method for obtaining the viscosity index of each minimum point according to the sewage texture coefficient and the fuzzy evaluation index of each local minimum point comprises the following steps:
for each local minimum point, the sewage texture coefficient of the local minimum point is used as a numerator, the fuzzy evaluation degree index of the local minimum point is used as a denominator, and the normalization result of the ratio of the numerator to the denominator is used as the viscosity index of the local minimum point.
Preferably, the method for merging the local minimum points according to the viscosity index to obtain the optimized local minimum points includes:
for each local minimum point, comparing the viscosity index of the local minimum point nearest to the local minimum point, and when the absolute value of the difference between the viscosity index of the local minimum point and the viscosity index of the local minimum point nearest to the local minimum point is smaller than a preset first threshold, merging the areas where the two local minimum points are located, and taking the local minimum point with the largest viscosity index in the two local minimum points as the merged local minimum point;
and merging each local minimum point until the absolute value of the difference between the viscosity index of all the local minimum points and the viscosity index of the nearest local minimum point is not smaller than a preset first threshold value, and taking the merged local minimum point as the optimized local minimum point.
Preferably, the method for obtaining the division result of the watershed algorithm according to the optimized local minimum point and obtaining the silica gel sewage index according to the division result of the watershed algorithm, and monitoring the silica gel sewage treatment condition in real time comprises the following steps:
obtaining a segmentation result of a silica gel sewage top view by using a watershed algorithm according to the optimized local minimum point, marking a segmentation area with viscosity index larger than a preset second threshold value as a sewage area, taking the total area of the sewage area as a molecule, taking the total area of the silica gel sewage top view as a denominator, and taking a percentage result of the ratio of the molecule to the denominator as a silica gel sewage index;
and monitoring the silica gel sewage treatment condition in real time, and when the silica gel sewage index is larger than a preset third threshold value, considering that the silica gel sewage in the water area exceeds the standard.
The beneficial effects of the invention are as follows: determining the position of a local minimum point based on a conventional watershed algorithm, performing distance transformation to obtain an area window of the local minimum point, constructing a sewage texture coefficient and a fuzzy evaluation index according to the sewage characteristics in the area window of the local minimum point, comprehensively obtaining the viscosity index of the local minimum point, and improving the selection of the local minimum point in the watershed algorithm. The method has the beneficial effects that the local minimum points are optimized by improving the selection of the local minimum points, so that the phenomenon of excessive separation easily occurs when the watershed algorithm segments the silica gel sewage top view is avoided, the segmentation quality of the silica gel sewage top view is improved, and the silica gel sewage detection precision is improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent monitoring method for silica gel sewage treatment based on computer vision according to an embodiment of the invention;
fig. 2 is a flowchart of a specific implementation of a silica gel sewage treatment intelligent monitoring method based on computer vision according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of a method for intelligent monitoring of silica gel sewage treatment based on computer vision according to an embodiment of the invention is shown, and the method comprises the following steps:
and S001, acquiring image data of a silica gel sewage top view.
Taking factors such as endurance time, load, windproof capability and the like into comprehensive consideration, DJI Mavic 3 is selected as shooting equipment, a grid type scanning route is adopted, the whole sewage discharge area is ensured to be covered comprehensively, and a Sonny QX1 camera is used for acquiring silica gel sewageResolution silica gel sewage top view. In addition, for the accuracy of subsequent analysis, the average value method is used for carrying out grey scale operation on the silica gel sewage top view, then the median filtering algorithm is used for denoising the silica gel sewage top view after the grey scale operation, finally the histogram equalization algorithm is used for limiting the image contrast,the effect of illumination on the image data is reduced. And marking the treated image as a pretreated silica gel sewage top view, wherein an average value method, a median filtering algorithm and a histogram equalization algorithm are known techniques, and redundant description is omitted.
The processed image is recorded as a pretreated silica gel sewage top view, and image data of the pretreated silica gel sewage top view is obtained.
Step S002, obtaining a distance change graph according to the silica gel sewage top view, obtaining a binary image according to the distance change graph, obtaining a maximum inscribed rectangular area according to the binary image, and obtaining a sewage texture coefficient according to the maximum inscribed rectangular area.
Under the general scene, after the silica gel sewage is discharged, the water surface is opaque and milky white, and because the silica gel sewage is strong in viscosity, the viscosity of a sewage area is high, obvious fluidity can not be presented, and meanwhile, the phenomenon that the vegetation around the water source is discolored or withered can be seen, so that the importance of sewage treatment is reflected. A specific implementation flow chart of the intelligent monitoring method for the silica gel sewage treatment is shown in fig. 2.
The watershed algorithm is a traditional image segmentation technology with more application scenes, has a good segmentation result on complex images, and is relatively simple in algorithm thought and efficient in calculation. However, the watershed algorithm is sensitive to noise in the image, and the segmentation result is easy to be subjected to over-segmentation. In order to avoid the phenomenon of over-segmentation and improve the accuracy of silica gel sewage treatment monitoring, the local minimum value point of the algorithm needs to be optimized.
The traditional watershed algorithm is utilized, the pretreated silica gel sewage top view is used as the input of the algorithm, the local minimum point in the pretreated silica gel sewage top view is used as the output of the algorithm, and the watershed algorithm is a known technology and is not redundant. At this time, the local minimum point is directly applied to the conventional watershed algorithm, the larger silica gel sewage area is divided into one connected area, and the smaller sewage area is divided into another connected area, so that an excessive phenomenon is generated, the calculated amount is increased, and the separation result is more complex.
In order to make the smaller sewage area and the larger sewage area belong to the same communication area, the obtained local minimum point is taken as an analysis object, and a distance transformation diagram of the silica gel sewage top view is constructed.
Specifically, the distance values of all the initially acquired local minimum points are set to 0, which means that the distance from itself to itself is 0, and then the distance values of all the pixel points except the local minimum points are set toHere according to the image resolution +.>Distance value +.>200, the implementer can set according to the actual situation. And replacing the gray value of each pixel point with the distance value of each pixel point, thereby obtaining a distance binary image, namely an image only comprising two distance values. For any pixel point with a distance value not being 0 in the distance binary image, calculating the Euclidean distance between the pixel point and the local minimum value point with all the distance values being 0, and selecting the distance value of the minimum value in all the Euclidean distances to the pixel point with the distance value not being 0>Updating, and traversing all pixel points with the distance value not being 0 in the distance binary image by the same method to obtain a distance transformation image of a local minimum point, namely a distance transformation image of a silica gel sewage top view.
Further, the distribution of the area around the local minimum point can be obtained by the distance transformation map, and the distribution is diffused in each direction around each local minimum point. For each diffusion direction, until the distance value of the pixel point in the direction cannot continue to increase, the pixel point that eventually stops diffusion is referred to as a diffusion boundary point. The above method can obtain a plurality of diffusion boundary points, but for each local minimum point, since diffusion is stopped when diffusion is stopped until the distance value of the pixel point cannot be increased, a plurality of discrete diffusion boundary points may exist after stopping diffusion, the distance value of the diffusion boundary point is updated to 255, and the distance value of the pixel point of the rest area is updated to 0. And updating the distance values of all the pixel points in the distance change graph, and taking the updated result as a binary image of the silica gel sewage top view.
In addition, the binary image of the silica gel sewage top view is subjected to morphological closing operation so that discrete diffusion boundary points can be connected, at the moment, the diffusion boundary points form the outline of the area to which the local minimum point belongs, and the outline of the area to which the local minimum point belongs is marked as an area window to which the local minimum point belongs. Therefore, the regional windows to which the local minimum points belong are obtained, and morphological closing operation is a known technology and redundant description is omitted.
Further, in order to analyze the surface characteristics of the silica gel sewage in the area window to which the local minimum point belongs, further construct the viscosity index of the local minimum point, and reflect the distribution density of the silica gel sewage in the area window. If the density of the silica gel sewage in the area window to which the local minimum point belongs is larger, the viscosity index of the local minimum point is larger, and the corresponding pollution degree is more serious. Meanwhile, the adjacent local minimum values are combined by comparing the distribution conditions in the region window to which the nearest neighbor local minimum value points belong, so that the subsequent excessive phenomenon is avoided. In a general scene, if the distribution density of silica gel sewage in a region window to which a local minimum point belongs is larger, the whole gray value of the region is higher, the texture features are not obvious, and the region is more blurred compared with other pollution-free water areas.
Specifically, for the area window to which each local minimum point belongs in the binary image of the silica gel sewage top view, the maximum inscribed rectangle technology is used to obtain the maximum inscribed rectangle area in the area window to which each local minimum point belongs, and the maximum inscribed rectangle technology is a known technology and is not redundant. The gray level co-occurrence matrix in the 0-degree direction is constructed based on the largest inscribed rectangular area in the area window to which each local minimum point belongs, the gray level co-occurrence matrix obtained through the area window to which each local minimum point belongs is used as the gray level co-occurrence matrix of each local minimum point, and the gray level co-occurrence matrix is a known technology and is not redundant.
Calculating the sewage texture coefficient of each local minimum point:
in the method, in the process of the invention,is->Sewage texture coefficient of local minimum point, < ->Is->First moment of gray level co-occurrence matrix of local minimum point, < ->Is->The second moment of the gray level co-occurrence matrix of each local minimum point.
When the first isThe first moment of gray level co-occurrence matrix of each local minimum point is larger, indicating +.>The texture contrast ratio in the area window to which the local minimum value points belong is higher, and the corresponding texture is clearer, so that the larger the sewage texture coefficient of the local minimum value points is, namely the smaller the distribution density of the silica gel sewage is. When->Gray scale symbiosis of individual local minimum pointsThe larger the second moment of the matrix, the description of +.>The texture in the area window to which the local minimum points belong is more complex, the larger the sewage texture coefficient of the local minimum points is, namely the smaller the distribution density of silica gel sewage is.
It should be noted that, the first moment of the gray level co-occurrence matrix of the local minimum point reflects the texture contrast of the local area, the second moment of the gray level co-occurrence matrix of the local minimum point reflects the uncertainty and complexity of the texture in the local area, and the first moment and the second moment of the gray level co-occurrence matrix are known techniques and are not redundant.
Step S003, obtaining a contour edge distance sequence according to the binary image, obtaining a fuzzy evaluation degree index according to the contour edge distance sequence, obtaining a viscosity index according to the sewage texture coefficient and the fuzzy evaluation degree index, and optimizing a local minimum point according to the viscosity index.
For the surface of the silica gel sewage in the area window of the local minimum point, the more blurred the image, the weaker the boundary sense, and the higher the similarity between the boundary sense and the area window of the surrounding local minimum point.
Specifically, the Euclidean distance from all pixel points to the local minimum point on the contour edge of the regional window to which each local minimum point belongs and the gray gradient amplitude sum of all contour edge pixel points in the regional window are calculated, and then a sequence formed by the Euclidean distances from all pixel points to the local minimum point on the contour edge of the regional window to which each local minimum point belongs according to a random arrangement mode is used as a contour edge distance sequence of each local minimum. It should be noted that, the contour edge pixel points are diffusion boundary points, the gray gradient amplitude can be obtained by calculating a Sobel operator, and the Sobel operator is a known technology and is not redundant.
Here, a fuzzy evaluation index of each local minimum point is calculated:
in the method, in the process of the invention,is->Fuzzy evaluation index of individual local minimum points,/->Is->Gray gradient amplitude sum,/-of contour edge pixel points in the region window to which the local minimum point belongs>Is->The gray value in the area window of the local minimum point is discrete cosine transformed and the square sum of low frequency coefficients in the low frequency area is +.>Is->Profile edge distance sequence of individual local minimum points +.>Variance of the values of the inner element. It should be noted that the gray gradient amplitude and the low frequency coefficient are known techniques, and redundant description is not made.
When the first isLow frequency coefficient sum of squares of the area window to which the local minimum point belongs +.>When the local minimum point is larger, the blurring evaluation index of the local minimum point is larger.When->Gradient sum +.>The smaller the image is, the more blurred the partial image is, and the greater the blur evaluation index is. When->Contour edge distance sequence of the region window to which the local minimum point belongs +.>Variance of->The larger the outline edge of the local minimum point area is, the relative tortuosity of the outline edge is indicated, namely, the less smooth the outline edge is, the more blurred the outline edge is, the blurring evaluation index is>The larger the silica gel sewage distribution density is, the higher the viscosity is.
Further, a viscosity index of each local minimum point is calculated:
in the method, in the process of the invention,is->Viscosity index of individual local minimum points, < ->For normalization function->Is->Fuzzy evaluation index of individual local minimum points,/->Is->Sewage texture coefficients for each local minimum point.
When the first isThe greater the fuzzy evaluation index of the local minimum point is, the +.>The more blurred the silica gel sewage image in the area window where the local minimum value points belong, namely the larger the distribution density of the silica gel sewage is, the larger the viscosity index of the local minimum value points is. When->The smaller the sewage texture coefficient of the local minimum point is, the +.>The more blurred the texture of the silica gel sewage in the area window of the local minimum point is, namely, the greater the distribution density of the silica gel sewage is, the greater the viscosity index of the local minimum point is.
So far, the viscosity index of each local minimum point is obtained.
Further, for the viscosity index of each local minimum point, comparing the absolute value of the difference value between the viscosity index of the local minimum point adjacent to the nearest point, and merging the local minimum values meeting the condition.
Specifically, in the firstThe local minimum point is exemplified by recording the viscosity index of the local minimum point nearest to Euclidean distance, when +.>Viscosity index of individual local minimum points +.>The absolute value of the difference between the viscosity index and the nearest neighbor local minimum point is smaller than a preset first threshold +.>When the two local minimum points can be combined, and the local minimum point coordinates corresponding to the larger viscosity index are used as the combined local minimum point coordinates, a first threshold value ∈10 is preset>Is 0.05. And merging each local minimum point until the absolute value of the difference between the viscosity index of all the local minimum points and the viscosity index of the nearest local minimum point is not smaller than a preset first threshold value, and taking the merged local minimum point as the optimized local minimum point.
Thus, the optimization of the local minimum point is completed.
Step S004, a division result of the silica gel top view is obtained by utilizing a watershed algorithm, and the silica gel pollution index is calculated to monitor the silica gel sewage treatment condition in real time.
Based on the optimized local minimum, the division of the silica gel sewage top view is completed by utilizing a watershed algorithm, which is a known technology and is not redundant. And analyzing the segmentation result, and constructing a viscosity index on the basis of a construction process of the viscosity index, wherein the viscosity index is constructed in the same mode for each segmentation area, the segmentation area with the viscosity index larger than a preset second threshold value is marked as a sewage area, and the experience value of the preset second threshold value is 0.1.
The total area of the sewage area in the silica gel sewage top view was counted and recorded asSimultaneously, the total area of the top view of the silica gel sewage is counted and is recorded as +.>Calculating the silica gel sewage index:
in the method, in the process of the invention,silica gel sewage index>Is the total area of the sewage area in the silica gel sewage top view, +.>Is the total area of the silica gel sewage top view.
Silica gel sewage index when monitoring water area imageGreater than a preset third threshold->And when the silica gel sewage in the water area is considered to exceed the standard, the empirical value of the preset third threshold value is 5%. From this, monitor the silica gel sewage index of silica gel sewage, monitor the silica gel sewage treatment condition in real time, avoid appearing the silica gel pollution phenomenon of great degree.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments. The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The intelligent monitoring method for the silica gel sewage treatment based on computer vision is characterized by comprising the following steps of:
acquiring image data of a silica gel sewage top view;
obtaining a distance change graph of the silica gel sewage top view according to each local minimum point in the silica gel sewage top view, obtaining a binary image of the silica gel sewage top view according to a neighborhood distribution rule of each local minimum point in the distance change graph, obtaining a maximum inscribed rectangular area of each local minimum point according to an area window of each local minimum point in the binary image of the silica gel sewage top view, and obtaining a sewage texture coefficient of each local minimum point according to the maximum inscribed rectangular area of each local minimum point;
acquiring a contour edge distance sequence of each local minimum point according to a region window of each local minimum point in a binary image of the silica gel sewage top view, acquiring a fuzzy evaluation index of each local minimum point according to the contour edge distance sequence of each local minimum point, acquiring a viscosity index of each minimum point according to a sewage texture coefficient and the fuzzy evaluation index of each local minimum point, and merging the local minimum points according to the viscosity indexes to acquire optimized local minimum points;
and obtaining a segmentation result of the watershed algorithm according to the optimized local minimum point, obtaining a silica gel sewage index according to the segmentation result of the watershed algorithm, and monitoring the silica gel sewage treatment condition in real time.
2. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for obtaining the distance change graph of the silica gel sewage top view according to each local minimum point in the silica gel sewage top view is as follows:
the method comprises the steps of taking a distance value of each local minimum point obtained by using a watershed algorithm in a silica gel sewage top view as a first preset parameter value of each local minimum point, setting distance values of all pixel points except all local minimum points as a second preset parameter value, and replacing gray values of the pixel points with the distance value of each pixel point to obtain a distance binary image;
calculating Euclidean distance between each pixel point with the distance value of the second preset parameter value and the nearest local minimum value point in the distance binary image, replacing and updating the distance value of the pixel point by the Euclidean distance, traversing all the pixel points with the distance values of the second preset parameter value in the whole distance binary image, and marking the replaced and updated result as a distance change image of the silica gel sewage top view.
3. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for obtaining the binary image of the silica gel sewage top view according to the neighborhood distribution rule of each local minimum point in the distance change graph is as follows:
taking each local minimum point in the distance change graph as a center, diffusing the pixel points in each direction until the distance value of the pixel points in each direction cannot be increased continuously, and finally, judging the pixel points stopping diffusing as diffusion boundary points;
setting the distance values of all the diffusion boundary points as a third preset parameter value, setting the distance values of the rest pixel points as a fourth preset parameter value, and recording the result after setting the distance values of all the pixel points in the image as a binary image of the silica gel sewage top view.
4. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for obtaining the largest inscribed rectangular area of each local minimum point according to the area window to which each local minimum point belongs in the binary image of the silica gel sewage top view comprises the following steps:
obtaining a processing result of a binary image of a silica gel sewage top view by using a morphological closing operation technology, and taking the outline of a region to which each minimum point in the processing result belongs as a region window to which each local minimum point belongs;
and acquiring a maximum inscribed rectangular area of each local minimum point according to the maximum inscribed rectangle in the area where each local minimum point is located for the area window where each local minimum point is located in the binary image of the silica gel sewage top view.
5. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for obtaining the sewage texture coefficient of each local minimum point according to the largest inscribed rectangular region of each local minimum point is as follows:
and acquiring a gray level co-occurrence matrix of each local minimum point according to the maximum inscribed rectangular area of each local minimum point, and taking the product of the first moment and the second moment of the gray level co-occurrence matrix of each local minimum point as the sewage texture coefficient of each local minimum point.
6. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for obtaining the contour edge distance sequence of each local minimum point according to the area window to which each local minimum point belongs in the binary image of the silica gel sewage top view comprises the following steps:
and for a region window of each local minimum point in the binary image of the silica gel sewage top view, acquiring Euclidean distances between all diffusion boundary points and the local minimum points in the region window of each local minimum point, and acquiring a contour edge distance sequence of each local minimum value according to the Euclidean distances between all diffusion boundary points and the local minimum points in a random arrangement.
7. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for obtaining the fuzzy evaluation index of each local minimum point according to the contour edge distance sequence of each local minimum point is as follows:
for each local minimum point, taking the product of the square sum of low-frequency coefficients contained in a low-frequency region after discrete cosine transformation in a region window to which the local minimum point belongs and the variance of elements in a profile edge distance sequence of the local minimum point as a numerator, taking the sum of gradient amplitudes of all diffusion boundary points in the region window to which the local minimum point belongs as a denominator, and taking the ratio of the numerator to the denominator as a fuzzy evaluation index of the local minimum point.
8. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for obtaining the viscosity index of each minimum point according to the sewage texture coefficient and the fuzzy evaluation index of each local minimum point is as follows:
for each local minimum point, the sewage texture coefficient of the local minimum point is used as a numerator, the fuzzy evaluation degree index of the local minimum point is used as a denominator, and the normalization result of the ratio of the numerator to the denominator is used as the viscosity index of the local minimum point.
9. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for merging the local minimum points according to the viscosity index to obtain the optimized local minimum points is as follows:
for each local minimum point, comparing the viscosity index of the local minimum point nearest to the local minimum point, and when the absolute value of the difference between the viscosity index of the local minimum point and the viscosity index of the local minimum point nearest to the local minimum point is smaller than a preset first threshold, merging the areas where the two local minimum points are located, and taking the local minimum point with the largest viscosity index in the two local minimum points as the merged local minimum point;
and merging each local minimum point until the absolute value of the difference between the viscosity index of all the local minimum points and the viscosity index of the nearest local minimum point is not smaller than a preset first threshold value, and taking the merged local minimum point as the optimized local minimum point.
10. The intelligent monitoring method for silica gel sewage treatment based on computer vision according to claim 1, wherein the method for obtaining the division result of the watershed algorithm according to the optimized local minimum point, obtaining the silica gel sewage index according to the division result of the watershed algorithm, and monitoring the condition of silica gel sewage treatment in real time is as follows:
obtaining a segmentation result of a silica gel sewage top view by using a watershed algorithm according to the optimized local minimum point, marking a segmentation area with viscosity index larger than a preset second threshold value as a sewage area, taking the total area of the sewage area as a molecule, taking the total area of the silica gel sewage top view as a denominator, and taking a percentage result of the ratio of the molecule to the denominator as a silica gel sewage index;
and monitoring the silica gel sewage treatment condition in real time, and when the silica gel sewage index is larger than a preset third threshold value, considering that the silica gel sewage in the water area exceeds the standard.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311286294.4A CN117036346B (en) | 2023-10-08 | 2023-10-08 | Silica gel sewage treatment intelligent monitoring method based on computer vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311286294.4A CN117036346B (en) | 2023-10-08 | 2023-10-08 | Silica gel sewage treatment intelligent monitoring method based on computer vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117036346A true CN117036346A (en) | 2023-11-10 |
| CN117036346B CN117036346B (en) | 2024-01-26 |
Family
ID=88632183
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311286294.4A Active CN117036346B (en) | 2023-10-08 | 2023-10-08 | Silica gel sewage treatment intelligent monitoring method based on computer vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117036346B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117649414A (en) * | 2024-01-30 | 2024-03-05 | 天津工大纺织助剂有限公司 | Textile auxiliary production wastewater treatment equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101493932A (en) * | 2009-03-05 | 2009-07-29 | 西安电子科技大学 | Watershed texture imaging segmenting method based on morphology Haar small wave texture gradient extraction |
| US20160156858A1 (en) * | 2014-12-02 | 2016-06-02 | Seek Thermal, Inc. | Image adjustment based on locally flat scenes |
| EP3188127A1 (en) * | 2015-12-29 | 2017-07-05 | Laboratoires Bodycad Inc. | Method and system for performing bone multi-segmentation in imaging data |
| CN109166098A (en) * | 2018-07-18 | 2019-01-08 | 上海理工大学 | Work-piece burr detection method based on image procossing |
| CN112233136A (en) * | 2020-11-03 | 2021-01-15 | 上海西井信息科技有限公司 | Method, system, equipment and storage medium for alignment of container trucks based on binocular recognition |
| CN115457004A (en) * | 2022-09-22 | 2022-12-09 | 山东华太新能源电池有限公司 | Intelligent detection method of zinc paste based on computer vision |
-
2023
- 2023-10-08 CN CN202311286294.4A patent/CN117036346B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101493932A (en) * | 2009-03-05 | 2009-07-29 | 西安电子科技大学 | Watershed texture imaging segmenting method based on morphology Haar small wave texture gradient extraction |
| US20160156858A1 (en) * | 2014-12-02 | 2016-06-02 | Seek Thermal, Inc. | Image adjustment based on locally flat scenes |
| EP3188127A1 (en) * | 2015-12-29 | 2017-07-05 | Laboratoires Bodycad Inc. | Method and system for performing bone multi-segmentation in imaging data |
| CN109166098A (en) * | 2018-07-18 | 2019-01-08 | 上海理工大学 | Work-piece burr detection method based on image procossing |
| CN112233136A (en) * | 2020-11-03 | 2021-01-15 | 上海西井信息科技有限公司 | Method, system, equipment and storage medium for alignment of container trucks based on binocular recognition |
| CN115457004A (en) * | 2022-09-22 | 2022-12-09 | 山东华太新能源电池有限公司 | Intelligent detection method of zinc paste based on computer vision |
Non-Patent Citations (1)
| Title |
|---|
| 林振荣;黎嘉诚;刘九畅;俞鹏飞;李建民;: "基于模糊逻辑和区域合并的分水岭变换图像分割", 南昌大学学报(工科版), no. 01 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117649414A (en) * | 2024-01-30 | 2024-03-05 | 天津工大纺织助剂有限公司 | Textile auxiliary production wastewater treatment equipment |
| CN117649414B (en) * | 2024-01-30 | 2024-04-09 | 天津工大纺织助剂有限公司 | Textile auxiliary production wastewater treatment equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117036346B (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114862862B (en) | Pump body cold shut defect identification method and system based on image processing | |
| CN117036346B (en) | Silica gel sewage treatment intelligent monitoring method based on computer vision | |
| CN116740070B (en) | Plastic pipeline appearance defect detection method based on machine vision | |
| CN115861291B (en) | Chip circuit board production defect detection method based on machine vision | |
| CN111582111B (en) | Cell component segmentation method based on semantic segmentation | |
| CN111402267B (en) | Segmentation method, device and terminal of epithelial cell nuclei in prostate cancer pathological image | |
| CN116385450B (en) | PS sheet wear resistance detection method based on image processing | |
| Qu et al. | Lining seam elimination algorithm and surface crack detection in concrete tunnel lining | |
| CN116309600B (en) | Environment-friendly textile quality detection method based on image processing | |
| CN115131354B (en) | Laboratory plastic film defect detection method based on optical means | |
| CN112215790A (en) | KI67 index analysis method based on deep learning | |
| Xie et al. | A fast threshold segmentation method for froth image base on the pixel distribution characteristic | |
| CN116630813B (en) | Highway road surface construction quality intelligent detection system | |
| CN116883408B (en) | Integrating instrument shell defect detection method based on artificial intelligence | |
| Mubashshira et al. | An unsupervised approach for road surface crack detection | |
| CN110084818B (en) | Dynamic down-sampling image segmentation method | |
| CN117542488B (en) | Intelligent processing method for brain tumor CT data | |
| CN116703787B (en) | Building construction safety risk early warning method and system | |
| Xu et al. | Random-valued impulse noise removal using adaptive ranked-ordered impulse detector | |
| CN101114341A (en) | Preprocess method for engineering drawing vectorization recognition system | |
| CN117129527A (en) | Urban road paving quality detection method and system | |
| CN116596911A (en) | Underwater planar structure sonar image crack quantification method | |
| Zhao et al. | The combined cloud model for edge detection | |
| Li et al. | Road crack detection and quantification based on segmentation network using architecture of matrix | |
| Eesa et al. | Comparison of the Methods of Image Slicing after Initial Image Processing Using the Statistical Confidence Limits |
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 |