CN115273078A - Sewage treatment method and system based on image data - Google Patents
Sewage treatment method and system based on image data Download PDFInfo
- Publication number
- CN115273078A CN115273078A CN202211205449.2A CN202211205449A CN115273078A CN 115273078 A CN115273078 A CN 115273078A CN 202211205449 A CN202211205449 A CN 202211205449A CN 115273078 A CN115273078 A CN 115273078A
- Authority
- CN
- China
- Prior art keywords
- image
- frame
- sewage treatment
- microorganism
- microorganisms
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 48
- 239000010865 sewage Substances 0.000 title claims abstract description 39
- 244000005700 microbiome Species 0.000 claims abstract description 80
- 239000010802 sludge Substances 0.000 claims abstract description 45
- 230000033001 locomotion Effects 0.000 claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 16
- 238000010586 diagram Methods 0.000 claims abstract description 16
- 230000008859 change Effects 0.000 claims abstract description 13
- 230000000694 effects Effects 0.000 claims abstract description 10
- 238000005273 aeration Methods 0.000 claims abstract description 9
- 241000894006 Bacteria Species 0.000 claims abstract description 7
- 230000004060 metabolic process Effects 0.000 claims abstract description 5
- 235000015097 nutrients Nutrition 0.000 claims abstract description 5
- 230000008569 process Effects 0.000 claims description 16
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 230000005484 gravity Effects 0.000 claims description 7
- 230000003044 adaptive effect Effects 0.000 claims description 4
- 238000006065 biodegradation reaction Methods 0.000 claims description 4
- 238000004939 coking Methods 0.000 claims description 4
- 239000002351 wastewater Substances 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 abstract description 3
- 238000001514 detection method Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 5
- 238000010191 image analysis Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000004065 wastewater treatment Methods 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 241000894007 species Species 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 241001474374 Blennius Species 0.000 description 1
- 241000195493 Cryptophyta Species 0.000 description 1
- 241000764238 Isis Species 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 230000004071 biological effect Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 230000000813 microbial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000002572 peristaltic effect Effects 0.000 description 1
- 230000000704 physical effect Effects 0.000 description 1
- 238000000746 purification Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000004062 sedimentation Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/69—Microscopic objects, e.g. biological cells or cellular parts
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/02—Aerobic processes
- C02F3/12—Activated sludge processes
-
- C—CHEMISTRY; METALLURGY
- C02—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F—TREATMENT OF WATER, WASTE WATER, SEWAGE, OR SLUDGE
- C02F3/00—Biological treatment of water, waste water, or sewage
- C02F3/34—Biological treatment of water, waste water, or sewage characterised by the microorganisms used
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/761—Proximity, similarity or dissimilarity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02W—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO WASTEWATER TREATMENT OR WASTE MANAGEMENT
- Y02W10/00—Technologies for wastewater treatment
- Y02W10/10—Biological treatment of water, waste water, or sewage
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Chemical & Material Sciences (AREA)
- Microbiology (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Biodiversity & Conservation Biology (AREA)
- Medical Informatics (AREA)
- Organic Chemistry (AREA)
- Environmental & Geological Engineering (AREA)
- Hydrology & Water Resources (AREA)
- Computing Systems (AREA)
- Water Supply & Treatment (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Computational Linguistics (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Activated Sludge Processes (AREA)
Abstract
The invention relates to the field of sewage treatment, in particular to a sewage treatment method and a sewage treatment system based on image data, which are used for obtaining activated sludge samples in different areas and obtaining multi-frame images; obtaining a target block diagram of a microorganism; performing motion analysis on each frame of image to obtain motion characteristics; carrying out shape analysis on each frame of image to obtain shape characteristics; calculating an offset distance and a shape matching degree; calculating the similarity of each target frame of the change frame image and the initial image, and when the similarity is greater than a set threshold value, determining that the microorganism is an active microorganism; counting the ratio of active microorganisms to total microorganisms in the sample, and when the ratio is smaller than a set threshold value, indicating that the activity of the activated sludge is too low, and adding a nutrient; on the contrary, if the dominant bacteria of facultative or anaerobic metabolism exist, the area in the aeration tank is selectively discharged. Namely, the scheme of the invention can more accurately treat the sewage according to the optical flow characteristics and the shape context characteristics of the microorganisms.
Description
Technical Field
The invention relates to the field of sewage treatment, in particular to a sewage treatment method and system based on image data.
Background
Sewage treatment is an important part of protecting the environment and food safety in urban drainage systems. According to statistics, at present, more than 80% of sewage in wastewater treatment plants using the activated sludge process in China is treated by the activated sludge process, and more than 85% of sewage is treated by the activated sludge process. The key of applying an activated sludge method to treat sewage is microorganisms, and the current methods for detecting the microorganisms in the activated sludge in the sewage are mainly divided into an indirect method and a direct method. The indirect method is mainly used for detection through molecular biology; indirect methods, while an accurate method, are time consuming and require expensive equipment. The direct method is that microscope observers of the sewage treatment plant observe the types and the quantity of microorganisms in the active sludge of the sewage treatment plant under different running states, and the microorganisms are observed and counted manually.
The accuracy of the microorganism counting using the microscope depends on the reading experience and attention of the observer in the reading process, the effectiveness of each operator for observing the diagnosis result of the microscope technology is different, the training process of the microscope observer is time-consuming, and the variety of the biological species of the sludge is also varied, so that the risk of misjudgment is caused. In addition, microorganisms in the sludge can move, and if the field of view of the microscope is too small, the microorganisms can be blocked and can also move out of the field of view, which brings a challenge to identification.
Disclosure of Invention
In order to solve the above technical problems, the present invention aims to provide a sewage treatment method and system based on image data, and adopts the following technical scheme:
the invention provides a sewage treatment method based on image data, which comprises the following steps:
acquiring activated sludge samples in different areas, and shooting microorganism images by using a microscope to obtain multi-frame images;
constructing a sludge microorganism recognition neural network, inputting each frame of image into the trained sludge microorganism recognition neural network, and outputting a target block diagram of microorganisms; performing motion analysis on each frame of image to obtain motion characteristics; carrying out shape analysis on each frame of image to obtain shape characteristics;
calculating an offset distance and a shape matching degree according to the obtained motion track and shape characteristics of the target block diagram of the microorganism; calculating the similarity of each target frame of the change frame image and the initial image based on the offset distance and the shape matching degree, and when the similarity is greater than a set threshold value, determining that the microorganism is an active microorganism;
counting the ratio of active microorganisms to total microorganisms in the sample, and when the ratio is smaller than a set threshold value, indicating that the activity of the activated sludge is too low, and adding a nutrient; if the dominant bacteria of facultative or anaerobic metabolism exist, the sludge is proved to be no longer adaptive to the aerobic biodegradation environment of the coking wastewater, and the selective sludge discharge is carried out in the area in the aeration tank.
Preferably, the motion characteristic obtaining process is as follows:
generating a dense light-flow graph by using the m-1 frame and the m frame as the motion analysis of the i frame;
analyzing the dense light-flow graph to obtain a connected domain of the dense light-flow graph;
and performing weighted summation on each point in the connected domain to obtain a moving gravity point, and then connecting the moving gravity points of each frame according to the time sequence to obtain a microorganism moving track graph serving as the motion characteristics of the microorganisms in a period of time.
Preferably, the shape feature obtaining process is as follows:
obtaining an edge image of a target frame by adopting a Sobel edge detection operator, uniformly taking points on the edge image to obtain sample points, then obtaining a histogram vector of each point by using a shape context descriptor, and assigning the pixel value of a background area of a non-target frame area to be black, namely the pixel value is black
And obtaining the shape characteristics.
Preferably, the offset distance is
Wherein,
centering of selected target frame in image of change frameThe coordinates of the points are determined by the coordinates of the points,
the coordinates of the center point of the target frame selected from the initial frame image are obtained.
Preferably, the shape matching degree is
Wherein K is the number of sample points,
is the histogram vector of the sample points on the initial image,
is a histogram vector of sample points on the change frame image.
Preferably, the similarity of the target frames is
Wherein D is the offset distance, C is the shape matching degree,
。
the invention also provides a sewage treatment system based on image data, which comprises a memory and a processor, wherein the processor is used for executing the steps stored in the memory for realizing the sewage treatment method based on the image data.
The invention has the beneficial effects that:
based on this application to the motion analysis and the image analysis of microorganism, compare in prior art beneficial effect and lie in combining the light stream characteristic and the shape context characteristic of microorganism, the motion state and the shape of single microorganism of more accurate estimation do benefit to subsequent preceding and back frame image matching to realize better microorganism count, be convenient for the little biological activity and the constitution of sampling statistics sample.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions and advantages of the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a method step diagram of a method for image data based wastewater treatment according to the present invention;
FIG. 2 is a block flow diagram of a method for image data based wastewater treatment according to the present invention.
Detailed Description
To further explain the technical means and effects of the present invention adopted to achieve the predetermined objects, the embodiments, structures, features and effects thereof according to the present invention will be described in detail below with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" refers to not necessarily the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention detects the sludge at the bottom of the aeration tank.
Specifically, the step flow chart of the method embodiment of the sewage treatment method based on the image data, as shown in fig. 1 and fig. 2, comprises the following steps:
the method comprises the following steps: and acquiring activated sludge samples in different areas, and shooting microorganism images by using a microscope to obtain multi-frame images.
Sampling sludge at the bottom of the aeration tank to prepare a sample, then sending the sample into an optical microscope, then shooting a multi-frame image in an ocular lens by using an RGB camera to serve as a detection object, and converting the RGB image into an HSV image, thereby facilitating subsequent analysis.
Due to the physical property of the optical lens, the resolution of the image is difficult to increase, so that only a local area in the sample can be observed; wherein the recording duration is
(unit: minute) of observation video, and empirical value taking
。
It should be noted that a great deal of research has confirmed the biological indicating ability of activated sludge microorganisms in sewage treatment, and the diversity and abundance of microorganism species in the activated sludge process are important parameters for controlling sewage treatment, which can be used to evaluate the operation state of sewage treatment plants and the purification degree of sewage, particularly, the primary microorganisms, secondary microorganisms, bacteria and algae in activated sludge. The operating state of the aeration tank of the sewage treatment plant is judged by observing the types and the number of microorganisms appearing in different operating states according to the basic rule between the types and the number of the activated sludge microorganisms and the adaptation to the water biochemical environment.
Step two: constructing a sludge microorganism recognition neural network, inputting each frame of image into the trained sludge microorganism recognition neural network, and outputting a target block diagram of microorganisms; performing motion analysis on each frame of image to obtain motion characteristics; and carrying out shape analysis on each frame of image to obtain shape characteristics.
The process of obtaining the target block diagram of the microorganism in this embodiment is as follows:
(1) Construction of sludge microorganism recognition neural network
The basic structure of the neural network in this embodiment is Yolo v5, and each frame of image observed by a microscope is input, and the result of example segmentation is output and is marked as a target block diagram a of microorganisms.
In the field of object detection, an object box may be represented as
，
Is the coordinate of the center point of the target frame,
the height of the target frame is the height of the target frame,
the width of the target frame.
(2) Construction of data set for training activated sludge detection neural network
In this embodiment, sludge samples with various microorganisms are found, images are collected, and large data labeling is arranged for a professional to label the microorganisms and their species labels with specific pixel values. 80% of images in the data set are used as a training set, 20% of images in the data set are used as a testing set, a cross entropy loss function is used, adam is used by an optimizer, and a neural network with a good recognition effect is finally obtained through training.
In this embodiment, the process of obtaining the motion characteristics of the target block diagram is as follows:
(1) And performing motion analysis on each frame of image, specifically, generating a light flow graph by using open-source and trained FlowNet2.0, wherein the FlowNet2.0 is a convolutional neural network, the input is two frames of images, the output is a dense light flow graph, and the m-1 frame and the m frame of images generate the dense light flow graph as the basis of the motion analysis of the i frame.
It should be noted that, in the dense light flow graph, the value of each pixel point on the dense light flow graph is the light flow moving toward the next frame, and the stationary background is stationary. Different HSV values represent the magnitude and direction of the light stream, green towards the upper left, and HSV values
(ii) a Orange towards the upper right corner, HSV value of
(ii) a Blue towards the bottom left, HSV value of
(ii) a Purple in the lower right corner, HSV value
。
(2) Analyzing the light flow diagram to obtain the connected domain of the light flow
According to the direction value represented by HSV value, every point in connected domain is obtained (HSV value is
) Degree of movement values with respect to four directions
The movement tendency of each point can be reflected according to the HSV value. Wherein
Wherein,
indicating taking the absolute value.
(3) And carrying out weighted summation on each point in the connected domain to obtain a moving gravity point, and then connecting the moving gravity points of each frame according to the time sequence to obtain a microorganism moving track graph so as to reflect the motion characteristics of the microorganisms in a period of time.
Wherein the coordinate value of the moving gravity center point is
Is composed of
Wherein,
the number of pixels in the connected domain.
The process of obtaining the shape feature of the target frame in this embodiment is as follows:
and analyzing the characteristics of each target in each frame of image, and using the shape context descriptor to enable the shape descriptor to have rotation invariance and scaling invariance, thereby facilitating target matching.
Specifically, a Sobel edge detection operator is used for obtaining an edge map (which is a binary map) of a target frame, then points are uniformly taken on the edge map to obtain sample points, then a shape context descriptor is used for obtaining a histogram vector of each point, and then the pixel value of a background area of a non-target frame area is assigned to be black, namely the pixel value is black
And obtaining a shape characteristic diagram T.
The process of obtaining the histogram vector is a known technology, and the method is not specifically described.
Since the microorganisms have an elliptical shape along the advancing direction, the presence of the microorganisms can be judged from the shape characteristics. The microorganisms are peristaltic when advancing, and the body shape can produce a scaling effect, so that operators of rotation invariance and scaling invariance are needed.
Step three: calculating an offset distance and a shape matching degree according to the obtained motion track and shape characteristics of the target block diagram of the microorganism; and calculating the similarity of each target frame of the change frame image and the initial image based on the offset distance and the shape matching degree, wherein when the similarity is greater than a set threshold value, the microorganism is an active microorganism.
When the number of microorganisms in the image changes, the image at the moment is matched with the initial image for detection, and the image when the image changes is called a change frame image, so that the tracking when bacteria are shielded is favorably detected, the target loss is avoided, and the detection of the microorganisms shielded by the seaweed is favorably realized.
Wherein, the microorganism in the matching change frame image, the position in the initial image prevents the repeated counting to exclude the microorganism that subsequently invades the visual field, specifically as follows:
first, an offset distance is calculated
：
Obtaining the moving track from the change frame image to the initial frame image, wherein the coordinate of the central point of the target frame selected from the change frame image is
The smaller the offset distance, the smoother the trace line, the more likely it is to be the locus of the active microorganism, the higher the likelihood of a match, and vice versa. Because the trajectory should not be abrupt but smooth over the course of the microbial walk.
Second, the degree of shape matching is calculated
Wherein K is the number of sample points,
is the histogram vector of the sample points on the initial image,
is a histogram vector of sample points on the change frame image.
It should be noted that the higher the degree of shape matching, the more likely it is that the microorganism is a previous microorganism, so that the effect of target tracking is achieved and the repeated counting is avoided.
Then, the similarity of each target frame of the change frame image and the initial image can be calculated
Empirical value taking
。
Step four: counting the ratio of active microorganisms to total microorganisms in the sample, and when the ratio is smaller than a set threshold value, indicating that the activity of the activated sludge is too low, and adding a nutrient; if the dominant bacteria of facultative or anaerobic metabolism exist, the sludge is proved to be no longer adaptive to the aerobic biodegradation environment of the coking wastewater, and the selective sludge discharge is carried out in the area in the aeration tank.
In this example, the similarity model (Sim) is normalized to ensure that the function value is (0, 1), and when the similarity is higher than the threshold value (0.5), it is considered as a viable microorganism.
The identified targets are classified into live microorganisms and dead microorganisms by whether the microorganisms move or not. And (3) eliminating microorganisms which subsequently intrude into the visual field in the counting process, and finally obtaining the active microorganism ratio of the sample:
In this example, the sludge in the aeration tank was sampled and detected based on the activated sludgeSelective sludge discharge, in particular if
Empirical value taking
If the activity of the activated sludge is too low, adding a nutrient; if dominant bacteria of facultative or anaerobic metabolism exist, the sludge is proved to be not adaptive to the aerobic biodegradation environment of the coking wastewater any more, and the selective sludge discharge is carried out on the area in the aeration tank so as to ensure the efficiency of sewage treatment.
The invention also provides a sewage treatment system based on image data, which comprises a memory and a processor, wherein the processor is used for executing the steps stored in the memory for realizing the sewage treatment method based on the image data. Since the sewage treatment method based on image data has been specifically described in the above method embodiments, it is not described herein in detail.
According to the scheme, the proportion of active microorganisms is found through image segmentation and chemical quantitative analysis of sludge microorganisms
And the image can reflect the condition of sludge loss in water. The research shows that the image information is not only related to the sludge sedimentation performance, but also can effectively predict the water quality.
The system arranged on the production line does not bear the training task of the neural network and is only used for operating the trained model, so that the occupation amount of the video memory in the test process reflects the real configuration requirement of the factory computing platform, and the occupation amount of the video memory in the test process of the algorithm is not obviously increased compared with the original algorithm, so that the algorithm can be operated in a general sewage treatment production line.
The image analysis technology comprehensively utilizes microscope technology and computer technology, the technology not only changes boring manual counting under a microscope into automatic image analysis counting, but also is widely applied to the analysis of morphological characteristics and microstructures of biological flocs and biological membranes in a sewage biological treatment system along with the continuous development of novel microscopes.
The above-mentioned embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the embodiments of the present application, and they should be construed as being included in the present application.
Claims (7)
1. The sewage treatment method based on the image data is characterized by comprising the following steps of:
acquiring activated sludge samples in different areas, and shooting microorganism images by using a microscope to obtain multi-frame images;
constructing a sludge microorganism recognition neural network, inputting each frame of image into the trained sludge microorganism recognition neural network, and outputting a target block diagram of microorganisms; performing motion analysis on each frame of image to obtain motion characteristics; carrying out shape analysis on each frame of image to obtain shape characteristics;
calculating an offset distance and a shape matching degree according to the obtained motion track and shape characteristics of the target block diagram of the microorganism; calculating the similarity of each target frame of the change frame image and the initial image based on the offset distance and the shape matching degree, wherein when the similarity is greater than a set threshold value, the microorganism is an active microorganism;
counting the ratio of active microorganisms to total microorganisms in the sample, and when the ratio is smaller than a set threshold value, indicating that the activity of the activated sludge is too low, and adding a nutrient; if the dominant bacteria of facultative or anaerobic metabolism exist, the sludge is proved to be no longer adaptive to the aerobic biodegradation environment of the coking wastewater, and the selective sludge discharge is carried out in the area in the aeration tank.
2. The image data based sewage treatment method according to claim 1, wherein the motion characteristic is obtained by:
generating a dense light flow graph by using the m-1 th frame and the m-th frame as the motion analysis of the i-th frame;
analyzing the dense light-ray diagram to obtain a connected domain of the dense light-ray diagram;
and performing weighted summation on each point in the connected domain to obtain a moving gravity point, and then connecting the moving gravity points of each frame according to the time sequence to obtain a microorganism moving track graph serving as the motion characteristics of the microorganisms in a period of time.
3. The image data-based sewage treatment method according to claim 1, wherein the shape feature acquisition process is:
obtaining an edge image of a target frame by adopting a Sobel edge detection operator, uniformly taking points on the edge image to obtain sample points, then obtaining a histogram vector of each point by using a shape context descriptor, and assigning the pixel value of a background area of a non-target frame area to be black, namely the pixel value is black
And obtaining the shape characteristics.
4. The image-data-based sewage treatment method according to claim 1, wherein the offset distance is
Wherein,
for changing the coordinates of the center point of the selected target frame in the frame image,
the coordinates of the center point of the target frame selected from the initial frame image are obtained.
5. The image-data-based sewage treatment method according to claim 1, wherein the shape matching degree is
Wherein K is the number of sample points,
is a histogram vector of sample points on the initial image,
is a histogram vector of sample points on the change frame image.
6. The image-data-based sewage treatment method according to claim 1, wherein the similarity of the target frames is
Wherein D is the offset distance, C is the shape matching degree,
。
7. image data based sewage treatment system comprising a memory and a processor, wherein the processor is configured to execute the steps stored in the memory for implementing the image data based sewage treatment method according to any of the claims 1-6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211205449.2A CN115273078A (en) | 2022-09-30 | 2022-09-30 | Sewage treatment method and system based on image data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211205449.2A CN115273078A (en) | 2022-09-30 | 2022-09-30 | Sewage treatment method and system based on image data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115273078A true CN115273078A (en) | 2022-11-01 |
Family
ID=83758032
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211205449.2A Pending CN115273078A (en) | 2022-09-30 | 2022-09-30 | Sewage treatment method and system based on image data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115273078A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115760613A (en) * | 2022-11-15 | 2023-03-07 | 江苏省气候中心 | Blue algae bloom short-time prediction method combining satellite image and optical flow method |
| CN116092078A (en) * | 2023-04-11 | 2023-05-09 | 深圳市信远环保水务有限公司 | Intelligent control system for sewage treatment |
| CN116135797A (en) * | 2023-04-19 | 2023-05-19 | 江苏海峡环保科技发展有限公司 | Intelligent control system for sewage treatment |
| CN116797557A (en) * | 2023-05-31 | 2023-09-22 | 浙江沃乐科技有限公司 | Device for intelligent sensing of anaerobic ammonia oxidation sludge activity |
| CN116935291A (en) * | 2023-09-15 | 2023-10-24 | 广东新泰隆环保集团有限公司 | Sewage treatment data real-time generation method and system |
| CN117585794A (en) * | 2024-01-19 | 2024-02-23 | 四川绿境科兴环境科技有限公司 | Sewage treatment aeration control method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103136520A (en) * | 2013-03-25 | 2013-06-05 | 苏州大学 | Shape matching and target recognition method based on PCA-SC algorithm |
| CN109919012A (en) * | 2019-01-28 | 2019-06-21 | 北控水务(中国)投资有限公司 | A kind of indicative microorganism image-recognizing method of sewage treatment based on convolutional neural networks |
| JP2020021368A (en) * | 2018-08-02 | 2020-02-06 | 三菱重工業株式会社 | Image analysis system, image analysis method and image analysis program |
| CN114529584A (en) * | 2022-02-21 | 2022-05-24 | 沈阳理工大学 | Single-target vehicle tracking method based on unmanned aerial vehicle aerial photography |
-
2022
- 2022-09-30 CN CN202211205449.2A patent/CN115273078A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103136520A (en) * | 2013-03-25 | 2013-06-05 | 苏州大学 | Shape matching and target recognition method based on PCA-SC algorithm |
| JP2020021368A (en) * | 2018-08-02 | 2020-02-06 | 三菱重工業株式会社 | Image analysis system, image analysis method and image analysis program |
| CN109919012A (en) * | 2019-01-28 | 2019-06-21 | 北控水务(中国)投资有限公司 | A kind of indicative microorganism image-recognizing method of sewage treatment based on convolutional neural networks |
| CN114529584A (en) * | 2022-02-21 | 2022-05-24 | 沈阳理工大学 | Single-target vehicle tracking method based on unmanned aerial vehicle aerial photography |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115760613A (en) * | 2022-11-15 | 2023-03-07 | 江苏省气候中心 | Blue algae bloom short-time prediction method combining satellite image and optical flow method |
| CN115760613B (en) * | 2022-11-15 | 2024-01-05 | 江苏省气候中心 | Blue algae bloom short-time prediction method combining satellite image and optical flow method |
| CN116092078A (en) * | 2023-04-11 | 2023-05-09 | 深圳市信远环保水务有限公司 | Intelligent control system for sewage treatment |
| CN116092078B (en) * | 2023-04-11 | 2023-06-09 | 深圳市信远环保水务有限公司 | Intelligent control system for sewage treatment |
| CN116135797A (en) * | 2023-04-19 | 2023-05-19 | 江苏海峡环保科技发展有限公司 | Intelligent control system for sewage treatment |
| CN116797557A (en) * | 2023-05-31 | 2023-09-22 | 浙江沃乐科技有限公司 | Device for intelligent sensing of anaerobic ammonia oxidation sludge activity |
| CN116935291A (en) * | 2023-09-15 | 2023-10-24 | 广东新泰隆环保集团有限公司 | Sewage treatment data real-time generation method and system |
| CN117585794A (en) * | 2024-01-19 | 2024-02-23 | 四川绿境科兴环境科技有限公司 | Sewage treatment aeration control method, device, equipment and storage medium |
| CN117585794B (en) * | 2024-01-19 | 2024-03-26 | 四川绿境科兴环境科技有限公司 | Sewage treatment aeration control method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115273078A (en) | Sewage treatment method and system based on image data | |
| Zhang et al. | LCU-Net: A novel low-cost U-Net for environmental microorganism image segmentation | |
| CN111178173B (en) | Target colony growth characteristic identification method | |
| Yu et al. | Floating pollutant image target extraction algorithm based on immune extremum region | |
| CN114882040B (en) | Sewage treatment detection method based on template matching | |
| Zhu et al. | Automated counting of bacterial colonies on agar plates based on images captured at near-infrared light | |
| US11807551B2 (en) | Systems and methods for treating wastewater | |
| Hiremath et al. | Automatic identification and classification of bacilli bacterial cell growth phases | |
| Inbar et al. | Analyzing the secondary wastewater-treatment process using Faster R-CNN and YOLOv5 object detection algorithms | |
| Bommanapally et al. | Self-supervised learning approach to detect corrosion products in biofilm images | |
| Zhao et al. | Segmentation of Activated Sludge Phase Contrast Microscopy Images Using U-Net Deep Learning Model. | |
| CN116343205A (en) | Automatic labeling method for fluorescence-bright field microscopic image of planktonic algae cells | |
| Hiremath et al. | Digital image analysis of cocci bacterial cells using active contour method | |
| CN117475432A (en) | Intelligent processing method for screening and sorting bacterial strains | |
| Struniawski et al. | Automated identification of soil fungi and chromista through convolutional neural networks | |
| Bonechi et al. | Segmentation of Petri plate images for automatic reporting of urine culture tests | |
| CN114037856A (en) | Identification method based on improved MSDNET and knowledge distillation | |
| Michal et al. | Machine-learning approach to microbial colony localisation | |
| Oriol et al. | Automatic identification of Collembola with deep learning techniques | |
| Men et al. | Application of support vector machine to heterotrophic bacteria colony recognition | |
| Nagro | A Systematic Literature Review of Deep Learning-Based Detection and Classification Methods for Bacterial Colonies | |
| CN116935291A (en) | Sewage treatment data real-time generation method and system | |
| Li et al. | A Deep Learning based Method for Microscopic Object Localization and Classification | |
| CN118314411B (en) | Microorganism detection method, system, equipment and medium based on image analysis | |
| Chen et al. | Research on color and shape recognition of maize diseases based on HSV and OTSU method |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20221101 |
|
| WD01 | Invention patent application deemed withdrawn after publication |