CN111339907A - Pollution discharge identification method and device based on image identification technology - Google Patents

Pollution discharge identification method and device based on image identification technology Download PDF

Info

Publication number
CN111339907A
CN111339907A CN202010110999.0A CN202010110999A CN111339907A CN 111339907 A CN111339907 A CN 111339907A CN 202010110999 A CN202010110999 A CN 202010110999A CN 111339907 A CN111339907 A CN 111339907A
Authority
CN
China
Prior art keywords
sewage
image
outlet
discharge
area
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
Application number
CN202010110999.0A
Other languages
Chinese (zh)
Inventor
陈鹏飞
周威
田丁
邹煜
聂一亮
林作永
舒伟
梁珂
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Richway Beijing Technology Co ltd
Original Assignee
Richway Beijing Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Richway Beijing Technology Co ltd filed Critical Richway Beijing Technology Co ltd
Priority to CN202010110999.0A priority Critical patent/CN111339907A/en
Publication of CN111339907A publication Critical patent/CN111339907A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • G06T7/60—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
    • G06T7/00—Image analysis
    • G06T7/70—Determining position or orientation of objects or cameras
    • G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • 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
    • G06T2207/10—Image acquisition modality
    • G06T2207/10024—Color image
    • 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
    • G06T2207/20081—Training; Learning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30232—Surveillance

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • General Engineering & Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Geometry (AREA)
  • Image Analysis (AREA)

Abstract

The invention provides a pollution discharge identification method and a device based on an image identification technology, which comprises the following steps: acquiring a video image around the sewage outlet; identifying the position coordinates of the sewage draining outlet in the video image by utilizing a pre-constructed sewage draining outlet target detection network model so as to obtain an image of the sewage draining outlet; and carrying out drain pollution discharge dynamic identification according to the image of the drain. The automatic sewage draining device and the automatic sewage draining method based on the real-time video images have the advantages that the automatic sewage draining detection of the sewage draining outlet based on the real-time video images is realized, the working efficiency is improved, and meanwhile, the maintenance cost is reduced. Meanwhile, the method (device) can monitor and transmit the sewage image of the sewage outlet in real time, once abnormity is found, illegal behaviors can be timely alarmed, and the sewage image can be stored and reserved as evidence of illegal sewage discharge.

Description

Pollution discharge identification method and device based on image identification technology
Technical Field
The application belongs to the technical field of sewage treatment, and particularly relates to a pollution discharge identification method and device based on an image identification technology.
Background
Sewage discharge has been an important cause of water pollution. The manual monitoring aiming at the sewage discharge needs to consume a large amount of manpower and material resources, the sewage theft discharge usually has large space concealment and temporal disordering, and the response and monitoring can not be carried out in time within 24 hours by using a manual measurement mode, so that the factors bring great difficulty to the sewage discharge supervision.
Disclosure of Invention
The application provides a pollution discharge identification method and device based on an image identification technology, and aims to solve the problems that in the prior art, the supervision on sewage discharge mainly depends on manual work, so that 24-hour supervision cannot be performed, and timely response and monitoring cannot be performed.
According to one aspect of the application, a pollution discharge identification method based on an image identification technology is provided, and comprises the following steps:
acquiring a video image around the sewage outlet;
identifying the position coordinates of the sewage draining outlet in the video image by utilizing a pre-constructed sewage draining outlet target detection network model so as to obtain an image of the sewage draining outlet;
and carrying out drain pollution discharge dynamic identification according to the image of the drain.
In one embodiment, the step of pre-constructing the drain target detection network model comprises:
acquiring a network and training parameters adopted by a target detection network model;
training the labeled target detection sample data to detect a network model according to the training parameters.
In one embodiment, the drain sewage dynamic identification is performed according to the image of the drain sewage, and comprises the following steps:
obtaining a corresponding difference image according to the image of the sewage outlet;
identifying whether the sewage draining outlet discharges sewage or not according to the difference image;
performing color area segmentation according to the image of the sewage outlet;
and judging sewage according to the divided color areas.
In one embodiment, identifying whether the drain is draining based on the difference image comprises:
calculating the pixel area of a color change area in the image of the sewage draining exit;
and comparing the pixel area of the color change area with a preset first threshold value, and if the pixel area of the color change area is larger than the preset first threshold value, discharging sewage through the sewage outlet.
In one embodiment, the sewage determination according to the divided color regions includes:
calculating the pixel area of the pollution discharge area;
and comparing the pixel area of the sewage discharge area with a preset second threshold value, and if the pixel area of the sewage discharge area is larger than the second threshold value, discharging sewage from the sewage discharge port.
According to another aspect of the present application, there is also provided an exhaust recognition apparatus based on an image recognition technology, including:
the video acquisition unit is used for acquiring a video image around the sewage draining exit;
the position coordinate identification unit is used for identifying the position coordinate of the sewage outlet in the video image by utilizing a pre-constructed sewage outlet target detection network model so as to obtain an image of the sewage outlet;
and the sewage discharge dynamic identification unit is used for carrying out sewage discharge dynamic identification on the sewage discharge outlet according to the image of the sewage discharge outlet.
In one embodiment, the step of pre-constructing the drain target detection network model comprises:
acquiring a network and training parameters adopted by a target detection network model;
training the labeled target detection sample data to detect a network model according to the training parameters.
In one embodiment, the dynamic sewage discharge identification unit includes:
the difference image acquisition module is used for acquiring a corresponding difference image according to the image of the sewage outlet;
the sewage discharge judgment module is used for identifying whether the sewage discharge outlet discharges sewage or not according to the difference image;
the color segmentation module is used for performing color region segmentation according to the image of the sewage outlet;
and the sewage judgment module is used for judging sewage according to the divided color areas.
In one embodiment, the pollution discharge determination module includes:
the first calculation module is used for calculating the pixel area of a color change area in the image of the sewage draining exit;
and the first comparison module is used for comparing the pixel area of the color change area with a preset first threshold value, and if the pixel area of the color change area is larger than the preset first threshold value, the sewage draining outlet discharges sewage.
In one embodiment, the sewage determining module includes:
the second calculation module is used for calculating the pixel area of the pollution discharge area;
and the second comparison module is used for comparing the pixel area of the sewage discharge area with a preset second threshold value, and if the pixel area of the sewage discharge area is larger than the preset second threshold value, sewage is discharged from the sewage discharge port.
The image recognition model based on the deep learning technology is applied to the sewage supervision scene, the image recognition model based on the deep learning technology has high recognition accuracy and better robustness, can work stably in a real scene, overcomes the defect of manual sewage monitoring, can perform 24-hour uninterrupted monitoring and can automatically recognize the sewage discharge state to give an alarm in real time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or 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 for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a pollution discharge identification method based on an image identification technology provided by the present application.
Fig. 2 is a flowchart of steps for pre-constructing a sewage drain target detection network model in the embodiment of the present application.
Fig. 3 is a flowchart of drain pollution dynamic identification according to an image of a drain in the embodiment of the present application.
Fig. 4 is a flowchart for identifying whether a sewage draining exit is draining according to a difference image in the embodiment of the application.
Fig. 5 is a flowchart of sewage determination according to the divided color regions in the embodiment of the present application.
Fig. 6 is a structural block diagram of an exhaust recognition device based on an image recognition technology provided by the present application.
Fig. 7 is a block diagram of a structure of a dynamic sewage disposal identification unit in an embodiment of the present application.
Fig. 8 is a block diagram of a sewage discharge determination module in the embodiment of the present application.
Fig. 9 is a block diagram of a sewage determination module in the embodiment of the present application.
Fig. 10 is a specific implementation of an electronic device provided in an embodiment of the present application;
FIG. 11 is a diagram showing a result of a target detection of a drain in the present application;
FIG. 12 is an image of a sewage drain cut in the present application;
FIG. 13 is an exemplary diagram illustrating a method for finding a changed area by inter-frame difference according to the present application;
FIG. 14 is a diagram of HSV color conversion according to the present application;
FIG. 15 is a table of HSV color space ranges for the present application.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Sewage discharge has been an important cause of water pollution. The manual monitoring aiming at the sewage discharge needs to consume a large amount of manpower and material resources, the sewage theft discharge usually has large space concealment and temporal disordering, and the response and monitoring can not be carried out in time within 24 hours by using a manual measurement mode, so that the factors bring great difficulty to the sewage discharge supervision. Nowadays, artificial intelligence technology is continuously developed, so that an image recognition model based on a deep learning technology is applied. The deep learning technology utilizes massive existing data to perform feature extraction, then constructs an identification model, and applies the identification model to an actual scene. The image recognition model based on the deep learning technology has high recognition accuracy and good robustness, so that the model can stably work in a real scene.
In order to solve the above-mentioned drawback of manual detection sewage discharge, this application provides a blowdown identification method based on deep learning technique and image recognition technique, as shown in fig. 1, includes:
s101: and acquiring a video image of the periphery of the sewage draining exit.
The camera is installed on the periphery of the sewage draining exit, and the video is continuously recorded for 24 hours on the sewage draining exit to obtain the video image on the periphery of the sewage draining exit.
S102: and identifying the position coordinates of the sewage draining outlet in the video image by utilizing a pre-constructed sewage draining outlet target detection network model so as to obtain the image of the sewage draining outlet.
And S101, after video images of the periphery of the sewage draining exit are obtained, the video images are input into a pre-constructed sewage draining exit target detection network model, the specific position coordinates of the sewage draining exit are identified through the sewage draining exit target detection network model, and the specific images of the sewage draining exit are obtained according to the specific position coordinates of the sewage draining exit.
S103: and carrying out drain pollution discharge dynamic identification according to the image of the drain.
After the specific image of the sewage draining exit is obtained in the S102, the image of the sewage draining exit is processed and calculated by using an image processing algorithm, the current discharge capacity of the sewage draining exit is obtained, and the color of the liquid discharged by the current sewage draining exit is judged.
The execution main body of the method shown in fig. 1 can be a PC, a server and the like, and the intelligent model replaces manual work to identify sewage discharge and supervise the sewage discharge, so that the functions of continuously and uninterruptedly reporting and early warning the sewage discharge condition timely and accurately are realized.
In one embodiment, as shown in fig. 2, the step of pre-constructing the sewage drain target detection network model includes:
s201: and acquiring a network and training parameters adopted by the target detection network model.
In a specific embodiment, before sewage identification and monitoring, a target detection network model needs to be established in advance and a sewage outlet needs to be automatically identified, the target detection network model is established and a fast-rcnn network based on a deep learning technology is adopted, then a large amount of sample data of video images around the sewage outlet is obtained, and the video images (sample data) required by model training are labeled. Then, training parameters of the target detection network model are set, the training learning rate of the target detection network model is set to be 0.01, the momentum is set to be 0.9, the weight attenuation parameter is set to be 0.0001, and the model training iteration period is set to be 20.
S202: training the labeled target detection sample data to detect a network model according to the training parameters.
And inputting the labeled sample data into the target detection network model with the parameter setting completed, and training the target detection network model until the set iteration cycle is completed.
In one embodiment, as shown in fig. 3, the sewage discharge dynamic identification according to the image of the sewage discharge outlet includes:
s301: and obtaining a corresponding difference image according to the image of the sewage outlet.
In a specific embodiment, the video image of the sewage draining exit is input into the trained target detection network model, as shown in fig. 11, the target detection network model automatically identifies the sewage draining exit and thus obtains the position coordinates of the sewage draining exit in the video image, and then according to the position coordinates of the sewage draining exit, the target detection network model cuts out the sewage draining exit from the video image separately, as shown in fig. 12, so as to obtain the image of the sewage draining exit. And after the image of the sewage draining exit is obtained, obtaining a difference image of the sewage draining exit by using an image processing algorithm of the interframe difference value.
S302: and identifying whether the sewage draining outlet discharges sewage or not according to the difference image.
In a specific embodiment, after obtaining the difference image of the sewage draining exit (as shown in fig. 13) by using the inter-frame difference image processing algorithm from S301, the difference image of the sewage draining exit is calculated, the pixel area of the changed region in the difference image is calculated, and if a certain region is changed, the region is indicated as flowing water flow, so that the size/flow rate of the water flow (sewage) can be known by calculating the pixel area of the changed region.
S303: and carrying out color region segmentation according to the image of the sewage draining exit.
In a specific embodiment, as shown in fig. 14, the obtained image of the sewage draining exit is processed by using an HSV color segmentation algorithm, the image of the sewage draining exit is converted into an HSV color space, and then the image of the sewage draining exit is subjected to color segmentation according to a preset color range (as shown in fig. 15).
S304: and judging sewage according to the divided color areas.
In a specific embodiment, the color of the sewage is different from that of the clean water, and an HSV color segmentation algorithm is used for segmenting a region with a specified color in the image of the sewage outlet, wherein the region is the sewage with the specified color, so that whether the sewage is discharged from the sewage outlet or not is judged.
In one embodiment, as shown in fig. 4, identifying whether the drain is discharging sewage according to the difference image includes:
s401: and calculating the pixel area of the color change area in the image of the sewage draining exit.
In one embodiment, the area of the pixels in the area of the sewage drain where the color changes is calculated by using image processing software.
S402: and comparing the pixel area of the color change area with a preset first threshold value, and if the pixel area of the color change area is larger than the preset first threshold value, discharging sewage through the sewage outlet.
In a specific embodiment, the area of the area with the changed color is compared with a set threshold value through the calculated area of the pixel of the area with the changed color in S401, and if the area of the pixel of the area with the changed color exceeds the threshold value, the sewage outlet is determined to be discharging liquid (sewage discharging); if the threshold is not exceeded, the drain is not considered draining (because the amount of water drained is too small to be ignored). Meanwhile, the size of the discharged water quantity can be judged according to the pixel area of the area with the changed color, the larger the pixel area of the area is, the larger the water quantity is, the smaller the pixel area of the area is, and the smaller the water quantity is, and the mapping relation between the pixel area of the area with the changed color and the actual water discharge quantity of the sewage draining outlet can be established by combining the reality.
In one embodiment, as shown in fig. 5, the sewage determination according to the divided color regions includes:
s501: and calculating the pixel area of the sewage discharge area.
After the set color area is divided from the sewage outlet image by using an HSV color division algorithm, the set color area is the sewage discharge area (sewage with the specified color), and the pixel area of the sewage discharge area is calculated, so that whether the discharged sewage with the specified color is the sewage with the specified color or not and whether the discharged sewage with the specified color exceeds an alarm value or not can be obtained.
S502: and comparing the pixel area of the sewage discharge area with a preset second threshold value, and if the pixel area of the sewage discharge area is larger than the second threshold value, discharging sewage from the sewage discharge port.
In one embodiment, the HSV image of the change area is calculated, and the area size of the designated color is searched according to the table to judge whether the area is sewage or not. Namely, if the sewage outlet image has a designated color area, the sewage outlet can be determined to have the sewage of the designated color in the discharged liquid, and if the pixel area of the sewage of the designated color in the sewage outlet image exceeds a preset value (threshold value), the sewage outlet can be determined to have the conditions of illegal sewage discharge and illegal sewage discharge.
Once the condition that the certain sewage discharge port has the illegal sewage discharge is identified, the alarm device is started immediately, and the position of the sewage discharge port with the problem and the sewage discharge condition are notified to related personnel of related departments.
The automatic identification method for monitoring sewage discharge is established based on an image identification technology and a deep learning technology, and the functions of judging the discharge capacity of the sewage discharge outlet and judging whether the sewage discharge outlet is the sewage with the specified color or not and giving an alarm are realized by utilizing an image identification model and a related method for processing the sewage discharge image. The method can acquire real-time monitoring video through the camera and realize uninterrupted automatic sewage discharge identification and early warning throughout the day, can replace manual observation of sewage discharge, reduces the realization difficulty of sewage discharge monitoring, and improves the supervision efficiency of sewage discharge.
Based on the same inventive concept, the embodiment of the present application further provides a pollution discharge recognition apparatus based on an image recognition technology, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Because the principle of solving the problems of the pollution discharge recognition device based on the image recognition technology is similar to that of the pollution discharge recognition method based on the image recognition technology, the implementation of the pollution discharge recognition device based on the image recognition technology can refer to the implementation of the pollution discharge recognition method based on the image recognition technology, and repeated parts are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. While the system described in the embodiments below is preferably implemented in software, implementations in hardware, or a combination of software and hardware are also possible and contemplated.
According to another aspect of the present application, there is also provided an exhaust recognition apparatus based on an image recognition technology, as shown in fig. 6, including:
the video acquisition unit 601 is used for acquiring a video image around the sewage draining exit;
a position coordinate identification unit 602, configured to identify a position coordinate of the sewage drain in the video image by using a pre-constructed sewage drain target detection network model, so as to obtain an image of the sewage drain;
and a sewage discharge dynamic identification unit 603, configured to perform sewage discharge dynamic identification according to the image of the sewage discharge outlet.
In one embodiment, the step of pre-constructing the drain target detection network model comprises:
acquiring a network and training parameters adopted by a target detection network model;
training the labeled target detection sample data to detect a network model according to the training parameters.
In one embodiment, as shown in fig. 7, the dynamic sewage discharge identification unit 603 includes:
a difference image obtaining module 701, configured to obtain a corresponding difference image according to an image of the sewage draining exit;
a pollution discharge judging module 702, configured to identify whether a pollution discharge outlet discharges pollution according to the difference image;
the color segmentation module 703 is used for performing color region segmentation according to the image of the sewage outlet;
and a sewage judging module 704, configured to judge sewage according to the segmented color regions.
In one embodiment, as shown in fig. 8, the pollution discharge determination module 702 includes:
the first calculation module 801 is used for calculating the pixel area of a color change area in an image of the sewage draining exit;
the first comparing module 802 is configured to compare the pixel area of the color change region with a preset first threshold, and if the pixel area of the color change region is greater than the preset first threshold, the drain is draining.
In one embodiment, as shown in fig. 9, the sewage determining module 704 includes:
a second calculating module 901, configured to calculate a pixel area of the pollution discharge area;
and a second comparing module 902, configured to compare the pixel area of the sewage draining area with a preset second threshold, and if the pixel area is greater than the preset second threshold, the sewage draining from the sewage draining outlet is sewage.
Through the pollution discharge recognition device provided by the application, automatic pollution discharge outlet pollution discharge detection based on real-time video images is realized, and the maintenance cost is reduced while the working efficiency is improved. Meanwhile, the method (device) can monitor and transmit the sent image of the sewage outlet in real time, once abnormity is found, illegal behaviors can be timely alarmed, and the reserved sewage image can be stored as the evidence of illegal sewage discharge.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The principle and the implementation mode of the invention are explained by applying specific embodiments in the invention, and the description of the embodiments is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
An embodiment of the present application further provides a specific implementation manner of an electronic device capable of implementing all steps in the method in the foregoing embodiment, and referring to fig. 10, the electronic device specifically includes the following contents:
a processor (processor)1001, a memory 1002, a communication Interface (Communications Interface)1003, a bus 1004, and a nonvolatile memory 1005;
the processor 1001, the memory 1002, and the communication interface 1003 complete mutual communication through the bus 1004;
the processor 1001 is configured to call the computer programs in the memory 1002 and the nonvolatile memory 1005, and when the processor executes the computer programs, the processor implements all the steps in the method in the foregoing embodiments, for example, when the processor executes the computer programs, the processor implements the following steps:
s101: and acquiring a video image of the periphery of the sewage draining exit.
S102: and identifying the position coordinates of the sewage draining outlet in the video image by utilizing a pre-constructed sewage draining outlet target detection network model so as to obtain the image of the sewage draining outlet.
S103: and carrying out drain pollution discharge dynamic identification according to the image of the drain.
Embodiments of the present application also provide a computer-readable storage medium capable of implementing all the steps of the method in the above embodiments, where the computer-readable storage medium stores thereon a computer program, and the computer program when executed by a processor implements all the steps of the method in the above embodiments, for example, the processor implements the following steps when executing the computer program:
s101: and acquiring a video image of the periphery of the sewage draining exit.
S102: and identifying the position coordinates of the sewage draining outlet in the video image by utilizing a pre-constructed sewage draining outlet target detection network model so as to obtain the image of the sewage draining outlet.
S103: and carrying out drain pollution discharge dynamic identification according to the image of the drain.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the hardware + program class embodiment, since it is substantially similar to the method embodiment, the description is simple, and the relevant points can be referred to the partial description of the method embodiment. Although embodiments of the present description provide method steps as described in embodiments or flowcharts, more or fewer steps may be included based on conventional or non-inventive means. The order of steps recited in the embodiments is merely one manner of performing the steps in a multitude of orders and does not represent the only order of execution. When an actual apparatus or end product executes, it may execute sequentially or in parallel (e.g., parallel processors or multi-threaded environments, or even distributed data processing environments) according to the method shown in the embodiment or the figures. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the presence of additional identical or equivalent elements in a process, method, article, or apparatus that comprises the recited elements is not excluded. For convenience of description, the above devices are described as being divided into various modules by functions, and are described separately. Of course, in implementing the embodiments of the present description, the functions of each module may be implemented in one or more software and/or hardware, or a module implementing the same function may be implemented by a combination of multiple sub-modules or sub-units, and the like. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form. The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
As will be appreciated by one skilled in the art, embodiments of the present description may be provided as a method, system, or computer program product. Accordingly, embodiments of the present description may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present description may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and so forth) having computer-usable program code embodied therein. The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction. The above description is only an example of the embodiments of the present disclosure, and is not intended to limit the embodiments of the present disclosure. Various modifications and variations to the embodiments described herein will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present specification should be included in the scope of the claims of the embodiments of the present specification.

Claims (10)

1. A pollution discharge identification method based on an image identification technology is characterized by comprising the following steps:
acquiring a video image around the sewage outlet;
identifying the position coordinates of the sewage draining outlet in the video image by utilizing a pre-constructed sewage draining outlet target detection network model so as to obtain an image of the sewage draining outlet;
and carrying out drain discharge dynamic identification according to the image of the drain discharge.
2. The exhaust recognition method according to claim 1, wherein the step of previously constructing the exhaust target detection network model comprises:
acquiring a network and training parameters adopted by the target detection network model;
and training the labeled target detection sample data according to the training parameters to obtain the target detection network model.
3. The method for identifying the sewage discharge according to the claim 1, wherein the dynamic identification of the sewage discharge outlet according to the image of the sewage discharge outlet comprises the following steps:
obtaining a corresponding difference image according to the image of the sewage outlet;
identifying whether the sewage draining outlet discharges sewage or not according to the difference image;
performing color region segmentation according to the image of the sewage outlet;
judging sewage according to the divided color areas;
the identifying whether the sewage draining outlet discharges sewage or not according to the difference image comprises the following steps:
calculating the pixel area of a color change area in the image of the sewage draining exit;
and comparing the pixel area of the color change area with a preset first threshold value, and if the pixel area of the color change area is larger than the preset first threshold value, discharging sewage through the sewage outlet.
4. The method for identifying the pollution discharge according to claim 3, wherein the judging the pollution discharge according to the divided color regions comprises:
calculating a pixel area of the dirt discharge area;
and comparing the pixel area of the sewage discharge area with a preset second threshold value, and if the pixel area of the sewage discharge area is larger than the second threshold value, discharging sewage from the sewage discharge port.
5. A pollution discharge recognition device based on an image recognition technology is characterized by comprising:
the video acquisition unit is used for acquiring a video image around the sewage draining exit;
the position coordinate identification unit is used for identifying the position coordinate of the sewage outlet in the video image by utilizing a pre-constructed sewage outlet target detection network model so as to obtain an image of the sewage outlet;
and the sewage discharge dynamic identification unit is used for carrying out sewage discharge dynamic identification on the sewage discharge outlet according to the image of the sewage discharge outlet.
6. The exhaust recognition device according to claim 5, wherein the step of pre-constructing the exhaust target detection network model comprises:
acquiring a network and training parameters adopted by the target detection network model;
and training the labeled target detection sample data according to the training parameters to obtain the target detection network model.
7. The exhaust recognition device according to claim 5, wherein the exhaust dynamic recognition unit comprises:
the difference image acquisition module is used for acquiring a corresponding difference image according to the image of the sewage outlet;
the sewage discharge judgment module is used for identifying whether the sewage discharge outlet discharges sewage or not according to the difference image;
the color segmentation module is used for carrying out color region segmentation according to the image of the sewage outlet;
the sewage judgment module is used for judging sewage according to the divided color areas;
the blowdown judgment module includes:
the first calculation module is used for calculating the pixel area of a color change area in the image of the sewage draining exit;
and the first comparison module is used for comparing the pixel area of the color change area with a preset first threshold value, and if the pixel area of the color change area is larger than the preset first threshold value, the sewage discharge port discharges sewage.
8. The exhaust recognition device according to claim 7, wherein the sewage judgment module comprises:
the second calculation module is used for calculating the pixel area of the pollution discharge area;
and the second comparison module is used for comparing the pixel area of the sewage discharge area with a preset second threshold value, and if the pixel area of the sewage discharge area is larger than the preset second threshold value, sewage is discharged from the sewage discharge port.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the image recognition technology-based pollution recognition method according to any one of claims 1 to 4 when executing the program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method of identifying an emissions based on image identification technology according to any one of claims 1 to 4.
CN202010110999.0A 2020-02-24 2020-02-24 Pollution discharge identification method and device based on image identification technology Pending CN111339907A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010110999.0A CN111339907A (en) 2020-02-24 2020-02-24 Pollution discharge identification method and device based on image identification technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010110999.0A CN111339907A (en) 2020-02-24 2020-02-24 Pollution discharge identification method and device based on image identification technology

Publications (1)

Publication Number Publication Date
CN111339907A true CN111339907A (en) 2020-06-26

Family

ID=71186967

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010110999.0A Pending CN111339907A (en) 2020-02-24 2020-02-24 Pollution discharge identification method and device based on image identification technology

Country Status (1)

Country Link
CN (1) CN111339907A (en)

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112364918A (en) * 2020-11-10 2021-02-12 深圳力维智联技术有限公司 Abnormality recognition method, terminal, and computer-readable storage medium
CN112560574A (en) * 2020-10-30 2021-03-26 广东柯内特环境科技有限公司 River black water discharge detection method and recognition system applying same
CN113344879A (en) * 2021-06-09 2021-09-03 成都之维安科技股份有限公司 Image target segmentation and color anomaly detection method based on pollution source discharge port
CN113887412A (en) * 2021-09-30 2022-01-04 中国科学院过程工程研究所 Detection method, detection terminal, monitoring system and storage medium for pollution emission
CN113920471A (en) * 2021-10-13 2022-01-11 平安国际智慧城市科技股份有限公司 Remote monitoring method and device for production waste, computer equipment and storage medium
CN113965731A (en) * 2021-11-25 2022-01-21 北京京诚嘉宇环境科技有限公司 Rainwater drainage port management and control method, device and system
CN115661695A (en) * 2022-12-26 2023-01-31 深圳联和智慧科技有限公司 Unmanned aerial vehicle-based river drain monitoring and early warning method and system

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105675623A (en) * 2016-01-29 2016-06-15 重庆扬讯软件技术有限公司 Real-time analysis method for sewage color and flow detection on basis of sewage port video
CN107403183A (en) * 2017-07-21 2017-11-28 桂林电子科技大学 The intelligent scissor method that conformity goal is detected and image segmentation is integrated
CN108881857A (en) * 2018-08-04 2018-11-23 肖恒念 Blowdown intelligent control method based on real-time video
CN109325403A (en) * 2018-08-07 2019-02-12 广州粤建三和软件股份有限公司 A kind of water pollution identification administering method and system based on image recognition
US20190102604A1 (en) * 2017-09-30 2019-04-04 Beijing Kingsoft Internet Security Software Co., Ltd. Method of determining image background, device and medium

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105675623A (en) * 2016-01-29 2016-06-15 重庆扬讯软件技术有限公司 Real-time analysis method for sewage color and flow detection on basis of sewage port video
CN107403183A (en) * 2017-07-21 2017-11-28 桂林电子科技大学 The intelligent scissor method that conformity goal is detected and image segmentation is integrated
US20190102604A1 (en) * 2017-09-30 2019-04-04 Beijing Kingsoft Internet Security Software Co., Ltd. Method of determining image background, device and medium
CN108881857A (en) * 2018-08-04 2018-11-23 肖恒念 Blowdown intelligent control method based on real-time video
CN109325403A (en) * 2018-08-07 2019-02-12 广州粤建三和软件股份有限公司 A kind of water pollution identification administering method and system based on image recognition

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
徐晶 等: "《计算机视觉中的运动检测与跟踪》", 30 September 2012, 国防工业出版社 *

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112560574A (en) * 2020-10-30 2021-03-26 广东柯内特环境科技有限公司 River black water discharge detection method and recognition system applying same
CN112364918A (en) * 2020-11-10 2021-02-12 深圳力维智联技术有限公司 Abnormality recognition method, terminal, and computer-readable storage medium
CN112364918B (en) * 2020-11-10 2024-04-02 深圳力维智联技术有限公司 Abnormality recognition method, terminal, and computer-readable storage medium
CN113344879A (en) * 2021-06-09 2021-09-03 成都之维安科技股份有限公司 Image target segmentation and color anomaly detection method based on pollution source discharge port
CN113887412A (en) * 2021-09-30 2022-01-04 中国科学院过程工程研究所 Detection method, detection terminal, monitoring system and storage medium for pollution emission
CN113920471A (en) * 2021-10-13 2022-01-11 平安国际智慧城市科技股份有限公司 Remote monitoring method and device for production waste, computer equipment and storage medium
CN113965731A (en) * 2021-11-25 2022-01-21 北京京诚嘉宇环境科技有限公司 Rainwater drainage port management and control method, device and system
CN113965731B (en) * 2021-11-25 2024-02-02 北京京诚嘉宇环境科技有限公司 Rainwater discharge port management and control method, device and system
CN115661695A (en) * 2022-12-26 2023-01-31 深圳联和智慧科技有限公司 Unmanned aerial vehicle-based river drain monitoring and early warning method and system

Similar Documents

Publication Publication Date Title
CN111339907A (en) Pollution discharge identification method and device based on image identification technology
Yang et al. Vision-based tower crane tracking for understanding construction activity
CN110210302B (en) Multi-target tracking method, device, computer equipment and storage medium
CN110650316A (en) Intelligent patrol and early warning processing method and device, electronic equipment and storage medium
CN109858367B (en) Visual automatic detection method and system for worker through supporting unsafe behaviors
LU502731B1 (en) Method for monitoring abnormality of power production, apparatus, computer device, and storage medium therefor
CN109085174A (en) Display screen peripheral circuit detection method, device, electronic equipment and storage medium
CN104282011A (en) Method and device for detecting interference stripes in video images
CN113449703B (en) Quality control method and device for environment online monitoring data, storage medium and equipment
CN115880598A (en) Ground image detection method based on unmanned aerial vehicle and related device
CN116311081A (en) Medical laboratory monitoring image analysis method and system based on image recognition
CN112801434A (en) Method, device, equipment and storage medium for monitoring performance index health degree
CN108629310B (en) Engineering management supervision method and device
JP2009545223A (en) Event detection method and video surveillance system using the method
CN114140684A (en) Method, device and equipment for detecting coal blockage and coal leakage and storage medium
CN109102486B (en) Surface defect detection method and device based on machine learning
CN116523475B (en) BIM-based water service engineering equipment management method and system
CN110704313B (en) JAVA virtual machine memory leakage detection method and device
CN102866158B (en) Detection method of power transmission and distribution cables for tunnel routing inspection
CN111738259A (en) Tower state detection method and device
CN112991807A (en) Parking space state detection method, device, equipment and storage medium
CN112861681B (en) Pipe gallery video intelligent analysis method and system based on cloud processing
CN110634124A (en) Method and equipment for area detection
CN114241400A (en) Monitoring method and device of power grid system and computer readable storage medium
CN114119531A (en) Fire detection method and device applied to campus smart platform and computer equipment

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20200626

RJ01 Rejection of invention patent application after publication