Image processing method, device and system for fly ash monitoring

Abstract

The invention relates to the field of image detection, in particular to an image processing method, device and system for fly ash monitoring. The image processing method for fly ash monitoring comprises the following steps: acquiring a first image acquired by first equipment within first preset time; determining a fly ash proportion in the first direction according to the first image; determining the flow velocity of fly ash according to the first image; determining the starting time and the starting duration of the second equipment according to the flow velocity of the fly ash; starting the second equipment according to the starting time of the second equipment, and acquiring a second image acquired by the second equipment within the starting duration of the second equipment; determining a target image corresponding to the first image in the second image, and determining a fly ash proportion in the second direction according to the target image; and determining a real-time monitoring value of the fly ash according to the fly ash proportions in the first direction and the second direction. The problem that the content of the fly ash cannot be monitored in real time is solved.

Description

Technical Field

[0001] The present invention relates to the field of image detection, and in particular to an image processing method, device and system for fly ash monitoring. Background Art

[0002] Thermal power generation is a technology that burns fossil fuels through thermal equipment to heat water in a boiler and drives a turbine with steam to generate electricity. However, during the combustion process of fossil fuels, impurities and residues in the fossil fuels cannot be completely burned and become fine particulate matter, which is fly ash. The content of fly ash can reflect the working conditions of boiler combustion, so during the combustion process of fossil fuels, it is necessary to detect the content of fly ash.

[0003] Currently, thermal power generation generally collects fly ash through a smoke pipe, takes some samples and sends them to a laboratory for analysis.

[0004] This method is an off-line analysis method. From collecting fly ash to sending samples for analysis and then to obtaining the analysis results, a relatively long time has passed since the real-time generation of fly ash. During this process, since the real-time data of the fly ash content cannot be determined, the working parameters of the thermal equipment cannot be accurately adjusted in real time. Therefore, a new method is needed to solve the problem of inability to monitor the fly ash content in real time. Summary of the Invention

[0005] Based on this, in view of the above problems, it is necessary to provide an image processing method, device and system for fly ash monitoring.

[0006] The embodiment of the present invention is implemented as follows. An image processing method for fly ash monitoring, the image processing method for fly ash monitoring includes: S101, within a first preset time, obtain a first image collected by a first device; S102, determine the fly ash proportion in a first direction according to the first image; S103, determine the flow rate of fly ash according to the first image; S104, determine the start time and start duration of a second device according to the flow rate of fly ash; S105, start the second device according to the start time of the second device, and within the start duration of the second device, obtain a second image collected by the second device; S106, determine a target image corresponding to the first image in the second image, and determine the fly ash proportion in a second direction according to the target image; S107, determine the real-time monitoring value of fly ash according to the fly ash proportions in the first direction and the second direction; Among them, the first device and the second device are image acquisition devices. The acquisition direction of the first device is the first direction perpendicular to the height direction of the smoke pipe, and the acquisition direction of the second device is the second direction perpendicular to the height direction of the smoke pipe. The acquisition direction of the first device is perpendicular to the acquisition direction of the second device, and the height of the first device in the height direction of the smoke pipe is lower than that of the second device.

[0007] In one embodiment, the present invention provides an image processing device for fly ash monitoring. The image processing device for fly ash monitoring includes: A first acquisition module, configured to acquire a first image acquired by the first device within a first preset time; A first proportion module, configured to determine the fly ash proportion in the first direction according to the first image; A flow velocity determination module, configured to determine the flow velocity of the fly ash according to the first image; A start control module, configured to determine the start time and start duration of the second device according to the flow velocity of the fly ash; A second acquisition module, configured to start the second device according to the start time of the second device, and acquire a second image acquired by the second device within the start duration of the second device; A second proportion module, configured to determine a target image corresponding to the first image in the second image, and determine the fly ash proportion in the second direction according to the target image; A real-time monitoring module, configured to determine the real-time monitoring value of the fly ash according to the fly ash proportions in the first direction and the second direction; Among them, the first device and the second device are image acquisition devices. The acquisition direction of the first device is the first direction perpendicular to the height direction of the smoke pipe, and the acquisition direction of the second device is the second direction perpendicular to the height direction of the smoke pipe. The acquisition direction of the first device is perpendicular to the acquisition direction of the second device, and the height of the first device in the height direction of the smoke pipe is lower than that of the second device.

[0008] In one embodiment, the present invention provides an image processing system for fly ash monitoring. The image processing system for fly ash monitoring includes: a first device, a second device, and a computer device; The first device is an image acquisition device, connected to the computer device, and configured to acquire a first image; The second device is an image acquisition device, connected to the computer device, and configured to acquire a second image; The computer device is configured to execute the steps of the above-mentioned image processing method for fly ash monitoring.

[0009] An image processing method for fly ash monitoring provided by an embodiment of the present invention includes obtaining a first image collected by a first device within a first preset time; determining the proportion of fly ash in a first direction according to the first image; determining the flow rate of fly ash according to the first image; determining the start time and start duration of a second device according to the flow rate of fly ash; starting the second device according to the start time of the second device, and obtaining a second image collected by the second device within the start duration of the second device; determining a target image corresponding to the first image in the second image, and determining the proportion of fly ash in a second direction according to the target image; determining a real-time monitoring value of fly ash according to the proportions of fly ash in the first direction and the second direction. The present invention first determines the proportion of fly ash in the first direction and the flow rate of fly ash through the first image. The flow rate of fly ash determines the start time and start duration of the second device. Find the target image corresponding to the first image in the second image, determine the proportion of fly ash in the second direction through the target image, and evaluate the real-time monitoring value of fly ash according to the proportions of fly ash in the first direction and the second direction, solving the problem that the content of fly ash cannot be monitored in real time. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is a flowchart of an image processing method for fly ash monitoring in an embodiment; Figure 2 is an application environment of an image processing method for fly ash monitoring in an embodiment Figure 1 ; Figure 3 is an application environment of an image processing method for fly ash monitoring in an embodiment Figure 2 ; Figure 4 is a schematic diagram of identifying fly ash particles in the first image using a fly ash particle recognition model in an embodiment; Figure 5 is a structural block diagram of an image processing device for fly ash monitoring in an embodiment; Figure 6 is an internal structural block diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0011] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0012] It is understood that the terms "first", "second", etc. used in the present invention may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of the present invention, the first xx script may be referred to as the second xx script, and similarly, the second xx script may be referred to as the first xx script.

[0013] As Figure 1 shown, in one embodiment, an image processing method for fly ash monitoring is proposed, which may specifically include the following steps: S101, within a first preset time, obtain a first image collected by a first device; S102, determine the fly ash proportion in a first direction according to the first image; S103, determine the flow rate of fly ash according to the first image; S104, determine the start time and start duration of a second device according to the flow rate of fly ash; S105, start the second device according to the start time of the second device, and within the start duration of the second device, obtain a second image collected by the second device; S106, determine a target image corresponding to the first image in the second image, and determine the fly ash proportion in a second direction according to the target image; S107, determine the real-time monitoring value of fly ash according to the fly ash proportions in the first direction and the second direction; Wherein, the first device and the second device are image acquisition devices, the acquisition direction of the first device is a first direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the second device is a second direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the first device is perpendicular to the acquisition direction of the second device, and the height of the first device in the height direction of the smoke pipe is lower than that of the second device.

[0014] In this embodiment, the first device and the second device are image acquisition devices of the same model, and the settings of the working operation parameters are also the same.

[0015] In this embodiment, the smoke pipe is vertically arranged in the vertical direction, the acquisition direction of the first device is from one side wall to the center of the smoke pipe for shooting and acquisition, and the same is true for the second device. The first device and the second device only have perpendicular acquisition directions, and there will be no overlapping part in the actual acquisition ranges corresponding to them.

[0016] In this embodiment, the first image collected by the first device is actually a two-dimensional image within the length, width, and height area of a part of the smoke pipe. The same is true for the second device. It can be considered that from bottom to top, the first image is the mapped distance of the height of a part of the smoke pipe on the image, and from left to right is the mapped distance of the length or width of a part of the smoke pipe on the image. The same is true for the second image.

[0017] In this embodiment, the first preset time can be set to 5 - 10 s.

[0018] In this embodiment, the acquisition speed of the first device for acquiring the first image is related to the frame rate of the first device. The frame rate is the number of images acquired by the image acquisition device per second. Within the first preset time, the first device can acquire multiple first acquired images.

[0019] In this embodiment, as Figure 2 、 Figure 3 shown, the first direction in the fly ash proportion in the first direction is the acquisition direction of the first device, that is, the first direction perpendicular to the height direction of the smoke pipe; the second direction in the fly ash proportion in the second direction is the acquisition direction of the second device, that is, the second direction perpendicular to the height direction of the smoke pipe.

[0020] In this embodiment, the fly ash is conveyed from the lower part to the upper part of the smoke pipe, so the flow direction of the fly ash in the first acquired image and the second acquired image is from bottom to top.

[0021] In this embodiment, the start times of the second device and the first device are different, and the start time of the second device is slower than that of the first device. The first device remains started within the first preset time, and the second device remains started within the start duration of the second device.

[0022] In this embodiment, the second device is started according to the start time of the second device. It can start from the moment when the first device stops acquiring the first image, and after the start time of the second device, start the second device to acquire the second image.

[0023] In this embodiment, the number of the second images is greater than the number of the first images, so it is necessary to determine the target image corresponding to the first image in the second images. The target image here refers to the second image acquired when the scene in the first image frame passes through the second device.

[0024] In this embodiment, the steps of determining the fly ash proportion in the second direction based on the target image are the same as the steps of determining the fly ash proportion in the first direction based on the first image.

[0025] An image processing method for fly ash monitoring provided by an embodiment of the present invention includes obtaining a first image collected by a first device within a first preset time; determining the proportion of fly ash in a first direction based on the first image; determining the flow rate of the fly ash based on the first image; determining the start time and start duration of a second device according to the flow rate of the fly ash; starting the second device according to the start time of the second device, and obtaining a second image collected by the second device during the start duration of the second device; determining a target image corresponding to the first image in the second image, and determining the proportion of fly ash in a second direction based on the target image; determining a real-time monitoring value of the fly ash according to the proportions of fly ash in the first direction and the second direction. First, the present invention determines the proportion of fly ash in the first direction and the flow rate of the fly ash through the first image. The flow rate of the fly ash determines the start time and start duration of the second device. Find the target image corresponding to the first image in the second image, determine the proportion of fly ash in the second direction through the target image, and evaluate the real-time monitoring value of the fly ash according to the proportions of fly ash in the first direction and the second direction, solving the problem that the content of fly ash cannot be monitored in real time.

[0026] In one embodiment, the determining the proportion of fly ash in the first direction based on the first image includes: For each first image, use a fly ash particle recognition model to identify the fly ash particles in the first image; Divide the first image into a plurality of first sub-regions from bottom to top according to a first preset area, and number the first sub-regions; Denote the first sub-region of the first first image as the region to be judged; Select a preset number of fly ash particles closest to the upper edge of the region to be judged in the region to be judged, and denote them as target particles; For the first sub-regions with the same number of each first image, judge whether there are target particles in the first sub-regions with the same number. If so, denote the first sub-region with the same number where the target particle is closest to the upper edge as the region to be judged; For each region to be judged, determine the number a of pixels occupied by the fly ash particles in the region to be judged i ; From Obtain the proportion of fly ash in the first direction; Where i is the serial number of the region to be judged, n is the number of regions to be judged, and N is the total number of pixels of the region to be judged.

[0027] In this embodiment, using a fly ash particle recognition model to identify the fly ash particles in the first image is an existing technology. It involves common technologies such as image recognition and edge technology, which will not be elaborated here.

[0028] In this embodiment, as Figure 4As shown, it is a schematic diagram of identifying fly ash particles in the first image using the fly ash particle recognition model. The red area in the figure is the first sub-region.

[0029] In this embodiment, the side length of the first image from bottom to top (i.e., the side of the first image) is evenly divided into several segments. The length of each divided side length segment multiplied by the side length of the first image from left to right (i.e., the bottom side of the first image) is the first preset area. For example, if the side of the first image is evenly divided into 5 segments, the first preset area is 1 / 5 of the area of the first image. The first preset area is generally set to 1 / 5 - 1 / 10 of the first image.

[0030] In this embodiment, since the fly ash moves from bottom to top, the numbers of the first sub-regions increase from bottom to top.

[0031] In this embodiment, the size and shape of the target particles are determined and can be selected and identified through computer language. The preset quantity can be any value from 1 to 10. For example, the fly ash particles closest to the upper edge of 5 regions to be judged. The simplest way is to set the preset quantity to 1.

[0032] In this embodiment, to judge whether there are target particles in the first sub-region with the same number, as long as there is one target particle, it is judged that there are target particles in the first sub-region with the same number, and it is not necessary for all target particles to exist. Similarly, there may be multiple first sub-regions that meet the requirements in the same-numbered first sub-regions where the target particles are closest to the upper edge. The numbers of these multiple first sub-regions are the same, but they belong to different first images. Suppose we are judging the second first sub-region of each first image now. Then, the second first sub-regions of multiple first images may be determined as the regions to be judged. At this time, only the second first sub-region of one first image needs to be selected and recorded as the region to be judged. Usually, the second first sub-region of the first image with the earliest time order can be selected and recorded as the region to be judged. In this way, the number of regions to be judged is the same as the number of first sub-regions in any one first image. In fact, the region to be judged is the movement change process of the fly ash in the first first sub-region of the first first image.

[0033] In this embodiment, there is a significant difference in the pixel values of the pixels of the fly ash particle image and the background color, and the distinction is simple.

[0034] In this embodiment, only the first sub-region of the first first image is calculated to obtain the fly ash proportion in the first direction. Of course, it is also possible to calculate using the data of the movement change process of the fly ash in the first sub-region of the second first image, or calculate the average value of the data of the movement change process of the fly ash in the first sub-regions of these two first images, or even calculate the average value of the data of the movement change process of the fly ash in the first sub-regions of more first images.

[0035] In one embodiment, determining the flow rate of fly ash according to the first image includes: Determine the first image A corresponding to each region to be judged; Determine the time interval between two adjacent first images A in time; Calculate the average value of all the time intervals according to all the time intervals; From Obtain the flow rate of fly ash; Wherein, s is the length of the side of a first sub-region from bottom to top, and t is the average value of all the time intervals.

[0036] In this embodiment, the time interval between two adjacent first images A in time can be obtained by subtracting the acquisition time of the previous first image A from the acquisition time of the latter first image A. There are several first images collected by the first device between two adjacent first images A in time, and it can be calculated according to the number of first images collected by the first device between two adjacent first images A in time, because the frequency of the first images collected by the first device is fixed.

[0037] In one embodiment, determining the start time and start duration of the second device according to the flow rate of fly ash includes: Determine the height difference h between the first device and the second device; From Obtain the start time of the second device; From Obtain the start duration of the second device; Wherein, v is the flow rate of fly ash, T 1 is the first error time, L is the length from bottom to top of the range photographed by the second device in the actual scene, T 2 is the second error time.

[0038] In this embodiment, in order to ensure that the second device is sure to collect the target image corresponding to the first image collected by the first device within the first preset time, the second device needs to be started in advance.

[0039] In this embodiment, if it is necessary to calculate the average value using the data of the movement change process of the fly ash in the first sub-region of more first images, the startup duration of the second device also needs to be extended. At this time, it can be obtained by the startup duration of the second device, where d is the number of first images corresponding to the data of the movement change process of the fly ash in the first sub-region of the first images used.

[0040] In this embodiment, since the flow rate of the fly ash is uncertain for the first preset time, a redundant duration generally needs to be reserved to ensure that at least one set of data of the movement change process of the fly ash in the first sub-region of the first image can be obtained. After knowing the flow rate of the fly ash, the startup duration of the second device is determined according to the flow rate of the fly ash.

[0041] In this embodiment, the first error time and the second error time can be set to 1 / 5 or less. If the startup duration of the second device obtained by is used, it can be set to 1 / 5 or less. The first error time and the second error time can be the same. This is because there may be an error between the calculated flow rate of the fly ash and the actual flow rate of the fly ash, and the actual flow rate of the fly ash may be a variable value fluctuating around the obtained flow rate of the fly ash. An error time needs to be reserved to ensure that at least one set of data of the movement change process of the fly ash in the first sub-region of the first image can be obtained. L is a fixed value, and L is essentially the mapped height of the height of the second image collected by the second device in the actual scenario.

[0042] In one embodiment, determining the target image corresponding to the first image in the second image includes: For the first first image or each second image, use the fly ash particle recognition model to identify the fly ash particles in the first first image or the second image; Determine the pixel data group X of the first first image according to the fly ash particles in the first first image 1 ; Determine the pixel data group Y of the second image according to the fly ash particles in the second image j ; Compare the pixel data group X 1 with the pixel data group Y j respectively to obtain the similarity value between each second image and the first first image; Obtain the selection time period by ; Determine the second image collected within the selection time period with the earliest time order in the startup duration of the second device as the selected image; Select the second image corresponding to the largest similarity value in the selected images as the target image corresponding to the first image; Use the target image corresponding to the first image as the first target image, and determine the target images corresponding to other first images in the second image; where j is the serial number of the second image, T 1 is the first error time, and T 2 is the second error time.

[0043] In this embodiment, only the target image corresponding to the first first image in the second image needs to be found, and the target images corresponding to other first images in the second image can be directly determined according to the collected time. For example, if the first first image is collected at the first second and the target image corresponding to the first first image in the second image is collected at the twentieth second, then the second images collected after the twentieth second are successively the target images corresponding to the first images collected after the first second.

[0044] In this embodiment, the step of determining the pixel data group Y of the second image according to the fly ash particles in the second image j is the same as the step of determining the pixel data group X of the first first image according to the fly ash particles in the first first image. 1

[0045] In this embodiment, select the second image corresponding to the largest similarity value in the selected images as the target image corresponding to the first image, which can ensure that the number of remaining images of the second image is greater than or equal to the number of first images corresponding to the movement change process of the fly ash in the first sub-region of the first image used. If there is a situation where the similarity values are the same during this process, select the second image with an earlier acquisition time among the second images corresponding to the same similarity value as the target image corresponding to the first image.

[0046] In one embodiment, the step of determining the pixel data group X of the first first image according to the fly ash particles in the first first image 1 , includes: Divide the first first image into a plurality of second sub-regions from bottom to top according to the second preset area; For each second sub-region, determine the fly ash particle B with the largest area in the second sub-region; Select the pixel column with the largest number of pixels belonging to the fly ash particle B in the vertical direction among the fly ash particles B; Mark the pixels belonging to the fly ash particle B on this pixel column as 1, and mark the pixels not belonging to the fly ash particle B on the pixel column as 0, to obtain the pixel data group of this second sub-region of the first first image; ​Determine the pixel data group X of the first first image according to the pixel data groups of all the second sub-regions 1 。

[0047] In this embodiment, the second preset area is smaller than the first preset area, and the splitting method is the same as the method for obtaining the first sub-region. The second preset area can be a value in the range of 1 / 5 - 1 / 10 of the first preset area. The bottom side of the second sub-region is the same length as the bottom side of the first image, and the length of the side of the second sub-region is determined by the second preset area.

[0048] In this embodiment, since the fly ash particle B is not blocked in both the first direction and the second direction, it can be used as a recognition condition. Since the fly ash particle B may be an irregular shape, the pixel column with the largest number of pixels belonging to the fly ash particle B in the vertical direction in the fly ash particle B is selected. The direction of the pixel column is consistent with the direction from bottom to top, that is, the height direction of the chimney in practice.

[0049] In this embodiment, the pixel columns selected for each second sub-region do not necessarily have to be the same pixel column of the first image. This is because only one pixel column is selected for each second sub-region, so there will be no conflict among the pixels corresponding to any data in the pixel data group in the vertical direction.

[0050] In this embodiment, the data in the data group will only be one of 0 or 1.

[0051] In one embodiment, the pixel data group X 1 is respectively compared with the pixel data group Y j to obtain the similarity value between each second image and the first first image, including: For each pixel data group Y j , obtain the similarity value between the second image corresponding to this pixel data group Y j and the first first image; wherein, m is the number of data in the pixel data group X 1 or Y j , k is the serial number of the data in the pixel data group Y j , x k is the k-th data in the pixel data group X 1 , and y jk is the k-th data in the pixel data group Y j .

[0052] In this embodiment, if x k and y jk are the same, then the result obtained is 0, 1 minus 0 is 1, so 1 is accumulated. If they are exactly the same, then the pixel data group X1 and the pixel data group Y j The final similarity value is 1 if they are exactly the same, and 0 if they are completely different. Therefore, the range of the similarity value is between 0 and 1.

[0053] In one embodiment, determining the real-time monitoring value of fly ash according to the fly ash proportion in the first direction and the second direction includes: Determining the first evaluation value R of fly ash by looking up a table according to the fly ash proportion in the first direction 1 ; Determining the first evaluation value R of fly ash by looking up a table according to the fly ash proportion in the second direction 2 ; From Obtain the real-time monitoring value of fly ash.

[0054] In this embodiment, looking up a table means finding the corresponding value in a manually set table according to the fly ash proportion.

[0055] In this embodiment, generally speaking, the distribution of fly ash in the flue gas duct space is relatively uniform. Therefore, according to R 1 and R 2 Generally, the difference is not significant. The real-time monitoring value of fly ash can be determined according to the average value of R 1 and R 2 .

[0056] As Figure 5 shown, in one embodiment, an image processing device for fly ash monitoring is provided, which may specifically include: A first acquisition module, configured to acquire a first image collected by a first device within a first preset time; A first proportion module, configured to determine the fly ash proportion in the first direction according to the first image; A flow rate determination module, configured to determine the flow rate of fly ash according to the first image; A start control module, configured to determine the start time and start duration of a second device according to the flow rate of fly ash; A second acquisition module, configured to start the second device according to the start time of the second device, and acquire a second image collected by the second device during the start duration of the second device; A second proportion module, configured to determine a target image corresponding to the first image in the second image, and determine the fly ash proportion in the second direction according to the target image; A real-time monitoring module, configured to determine the real-time monitoring value of fly ash according to the fly ash proportions in the first direction and the second direction; Among them, the first device and the second device are image acquisition devices. The acquisition direction of the first device is the first direction perpendicular to the height direction of the smoke pipe, and the acquisition direction of the second device is the second direction perpendicular to the height direction of the smoke pipe. The acquisition direction of the first device is perpendicular to the acquisition direction of the second device, and the height of the first device in the height direction of the smoke pipe is lower than that of the second device.

[0057] In this embodiment, each module of the image processing device for fly ash monitoring is modularized in the method part of the present invention. For the specific explanations of each module, please refer to the corresponding content in the method part of the present invention, and the embodiments of the present invention will not be elaborated herein.

[0058] As Figure 2 shown, in one embodiment, an image processing device system for fly ash monitoring is provided, which may specifically include: a first device, a second device, and a computer device; The first device is an image acquisition device, connected to the computer device, and is used to acquire a first image; The second device is an image acquisition device, connected to the computer device, and is used to acquire a second image; The computer device is used to execute the steps of the above-mentioned image processing method for fly ash monitoring.

[0059] In this embodiment, the first device and the second device have the same model and set the same operating parameters.

[0060] In this embodiment, the computer can be an independent physical server or terminal, or a server cluster composed of multiple physical servers, and can be a cloud server providing basic cloud computing services such as cloud servers, cloud databases, cloud storage, and CDN.

[0061] In this embodiment, the image processing device system for fly ash monitoring further includes general devices such as a power supply device and a communication device.

[0062] An image processing system for fly ash monitoring provided by an embodiment of the present invention acquires a first image collected by a first device within a first preset time; determines the proportion of fly ash in a first direction according to the first image; determines the flow rate of the fly ash according to the first image; determines the start time and start duration of a second device according to the flow rate of the fly ash; starts the second device according to the start time of the second device, and within the start duration of the second device, acquires a second image collected by the second device; determines a target image corresponding to the first image in the second image, and determines the proportion of fly ash in a second direction according to the target image; determines a real-time monitoring value of the fly ash according to the proportions of fly ash in the first direction and the second direction. First, the present invention determines the proportion of fly ash in the first direction and the flow rate of the fly ash through the first image. The flow rate of the fly ash determines the start time and start duration of the second device. Finds the target image corresponding to the first image in the second image, determines the proportion of fly ash in the second direction through the target image, and evaluates the real-time monitoring value of the fly ash according to the proportions of fly ash in the first direction and the second direction, solving the problem that the content of fly ash cannot be monitored in real time.

[0063] Figure 6 shows the internal structure diagram of a computer device in one embodiment. As Figure 6 shown, the computer device includes a processor, a memory, a network interface, an input device, and a display screen connected through a system bus. Among them, the memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and can also store a computer program. When the computer program is executed by the processor, the processor can implement an image processing method for fly ash monitoring provided by an embodiment of the present invention. The internal memory can also store a computer program. When the computer program is executed by the processor, the processor can execute an image processing method for fly ash monitoring provided by an embodiment of the present invention. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the outer shell of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0064] Those skilled in the art can understand that Figure 6 the structure shown in

[0065] In one embodiment, an image processing device for fly ash monitoring provided by an embodiment of the present invention can be implemented in the form of a computer program. The computer program can be stored in a storage medium such as Figure 6Run on the computer device shown. In the memory of the computer device, each program module constituting the image processing device for fly ash monitoring can be stored. For example, Figure 5 The first acquisition module, the first proportion module, the flow rate determination module, the start control module, the second acquisition module, the second proportion module, and the real-time monitoring module shown. The computer program composed of each program module enables the processor to execute the steps in a fly ash monitoring image processing method according to various embodiments of the present invention described in this specification.

[0066] For example, Figure 6 The computer device shown can execute step S101 through the first acquisition module in an image processing device for fly ash monitoring as shown in Figure 5 ; the computer device can execute step S102 through the first proportion module; the computer device can execute step S103 through the flow rate determination module; the computer device can execute step S104 through the start control module; the computer device can execute step S105 through the second acquisition module; the computer device can execute step S106 through the second proportion module; the computer device can execute step S107 through the real-time monitoring module.

[0067] In one embodiment, a computer device is proposed. The computer device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the following steps are implemented: S101, within a first preset time, acquire a first image collected by a first device; S102, determine the proportion of fly ash in a first direction according to the first image; S103, determine the flow rate of fly ash according to the first image; S104, determine the start time and start duration of a second device according to the flow rate of fly ash; S105, start the second device according to the start time of the second device, and within the start duration of the second device, acquire a second image collected by the second device; S106, determine a target image corresponding to the first image in the second image, and determine the proportion of fly ash in a second direction according to the target image; S107, determine the real-time monitoring value of fly ash according to the proportions of fly ash in the first direction and the second direction; Wherein, the first device and the second device are image acquisition devices. The acquisition direction of the first device is a first direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the second device is a second direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the first device is perpendicular to the acquisition direction of the second device, and the height of the first device in the height direction of the smoke pipe is lower than that of the second device.

[0068] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the processor is caused to perform the following steps: S101, within a first preset time, obtain a first image collected by a first device; S102, determine the proportion of fly ash in a first direction based on the first image; S103, determine the flow rate of the fly ash based on the first image; S104, determine the start time and start duration of a second device based on the flow rate of the fly ash; S105, start the second device according to the start time of the second device, and within the start duration of the second device, obtain a second image collected by the second device; S106, determine a target image corresponding to the first image in the second image, and determine the proportion of fly ash in a second direction based on the target image; S107, determine a real-time monitoring value of the fly ash based on the proportions of fly ash in the first direction and the second direction; Wherein, the first device and the second device are image acquisition devices, the acquisition direction of the first device is a first direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the second device is a second direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the first device is perpendicular to the acquisition direction of the second device, and the height of the first device in the height direction of the smoke pipe is lower than that of the second device.

[0069] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same moment, but can be executed at different moments. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or sub-steps or stages of other steps. Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided by the present invention can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0070] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0071] The above embodiments only represent several implementation manners of the present invention. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention.

Claims

1. An image processing method for fly ash monitoring, characterized in that: The image processing method for fly ash monitoring comprises: S101, acquiring a first image captured by a first device within a first preset time; S102, determining a fly ash proportion in a first direction according to the first image; S103, determining the flow rate of fly ash according to the first image; S104, determining the start-up time and start-up duration of the second device according to the flow rate of the fly ash; S105, starting the second device according to the startup time of the second device, and acquiring a second image captured by the second device within the startup time of the second device; S106, determining a target image corresponding to the first image in the second image, and determining a fly ash ratio in the second direction according to the target image; S107, determining a real-time monitoring value of fly ash according to the fly ash proportions in the first direction and the second direction; Among them, the first device and the second device are image acquisition devices, the acquisition direction of the first device is a first direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the second device is a second direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the first device is perpendicular to the acquisition direction of the second device, and the height of the first device in the height direction of the smoke pipe is lower than that of the second device.

2. The image processing method for fly ash monitoring according to claim 1, characterized in that: The step of determining the fly ash proportion in the first direction according to the first image includes: For each first image, using a fly ash particle recognition model to identify fly ash particles in the first image; Dividing the first image into a plurality of first sub-regions from bottom to top according to a first preset area, and numbering the first sub-regions; Recording the first sub-region of the first first image as the region to be determined; Select a preset number of fly ash particles closest to the upper edge of the area to be judged in the area to be judged, and record them as target particles; For each first sub-region with the same number in the first image, determine whether there is a target particle in the first sub-region with the same number, and if so, record the first sub-region with the same number that is closest to the upper edge of the target particle as the region to be determined; For each area to be judged, determine the number of pixels occupied by the fly ash particles in the area to be judged. i ; Depend on Obtaining the fly ash proportion in the first direction; Wherein, i is the serial number of the area to be determined, n is the number of the areas to be determined, and N is the total number of pixels in the area to be determined.

3. The image processing method for fly ash monitoring according to claim 2, characterized in that: Determining the flow rate of fly ash according to the first image comprises: Determine a first image A corresponding to each area to be determined; Determine an interval time between two first images A that are adjacent in time; Calculate the average of all interval times based on all interval times; Depend on Get the flow rate of fly ash; Wherein, s is the length of the side of the first sub-region from bottom to top, and t is the average value of all interval times.

4. The image processing method for fly ash monitoring according to claim 1, characterized in that: The step of determining the start-up time and start-up duration of the second device according to the flow rate of the fly ash comprises: Determine a height difference h between the first device and the second device; Depend on Get the startup time of the second device; Depend on Get the startup time of the second device; Wherein, v is the flow velocity of fly ash, T1 is the first error time, L is the length from bottom to top of the range photographed by the second device in the actual scene, and T2 is the second error time.

5. The image processing method for fly ash monitoring according to claim 4, characterized in that: The step of determining the target image corresponding to the first image in the second image includes: For the first first image or each second image, using a fly ash particle recognition model to identify fly ash particles in the first first image or the second image; Determine the pixel data group X1 of the first first image according to the fly ash particles in the first first image; Determine the pixel data set Y of the second image according to the fly ash particles in the second image j ; The pixel data set X1 is respectively combined with the pixel data set Y j Compare and obtain a similarity value between each second image and the first first image; Depend on Get the selected time period; Determine the second image captured in the earliest selected time period in the startup time of the second device as the selected image; Select the second image corresponding to the maximum similarity value in the selected images as the target image corresponding to the first image; Taking the target image corresponding to the first image as the first target image, determining other target images corresponding to the first image in the second image; Wherein, j is the serial number of the second image, T1 is the first error time, and T2 is the second error time.

6. The image processing method for fly ash monitoring according to claim 5, characterized in that: The step of determining the pixel data group X1 of the first first image according to the fly ash particles in the first first image comprises: Dividing the first first image into a plurality of second sub-areas from bottom to top according to a second preset area; For each second sub-region, determining the fly ash particle B with the largest area in the second sub-region; Selecting a pixel column with the largest number of pixels belonging to fly ash particle B in the vertical direction in fly ash particle B; The pixels belonging to the fly ash particles B on the pixel column are marked as 1, and the pixels not belonging to the fly ash particles B on the pixel column are marked as 0, to obtain a pixel data group of the second sub-region of the first first image; The pixel data set X1 of the first first image is determined based on the pixel data sets of all the second sub-areas.

7. The image processing method for fly ash monitoring according to claim 5, characterized in that: The pixel data set X1 is respectively combined with the pixel data set Y j Compare and obtain the similarity value between each second image and the first image, including: For each pixel data set Y j ,Depend on Get the pixel data set Y j The similarity value between the corresponding second image and the first first image; Where m is the pixel data set X1 or Y j The number of data, k is the pixel data group Y j The serial number of the data, x k is the kth data in the pixel data set X1, y jk is the pixel data set Y j The kth data in .

8. The image processing method for fly ash monitoring according to claim 1, characterized in that: The method of determining the real-time monitoring value of fly ash according to the fly ash proportions in the first direction and the second direction includes: Determine a first evaluation value R1 of the fly ash by looking up a table according to the fly ash proportion in the first direction; Determine a first evaluation value R2 of the fly ash by looking up a table according to the fly ash proportion in the second direction; Depend on Get real-time monitoring value of fly ash.

9. An image processing device for fly ash monitoring, characterized in that: The image processing device for fly ash monitoring comprises: A first acquisition module, used to acquire a first image acquired by a first device within a first preset time; A first proportion module, used to determine the fly ash proportion in a first direction according to the first image; a flow rate determination module, configured to determine the flow rate of fly ash according to the first image; A start-up control module, used to determine the start-up time and start-up duration of the second device according to the flow rate of the fly ash; A second acquisition module is used to start the second device according to the startup time of the second device, and obtain the second image captured by the second device within the startup time of the second device; A second proportion module is used to determine a target image corresponding to the first image in the second image, and determine the fly ash proportion in the second direction according to the target image; A real-time monitoring module, used to determine a real-time monitoring value of fly ash according to the fly ash proportions in the first direction and the second direction; Among them, the first device and the second device are image acquisition devices, the acquisition direction of the first device is a first direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the second device is a second direction perpendicular to the height direction of the smoke pipe, the acquisition direction of the first device is perpendicular to the acquisition direction of the second device, and the height of the first device in the height direction of the smoke pipe is lower than that of the second device.

10. An image processing system for fly ash monitoring, characterized in that: The image processing system for fly ash monitoring comprises: a first device, a second device and a computer device; The first device is an image acquisition device, connected to the computer device, and used to acquire a first image; The second device is an image acquisition device, connected to the computer device, and used to acquire a second image; The computer device is used to execute the steps of the image processing method for fly ash monitoring according to any one of claims 1 to 8.

Images