CN111812113A - On-line monitoring method and monitoring system for oil smoke pipeline - Google Patents
On-line monitoring method and monitoring system for oil smoke pipeline Download PDFInfo
- Publication number
- CN111812113A CN111812113A CN202010812830.XA CN202010812830A CN111812113A CN 111812113 A CN111812113 A CN 111812113A CN 202010812830 A CN202010812830 A CN 202010812830A CN 111812113 A CN111812113 A CN 111812113A
- Authority
- CN
- China
- Prior art keywords
- target image
- image
- real
- real target
- images
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/01—Arrangements or apparatus for facilitating the optical investigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/94—Investigating contamination, e.g. dust
- G01N2021/945—Liquid or solid deposits of macroscopic size on surfaces, e.g. drops, films, or clustered contaminants
Abstract
The application discloses an online monitoring method and a monitoring system for an oil smoke pipeline, wherein the online monitoring method for the oil smoke pipeline specifically comprises the following steps: acquiring a target object; carrying out first detection on a target object, and detecting whether a target image exists in the target object; if the target image exists, performing second detection on the target image, and checking whether the target image is a real target image; if the real target image is the real target image, performing coordination processing on the real target image; performing third detection on the coordinated real target image to obtain a third detection result; and monitoring according to the third detection result and sending out a prompt at the same time. This application can carry out real time monitoring to the oil smoke pipeline, avoids appearing because the oil smoke area in the oil smoke pipeline is too big and the clearance is untimely, the conflagration problem of emergence.
Description
Technical Field
The application relates to the field of oil smoke, in particular to an online monitoring method and a monitoring system for an oil smoke pipeline.
Background
The oil fume exhaust gas is an aerosol mixed by gas, liquid and solid phases, the components of the aerosol contain various toxic, harmful and pathogenic components, and the direct emission can cause serious pollution to the atmosphere, so that the national relevant laws stipulate that catering service operators discharging oil fume must install oil fume purification facilities, and catering service operators discharging oil fume are subjected to relevant penalties when the emission standards of the oil fume exhaust gas exceed the emission standards without installing oil fume purification facilities, abnormally using oil fume purification facilities or taking other oil fume purification measures. However, the fume purification equipment cannot monitor the fume pipeline, and according to investigation, the fume pipeline of catering units in the current market often causes more fire cases of the fume pipeline because the fume pipeline is not cleaned for a long time or cannot be cleaned. In addition, because the oil smoke pipeline is not well supervised and a real-time monitoring system is lacked, the potential safety hazard is not found in time, the waste of cleaning energy is seriously caused, the fire safety of the oil smoke pipeline is also aggravated, and the national environmental protection and energy conservation are not facilitated.
Therefore, how to effectively perform online monitoring on the oil smoke pipeline so as to avoid the fire problem is a problem which needs to be solved urgently by people in the field.
Disclosure of Invention
The application provides an online monitoring method of an oil smoke pipeline, which specifically comprises the following steps: acquiring a target object; carrying out first detection on a target object, and detecting whether a target image exists in the target object; if the target image exists, performing second detection on the target image, and checking whether the target image is a real target image; if the real target image is the real target image, performing coordination processing on the real target image; performing third detection on the coordinated real target image to obtain a third detection result; and monitoring according to the third detection result and sending out a prompt at the same time.
As above, wherein the target object is an image of an inner wall of the fume duct in the operating range hood.
As above, the coordination processing on the real target image specifically includes the following sub-steps: judging the positions of one or more real target images; and performing coordination processing on the real target images according to the positions of one or more real target images.
As described above, the performing of the coordination processing on the real target image specifically includes performing the integration processing on a plurality of real target images appearing at the same designated distance, and performing the sharpness enhancement processing on a plurality of images dispersed at different designated distances or a single target image.
As above, the coordination processing on the real target images according to the positions of one or more real target images specifically includes the following sub-steps: selecting a matching point in the real target image, and carrying out alignment processing on the real target image; and integrating the real target images after the alignment processing is finished.
As above, the selecting of the matching point in the real target image and the aligning process of the real target image include transforming the real target image and integrating a plurality of real target images into the same plane.
As above, the third detection of the coordinated real target image is specifically area detection of the coordinated real target image; the area G of the real target image is specifically expressed as:
wherein x isdmaxIs the maximum value of x coordinate on the edge contour of the real target image, wherein the x coordinate corresponds to the y coordinate value as ddminThe minimum value of the x coordinate corresponding to d as the y coordinate value on the edge contour of the real target image is obtained.
As above, if there is one real target image and the real target image is located at any specified distance, and the area of the real target image is larger than the specified area, the monitoring result is abnormal, and an abnormal warning prompt is sent; and if the number of the real target images is one and the real target images are positioned at any specified distance, and the area of the real image images is smaller than the specified area, sending a normal prompt of the monitoring result.
An online monitoring system of an oil smoke pipeline comprises an acquisition unit, a first detection unit, a second detection unit, a coordination processing unit, a third detection unit and a monitoring unit; an acquisition unit configured to acquire a target object; the first detection unit is used for carrying out first detection on the target object and detecting whether a target image exists in the target object; the second detection unit is used for carrying out second detection on the target image according to the position of the target image and checking whether the target image is a real target image; the coordination processing unit is used for acquiring the position of the target image and carrying out coordination processing on the target image; the third detection unit is used for carrying out third detection on the coordinated target image to obtain a third detection result; and the monitoring unit is used for monitoring according to the third detection result and carrying out prompt processing.
As above, the first detection unit specifically includes the following sub-modules: the device comprises a standard image acquisition module, a first comparison module and a second comparison module; the standard image storage module is used for acquiring a pre-stored standard object; the first comparison module is used for carrying out first comparison on the target object and the standard object; and the second comparison module is used for carrying out second comparison on the foreign matter image and the oil smoke image if one or more foreign matter images exist.
The application has the beneficial effects that: the application provides an online monitoring method and a monitoring system of an oil smoke pipeline, which can monitor the oil smoke pipeline in real time, and avoid the fire problem caused by untimely cleaning due to overlarge oil smoke area in the oil smoke pipeline.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings needed to be 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 described in the present application, and other drawings can be obtained by those skilled in the art according to the drawings.
FIG. 1 is a flow chart of a method for online monitoring of a fume conduit according to an embodiment of the present application;
fig. 2 is an internal structure diagram of an oil smoke pipeline online monitoring system provided according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application are clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all, embodiments of the present application. 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 application.
The application relates to an online monitoring method and a monitoring system for an oil smoke pipeline. According to the application, the oil smoke pipeline is monitored in real time, and the fire problem caused by untimely cleaning due to overlarge oil smoke area in the oil smoke pipeline is avoided.
Fig. 1 is a flowchart of an online oil smoke pipeline monitoring method provided by the present application, which specifically includes the following steps:
step S110: and acquiring the target object.
Specifically, the target object is an image of the inner wall of the oil smoke pipeline in the operating range hood, and the image of the inner wall of the oil smoke pipeline is acquired according to an image acquisition sensor arranged in the system.
Step S120: and carrying out first detection on the target object, and detecting whether a target image exists in the target object.
Wherein step S120 specifically includes the following substeps:
step D1: and acquiring a standard object.
Specifically, the standard object is a pre-stored image of the inner wall of the oil smoke pipeline without oil smoke.
Step D2: and carrying out first comparison on the target object and the standard object, and checking whether a foreign object image exists in the target object.
In the prior art, methods such as histogram features and color features may be adopted to perform image comparison between the target object and the standard object, check whether a foreign object image exists in the target object, execute step D3 if one or more foreign object images exist, otherwise exit the process.
Step D3: and performing second comparison on the foreign matter image and the oil smoke image, and judging whether the foreign matter image is a target image.
Specifically, the oil smoke image is an oil smoke stain image formed by gathering oil smoke particles and is stored in the system in advance. And if one or more foreign matter images exist in the target object, comparing the one or more foreign matter images with the oil smoke image. The step D3 specifically includes the following sub-steps:
step D310: and preprocessing the foreign matter image and the oil smoke image.
Further, one or more foreign body images and the oil smoke image are respectively subjected to Q bit quantization and converted into gray level images, wherein the gray level images are spatially discrete GiPixel configuration of one gray level, i ═ 0,1,2.. 2Q-1. Wherein the value of Q is selected from 5-8.
Step D320: and dividing the area blocks of the preprocessed foreign object image.
Specifically, the area block division of the foreign object image includes establishing a pixel coordinate system in one or more foreign object images, wherein an origin of the pixel coordinate system is a central point or an arbitrary point of the foreign object image.
Further, the foreign matter image and the oil smoke image are divided into area blocks according to a pixel coordinate system, for example, the foreign matter image and the oil smoke image are equally divided into a plurality of area blocks according to an equal division rule, and the area blocks are labeled, wherein the label of the area block is based on the number of the area blocks, and if the number of the area blocks is 5 in total, the area blocks are labeled as an area block 1 and an area block 2.
Step D330: and adjusting the oil smoke image according to the area block obtained after the pretreatment.
Wherein, the oil smoke image is reduced according to the size difference of the area blocks of the oil smoke image and the foreign matter image.
Specifically, since the size of an image is determined by the number of pixels in the image, for example, a 1920 × 1080 picture is composed of 1920 pixels in the horizontal direction and 1080 pixels in the vertical direction (2,073,600 pixels in total). Therefore, the number of pixels of the oil smoke image can be increased or decreased according to the difference (referred to as a reference factor) between the number of pixels of the foreign object image and the number of pixels of the oil smoke image.
Wherein the reference factor C is specifically represented as:
wherein S is1Number of pixels, S, representing a soot image2Indicating the number of pixels of a certain area block of the foreign object image. Wherein if C is a decimal number, it is rounded off such that C is an integer.
Specifically, if the size of the oil smoke image is larger than the size of the region block of the foreign object image, the reference factor is used as the maximum reduction scale, and the oil smoke image is reduced according to the value smaller than the reference factor, so that the size of the oil smoke image is smaller or far smaller than the size of each region block. If the size of the oil smoke image is smaller than the size of the region block of the foreign matter image, no adjustment is performed.
Step D340: and placing the adjusted oil smoke image in each area block of the foreign matter image for moving.
Specifically, the soot image V (M × N pixels, M × N pixels ═ S) is displayed1) Shifting on a certain area block W (E x O pixels) of the foreign matter image, and defining a certain area covered by the oil smoke image as Ki,j(will be simply referred to as "region image"). Where i, j are the pixel coordinates of the covered area K.
Further, where i, j ranges from: i is more than or equal to 1 and less than or equal to E-M, and j is more than or equal to 1 and less than or equal to O-N.
The oil smoke image is translated in all the area blocks of the foreign matter image, namely, the oil smoke image and all the area blocks of the foreign matter image are covered.
Step S350: the area image is compared with an area image of the soot image.
Specifically, the soot image is compared with the area image of the covered area block, and the similarity D after comparison can be specifically expressed as:
wherein, M and N represent the number of pixels of the oil smoke image, M and N are natural numbers, and Ki,j(m, n) denotes a region image containing m x n pixels with coordinates i, j, Vi',j'(m, n) denotes oil with coordinates i ', j' comprising m x n pixelsAnd (3) a smoke image, wherein i ', j' is a coordinate when the smoke image covers the area image.
If the value of D is less than the designated threshold, the more similar the lampblack image is to the area block, and if the value of D is greater than the designated threshold, the more dissimilar the lampblack image is to the area block.
And finishing the comparison of the oil smoke image and each region block of the foreign matter image according to a formula II. When the specified number of the all the area blocks are similar to the soot image, step S360 is executed, otherwise, the process exits.
The specified threshold value can be set by a worker according to actual conditions, and specific numerical values are not limited herein.
Step S360: and acquiring the communication degree of the foreign matter image and the oil smoke image according to the comparison result of the area image and the oil smoke image.
Specifically, before the similarity between the foreign matter image and the oil smoke image is obtained, different weights are given to the region blocks in the foreign matter image, and the communication degree between the foreign matter image and the oil smoke image is calculated according to the weights of the region blocks.
Specifically, the degree F of communication between the foreign matter image and the smoke image is specifically expressed as:
where a denotes the number of region blocks of the foreign object image, a is a constant, and denotes a reference numeral of each region, for example, region block 1(a is 1), region block 2(a is 2), and DaIndicating the similarity of each region block to the smoke image, e.g., the similarity of region block 1 to the smoke image, the similarity of region block 2 to the smoke image, etc., ηaRepresenting the weight of each region block.
And if the result of the third formula is the result of the second comparison, and if the result of the second comparison is greater than the specified threshold, the degree of communication between the foreign object image and the target image is considered to be greater, that is, the comparison is similar, the foreign object image is the target image, and the step S130 is executed, otherwise, the process exits.
And if the number of the foreign body images is multiple, respectively comparing the multiple foreign body images with the oil smoke image according to the second comparison of the steps, so as to obtain whether one or more target images exist in the foreign body images. If one or more target images exist, step S130 is performed.
Step S130: and carrying out second detection on the target image, and checking whether the target image is a real target image.
Specifically, second detection is performed on one or more target images, specifically, detection is performed on pixel points of the target images (assuming that the target images are T), whether one or more target pixel points in each target image are random noise is checked, and whether the target image is a real target image is finally determined.
The probability p that the detected target pixel point is random noise is specifically expressed as:
wherein Z ist(T ═ 1,2.. times.t) denotes a gradation value of a certain target image among the plurality of target images, v ═ v ·tThe sum of the average gray values of the pixel points of a certain target image in the detected multiple target images is represented, sigma represents variance, and H represents the existence environment of random noise in the multiple target images.
If the p values of the specified number of pixel points are less than the specified threshold, it is determined that the pixel points in the target image are real pixel points rather than random noise, and the target image is a real target image, the step S140 is continuously executed. If the p values of the specified number of the pixel points are greater than the specified threshold, it is determined that the pixel points in the target image are random noise, and then the target image is re-screened, that is, step S120, a second detection is performed on the target image again, and it is determined whether the target image after the second detection is the same as the target image after the first detection. If they are the same, an error reporting process is performed, otherwise, step S130 is performed.
Step S140: and carrying out coordination processing on the real target image.
Wherein, step S140 specifically includes the following substeps:
step Q1: and judging the positions of one or more real target images.
Specifically, if the number of the real target images is one or more, before the coordination process, the method further includes performing position judgment on the one or more real target images.
Specifically, before acquiring the positions of one or more real target images, the method further comprises dividing the real target object by a plurality of specified distances.
Wherein, an image coordinate system is established in the target object in advance, and the opening position of the inner wall of the oil smoke pipeline is taken as the origin of the image coordinate system.
The opening position of the inner wall of the oil smoke pipeline is used as a starting point, an abscissa (or an ordinate) extending backwards for a specified distance is used as an end point, and the distance from the starting point to the end point is used as a first specified distance. The end point of the first specified distance is taken as the starting point of the second specified distance, the abscissa (or ordinate) extending backward by the specified distance is taken as the end point of the second specified distance, and the distance from the starting point to the end point is taken as the second specified distance. And taking the end point of the second designated distance as a starting point, taking the position of the outlet of the oil smoke inner wall pipeline as an end point, and taking the distance from the starting point to the end point as a third designated distance.
For example, if the abscissa of the target object indicates the length of the target object and the ordinate indicates the width of the target object, the abscissa is extended backward as the end point, and if the abscissa of the target object indicates the width of the target object and the ordinate indicates the length of the target object, the ordinate is extended backward as the end point.
Step Q2: and performing coordination processing on the real target image according to the position of the real target image.
The coordination processing of the real target images specifically includes integration processing of a plurality of real target images appearing at the same designated distance, and sharpness enhancement processing of a plurality of images dispersed at different designated distances or a single target image.
Specifically, the multiple real target images are aligned, and the aligned real target images are integrated to integrate the multiple real target images into a total real target image.
Preferably, the sharpness enhancement can refer to the method in the prior art, which is not described herein.
Specifically, the step Q2 specifically includes the following sub-steps:
step Q210: and selecting a matching point in the real target image, and carrying out alignment processing on the real target image.
Firstly, a real target image needs to be transformed, a plurality of real target images are integrated into the same plane, taking two real target images as an example (two target images are respectively defined as a real target image a and a real target image B), a relevant window with the size of (2h +1) × (2l +1) is established in the target image a based on any pixel point X (X1, y1) of the real target image a, and a relevant window with the size of (2h +1) × (2l +1) is also established at a position (X1', y1') in the real target image B, which is the same as the pixel coordinate of the pixel point X. And establishing a (2w +1) × (2r +1) search window in the real target image B by taking any pixel point Y (X2, Y2) of the real target image B as a reference, and determining whether the Z point is a matching point corresponding to the X point according to a correlation value of any point Z in the search window and the X point in a correlation window.
Wherein the correlation value can be expressed as:
wherein cov (X, Z) represents the covariance of pixel X and pixel Z, and σ (X) σ (Z) represents the standard deviation of pixel X and pixel Z.
If the correlation value is larger than the specified threshold value, the pixel points Z and X are indicated as matching points, and all the matching points existing in the two real target images are determined according to the mode.
Specifically, after all the matching points of the two real target images are determined, it is indicated that the two images can be aligned. And operating the rest real target images according to the method to finish the alignment processing of all the real images.
Step Q220: and integrating the real target images after the alignment processing is finished.
Specifically, after the alignment processing is completed on all of the plurality of target images, the real target images can be integrated two by two according to the aligned matching points.
For example, after the target image a is aligned with the target image B, the matching point between the target image C and the target image B is determined, and the target image C is aligned with the target image B according to the matching point between the target image C and the target image B. And after all the target images are aligned, fusing every two target images. For example, with the target image a as a reference, the target image B is fused with the target image a to form a target image 1, the target image C is fused with the target image 1 to form a target image 2, the target image D is fused with the target image 2 to form a target image 3, and so on, the integration of a plurality of target images is completed, and the coordination processing of the plurality of target images is completed.
Preferably, the integration method between images according to the aligned matching points can refer to the rules in the prior art, such as the HIS, KL method, etc.
Step S150: and performing third detection on the coordinated real target image to obtain a third detection result.
Specifically, the third detection on the coordinated real target image is specifically area detection on the coordinated real target image.
Before the third detection, judging whether a defect exists in the real target image. Wherein the defect is whether there is a discontinuous position in the real target image (for example, there is a hollow part in the real target image), wherein a significantly different position in the image can be detected according to the texture defect detection method.
If the real target image has no defect, the area G of the real target image is specifically represented as:
wherein x isdmaxFor edges of real target imagesMaximum value of x coordinate on the contour corresponding to y coordinate value d, xdminThe minimum value of the x coordinate corresponding to d as the y coordinate value on the edge contour of the real target image is obtained.
If the real target image has defects, the area G of the real target image is specifically represented as:
wherein x isdmaxIs the maximum value of x coordinate on the edge contour of the real target image, wherein the x coordinate corresponds to the y coordinate value as ddminIs the minimum value of an x coordinate on the edge contour of a real target image corresponding to the y coordinate value of d, RdWhen the y coordinate value is d, the difference between the minimum value of the abscissa of the edge profile of the real target image and the minimum value of the abscissa of the edge profile of the discontinuous position, OdWhen the y coordinate value is d, the difference between the maximum value of the abscissa of the edge profile of the real target image and the maximum value of the abscissa of the edge profile of the discontinuous position.
Through the formulas six and seven, the area of the real target image located in an arbitrary specified distance can be calculated.
Step S160: and monitoring according to the third detection result and sending out a prompt at the same time.
And acquiring a monitoring result according to the area of the real target image and the position of the real target image.
Specifically, if one real target image is located at any specified distance, and the area of the real target image is larger than the specified area, the monitoring result is abnormal, and an abnormal warning prompt is sent out.
And if the number of the real target images is one and the real target images are positioned at any specified distance, and the area of the real image images is smaller than the specified area, sending a normal prompt of the monitoring result.
Further, if the number of the real target images is multiple and the real target images are distributed in any specified distance, the monitoring is performed according to the rule specified in the embodiment.
In this embodiment, since the first designated distance is the opening position of the fume pipe and the third designated distance is the outlet position of the fume pipe, the area of the target image in the first and third designated distances must not be larger than the designated area, and based on this rule, the following determination is made:
if a certain real target image is located in the first designated distance and the area of the real target image is larger than the first designated area, the positions and the areas of the remaining target real target images are not checked, and a warning prompt for monitoring abnormity is directly sent out.
And if the area of the real target image at the first specified distance is smaller than the first specified area, continuing to check the area of the remaining real target images, and if the area of the real target image at the second specified distance is larger than the second specified area, not considering that an abnormal warning needs to be sent, and continuing to check the area of the real target image at the third specified distance. And if the area of the real target image positioned at the third specified distance is larger than the first specified area, the monitoring result is abnormal, and an abnormal warning prompt is sent out.
And if the area of the real target image at the first specified distance is smaller than the first specified area, continuing to check the area of the remaining real target images, and if the area of the real target image at the second specified distance is larger than the second specified area, not considering that an abnormal warning needs to be sent, and continuing to check the area of the real target image at the third specified distance. And if the area of the real target image located at the third specified distance is smaller than the first specified area, normally prompting the monitoring result.
And if the area of the real target image at the first specified distance is smaller than the first specified area, continuing to check the area of the remaining real target images, and if the area of the real target image at the second specified distance is smaller than the second specified area, continuing to check the area of the real target image at the third specified distance. And if the area of the real target image positioned at the third specified distance is larger than the first specified area, the monitoring result is abnormal, and an abnormal warning prompt is sent out.
And if the areas of the real target images positioned in the first to third specified distances are smaller than the specified area, normally prompting the monitoring result.
If a plurality of real target images appear in any two specified distances, the determination can still be performed according to the above rules, and the detailed determination is not repeated here.
Notably, the first designated area is smaller than the second designated area.
Because a plurality of real target images positioned at the same designated distance are integrated into a whole real target image, only two situations can occur during monitoring in the step, namely, one real target image (or one integrated target image) is positioned at any designated distance, or a plurality of real target images are formed after integration, the plurality of real target images appear in any designated distance, only the two situations need to be monitored during monitoring, and too much time cannot be delayed in the area calculation process because of too many real target images, so that the monitoring process is more convenient.
The present application provides a monitoring system of a fume pipe, as shown in fig. 2, wherein the monitoring system includes an obtaining unit 201, a first detecting unit 202, a second detecting unit 203, a coordination processing unit 204, a third detecting unit 205, and a monitoring unit 206.
The obtaining unit 201 is specifically an image capturing sensor, and is configured to obtain an image of a target object (i.e., an inner wall of the oil smoke pipe).
The first detecting unit 202 is connected to the acquiring unit 201, and is configured to perform first detection on the target object, and detect whether a target image exists in the target object.
Specifically, the first detection unit 202 specifically includes the following sub-modules: the device comprises a standard image acquisition module, a first comparison module and a second comparison module.
The standard image storage module is used for acquiring a pre-stored standard object.
The first comparison module is connected with the standard image storage module and is used for carrying out first comparison on the target object and the standard object.
The second comparison module is connected with the first comparison module and used for carrying out second comparison on the foreign matter images and the oil smoke images if one or more foreign matter images exist.
The second detecting unit 203 is connected to the first detecting unit 202, and is configured to perform second detection on the target image according to the position of the target image, and check whether the target image is a real target image.
The coordination processing unit 204 is connected to the second detection unit 203, and is configured to acquire a position of the target image and perform coordination processing on the target image.
Specifically, the coordination processing unit 204 specifically includes the following sub-modules: a designated distance dividing module and a coordinating module.
The specified distance dividing module is used for dividing the target object by a plurality of specified distances.
The coordination module is connected with the appointed distance division module and is used for carrying out coordination processing on the target images according to the positions of one or more target images.
The third detecting unit 205 is connected to the coordination processing unit 204, and is configured to perform third detection on the coordinated target image, and obtain a third detection result.
The monitoring unit 206 is connected to the third detecting unit 205, and is configured to perform monitoring according to the third detection result, and perform prompt processing.
The application has the beneficial effects that:
the application provides an online monitoring method and a monitoring system of an oil smoke pipeline, which can monitor the oil smoke pipeline in real time, and avoid the fire problem caused by untimely cleaning due to overlarge oil smoke area in the oil smoke pipeline.
Although the present application has been described with reference to examples, which are intended to be illustrative only and not to be limiting of the application, changes, additions and/or deletions may be made to the embodiments without departing from the scope of the application.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An online monitoring method of an oil smoke pipeline is characterized by comprising the following steps:
acquiring a target object;
carrying out first detection on a target object, and detecting whether a target image exists in the target object;
if the target image exists, performing second detection on the target image, and checking whether the target image is a real target image;
if the real target image is the real target image, performing coordination processing on the real target image;
performing third detection on the coordinated real target image to obtain a third detection result;
and monitoring according to the third detection result and sending out a prompt at the same time.
2. The on-line monitoring method of a fume duct according to claim 1, wherein the target object is an image of an inner wall of the fume duct in the operating range hood.
3. The method for on-line monitoring of a fume pipeline according to claim 1, wherein the coordination processing of the real target image specifically comprises the following substeps:
judging the positions of one or more real target images;
and performing coordination processing on the real target images according to the positions of one or more real target images.
4. The method of claim 3, wherein the coordinating of the real target images comprises integrating a plurality of real target images that appear at a same designated distance, and performing sharpness enhancement on a plurality of images scattered at different designated distances or a single target image.
5. The method for on-line monitoring of a fume pipe according to claim 3 or 4, wherein the coordination process of the real target images according to the position of one or more real target images specifically comprises the following sub-steps:
selecting a matching point in the real target image, and carrying out alignment processing on the real target image;
and integrating the real target images after the alignment processing is finished.
6. The method of claim 5 wherein the selecting of matching points in the real target image and the aligning of the real target image comprises transforming the real target image to integrate multiple real target images into the same plane.
7. The online monitoring method of the oil smoke pipeline according to claim 1, wherein the third detection of the coordinated real target image is specifically an area detection of the coordinated real target image; the area G of the real target image is specifically expressed as:
wherein x isdmaxIs the maximum value of x coordinate on the edge contour of the real target image, wherein the x coordinate corresponds to the y coordinate value as ddminThe minimum value of the x coordinate corresponding to d as the y coordinate value on the edge contour of the real target image is obtained.
8. The online monitoring method of the oil smoke pipeline according to claim 1, wherein if one real target image is located at any specified distance and the area of the real target image is larger than the specified area, the monitoring result is abnormal and an abnormal warning prompt is sent; and if the number of the real target images is one and the real target images are positioned at any specified distance, and the area of the real image images is smaller than the specified area, sending a normal prompt of the monitoring result.
9. An online monitoring system of an oil smoke pipeline is characterized by comprising an acquisition unit, a first detection unit, a second detection unit, a coordination processing unit, a third detection unit and a monitoring unit;
an acquisition unit configured to acquire a target object;
the first detection unit is used for carrying out first detection on the target object and detecting whether a target image exists in the target object;
the second detection unit is used for carrying out second detection on the target image according to the position of the target image and checking whether the target image is a real target image;
the coordination processing unit is used for acquiring the position of the target image and carrying out coordination processing on the target image;
the third detection unit is used for carrying out third detection on the coordinated target image to obtain a third detection result;
and the monitoring unit is used for monitoring according to the third detection result and carrying out prompt processing.
10. The system of claim 9, wherein the first detecting unit comprises the following sub-modules: the device comprises a standard image acquisition module, a first comparison module and a second comparison module;
the standard image storage module is used for acquiring a pre-stored standard object;
the first comparison module is used for carrying out first comparison on the target object and the standard object;
and the second comparison module is used for carrying out second comparison on the foreign matter image and the oil smoke image if one or more foreign matter images exist.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010812830.XA CN111812113A (en) | 2020-08-13 | 2020-08-13 | On-line monitoring method and monitoring system for oil smoke pipeline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010812830.XA CN111812113A (en) | 2020-08-13 | 2020-08-13 | On-line monitoring method and monitoring system for oil smoke pipeline |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111812113A true CN111812113A (en) | 2020-10-23 |
Family
ID=72860241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010812830.XA Withdrawn CN111812113A (en) | 2020-08-13 | 2020-08-13 | On-line monitoring method and monitoring system for oil smoke pipeline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111812113A (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102116736B (en) * | 2011-01-25 | 2012-07-04 | 广州正虹科技发展有限公司 | Oil fume concentration detection system and method |
| CN203771504U (en) * | 2014-03-06 | 2014-08-13 | 宁波方太厨具有限公司 | Smoke detection device of range hood |
| JP2019027972A (en) * | 2017-08-01 | 2019-02-21 | 株式会社日立製作所 | Inspection system for inside of pipeline facility |
-
2020
- 2020-08-13 CN CN202010812830.XA patent/CN111812113A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102116736B (en) * | 2011-01-25 | 2012-07-04 | 广州正虹科技发展有限公司 | Oil fume concentration detection system and method |
| CN203771504U (en) * | 2014-03-06 | 2014-08-13 | 宁波方太厨具有限公司 | Smoke detection device of range hood |
| JP2019027972A (en) * | 2017-08-01 | 2019-02-21 | 株式会社日立製作所 | Inspection system for inside of pipeline facility |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116309579B (en) | Transformer welding seam quality detection method using image processing | |
| CN111932709A (en) | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification | |
| CN111812116B (en) | On-line monitoring method and monitoring system for oil smoke pipeline | |
| WO2020175589A1 (en) | Information providing system | |
| CN107292879A (en) | A kind of sheet metal surface method for detecting abnormality based on graphical analysis | |
| CN111812114A (en) | On-line monitoring method and monitoring system for oil smoke pipeline | |
| CN109460705A (en) | Oil pipeline monitoring method based on machine vision | |
| CN111461487B (en) | Indoor decoration engineering wisdom management system based on BIM | |
| CN116611562A (en) | Intelligent park fire early warning management system and method based on Internet of things | |
| CN112949536B (en) | Fire alarm method based on cloud platform | |
| CN111812115A (en) | On-line monitoring method and monitoring system for oil smoke pipeline | |
| CN111812113A (en) | On-line monitoring method and monitoring system for oil smoke pipeline | |
| Liu et al. | An approach for auto bridge inspection based on climbing robot | |
| CN112560574A (en) | River black water discharge detection method and recognition system applying same | |
| CN112507789A (en) | Construction site safety behavior monitoring working method under block chain network state | |
| JP5186973B2 (en) | Worker safety inspection device | |
| KR100711364B1 (en) | An Exhaust Smoke Recognition and Auto-alarm Device and Method using Picture Image Analysis | |
| CN113781422A (en) | Pipeline construction violation identification method based on single image geometric measurement algorithm | |
| KR100627483B1 (en) | An Exhaust Smoke Recognition and Alarm Device and Method using Picture Image Analysis | |
| EP3825875A1 (en) | Installation environment estimation device and program | |
| CN111192253A (en) | Definition checking method and system based on contrast sensitivity and contrast | |
| JP5309069B2 (en) | Smoke detector | |
| Liu et al. | Imaging air quality evaluation using definition metrics and detrended fluctuation analysis | |
| CN112183342B (en) | Comprehensive convertor station defect identification method with template | |
| Wang et al. | Segmentation of casting defects in X-ray images based on fractal dimension |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20201023 |
|
| WW01 | Invention patent application withdrawn after publication |