CN116612118B - Artificial intelligence-based quality detection and evaluation method for building lightning arrester - Google Patents
Artificial intelligence-based quality detection and evaluation method for building lightning arrester Download PDFInfo
- Publication number
- CN116612118B CN116612118B CN202310883047.6A CN202310883047A CN116612118B CN 116612118 B CN116612118 B CN 116612118B CN 202310883047 A CN202310883047 A CN 202310883047A CN 116612118 B CN116612118 B CN 116612118B
- Authority
- CN
- China
- Prior art keywords
- area
- disc
- processed
- determining
- center point
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 31
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 15
- 238000011156 evaluation Methods 0.000 title claims abstract description 10
- 238000004088 simulation Methods 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims abstract description 13
- 238000010606 normalization Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims 1
- 238000003384 imaging method Methods 0.000 description 6
- 230000000007 visual effect Effects 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012163 sequencing technique Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of image processing, in particular to a quality detection and evaluation method for a building lightning arrester based on artificial intelligence. The method comprises the following steps: acquiring a gray level image of a lightning arrester, determining a large disc area and a small disc area, calculating the center point distance of the small disc area, determining the deviation degree of the small disc area according to the center point distance and the elliptical short axis length of the small disc area, and further determining the area to be processed; determining a reference pixel point, and determining the position of a simulation center point of a region to be processed according to the reference pixel point, the simulation area and the length of a long shaft of a large disc region; and determining the distribution quality of the disc areas according to the simulated center point positions of the areas to be processed and the center point positions of all the disc areas except the areas to be processed. The invention can effectively avoid detection errors caused by different disc sizes, effectively improve the reliability and objectivity of the distribution detection of the disc area, and further improve the accuracy of the quality detection of the lightning arrester.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to a quality detection and evaluation method for a building lightning arrester based on artificial intelligence.
Background
A lightning arrester is a device that protects the device from lightning strikes or transient overvoltage damage released by the power system. The phase of arrester is the disc of distributing on the arrester generally, when the disc interval of arrester does not accord with the design requirement, can lead to the arrester electrical property to drop, influences the arrester result of use. Therefore, the detection of the gap between the arrester disks is an important ring in the quality detection of the arrester.
In the related art, through shooting the image of arrester, then, confirm the interval between the arrester disc according to the position that different discs correspond in the image, under this kind of mode, because probably use two kinds at least discs on same arrester, and the size is different, the mode error of the direct distance of disc position determination in the image is great, and then leads to the reliability to disc distribution detection not enough, and the accuracy of arrester quality detection is relatively poor.
Disclosure of Invention
In order to solve the technical problems of insufficient reliability of disc distribution detection and poor accuracy of lightning arrester quality detection, the invention provides an artificial intelligence-based building lightning arrester quality detection and evaluation method, which adopts the following technical scheme:
the invention provides a quality detection and evaluation method of a building lightning arrester based on artificial intelligence, which comprises the following steps:
acquiring a gray level image of an arrester, carrying out semantic recognition and ellipse fitting on the gray level image of the arrester, determining at least two disc areas, dividing the disc areas into a large disc area and a small disc area according to the type of the arrester, and determining two large disc areas closest to the small disc area as adjacent areas of the small disc area;
taking a disc area with the shortest elliptical short axis as a reference area, calculating the distance between the center point of any small disc area and the center point of the reference area, determining the deviation degree of the small disc area according to the distance between the center point and the length of the elliptical short axis of the small disc area, and determining the area to be processed from the small disc area according to the deviation degree;
determining a simulation area of the to-be-processed area according to the area of the adjacent area and the short axis length of the to-be-processed area, taking a pixel point, which is closest to the center point of the reference area, in the to-be-processed area as a reference pixel point, and determining the simulation center point position of the to-be-processed area according to the reference pixel point, the simulation area and the long axis length of the large disc area;
and determining the distribution quality of the disc areas according to the simulated center point positions of the areas to be processed and the center point positions of all the disc areas except the areas to be processed.
Further, the determining a region to be processed from the small disc region according to the deviation degree includes:
and taking the small disc area with the deviation degree meeting the deviation condition as an area to be treated.
Further, the taking the small disc area, of which the deviation degree satisfies a deviation condition, as an area to be treated includes:
when the deviation degree is larger than a preset deviation degree threshold value, determining that the deviation degree meets a deviation condition;
and when the deviation degree is smaller than or equal to a preset deviation degree threshold value, determining that the deviation degree does not meet a deviation condition.
Further, the determining the simulation area of the area to be processed according to the area of the adjacent area and the short axis length of the area to be processed includes:
calculating the area difference value of the adjacent areas, and carrying out normalization processing on the area difference value to obtain an adjusting factor;
and taking the product of the adjustment factor and the area difference as a correction area, and calculating the sum of the minimum value of the areas of the adjacent areas and the correction area as the simulation area of the area to be processed.
Further, the determining the position of the simulation center point of the area to be processed according to the reference pixel point, the simulation area and the long axis length of the large disc area includes:
determining the simulated short axis length of the region to be processed after simulation according to the simulated area and the long axis length of the large disc region;
and determining the position of a simulation center point along the direction away from the reference area by taking the reference pixel point as a starting point and taking half of the length of the simulation minor axis as a distance.
Further, the determining the distribution quality of the disc area according to the simulated center point position of the area to be processed and the center point positions of all disc areas except the area to be processed includes:
counting the intervals between adjacent positions to be used as interval sequences according to the central point positions of all disc areas except the area to be processed and the simulated central point positions of all the area to be processed;
when the numerical value of each interval in the interval sequence is in a preset numerical value interval, determining that the distribution quality is qualified;
and when the numerical value of each interval in the interval sequence is not in a preset numerical value interval, determining that the distribution quality is unqualified.
Further, the determining the deviation degree of the small disc area according to the center point distance and the elliptical short axis length of the small disc area includes:
and calculating a sum normalized value of the center point distance and the elliptical short axis length of the small disc area as the deviation degree.
The invention has the following beneficial effects:
in order to prevent the distance between the discs of the lightning arrester from being influenced by the size of the discs after imaging, the small discs are stretched to be consistent with the area of the adjacent large discs, the quality detection is carried out on the disc distribution of the lightning arrester according to the simulated to-be-processed area and the distribution of the large disc area; according to the invention, the disc area with the shortest elliptical short axis is used as a reference area, and the reference area closest to the parallel visual angle of the camera can be determined according to the objective rule of camera imaging, so that the deviation degree of the small disc area can be determined according to the reference area, wherein the deviation degree can accurately represent the deviation characteristics of the corresponding small disc area, so that the small disc area to be processed can be determined according to the deviation characteristics, and the area to be processed is obtained; the method comprises the steps of determining the simulation area of the to-be-processed area, combining a reference pixel point and the simulation area to simulate the to-be-processed area, enabling the to-be-processed area representing the small disc to be used for simulating large discs with the same distribution, obtaining more accurate and reliable simulation center point positions, effectively representing the center point of the corresponding to-be-processed area, and carrying out quality detection according to the simulation center point positions and the center point positions of other disc areas.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a method for detecting and evaluating quality of a lightning arrester in a building based on artificial intelligence according to an embodiment of the invention.
Detailed Description
In order to further explain the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of the specific implementation, structure, characteristics and effects of the artificial intelligence-based quality detection and evaluation method for the construction lightning arrester according to the invention, which is provided by the invention, with reference to the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The invention provides a concrete scheme of a quality detection and evaluation method for a building lightning arrester based on artificial intelligence, which is specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for detecting and evaluating quality of a lightning arrester in a building based on artificial intelligence according to an embodiment of the invention is shown, where the method includes:
s101: acquiring a gray level image of the lightning arrester, carrying out semantic recognition and ellipse fitting on the gray level image of the lightning arrester, determining at least two disc areas, dividing the disc areas into a large disc area and a small disc area according to the type of the lightning arrester, and determining two large disc areas closest to the small disc area as adjacent areas of the small disc area.
In the embodiment of the invention, the arrester with the alternate large and small discs can be used as the arrester for quality detection, that is, the discs on the arrester are distributed into the large discs and the small discs at intervals, the arrester can be placed on the horizontal ground, a camera is used for shooting the arrester to obtain an original image of the arrester, and then the original image is subjected to preprocessing such as graying, image denoising and the like to obtain a gray image of the arrester.
In the embodiment of the present invention, the image graying may be, for example, mean graying processing, and the image denoising may be, for example, mean filtering denoising, where the image graying and the image denoising are well known in the art, and are not further described and limited.
It can be understood that, because the camera shoots the lightning arrester right, the area corresponding to the disc is shown as an elliptical area in the lightning arrester gray level image, and because the area is not on the same horizontal plane with the camera and the shape of the disc area in the lightning arrester gray level image is different due to the difference of the corresponding imaging angles, the disc areas of the same type are elliptical, but the elliptical shape has different shapes, that is, when the quality detection is carried out directly according to the distance of each disc in the shot lightning arrester gray level image as the real disc distance, the error is larger, therefore, the invention solves the problem by processing different disc areas.
The discs are distributed in a mode that the large discs and the small discs are distributed at intervals on the lightning arrester, so that the discs can be identified by semantic identification, then, the covered parts of the discs are fitted based on ellipse fitting to obtain disc areas, the disc areas of the same type have the same long axis length, and the short axis length of the disc areas changes along with the change of the visual angle. In the embodiment of the invention, the processing can be performed according to the scene, so that the quality detection of the lightning arrester is realized, and the following embodiment is specifically referred to.
It will be appreciated that since the small and large discs are spaced apart, i.e. the two large disc regions closest to any one small disc region are adjacent to that small disc, and when the small disc is at the top end of the arrester or at the bottom end of the arrester, the two large discs closest to each other, i.e. the two large discs closest below or above it, will correspond to the large disc region as the adjacent region to that small disc region.
S102: and taking the disc area with the shortest elliptical short axis as a reference area, calculating the center point distance between the center point of any small disc area and the center point of the reference area, determining the deviation degree of the small disc area according to the center point distance and the elliptical short axis length of the small disc area, and determining the area to be processed from the small disc area according to the deviation degree.
In the embodiment of the invention, it can be understood that as the viewing angle becomes larger, the corresponding elliptical short axis becomes larger gradually, that is, when the elliptical short axis is shortest, the viewing angle formed by the disc and the camera shooting is smallest, the disc area corresponding to the smallest viewing angle is taken as the reference area, and the reference area can represent the standard area of the disc, that is, other disc areas can be processed according to the reference area as the standard.
In the embodiment of the present invention, after the reference area is determined, the center point of the reference area may be further determined, and since the reference area is a standard elliptical area, the center point of the reference area is the center point of the elliptical area, and the obtaining of the center point of the ellipse is a well-known technique in the art, which is not limited thereto.
After the center point of the reference area and the center point of each small disc area are determined, the distance value between the center point of the reference area and the center point of the small disc area can be used as the center point distance of the small disc area, so that each disc area has a corresponding center point distance.
Further, in some embodiments of the present invention, determining the degree of deviation of the small disc region based on the center point distance and the elliptical short axis length of the small disc region comprises: and calculating a sum normalized value of the center point distance and the elliptical short axis length of the small disc area as the deviation degree.
The normalization process may specifically be, for example, maximum and minimum normalization processes, and the normalization in the subsequent steps may all employ maximum and minimum normalization processes, and in other embodiments of the present invention, other normalization methods may be selected according to a specific numerical range, which will not be described herein.
In the embodiment of the invention, when the short axis length of the small disc area is longer, the larger the horizontal visual angle difference between the small disc area and the camera can be represented, that is, the larger the deviation degree of the small disc area is. It will be appreciated that for small disc areas with a small degree of deviation, the position itself is relatively accurate and no processing is required, whereas for small disc areas with a large degree of deviation, the position error is large and processing can be performed, so that the invention can screen small disc areas with a large degree of deviation.
Further, in an embodiment of the present invention, determining a region to be processed from the small disc region according to the degree of deviation includes: and taking the small disc area with the deviation degree meeting the deviation condition as the area to be treated. The deviation condition is a judgment condition of the deviation degree, and in some embodiments of the present invention, the deviation condition may specifically be that the deviation degree meets a certain numerical requirement, that is, may be: when the deviation degree is larger than a preset deviation degree threshold value, determining that the deviation degree meets a deviation condition; and when the deviation degree is smaller than or equal to a preset deviation degree threshold value, determining that the deviation degree does not meet the deviation condition.
The preset deviation degree threshold is a deviation degree threshold, and optionally, the preset deviation degree threshold may be specifically, for example, 0.3, or may be adjusted according to actual requirements, which is not limited. That is, when the degree of deviation of the small disk region is greater than 0.3, the small disk region is regarded as the region to be treated.
In other embodiments of the present invention, the deviation condition may also be, for example, that the deviation degree is in a certain value interval, and the setting of the deviation condition may be according to the actual detection requirement, which is not limited.
S103: and determining the simulation area of the to-be-processed area according to the area of the adjacent area and the short axis length of the to-be-processed area, taking the pixel point closest to the center point of the reference area in the to-be-processed area as a reference pixel point, and determining the simulation center point position of the to-be-processed area according to the reference pixel point, the simulation area and the long axis length of the large disc area.
In the embodiment of the invention, in order to ensure that the calculation of the distance between the arrester discs is not influenced by the areas of the large discs and the small discs in the arrester gray level image, the embodiment of the invention can simulate and adjust the area of the small discs to match with the area of the adjacent large discs, thereby being capable of detecting the quality according to the simulated small disc area.
Further, in some embodiments of the present invention, determining the simulated area of the region to be processed based on the area of the adjacent region and the short axis length of the region to be processed includes: calculating the area difference value of the adjacent areas, and carrying out normalization processing on the area difference value to obtain an adjusting factor; and taking the product of the adjustment factor and the area difference as a correction area, and calculating the sum of the minimum value of the areas of the adjacent areas and the correction area as the simulation area of the area to be processed. The calculation formula corresponding to the simulation area may specifically be, for example:
in the method, in the process of the invention,representing the simulated area of the region to be treated,representing the maximum value of the area of the adjacent region,representing the minimum value of the area of the adjacent region,representing the difference in area of the adjacent regions,the normalization process is represented by the process of normalization,the expression "adjustment factor" is used to indicate,representing the correction area. The normalization process may specifically be, for example, a linear normalization process, or other normalization processes may be selected according to actual requirements, which is not limited.
In the embodiment of the invention, the area change of the disc under different angles generates the difference, so that the area of the area to be processed can be corrected according to the area change trend of the adjacent area of the area to be processed, and the corrected simulation area can be matched with the adjacent area. The area difference value of the adjacent areas is calculated to process the area change of the adjacent areas, and it can be understood that when the area change of the adjacent areas is larger, the corresponding deviation degree is larger, the same distance can correspond to the larger area difference, therefore, the distance is adjusted to be larger.
In the embodiment of the invention, the pixel point closest to the center point of the reference area in the area to be processed is taken as the reference pixel point, and the reference pixel point can be taken as the reference point when the area to be processed is adjusted according to the simulation area, so that the position analysis is performed.
Optionally, in some embodiments of the present invention, determining the location of the simulated center point of the area to be processed according to the reference pixel point, the simulated area, and the length of the long axis of the large disk area includes: determining the simulated short axis length of the region to be processed after simulation according to the simulated area and the long axis length of the large disc region; and determining the position of the simulation center point along the direction away from the reference area by taking the reference pixel point as a starting point and taking half of the length of the simulation short axis as a distance.
In the embodiment of the present invention, the major axis length of the large disc area is fixed, that is, the simulated minor axis length, can be calculated by combining the elliptic area calculation formula based on the simulated area and the major axis length, and it can be understood that the simulated minor axis length of the area to be processed is obtained by using the elliptic area=the circumferential rate×half of the major axis length×half of the minor axis length. And then, determining the position of the simulated center point according to the length of the simulated short axis and the reference pixel point, wherein the corresponding acquisition mode of the position of the simulated center point is that the reference pixel point is taken as a starting point, and half of the length of the simulated short axis is taken as a distance, so as to determine the position of the simulated center point. Thus, the simulated center point position of the simulated region to be processed is determined.
S104: and determining the distribution quality of the disc areas according to the simulated center point positions of the areas to be processed and the center point positions of all the disc areas except the areas to be processed.
Further, in other embodiments of the present invention, determining the distribution quality of the disc area according to the simulated center point position of the area to be processed and the center point positions of all disc areas except the area to be processed includes: counting the intervals between adjacent positions to be used as interval sequences according to the center point positions of all disc areas except the area to be processed and the simulated center point positions of all the area to be processed; when the numerical value of each interval in the interval sequence is in a preset numerical value interval, determining that the distribution quality is qualified; and when the numerical value of each interval in the interval sequence is not in the preset numerical value interval, determining that the distribution quality is unqualified.
After determining the simulated center point positions of the to-be-processed area, the embodiment of the invention can directly determine the center point positions of all the disc areas except the to-be-processed area, and sequence the center point positions and the simulated center point positions according to the position sequence, such as sequencing from top to bottom in the gray level image of the lightning arrester, that is, the embodiment of the invention acquires the center points finally obtained by each disc area, and sequences the center point positions so as to count the intervals between the adjacent center point positions according to the sequencing result, thereby obtaining the interval sequence.
In the embodiment of the invention, all disc areas except the area to be processed comprise all large disc areas and small disc areas which are used as the area to be processed, that is, the center point positions of all disc areas after being subjected to simulation processing are counted.
In the embodiment of the invention, each numerical value in the interval sequence can represent the corresponding interval length, and it can be understood that the interval length is still influenced by the camera angle, but the standard value corresponding to each interval length is set through the camera angle, so that the result is more accurate and more convenient for detecting the distribution quality.
Therefore, by setting the preset value interval, the embodiment of the invention can characterize that the distribution meets the corresponding standard when the value of the interval belongs to the preset value interval, and can characterize that the interval between the discs is larger or smaller and the corresponding quality is unqualified when the value of the interval does not belong to the preset value interval. The preset value interval may be, for example, a [50, 100] pixel point interval, and of course, the present invention may also be adjusted according to factors such as an imaging angle, a distance between a camera and a lightning arrester, and the like, which is not limited.
In other embodiments of the present invention, the numerical intervals of the intervals corresponding to the up and down of each different disc may be obtained respectively, so as to perform adaptive detection according to the actual detection situation. Of course, in other embodiments of the present invention, the real interval distance may be obtained according to the length of the interval section and the viewing angle, that is, converted into a length value representing the real interval, and adjusted according to the length value of the real interval. In the embodiment of the invention, the quality detection can be realized by processing the quality detection by using a plurality of other arbitrary possible implementation manners, and the method is not limited to the above.
In order to prevent the distance between the discs of the lightning arrester from being influenced by the size of the discs after imaging, the small discs are stretched to be consistent with the area of the adjacent large discs, the quality detection is carried out on the disc distribution of the lightning arrester according to the simulated to-be-processed area and the distribution of the large disc area; according to the invention, the disc area with the shortest elliptical short axis is used as a reference area, and the reference area closest to the parallel visual angle of the camera can be determined according to the objective rule of camera imaging, so that the deviation degree of the small disc area can be determined according to the reference area, wherein the deviation degree can accurately represent the deviation characteristics of the corresponding small disc area, so that the small disc area to be processed can be determined according to the deviation characteristics, and the area to be processed is obtained; the method comprises the steps of determining the simulation area of the to-be-processed area, combining a reference pixel point and the simulation area to simulate the to-be-processed area, enabling the to-be-processed area representing the small disc to be used for simulating large discs with the same distribution, obtaining more accurate and reliable simulation center point positions, effectively representing the center point of the corresponding to-be-processed area, and carrying out quality detection according to the simulation center point positions and the center point positions of other disc areas.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
Claims (5)
1. The quality detection and evaluation method for the building lightning arrester based on artificial intelligence is characterized in that the types of discs in the lightning arrester comprise large discs and small discs, the large discs and the small discs are alternately distributed, and the method comprises the following steps:
acquiring a gray level image of an arrester, carrying out semantic recognition and ellipse fitting on the gray level image of the arrester, determining at least two disc areas, dividing the disc areas into a large disc area and a small disc area according to the type of the arrester, and determining two large disc areas closest to the small disc area as adjacent areas of the small disc area;
taking a disc area with the shortest elliptical short axis as a reference area, calculating the distance between the center point of any small disc area and the center point of the reference area, determining the deviation degree of the small disc area according to the distance between the center point and the length of the elliptical short axis of the small disc area, and determining the area to be processed from the small disc area according to the deviation degree;
determining a simulation area of the to-be-processed area according to the area of the adjacent area and the short axis length of the to-be-processed area, taking a pixel point, which is closest to the center point of the reference area, in the to-be-processed area as a reference pixel point, and determining the simulation center point position of the to-be-processed area according to the reference pixel point, the simulation area and the long axis length of the large disc area;
determining the distribution quality of the disc areas according to the simulated center point positions of the areas to be processed and the center point positions of all the disc areas except the areas to be processed;
the determining the simulation area of the area to be processed according to the area of the adjacent area and the short axis length of the area to be processed comprises the following steps:
calculating the area difference value of the adjacent areas, and carrying out normalization processing on the area difference value to obtain an adjusting factor;
taking the product of the adjustment factor and the area difference as a correction area, and calculating the sum of the minimum value of the areas of the adjacent areas and the correction area as the simulation area of the area to be processed;
the determining the position of the simulation center point of the area to be processed according to the reference pixel point, the simulation area and the long axis length of the large disc area comprises the following steps:
determining the simulated short axis length of the region to be processed after simulation according to the simulated area and the long axis length of the large disc region;
and determining the position of a simulation center point along the direction away from the reference area by taking the reference pixel point as a starting point and taking half of the length of the simulation minor axis as a distance.
2. The artificial intelligence based quality inspection and evaluation method for a construction lightning arrester according to claim 1, wherein the determining the area to be processed from the small disc area according to the degree of deviation comprises:
and taking the small disc area with the deviation degree meeting the deviation condition as an area to be treated.
3. The method for detecting and evaluating the quality of a construction lightning arrester based on artificial intelligence according to claim 2, wherein the small disc area, which has the degree of deviation satisfying a deviation condition, is used as an area to be processed, and comprises the steps of:
when the deviation degree is larger than a preset deviation degree threshold value, determining that the deviation degree meets a deviation condition;
and when the deviation degree is smaller than or equal to a preset deviation degree threshold value, determining that the deviation degree does not meet a deviation condition.
4. The method for detecting and evaluating the quality of the building lightning arrester based on artificial intelligence according to claim 1, wherein the determining the distribution quality of the disc areas according to the simulated center point positions of the areas to be processed and the center point positions of all disc areas except the areas to be processed comprises:
counting the intervals between adjacent positions to be used as interval sequences according to the central point positions of all disc areas except the area to be processed and the simulated central point positions of all the area to be processed;
when the numerical value of each interval in the interval sequence is in a preset numerical value interval, determining that the distribution quality is qualified;
and when the numerical value of each interval in the interval sequence is not in a preset numerical value interval, determining that the distribution quality is unqualified.
5. The method for evaluating the quality detection of the building lightning arrester based on artificial intelligence according to claim 1, wherein the determining the deviation degree of the small disc area according to the center point distance and the elliptical short axis length of the small disc area comprises:
and calculating a sum normalized value of the center point distance and the elliptical short axis length of the small disc area as the deviation degree.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310883047.6A CN116612118B (en) | 2023-07-19 | 2023-07-19 | Artificial intelligence-based quality detection and evaluation method for building lightning arrester |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310883047.6A CN116612118B (en) | 2023-07-19 | 2023-07-19 | Artificial intelligence-based quality detection and evaluation method for building lightning arrester |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116612118A CN116612118A (en) | 2023-08-18 |
| CN116612118B true CN116612118B (en) | 2023-10-03 |
Family
ID=87678624
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310883047.6A Active CN116612118B (en) | 2023-07-19 | 2023-07-19 | Artificial intelligence-based quality detection and evaluation method for building lightning arrester |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116612118B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06331337A (en) * | 1993-05-26 | 1994-12-02 | Ricoh Co Ltd | Method for inspecting optical disk defect |
| JP2004178783A (en) * | 2002-08-01 | 2004-06-24 | Ricoh Co Ltd | Optical disk inspection device, optical disk inspection method, manufacturing method of optical disk, and optical disk |
| DE102010061505A1 (en) * | 2010-12-22 | 2012-06-28 | Kla-Tencor Mie Gmbh | Method for inspection and detection of defects on surfaces of disk-shaped objects and computer system with a software product for carrying out the method |
| CN105392286A (en) * | 2015-11-10 | 2016-03-09 | 深圳崇达多层线路板有限公司 | Method for detecting circuit offset situation of core plate |
| CN106951900A (en) * | 2017-04-13 | 2017-07-14 | 杭州申昊科技股份有限公司 | A kind of automatic identifying method of arrester meter reading |
| CN113077447A (en) * | 2021-04-02 | 2021-07-06 | 保定市毅格通信自动化有限公司 | Method capable of detecting weak discharge of high-voltage equipment and analyzing defects |
-
2023
- 2023-07-19 CN CN202310883047.6A patent/CN116612118B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH06331337A (en) * | 1993-05-26 | 1994-12-02 | Ricoh Co Ltd | Method for inspecting optical disk defect |
| JP2004178783A (en) * | 2002-08-01 | 2004-06-24 | Ricoh Co Ltd | Optical disk inspection device, optical disk inspection method, manufacturing method of optical disk, and optical disk |
| DE102010061505A1 (en) * | 2010-12-22 | 2012-06-28 | Kla-Tencor Mie Gmbh | Method for inspection and detection of defects on surfaces of disk-shaped objects and computer system with a software product for carrying out the method |
| CN105392286A (en) * | 2015-11-10 | 2016-03-09 | 深圳崇达多层线路板有限公司 | Method for detecting circuit offset situation of core plate |
| CN106951900A (en) * | 2017-04-13 | 2017-07-14 | 杭州申昊科技股份有限公司 | A kind of automatic identifying method of arrester meter reading |
| CN113077447A (en) * | 2021-04-02 | 2021-07-06 | 保定市毅格通信自动化有限公司 | Method capable of detecting weak discharge of high-voltage equipment and analyzing defects |
Non-Patent Citations (3)
| Title |
|---|
| Evaluating surface quality by luminance and surface roughness;Toshiaki Otsuki;Precision Engineering;第74卷;147-162 * |
| 一种有效的影像中椭圆形目标提取方法;郭成成;郑守住;;电子测量技术;第40卷(第04期);167-171 * |
| 基于数字图像分析法的机制砂清水混凝土外观质量评价;屠海峰;铁道建筑;第63卷(第06期);140-144 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116612118A (en) | 2023-08-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110349199B (en) | Object roundness measuring method | |
| CN112818988A (en) | Automatic reading identification method and system for pointer instrument | |
| CN108764257A (en) | A kind of pointer instrument recognition methods of various visual angles | |
| Dong et al. | Robust circular marker localization under non-uniform illuminations based on homomorphic filtering | |
| CN110049319B (en) | Camera definition detection method and definition detection graphic card | |
| CN110443278B (en) | Method, device and equipment for detecting thickness abnormality of grid line of solar cell | |
| CN113514036B (en) | Super high-rise building verticality measurement and control method | |
| CN107356202A (en) | A kind of laser scanning measurement system target sights method automatically | |
| CN117152163B (en) | Bridge construction quality visual detection method | |
| CN109992011B (en) | Secondary alignment method, device and equipment for inspection robot holder | |
| CN114782421B (en) | Poultry veterinarian auxiliary system based on egg laying abnormality detection | |
| CN112861870B (en) | Pointer instrument image correction method, system and storage medium | |
| CN110991297A (en) | Target positioning method and system based on scene monitoring | |
| CN107525652B (en) | Lens distortion testing method, device and system | |
| CN105701776B (en) | A kind of lens distortion antidote and system for automatic optics inspection | |
| CN114413854B (en) | Real-scene three-dimensional image checking system based on oblique photography | |
| CN115272349A (en) | Method for detecting welding defects of computer PCB main board | |
| CN116612118B (en) | Artificial intelligence-based quality detection and evaluation method for building lightning arrester | |
| CN113128378B (en) | Finger vein rapid identification method | |
| CN112560839A (en) | Automatic identification method and system for reading of pointer instrument | |
| CN117372515A (en) | Self-adaptive deviation rectifying control system | |
| CN115272345B (en) | Image processing-based fireproof fabric quality analysis method | |
| CN115205317B (en) | Bridge monitoring photoelectric target image light spot center point extraction method | |
| CN116403085A (en) | Multi-pointer instrument identification method and device for transformer substation based on multitasking | |
| CN116823709A (en) | Automatic transformer oil level identification method and device based on image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |