CN113822180A - Air switch on-off state identification method and device, electronic equipment and storage medium - Google Patents

Air switch on-off state identification method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN113822180A
CN113822180A CN202111045795.4A CN202111045795A CN113822180A CN 113822180 A CN113822180 A CN 113822180A CN 202111045795 A CN202111045795 A CN 202111045795A CN 113822180 A CN113822180 A CN 113822180A
Authority
CN
China
Prior art keywords
air switch
state
area
picture
air
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202111045795.4A
Other languages
Chinese (zh)
Inventor
刘涛
符子瑞
赵海红
王立延
胡正扬
董浩
魏永涛
刘军
赵淑钰
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Changlong Railway Electronic Engineering Co ltd
Original Assignee
Shenzhen Changlong Railway Electronic Engineering Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Changlong Railway Electronic Engineering Co ltd filed Critical Shenzhen Changlong Railway Electronic Engineering Co ltd
Priority to CN202111045795.4A priority Critical patent/CN113822180A/en
Publication of CN113822180A publication Critical patent/CN113822180A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/21Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
    • G06F18/214Generating training patterns; Bootstrap methods, e.g. bagging or boosting
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00Pattern recognition
    • G06F18/20Analysing
    • G06F18/24Classification techniques
    • G06F18/241Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • GPHYSICS
    • G07CHECKING-DEVICES
    • G07CTIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
    • G07C1/00Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
    • G07C1/20Checking timed patrols, e.g. of watchman

Landscapes

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

Abstract

The invention relates to an air switch on-off state identification method and device, electronic equipment and a storage medium, and relates to the technical field of power equipment. The method for identifying the on-off state of the air switch comprises the following steps: acquiring a picture of an air switch on a machine room inspection site; intercepting a picture of the air switch on the machine room inspection site based on a preset pixel coordinate of the air switch to obtain a regional map of the air switch; carrying out edge detection on the area diagram of the air switch to obtain an edge diagram of the air switch; detecting all contours in the edge map of the air switch to obtain the maximum contour of the air switch; acquiring a minimum circumscribed rectangle of the maximum outline of the air switch, and intercepting an insulating handle area diagram from an area diagram of the air switch according to the minimum circumscribed rectangle; and judging the on-off state of the air switch according to the insulating handle area diagram, and intelligently monitoring the on-off state of the air switch.

Description

Air switch on-off state identification method and device, electronic equipment and storage medium
Technical Field
The invention relates to the technical field of routing inspection of equipment in a rail transit machine room and low-voltage distribution equipment of an electric power system, in particular to a method and a device for identifying the on-off state of an air switch, electronic equipment and a storage medium.
Background
An air switch is a kind of circuit breaker, which can automatically open as long as the current in the circuit exceeds the rated current. The air switch is an important electrical appliance in a low-voltage distribution system of a railway machine room, can complete contact and breaking of a circuit, and can also protect the short circuit, serious overload, undervoltage and the like of the circuit or electrical equipment. Therefore, the inspection of the state of the air switch is an important point in the inspection of equipment in a machine room. In the prior art, the on-off state of the air switch in the machine room is mostly detected by adopting a manual inspection mode, the workload is large, the real-time monitoring cannot be realized, and the on-off state of the air switch and the power supply condition of the equipment cannot be timely mastered.
Disclosure of Invention
The invention provides a method and a device for identifying the on-off state of an air switch, electronic equipment and a storage medium, and aims to solve the problem that the on-off state of the air switch cannot be automatically and intelligently monitored.
In a first aspect, the invention provides a method for identifying an on-off state of an air switch, which comprises the following steps:
acquiring a picture of an air switch on a machine room inspection site;
intercepting the picture of the air switch on the inspection site based on the pixel coordinates of a preset air switch to obtain a regional map of the air switch;
carrying out edge detection on the area diagram of the air switch to obtain an edge diagram of the air switch;
detecting all contours in the edge map of the air switch to obtain the maximum contour of the air switch;
acquiring a minimum circumscribed rectangle of the maximum outline of the air switch, and intercepting an insulating handle area diagram from an area diagram of the air switch according to the minimum circumscribed rectangle;
and judging the on-off state of the air switch according to the insulating handle area diagram.
In a second aspect, the invention provides an identification device, which comprises a unit for executing the method for identifying the on-off state of the air switch in any embodiment of the first aspect.
In a third aspect, an electronic device is provided, which includes a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the steps of the method for identifying the on-off state of the air switch according to any embodiment of the first aspect when executing the program stored in the memory.
In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, which when executed by a processor implements the steps of the air switch on-off state identification method according to any one of the embodiments of the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the invention has the following advantages:
according to the method provided by the embodiment of the invention, the area map of the air switch is processed by an edge detection method to obtain an edge map of the air switch; detecting all the contours of the air switch edge map to obtain the maximum contour of the air switch; acquiring a minimum circumscribed rectangle of the maximum outline of the air switch, and acquiring an insulating handle area diagram from the area diagram of the air switch according to the description information of the minimum circumscribed rectangle; and judging the on-off state of the air switch according to the insulating handle area diagram and a preset insulating handle reference diagram, so as to realize intelligent monitoring of the on-off state of the air switch.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without inventive exercise.
Fig. 1 is a schematic flow chart of an air switch on-off state identification method provided in an embodiment of the present invention;
fig. 2 is a sub-flow schematic diagram of an air switch on-off state identification method provided by an embodiment of the present invention;
fig. 3 is a sub-flow schematic diagram of an air switch on-off state identification method provided by an embodiment of the present invention;
FIG. 4 is a pictorial view of an insulated handle of an air switch provided in accordance with an embodiment of the present invention;
fig. 5 is a sub-flow schematic diagram of an air switch on-off state identification method provided in an embodiment of the present invention;
fig. 6 is a sub-flow schematic diagram of an air switch on-off state identification method provided in an embodiment of the present invention;
fig. 7 is a sub-flow schematic diagram of an air switch on-off state identification method provided in an embodiment of the present invention;
fig. 8 is a schematic diagram of an insulating handle sub-region of an air switch in an air switch on-off state identification method according to an embodiment of the present invention;
fig. 9 is a block diagram of an identification apparatus according to an embodiment of the present invention;
fig. 10 is a block diagram of another identification apparatus according to an embodiment of the present invention;
fig. 11 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
Example 1
Fig. 1 is a schematic flow chart of an air switch on-off state identification method according to an embodiment of the present invention. The embodiment of the invention provides an air switch on-off state identification method, and particularly relates to fig. 1, the air switch on-off state identification method comprises the following steps of S101-S106.
S101, obtaining a picture of the air switch of the machine room inspection site.
In specific implementation, a camera inspection preset position is set according to the optimal shooting angle; and during inspection, the camera locks the inspection equipment to shoot according to preset position information set by the inspection task to obtain a corresponding air switch picture.
S102, intercepting the picture of the air switch on the inspection site based on the preset pixel coordinates of the air switch to obtain the area map of the air switch.
And manually processing the preset bitmap of the air switch area in advance to obtain the pixel coordinates of the air switch and storing the pixel coordinates into the inspection platform.
When the machine room equipment is patrolled, the air switch area is intercepted from the patrolling and examining field air switch picture according to the pixel coordinate of the air switch stored in the patrolling and examining platform, and the area map of the air switch is obtained.
Wherein, before equipment patrols and examines, training target detection model need gather on-the-spot air switch in advance and shoot the picture as training data, and the picture of shooing should simulate actual shooting condition as far as possible, contains and is not limited to: the camera is at different preset positions, different angles, different focal lengths, different distances, different lighting conditions and the like.
Optionally, before step S102, processing a preset position picture by using a pre-trained target detection model to obtain pixel coordinates of an air switch region in the preset position picture, storing the pixel coordinates of the air switch in a json format, and storing the pixel coordinates into an inspection platform after manual rechecking;
in an embodiment, referring to fig. 2, fig. 2 is a sub-flow schematic diagram of an air switch on-off state identification method provided by an embodiment of the present invention. The above step S102 includes steps S201 to S202.
S201, numbering area graphs of all the air switches in the computer room polling field air switch picture according to pixel coordinates in rows and columns, and associating corresponding air switch pixel coordinates to obtain air switch numbers corresponding to the pixel coordinates of the air switches.
In specific implementation, as one power supply screen is provided with a plurality of rows of air switches, each row is provided with a plurality of air switches, and in a deployment stage, each air switch is numbered according to rows and columns and is associated with a corresponding air switch pixel coordinate; in the actual inspection stage, only the air switch area is calculated instead of the original image, so that the waste of calculation resources is avoided, the processing time is shortened, and the detection efficiency is improved.
S202, obtaining an area map of the air switch according to the air switch number corresponding to the pixel coordinate of the air switch.
It should be noted that, the area diagram of the air switch is obtained according to the air switch number, and then whether the on-off state of each air switch is normal is judged, and the maintenance of the worker is facilitated through the air switch number.
S103, carrying out edge detection on the area map of the air switch to obtain an edge map of the air switch.
Referring to fig. 3, fig. 3 is a sub-flow schematic diagram of an air switch on-off state identification method according to an embodiment of the present invention. In one embodiment, the above step S103 includes the following steps: S301-S303.
S301, cutting edge areas with preset widths on two sides of the area diagram of the air switch respectively to obtain a middle area picture.
In specific implementation, in order to eliminate interference, edges with preset widths are respectively cut at two sides of a region diagram of the air switch, wherein the width of the left side and the width of the right side can be respectively cut by 10%, the middle 80% of the region is reserved, the height of the picture is kept unchanged, and a picture in the middle region is obtained.
The cutting proportion of 10% and 80% should be adjusted according to the actual situation, and this patent does not limit this.
And S302, if the middle area picture is a color picture, converting the middle area picture into a gray scale picture.
If the intermediate image is a color image, the intermediate image is converted into a gray image, and the edge of the image is determined by the gradient change of the gray image to obtain an edge image.
The method obtains an edge image through gray image conversion, can also directly process the color image, decomposes the color image into different channels according to a color space model, carries out edge detection on each channel image to obtain an edge image corresponding to each channel, and obtains a group of channel edge images.
And S303, carrying out edge detection on the gray-scale image to obtain an edge image of the air switch.
In specific implementation, the edge of the image is judged through the change of the image gray gradient to obtain an edge image, wherein the image gray gradient is the difference value between two adjacent pixels.
And S104, detecting all the contours in the edge map of the air switch to obtain the maximum contour of the air switch.
In specific implementation, the maximum contour is screened out according to the area of the contour of the air switch; the area of the outline can be calculated according to the number of pixels contained in the outline or the areas of various circumscribed polygons, circumscribed circles and circumscribed ellipses; if the set of channel edge maps is a set of channel edge maps, the maximum profile of each channel is calculated first, and then the maximum profile in the set is obtained through comparison.
S105, acquiring a minimum circumscribed rectangle of the maximum outline of the air switch, and intercepting an insulating handle area diagram from the air switch area diagram according to the minimum circumscribed rectangle.
In a specific implementation, all points on the maximum contour form a point set, and a circumscribed rectangle which can contain all the points and has the minimum area is fitted according to the coordinate positions of the points. The circumscribed rectangle contains exactly the insulated handle area, possibly a rectangle with a certain angle of inclination.
Referring to fig. 4, fig. 4 is a physical diagram of an insulated handle of an air switch provided in an embodiment of the present invention. In fig. 4 the insulated handle 400 is located in the middle black area of the picture.
Referring to fig. 5, fig. 5 is a sub-flow schematic diagram of an air switch on-off state identification method according to an embodiment of the present invention. In one embodiment, the above step S105 includes the following steps: S501-S502.
S501, acquiring a minimum circumscribed rectangle corresponding to the maximum outline in the area diagram of the air switch, and acquiring description information of the minimum circumscribed rectangle of the air switch, wherein the description information comprises the width, the height, the angle and the vertex of the minimum circumscribed rectangle.
In specific implementation, the maximum outline is obtained according to the enclosed area of the image edge outline, then the minimum circumscribed rectangle of the maximum outline is obtained, the area enclosed by the minimum circumscribed rectangle is the insulated handle area, and the description information of the minimum circumscribed rectangle of the air switch is obtained. The description information includes a width, a height, an angle, and a vertex of the minimum bounding rectangle.
S502, according to the description information of the minimum circumscribed rectangle of the air switch, the area diagram of the insulated handle is obtained by intercepting from the area diagram of the air switch.
In specific implementation, the area map of the insulated handle is obtained according to the area corresponding to the minimum circumscribed rectangle cut out from the area map of the air switch by the description information of the minimum circumscribed rectangle. Due to the restriction of the field environment, the insulating handle obtained by actual shooting may have a certain inclination or deformation.
For tilt problems, the corresponding region may be rotated according to an angle in the description information.
For the deformation problem, a group of corresponding points can be set according to the corner points with large edge gradient change or the center, the gravity center and the like of the area; calculating a transformation matrix of corresponding affine transformation or transmission transformation according to the corresponding point; and calculating the insulating handle area graph according to the corresponding area and the transformation matrix.
And S106, judging the on-off state of the air switch according to the insulating handle area diagram.
In specific implementation, the on-off state of the air switch can be judged by two methods: firstly, after the insulating handle area graph is divided by a threshold value, comparing pixel mean values of an upper part and a lower part of an insulating handle; and secondly, calculating the similarity between the insulating handle area graph and a preset insulating handle reference graph to judge the on-off state of the air switch. It should be noted that the insulating handle area map may be a gray map or a color map; for the color image, the similarity can be calculated by using the whole image, or the similarity can be calculated by using a certain channel image or a weighted addition image of a plurality of channel images, or the similarity can be a weighted result of the similarity. The type of the preset insulated handle reference picture corresponds to the insulated handle area picture.
The invention is not limited to the calculation method of the similarity, and the following method of the Dice coefficient is only used as an example.
The method for judging the on-off state of the air switch through the similarity specifically refers to fig. 6, and fig. 6 is a sub-flow schematic diagram of the method for identifying the on-off state of the air switch provided by the embodiment of the invention. In one embodiment, the above step S106 includes the following steps: S601-S603.
S601, obtaining a plurality of preset insulation handle reference pictures, wherein the insulation handle reference pictures comprise classification labels, and the classification labels are opened or closed.
It should be noted that, a group of insulating handle pictures is prepared in advance as reference pictures, and is classified according to the on-off state of the air switch into two types, namely open and closed, for example, the insulating handle area is open in the upper half of the picture, and the insulating handle area is closed in the lower half of the picture. Each type of reference picture comprises shot pictures with different shooting angles and different lighting conditions in actual detection.
And S602, calculating the similarity between the insulating handle area graph and each insulating handle reference graph.
And obtaining the similarity of the reference image by calculating the Dice coefficient of the insulating handle area image and the reference image. The Dice coefficient is a set similarity measurement function, and is usually used for calculating the similarity of two samples, and the value range is [0,1], that is, the equation of Dice coefficient s is:
Figure BDA0003251147950000061
wherein | X | Y | is the intersection between X and Y, and | X | and | Y | respectively represent the number of elements of X and Y; in this embodiment, X is a diagram of the area of the insulated handle, and Y is a reference diagram of each insulated handle.
And S603, determining the on-off state of the air switch according to the classification label of the insulation handle reference picture with the highest similarity.
In specific implementation, the similarity between the insulating handle area graph and the preset insulating handle reference graph is respectively obtained according to the Dice coefficient, the insulating handle area graph and the preset insulating handle reference graph are sorted from high to low to obtain the insulating handle reference graph with the highest similarity, the type of the insulating handle reference graph with the highest similarity is judged, and the on-off state of the air switch can be obtained according to the classification of the on-off state or the on-off state of the insulating handle reference graph.
The method for judging the on-off state of the air switch through the pixel mean value of the region specifically refers to fig. 7, and fig. 7 is a sub-flow schematic diagram of the method for identifying the on-off state of the air switch provided by the embodiment of the invention. In one embodiment, the above step S106 includes the following steps: S701-S702.
S701, dividing the insulating handle region map into an upper sub-region and a lower sub-region according to a preset proportion, and calculating pixel mean values of the two sub-regions respectively.
In specific implementation, if the insulating handle area image is a gray scale image, threshold segmentation is performed, then the number of pixel points in the upper sub-area of the insulating handle area image and the pixel value of each pixel point are obtained, and the pixel values are accumulated and then divided by the number of the pixel points to obtain the pixel average value of the upper sub-area of the insulating handle area image; and similarly, acquiring the pixel mean value of the lower sub-region of the insulating handle region map. If the insulating handle area image is a color image, the color image can be decomposed into different channels according to a color space model, a certain channel image or a weighted addition image of a plurality of channel images is used for threshold segmentation, and then the pixel mean value of the upper subregion and the lower subregion is obtained.
S702, determining the on-off state of the air switch according to the pixel mean value of the sub-region.
The threshold value division method determines the final comparison method. The insulation handle of the air switch is generally dark, the pixel value is low, after threshold segmentation is carried out, the pixel mean values of the upper and lower sub-areas of the insulation handle area are compared, wherein if the sub-area with the small pixel mean value is below, the insulation handle is indicated to be pushed below, and the opening and closing state of the air switch is further determined; if the threshold segmentation adopts binary negation, the situation is opposite to the actual situation, the sub-region with the large pixel mean value is an insulating handle, and the on-off state of the air switch is determined according to the position of the sub-region with the large pixel mean value.
For example, referring to fig. 8, fig. 8 is a schematic view of an insulating handle portion of an air switch in an air switch on-off state identification method according to an embodiment of the present invention. In specific implementation, if the maximum contour cannot be found successfully, the area map of the air switch may be cut according to a fixed proportion, the cut part is divided into an upper part and a lower part, and the pixel mean values of the two areas are used for comparison to judge the opening and closing state of the air switch. In fig. 8, a is an upper sub-region of the insulated handle region, and B is a lower sub-region of the insulated handle region.
The mean value in this embodiment is only an example, and other statistical features may be used, which is not limited herein.
Example 2
Referring to fig. 9, fig. 9 is a block diagram of an identification apparatus according to an embodiment of the present invention. As shown in fig. 9, an embodiment of the present invention further provides an identification apparatus 900, which includes a first obtaining unit 901, a first truncating unit 902, a first detecting unit 903, a second detecting unit 904, a second obtaining unit 905, and a first judging unit 906.
The first obtaining unit 901 is used for obtaining a picture of the air switch of the machine room inspection field.
The first intercepting unit 902 is configured to intercept the picture of the on-site air switch for machine room inspection based on preset pixel coordinates of the air switch, so as to obtain a region map of the air switch.
A first detecting unit 903, configured to perform edge detection on the area map of the air switch, so as to obtain an edge map of the air switch.
A second detecting unit 904, configured to detect all contours in the edge map of the air switch, and obtain a maximum contour of the air switch.
The second obtaining unit 905 is configured to obtain a minimum circumscribed rectangle of a maximum outline of the air switch, and intercept an insulating handle area diagram from the air switch area diagram according to the minimum circumscribed rectangle.
And a first judging unit 906 configured to judge an on/off state of the air switch according to the insulating handle region map.
In an embodiment, the acquiring the on-off state of the air switch according to the insulating handle area diagram includes:
acquiring a plurality of preset insulation handle reference pictures, wherein the insulation handle reference pictures comprise classification labels, and the classification labels are opened or closed;
calculating the similarity between the insulating handle area graph and each insulating handle reference graph;
and determining the on-off state of the air switch according to the classification label of the insulation handle reference picture with the highest similarity.
In an embodiment, the acquiring the on-off state of the air switch according to the insulating handle area diagram includes:
dividing the insulating handle region map into an upper sub region and a lower sub region according to a preset proportion, and respectively calculating the pixel mean values of the two sub regions;
and determining the on-off state of the air switch according to the pixel average value of the sub-region.
In an embodiment, if the number of the air switches is greater than 1, the intercepting is performed on the picture of the air switch on the inspection site based on the preset pixel coordinates of the air switches to obtain the area map of the air switches, including:
and numbering the area maps of the air switches in the computer room inspection site air switch picture according to pixel coordinates in rows and columns, and associating the corresponding air switch pixel coordinates to obtain the air switch numbers corresponding to the pixel coordinates of the air switches.
In an embodiment, the performing edge detection on the area map of the air switch to obtain an edge map of the air switch includes:
respectively cutting edge areas with preset widths at two sides of the area diagram of the air switch to obtain a middle area picture;
if the middle area picture is a color picture, converting the middle area picture into a gray scale picture;
and carrying out edge detection on the gray-scale image to obtain an edge image of the air switch.
In one embodiment, the obtaining a minimum bounding rectangle of a maximum outline of the air switch, the insulating handle region map being taken from a region map of the air switch according to the minimum bounding rectangle, includes:
acquiring a minimum circumscribed rectangle corresponding to a maximum outline in a regional diagram of the air switch to obtain description information of the minimum circumscribed rectangle of the air switch, wherein the description information comprises the width, the height, the angle and the vertex of the minimum circumscribed rectangle;
and according to the description information of the minimum circumscribed rectangle of the air switch, the area diagram of the insulated handle is obtained by intercepting from the area diagram of the air switch.
Example 3
Referring to fig. 10, fig. 10 is a block diagram of another identification apparatus according to an embodiment of the present invention. As shown in fig. 10, an identification apparatus 900 is further provided in an embodiment of the present invention, and embodiment 3 differs from embodiment 2 in that it further includes: a third acquisition unit 907 and a first storage unit 908.
A third obtaining unit 907, configured to process the reference map of the air switch area through a pre-trained target detection model, so as to obtain pixel coordinates of the air switch.
The first storage unit 908 is configured to store the pixel coordinates of the air switch in a json format and store the pixel coordinates in a preset storage location.
Example 4
As shown in fig. 11, an embodiment of the present invention provides an electronic device, which includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114, where the processor 111, the communication interface 112, and the memory 113 complete mutual communication via the communication bus 114,
a memory 113 for storing a computer program;
and the processor 111 is configured to implement the method for identifying the on/off state of the air switch according to any one of the above-described method embodiments when executing the program stored in the memory 113.
Embodiments of the present invention further provide a computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for identifying the on/off state of the air switch provided in any one of the foregoing method embodiments.
It is noted that, in this document, relational terms such as "first" and "second," and the like, may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The foregoing are merely exemplary embodiments of the present invention, which enable those skilled in the art to understand or practice the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (10)

1. An air switch on-off state identification method is characterized by comprising the following steps:
acquiring a picture of an air switch on a machine room inspection site;
intercepting the picture of the air switch on the inspection site based on the pixel coordinates of a preset air switch to obtain a regional map of the air switch;
carrying out edge detection on the area diagram of the air switch to obtain an edge diagram of the air switch;
detecting all contours in the edge map of the air switch to obtain the maximum contour of the air switch;
acquiring a minimum circumscribed rectangle of the maximum outline of the air switch, and intercepting an insulating handle area diagram from an area diagram of the air switch according to the minimum circumscribed rectangle;
and judging the on-off state of the air switch according to the insulating handle area diagram.
2. The method for identifying the on/off state of the air switch according to claim 1, wherein the acquiring the on/off state of the air switch from the insulating handle area diagram includes:
acquiring a plurality of preset insulation handle reference pictures, wherein the insulation handle reference pictures comprise classification labels, and the classification labels are opened or closed;
calculating the similarity between the insulating handle area graph and each insulating handle reference graph;
and determining the on-off state of the air switch according to the classification label of the insulation handle reference picture with the highest similarity.
3. The method for identifying the on/off state of the air switch according to claim 1, wherein the acquiring the on/off state of the air switch from the insulating handle area diagram includes:
dividing the insulating handle region map into an upper sub region and a lower sub region according to a preset proportion, and respectively calculating the pixel mean values of the two sub regions;
and determining the on-off state of the air switch according to the pixel average value of the sub-region.
4. The air switch on-off state identification method according to claim 1, wherein before the intercepting the picture of the inspection field air switch based on the preset pixel coordinates of the air switch to obtain the area map of the air switch, the method further comprises:
processing the reference image of the air switch area through a pre-trained target detection model to obtain the pixel coordinates of the air switch;
and storing the pixel coordinates of the air switch into a json format, and storing the pixel coordinates to a preset storage position.
5. The method for identifying the on-off state of the air switch according to claim 1, wherein if the number of the air switches is greater than 1, the process of intercepting the picture of the inspection on-site air switch based on the preset pixel coordinates of the air switches to obtain the area map of the air switches comprises the following steps:
and numbering the area maps of the air switches in the computer room inspection site air switch picture according to pixel coordinates in rows and columns, and associating the corresponding air switch pixel coordinates to obtain the air switch numbers corresponding to the pixel coordinates of the air switches.
6. The method for identifying an on/off state of an air switch according to claim 1, wherein the edge detection of the area map of the air switch to obtain the edge map of the air switch includes:
respectively cutting edge areas with preset widths at two sides of the area diagram of the air switch to obtain a middle area picture;
if the middle area picture is a color picture, converting the middle area picture into a gray scale picture;
and carrying out edge detection on the gray-scale image to obtain an edge image of the air switch.
7. The air switch on-off state recognition method according to claim 1, wherein the step of obtaining a minimum circumscribed rectangle of a maximum outline of the air switch and cutting out an insulating handle region diagram from the region diagram of the air switch according to the minimum circumscribed rectangle comprises:
acquiring a minimum circumscribed rectangle corresponding to a maximum outline in a regional diagram of the air switch to obtain description information of the minimum circumscribed rectangle of the air switch, wherein the description information comprises the width, the height, the angle and the vertex of the minimum circumscribed rectangle;
and according to the description information of the minimum circumscribed rectangle of the air switch, the area diagram of the insulated handle is obtained by intercepting from the area diagram of the air switch.
8. An identification device, characterized by comprising means for carrying out the method for identifying the on/off state of an air switch according to any one of claims 1 to 7.
9. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the steps of the method for identifying an open/close state of an air switch according to any one of claims 1 to 7 when executing a program stored in the memory.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the air switch on/off state identification method according to any one of claims 1 to 7.
CN202111045795.4A 2021-09-07 2021-09-07 Air switch on-off state identification method and device, electronic equipment and storage medium Pending CN113822180A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111045795.4A CN113822180A (en) 2021-09-07 2021-09-07 Air switch on-off state identification method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111045795.4A CN113822180A (en) 2021-09-07 2021-09-07 Air switch on-off state identification method and device, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN113822180A true CN113822180A (en) 2021-12-21

Family

ID=78922169

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111045795.4A Pending CN113822180A (en) 2021-09-07 2021-09-07 Air switch on-off state identification method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN113822180A (en)

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115578630A (en) * 2022-11-09 2023-01-06 广东科凯达智能机器人有限公司 Method and system for judging working gear of air switch
CN116229433A (en) * 2023-01-03 2023-06-06 北京和利时系统集成有限公司 Device state identification method and device
CN116563272A (en) * 2023-06-29 2023-08-08 深圳优立全息科技有限公司 Isolating switch on-off state identification method based on high-precision point cloud and related device
CN116907349A (en) * 2023-09-12 2023-10-20 北京宝隆泓瑞科技有限公司 Universal switch state identification method based on image processing

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115578630A (en) * 2022-11-09 2023-01-06 广东科凯达智能机器人有限公司 Method and system for judging working gear of air switch
CN115578630B (en) * 2022-11-09 2023-03-21 广东科凯达智能机器人有限公司 Method and system for judging working gear of air switch
CN116229433A (en) * 2023-01-03 2023-06-06 北京和利时系统集成有限公司 Device state identification method and device
CN116229433B (en) * 2023-01-03 2024-01-26 北京和利时系统集成有限公司 Device state identification method and device
CN116563272A (en) * 2023-06-29 2023-08-08 深圳优立全息科技有限公司 Isolating switch on-off state identification method based on high-precision point cloud and related device
CN116563272B (en) * 2023-06-29 2023-09-01 深圳优立全息科技有限公司 Isolating switch on-off state identification method based on high-precision point cloud and related device
CN116907349A (en) * 2023-09-12 2023-10-20 北京宝隆泓瑞科技有限公司 Universal switch state identification method based on image processing
CN116907349B (en) * 2023-09-12 2023-12-08 北京宝隆泓瑞科技有限公司 Universal switch state identification method based on image processing

Similar Documents

Publication Publication Date Title
CN113822180A (en) Air switch on-off state identification method and device, electronic equipment and storage medium
CN112199993B (en) Method for identifying transformer substation insulator infrared image detection model in any direction based on artificial intelligence
CN113435508B (en) Method, device, equipment and medium for detecting opening state of glass curtain wall opening window
CN111275759A (en) Transformer substation disconnecting link temperature detection method based on unmanned aerial vehicle double-light image fusion
CN110346699B (en) Insulator discharge information extraction method and device based on ultraviolet image processing technology
CN111325769B (en) Target object detection method and device
CN109145756A (en) Object detection method based on machine vision and deep learning
CN108648169A (en) The method and device of high voltage power transmission tower defects of insulator automatic identification
CN110991448A (en) Text detection method and device for nameplate image of power equipment
CN105631418A (en) People counting method and device
CN108229524A (en) A kind of chimney and condensing tower detection method based on remote sensing images
CN110610483A (en) Crack image acquisition and detection method, computer equipment and readable storage medium
CN110807430B (en) Method for preprocessing live panoramic traffic sign picture
CN113255590A (en) Defect detection model training method, defect detection method, device and system
CN112634254A (en) Insulator defect detection method and related device
CN113065484A (en) Insulator contamination state assessment method based on ultraviolet spectrum
KR101874968B1 (en) Visibility measuring system base on image information and method for using the same
CN114880730A (en) Method and device for determining target equipment and photovoltaic system
van den Hengel et al. Automatic camera placement for large scale surveillance networks
CN111597904A (en) Identification method for inclination of tunnel cable support
CN113591973B (en) Intelligent comparison method for appearance state change of track plate
CN114581419A (en) Transformer insulating sleeve defect detection method, related equipment and readable storage medium
CN112926426A (en) Ship identification method, system, equipment and storage medium based on monitoring video
CN108596196A (en) A kind of filthy state evaluating method based on insulator characteristics of image dictionary
CN112364884A (en) Method for detecting moving object

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