CN114972314A - Crack detection method for power equipment, computer equipment and storage medium - Google Patents
Crack detection method for power equipment, computer equipment and storage medium Download PDFInfo
- Publication number
- CN114972314A CN114972314A CN202210711823.XA CN202210711823A CN114972314A CN 114972314 A CN114972314 A CN 114972314A CN 202210711823 A CN202210711823 A CN 202210711823A CN 114972314 A CN114972314 A CN 114972314A
- Authority
- CN
- China
- Prior art keywords
- image data
- crack
- incremental
- power equipment
- period
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000004590 computer program Methods 0.000 claims description 7
- 230000004044 response Effects 0.000 claims description 2
- 239000003086 colorant Substances 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 5
- 238000012545 processing Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 230000006870 function Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
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
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
- G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K17/00—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations
- G06K17/0022—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device
- G06K17/0025—Methods or arrangements for effecting co-operative working between equipments covered by two or more of main groups G06K1/00 - G06K15/00, e.g. automatic card files incorporating conveying and reading operations arrangements or provisions for transferring data to distant stations, e.g. from a sensing device the arrangement consisting of a wireless interrogation device in combination with a device for optically marking the record carrier
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T11/00—2D [Two Dimensional] image generation
- G06T11/40—Filling a planar surface by adding surface attributes, e.g. colour or texture
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Quality & Reliability (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a crack detection method and device for power equipment, computer equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of displaying original image data acquired by calling a camera for the power equipment on a detection interface, adjusting the camera according to shooting parameters, loading a calibration frame on the detection interface, generating target image data when the calibration frame is overlapped with a two-dimensional code, segmenting semantics of each element in the power equipment in the target image data to serve as characteristic image data, calculating a difference between the characteristic image data of the period and the characteristic image data of the previous period to obtain incremental cracks, determining the incremental cracks to be newly added cracks in the power equipment or cracks expanded on original cracks, filling new colors into the newly added cracks, filling the colors of the expanded cracks on the original cracks and the original cracks, and ensuring the accuracy of detecting the incremental cracks and small errors so as to accurately evaluate the state of the power equipment.
Description
Technical Field
The present invention relates to the field of power technologies, and in particular, to a crack detection method for a power device, a computer device, and a storage medium.
Background
Numerous power equipment such as transformer, power box dispose in the open air, because the influence of reasons such as temperature, humidity, ground subside in the use, can lead to power equipment ageing comparatively obvious, produce the crack at positions such as casing, fixed column easily.
The crack is a mark for representing the state of the power equipment, the state of the power equipment can be evaluated in an auxiliary mode by monitoring the state of the crack, at present, the monitoring of the crack mainly depends on manual measurement and recording when technicians patrol, and the error is large.
Disclosure of Invention
The invention provides a crack detection method and device for power equipment, computer equipment and a storage medium, and aims to solve the problem that the error of monitoring cracks of the power equipment is large.
In a first aspect, an embodiment of the present invention provides a crack detection method for an electrical device, including:
in each period, displaying original image data acquired by calling a camera to the power equipment on a detection interface, wherein the original image data is provided with a two-dimensional code;
converting the two-dimensional code into a code and an angle code of the power equipment, wherein in a non-first period, the code and the angle code jointly map shooting parameters;
adjusting the camera according to the shooting parameters, loading a calibration frame on the detection interface, and generating target image data when the calibration frame is overlapped with the two-dimensional code;
inputting the target image data into a preset U-shaped network, and segmenting semantics of each element in the power equipment in the target image data to serve as feature image data;
calculating the difference between the characteristic image data of the period and the characteristic image data of the previous period to obtain an incremental crack;
comparing the incremental crack to the feature image data of a previous cycle to determine whether the incremental crack is a newly added crack or an enlarged crack on an original crack in the power device;
in the target image data of the present period, a new color is applied to the newly added crack, and a color different from the original color is applied to the crack expanded on the original crack.
In a second aspect, an embodiment of the present invention further provides a crack detection apparatus for an electrical device, including:
the preview module is used for displaying original image data acquired by calling a camera to the power equipment on a detection interface in each period, wherein the original image data is provided with two-dimensional codes;
the two-dimension code conversion module is used for converting the two-dimension code into a code and an angle code of the power equipment, and in a non-first period, the code and the angle code are mapped together to shoot parameters;
the parameter shooting module is used for adjusting the camera according to the shooting parameters, loading a calibration frame on the detection interface and generating target image data when the calibration frame is overlapped with the two-dimensional code;
the semantic recognition module is used for inputting the target image data into a preset U-shaped network, and segmenting the semantics of each element in the power equipment in the target image data to be used as characteristic image data;
the incremental crack detection module is used for calculating the difference between the characteristic image data of the period and the characteristic image data of the previous period to obtain an incremental crack;
a crack comparison module for comparing the incremental crack with the characteristic image data of the previous period to determine that the incremental crack is a newly added crack or an enlarged crack on an original crack in the power equipment;
and the color filling module is used for filling a new color into the newly added cracks and filling a color different from the original color into the cracks expanded on the original cracks in the target image data in the period.
In a third aspect, an embodiment of the present invention further provides a computer device, where the computer device includes:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors are caused to implement the crack detection method for an electrical power device as described in the first aspect.
In a fourth aspect, the embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the crack detection method for an electric power device according to the first aspect is implemented.
In the embodiment, in each period, original image data acquired by calling a camera for the power equipment is displayed on a detection interface, the original image data has a two-dimensional code, the two-dimensional code is converted into a code and an angle code of the power equipment, in a non-first period, the code and the angle code jointly map shooting parameters, the camera is adjusted according to the shooting parameters, a calibration frame is loaded on the detection interface, target image data is generated when the calibration frame is overlapped with the two-dimensional code, the target image data is input into a preset U-shaped network, the semantics of each element in the power equipment is divided in the target image data and is used as characteristic image data, the difference between the characteristic image data of the period and the characteristic image data of the previous period is calculated to obtain an incremental crack, the incremental crack is compared with the characteristic image data of the previous period to determine the incremental crack as a newly increased crack in the power equipment or a crack expanded on the original crack, in the target image data of the period, a new color is filled in the newly-added cracks, and the color different from the original color is filled in the cracks expanded on the original cracks.
Drawings
Fig. 1 is a flowchart of a crack detection method for an electrical device according to an embodiment of the present invention;
fig. 2 is a flowchart of a crack detection method for an electrical device according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of a crack detection device of an electrical apparatus according to a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures.
Example one
Fig. 1 is a flowchart of a crack detection method for an electrical device according to an embodiment of the present invention, where the embodiment is applicable to a situation that image data is collected for the electrical device in a predetermined shooting mode and an incremental crack is calculated, and the method may be executed by a crack detection apparatus of the electrical device, where the crack detection apparatus of the electrical device may be implemented by software and/or hardware, and may be configured in a computer device, for example, a mobile terminal (e.g., a mobile phone, a tablet computer, etc.), an intelligent wearable device (e.g., an intelligent watch, an intelligent glasses, etc.), and the method specifically includes the following steps:
In this embodiment, the technician carries the computer device to inspect the power device at each detection period, which may be regular or irregular.
Wherein, the power equipment is configured with a two-dimension code recorded by a real object such as a nameplate, so that, when shooting, the original image data has the two-dimension code (i.e. the content is the pixel point of the two-dimension code),
the two-dimensional code is formed by encoding codes (such as ID) and angle codes of power equipment, the angle codes represent angles of cracks in the shooting power equipment, and due to the fact that some power equipment belongs to large-scale equipment, the cracks can exist in multiple positions, different angles can be set for different cracks, namely, the codes of the same power equipment correspond to one or more angle codes, and one or more cracks can be contained at the same angle.
In a non-first period, a technician starts a detection program, displays a User Interface (UI) which is recorded as a detection Interface, calls a camera on computer equipment to acquire original image data of the power equipment, and displays the original image data on the detection Interface in a preview mode.
And 102, converting the two-dimensional code into a code and an angle code of the power equipment.
In this embodiment, according to an agreed decoding manner, the two-dimensional code in the original image data is decoded to obtain a group of character strings, and the character strings are disassembled according to an agreed combination manner to obtain the codes and angle codes of the electrical equipment, for example, the length of the character strings is 10 bits, the first 9 bits are the codes of the electrical equipment, and the last bit is the angle code.
In the present embodiment, in a non-first period, the code maps the shooting parameters in common with the angle code, wherein the shooting parameters are parameters recorded in a mode of shooting the power device at a specified angle.
After the code and the angle code are obtained through analysis, the computer equipment can search whether shooting parameters mapped together by the code and the angle code exist in a local cache or a database, if so, the shooting parameters are extracted from the local cache or the database, if not, the shooting parameters mapped together by the code and the angle code are requested from a server, and the mapping relation among the code, the angle code and the shooting parameters is stored in the local cache or the database for subsequent use.
And 103, adjusting the camera according to the shooting parameters, loading a calibration frame on the detection interface, and generating target image data when the calibration frame is overlapped with the two-dimensional code.
The shooting parameters belong to parameters recorded when image data are collected on the cracks of the power equipment at the same angle, the shooting parameters are analyzed, in the previewing process, part of the shooting parameters related to the camera are sent to a driver of the camera, the driver adjusts the camera according to the part of the shooting parameters, a calibration frame is loaded on a detection interface according to the shooting parameters, a user moves the computer equipment according to the calibration frame, the calibration frame is overlapped with the two-dimensional code, when the calibration frame is overlapped with the two-dimensional code, the current state is the same as the state of the image data collected on the cracks of the power equipment at the previous time, shooting operation can be executed, and target image data are generated.
In a specific implementation, the focal length, the size and the coordinates of the calibration frame, and the focal point may be read from the shooting parameters, where the focal point indicates a position where an original crack of the power device is located, that is, the crack is a crack detected for the power device in advance, the crack belongs to an area, and values such as an average value and a midpoint of the area may be calculated as the position where the focal point is located.
In the previewing process, the lens of the camera is adjusted according to the focal length, the calibration frame is loaded on the coordinate of the detection interface according to the size, wherein the two-dimensional code is provided with positioning points, the calibration frame is provided with calibration points, the positioning points are asymmetric, the direction of the two-dimensional code can be reflected, and correspondingly, the calibration points are asymmetric, and the direction of the calibration frame can be reflected.
And when the outline of the calibration frame is aligned with the outline of the two-dimensional code and the calibration point is aligned with the positioning point, performing focusing operation on the focus to generate target image data.
When the number of the focuses is two or more, the focusing operation can be respectively executed on each focus to generate target image data of two or more frames, and finally the target image data of two or more frames are combined into the target image data of one frame with clear focuses.
It should be noted that the focal length, the calibration frame, and the focus all belong to fixed shooting parameters, and the current user cannot adjust the focal length, and the parameters such as white balance belong to dynamic shooting parameters, and are automatically adjusted according to the actual shooting environment.
Then, a first touch operation for adjusting the focal length is received on the detection interface, and the first touch operation is ignored, so that the camera maintains the focal length.
And receiving a second touch operation for adjusting the calibration frame on the detection interface, and ignoring the second touch operation to enable the calibration frame to maintain the coordinates and the size.
And receiving a third touch operation for adjusting the focus on the detection interface, and ignoring the third touch operation to maintain the focus.
Of course, the above shooting parameters are only examples, and when implementing the embodiment of the present invention, other shooting parameters may be set according to practical situations, which is not limited by the embodiment of the present invention. In addition, besides the above shooting parameters, those skilled in the art may also adopt other shooting parameters according to actual needs, and the embodiment of the present invention is not limited to this.
And step 104, inputting the target image data into a preset U-shaped network, and dividing the semantics of each element in the power equipment in the target image data to be used as characteristic image data.
In this embodiment, a U-network (U-Net) may be trained in advance, and the U-Net may be configured to semantically segment target image data, input the target image data into a preset U-network, and segment semantics of each element in the power device in the target image data as feature image data.
Wherein the target of the segmentation is a crack on the power device.
The structure of U-Net is that the encoding (down sampling) is performed first, then the decoding (up sampling) is performed, and the classification of the pixel points with the same size as the target image data is returned.
U-Net may be able to combine both the underlying and higher layer information:
bottom layer (deep layer) information: the low resolution information after multiple downsampling can provide the context semantic information of the segmented target (crack) in the whole target image data, and can be understood as the characteristic of the relation between the reaction target (crack) and the environment thereof. This feature aids in the class determination of objects (so the classification problem usually involves low resolution/deep information, not multi-scale fusion).
High-level (shallow) information: the high-resolution information directly transferred from the encoder to the decoder at the same height through the occlusion operation can provide more fine features such as gradient and the like for the segmentation.
The U-Net combines low-resolution information (providing object class identification basis) and high-resolution information (providing accurate segmentation positioning basis), and is applicable to segmenting cracks on electric power equipment.
In addition, the U-Net comprises a residual connection (skip connection), the residual connection is also called as a jump connection, and the problem of gradient loss and gradient explosion in the training process can be solved by adding the residual connection in the U-Net, so that the number of layers of the network can be effectively reduced, and the training is easier.
And 105, calculating the difference between the characteristic image data of the period and the characteristic image data of the previous period to obtain the incremental crack.
In this embodiment, the feature image data of the previous period may be queried from a local database according to the code and the angle code of the power device, if the feature image data of the previous period is found, the feature image data of the previous period is loaded, and if the feature image data of the previous period is not found, the feature image data of the previous period may be requested from the server according to the code and the angle code of the power device.
Comparing the characteristic image data of the period with the characteristic image data of the previous period, and calculating the difference between the characteristic image data of the period and the characteristic image data of the previous period, wherein the difference between the characteristic image data of the period and the characteristic image data of the previous period can show incremental cracks due to small change of the power equipment in a relatively short period, namely, the amount of the incremental cracks between the characteristic image data of the period and the characteristic image data of the previous period is increased by taking the cracks as variables.
In one embodiment of the present invention, step 105 may include the steps of:
step 1051, difference operation is executed to the feature image data of the current period and the feature image data of the previous period, and difference image data is obtained.
In the present embodiment, a difference operation is performed on the feature image data of the present period and the feature image data of the previous period, and the result of the difference operation is denoted as difference image data.
The differential operation may be to subtract the pixel value of the feature image data of the previous period from the pixel value of the feature image data of the current period to weaken the similar portion of the feature image data of the current period and the feature image data of the previous period, and to highlight the changed portion of the feature image data of the current period and the feature image data of the previous period, which may include other situations, such as paint removal, dirt, noise, and the like, in addition to the increased crack.
Step 1052 detects a connected component area as a candidate in the difference image data.
Considering that the cracks are internally Connected, it is possible to perform Connected region analysis on the difference image data, detect a Connected Component (Connected Component) in the difference image data, and mark the Connected Component as a candidate.
The connected Region generally refers to an image Region (Blob) formed by foreground pixels with the same pixel value and adjacent positions in the differential image data, that is, a target with a crack as a foreground is extracted, so that the connected Region analysis method can be used in an application scene to be processed subsequently.
And 1053, extracting the geometric characteristics of the candidate object.
And 1054, if the characteristics meet the preset target conditions, determining the candidate object as an incremental crack.
In this embodiment, the crack may be analyzed in advance, and the geometric characteristic of the crack is searched, so that a target condition is set for the characteristic of the crack geometrically, and the crack may be considered as a crack if the target condition is met.
Then, for the candidate object, according to the specification of the target condition, the geometric feature of the candidate object may be extracted, and the geometric feature of the candidate object may be compared with the preset target condition.
If the target condition is satisfied by the geometric features of the candidate object, the candidate object may be determined to be an incremental crack.
If the target condition is not satisfied by the geometric features of the candidate object, it may be determined that the candidate object is not an incremental crack.
Illustratively, the total number of pixel points in the candidate object may be counted as a geometric feature.
Connecting any two pixel points on the edge of the candidate object to form a first candidate line segment, and taking the first candidate line segment with the largest length as a first target line segment.
And connecting any two pixel points on the edge of the candidate object as a second candidate line segment in the direction vertical to the first target line segment, and taking the second candidate line segment with the maximum length as a second target line segment.
And calculating the ratio of the first target line segment to the second target line segment as a geometrical characteristic.
That is, the first target line segment is the longest distance of the candidate object in any direction, the second target line segment is perpendicular to the first target line segment, and the ratio between the first target line segment and the second target line segment may represent the shape of the candidate object.
In this example, the target condition is that the total number of the pixel points is greater than or equal to a preset first threshold, and the ratio is greater than or equal to a preset second threshold.
Then, on the one hand, the total number of the pixels is compared with a preset first threshold, and on the other hand, the ratio is compared with a preset second threshold.
If the total number of the pixel points is less than the first threshold value, the number of the pixel points of the candidate object is less, and the candidate object is probably noise.
If the total number of the pixel points is larger than or equal to the first threshold value, the number of the pixel points representing the candidate object is more, and the candidate object is probably an object with practical significance.
If the ratio is less than the second threshold, it indicates that the shape of the candidate object is not elongated and does not match the shape of the fracture.
If the ratio is greater than or equal to the second threshold, the shape of the candidate object is elongated and matched with the shape of the crack.
Then, if the total number is smaller than a preset first threshold, or the ratio is smaller than a preset second threshold, it is determined that the candidate object is not an incremental crack.
And if the total number is greater than or equal to a preset first threshold value and the ratio is greater than or equal to a preset second threshold value, determining that the candidate object is an incremental crack.
And 106, comparing the incremental cracks with the characteristic image data of the previous period to determine that the incremental cracks are newly added cracks in the power equipment or expanded cracks on the original cracks.
The characteristic image data of the previous period has corrected the semantics of each element, and the crack of the previous period is detected, so that the incremental crack of the current period can be compared with the characteristic image data of the previous period, and the incremental crack of the current period is determined to be a newly-increased crack in the power equipment or a crack expanded on the original crack.
In a specific implementation, the characteristic image data of the previous cycle is queried for an existing crack of the power equipment (i.e., a crack of an increment detected in the previous cycle).
And calculating the distance between the incremental crack of the period and the original crack of the previous period.
If the distance is smaller than or equal to the preset third threshold, the distance between the incremental crack of the period and the original crack of the previous period is smaller and belongs to an error, and the incremental crack is determined to be a crack expanded on the original crack in the power equipment.
If the distance is larger than the preset third threshold, the distance between the incremental crack in the current period and the original crack in the previous period is larger and does not belong to an error, and the incremental crack is determined to be a newly-increased crack in the power equipment.
In the target image data of the period, the newly added cracks are filled with new colors, so that a user can visually observe the newly added cracks.
In the target image data of the period, the color different from the original color is filled in the crack expanded on the original crack, namely different colors are filled in the same crack for the crack expanded each time, so that the user can distinguish the development condition of the crack through the color, and the state of the power equipment is judged.
In the embodiment, in each period, original image data acquired by calling a camera for the power equipment is displayed on a detection interface, the original image data has a two-dimensional code, the two-dimensional code is converted into a code and an angle code of the power equipment, in a non-first period, the code and the angle code jointly map shooting parameters, the camera is adjusted according to the shooting parameters, a calibration frame is loaded on the detection interface, target image data is generated when the calibration frame is overlapped with the two-dimensional code, the target image data is input into a preset U-shaped network, the semantics of each element in the power equipment is divided in the target image data and is used as characteristic image data, the difference between the characteristic image data of the period and the characteristic image data of the previous period is calculated to obtain an incremental crack, the incremental crack is compared with the characteristic image data of the previous period to determine the incremental crack as a newly increased crack in the power equipment or a crack expanded on the original crack, in the target image data of the period, a new color is filled in the newly-added cracks, and the color different from the original color is filled in the cracks expanded on the original cracks.
Example two
Fig. 2 is a flowchart of a crack detection method for an electrical device according to a second embodiment of the present invention, where the second embodiment is based on the foregoing embodiment, and the method further includes the following steps:
In the first period, a technician records the two-dimensional code in real objects such as a nameplate and the like and configures the two-dimensional code for the power equipment, the technician starts a detection program and displays a detection interface, the detection program calls a camera on the computer equipment to collect original image data for the power equipment, and the original image data are displayed on the detection interface in a preview mode.
In this embodiment, the original image data has a two-dimensional code (i.e., the content is a pixel point of the two-dimensional code), the two-dimensional code in the original image data is decoded according to an agreed decoding method to obtain a group of character strings, the character strings are disassembled according to an agreed combination method to obtain a code and an angle code of the power equipment, for example, the length of the character string is 10 bits, the first 9 bits are the code of the power equipment, and the last bit is the angle code.
The user moves the computer equipment and adjusts the shooting parameters, so that cracks on the power equipment can be clearly seen on the detection interface, the cracks can be used for later observation, at the moment, the determination operation is triggered on the detection interface, the detection program executes the shooting operation, and the target image data is generated.
And step 204, generating shooting parameters aiming at the target image data, and establishing a relation that the codes and the angle codes are mapped to the shooting parameters together.
In this embodiment, parameters when the target image data is generated are recorded and recorded as shooting parameters, a mapping relationship between the codes, the angle codes and the shooting parameters is established, and the mapping relationship is recorded in a local database and uploaded to a server.
Illustratively, the two-dimensional code has a positioning point, in this example, on one hand, the focal length of the camera used for generating the target image data can be recorded, on the other hand, the size and the coordinates of the outline of the two-dimensional code can be measured and used as the size and the coordinates of the calibration frame, the positioning point of the two-dimensional code can be inquired and used as the positioning point in the calibration frame, and on the other hand, the position where the crack is located in the target image data can be inquired and used as the focus.
Wherein, for a crack in the target image data, the focus can be supplemented after the crack is detected.
And step 205, in a non-first period, searching for a code and an angle code to jointly map the shooting parameters.
And step 206, adjusting the camera according to the shooting parameters, loading a calibration frame on the detection interface, and generating target image data when the calibration frame is overlapped with the two-dimensional code.
And step 207, inputting the target image data into a preset U-shaped network, and dividing the semantics of each element in the power equipment in the target image data to be used as characteristic image data.
And step 208, calculating the difference between the characteristic image data of the current period and the characteristic image data of the previous period to obtain the incremental crack.
And step 209, comparing the incremental crack with the characteristic image data of the previous period to determine that the incremental crack is a newly added crack in the power equipment or a crack expanded on the original crack.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
EXAMPLE III
Fig. 3 is a block diagram of a crack detection apparatus for an electrical device according to a third embodiment of the present invention, which may specifically include the following modules:
the preview module 301 is configured to display, on a detection interface, original image data acquired by calling a camera for the power equipment in each cycle, where the original image data has a two-dimensional code;
a two-dimension code conversion module 302, configured to convert the two-dimension code into a code and an angle code of the power device, where in a non-first period, the code and the angle code jointly map shooting parameters;
a parameter shooting module 303, configured to adjust the camera according to the shooting parameters, load a calibration frame on the detection interface, and generate target image data when the calibration frame overlaps with the two-dimensional code;
a semantic recognition module 304, configured to input the target image data into a preset U-shaped network, and segment semantics of each element in the electrical power device in the target image data as feature image data;
an incremental crack detection module 305, configured to calculate a difference between the feature image data of the current period and the feature image data of the previous period, and obtain an incremental crack;
a crack comparison module 306, configured to compare the incremental crack with the characteristic image data of the previous period to determine that the incremental crack is a newly-added crack or a crack that expands on an original crack in the power equipment;
a color filling module 307, configured to fill a new color into the newly added crack and fill a color different from the original crack into the crack expanded on the original crack in the target image data of the current period.
In one embodiment of the present invention, the two-dimensional code has a positioning point therein;
the shooting module 303 is further configured to:
reading a focal length, the size and the coordinate of a calibration frame and a focus from the shooting parameters, wherein the focus represents the position of an original crack of the power equipment;
adjusting a lens of the camera according to the focal length;
loading the calibration frame on the coordinates of the detection interface according to the size, wherein the calibration frame is provided with a calibration point;
and when the outline of the calibration frame is aligned with the outline of the two-dimensional code and the calibration point is aligned with the positioning point, performing focusing operation on the focus to generate target image data.
In an embodiment of the present invention, the shooting module 303 is further configured to:
receiving a first touch operation for adjusting the focal length on the detection interface;
ignoring the first touch operation to enable the camera to maintain the focal length;
receiving a second touch operation for adjusting the calibration frame on the detection interface;
ignoring the second touch operation to enable the calibration frame to maintain the coordinates and the size;
receiving a third touch operation for adjusting the focus on the detection interface;
ignoring the third touch operation to maintain focusing on the focus.
In one embodiment of the present invention, the incremental crack detection module 305 is further configured to:
performing difference operation on the characteristic image data of the period and the characteristic image data of the previous period to obtain difference image data;
detecting a connected region in the differential image data as a candidate object;
extracting the geometrical characteristics of the candidate object;
and if the characteristics meet preset target conditions, determining the candidate object to be an incremental crack.
In one embodiment of the present invention, the incremental crack detection module 305 is further configured to:
counting the total number of pixel points in the candidate object;
connecting any two pixel points on the edge of the candidate object into a first candidate line segment;
taking the first candidate line segment with the maximum length as a first target line segment;
connecting any two pixel points on the edge of the candidate object as a second candidate line segment in the direction vertical to the first target line segment;
taking the second candidate line segment with the maximum length as a second target line segment;
calculating a ratio between the first target line segment and the second target line segment;
if the characteristic meets a preset target condition, determining that the candidate object is an incremental crack, including:
and if the total number is greater than or equal to a preset first threshold value and the ratio is greater than or equal to a preset second threshold value, determining that the candidate object is an incremental crack.
In one embodiment of the invention, the fracture comparison module 306 is further configured to:
inquiring the original cracks of the power equipment in the characteristic image data of the previous period;
calculating a distance between the incremental crack and the existing crack;
if the distance is smaller than or equal to a preset third threshold value, determining the incremental crack as a crack expanded on the original crack in the power equipment;
and if the distance is larger than a preset third threshold value, determining the incremental crack as a newly-increased crack in the power equipment.
In one embodiment of the present invention, further comprising:
the user-defined shooting module is used for responding to the determination operation received on the detection interface in the first period and generating target image data;
and the shooting parameter generating module is used for generating shooting parameters aiming at the target image data and establishing the relation that the codes and the angle codes are mapped to the shooting parameters together.
In one embodiment of the present invention, the two-dimensional code has a positioning point therein; the shooting parameter generation module is further configured to:
recording a focal length of the camera for generating the target image data;
measuring the size and the coordinates of the outline of the two-dimensional code to be used as the size and the coordinates of a calibration frame;
querying a positioning point of the two-dimensional code as a positioning point in a positioning frame;
and inquiring the position of the crack in the target image data as a focus.
The crack detection device of the power equipment provided by the embodiment of the invention can execute the crack detection method of the power equipment provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method.
Example four
Fig. 4 is a schematic structural diagram of a computer device according to a fourth embodiment of the present invention. FIG. 4 illustrates a block diagram of an exemplary computer device 12 suitable for use in implementing embodiments of the present invention. The computer device 12 shown in FIG. 4 is only one example and should not bring any limitations to the functionality or scope of use of embodiments of the present invention.
As shown in FIG. 4, computer device 12 is in the form of a general purpose computing device. The components of computer device 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. Computer device 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 4, commonly referred to as a "hard drive"). Although not shown in FIG. 4, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The processing unit 16 executes various functional applications and data processing by executing programs stored in the system memory 28, for example, implementing a crack detection method for an electric power device provided by an embodiment of the present invention.
EXAMPLE five
An embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process of the crack detection method for an electrical device, and can achieve the same technical effect, and in order to avoid repetition, the computer program is not described herein again.
A computer readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (10)
1. A crack detection method for an electric power device, comprising:
in each period, displaying original image data acquired by calling a camera to the power equipment on a detection interface, wherein the original image data is provided with a two-dimensional code;
converting the two-dimensional code into a code and an angle code of the power equipment, wherein in a non-first period, the code and the angle code jointly map shooting parameters;
adjusting the camera according to the shooting parameters, loading a calibration frame on the detection interface, and generating target image data when the calibration frame is overlapped with the two-dimensional code;
inputting the target image data into a preset U-shaped network, and segmenting semantics of each element in the power equipment in the target image data to serve as feature image data;
calculating the difference between the characteristic image data of the period and the characteristic image data of the previous period to obtain an incremental crack;
comparing the incremental crack to the feature image data of a previous cycle to determine whether the incremental crack is a newly added crack or an enlarged crack on an original crack in the power device;
in the target image data of the present period, a new color is applied to the newly added crack, and a color different from the original color is applied to the crack expanded on the original crack.
2. The method of claim 1, wherein the two-dimensional code has anchor points therein;
the adjusting the camera according to the shooting parameters, loading a calibration frame on the detection interface, and generating target image data when the calibration frame is overlapped with the two-dimensional code includes:
reading a focal length, the size and the coordinate of a calibration frame and a focus from the shooting parameters, wherein the focus represents the position of an original crack of the power equipment;
adjusting a lens of the camera according to the focal length;
loading the calibration frame on the coordinates of the detection interface according to the size, wherein the calibration frame is provided with a calibration point;
and when the outline of the calibration frame is aligned with the outline of the two-dimensional code and the calibration point is aligned with the positioning point, performing focusing operation on the focus to generate target image data.
3. The method of claim 2, wherein adjusting the camera according to the shooting parameters loads a calibration frame on the detection interface, and wherein generating target image data when the calibration frame overlaps the two-dimensional code further comprises:
receiving a first touch operation for adjusting the focal length on the detection interface;
ignoring the first touch operation to enable the camera to maintain the focal length;
receiving a second touch operation for adjusting the calibration frame on the detection interface;
ignoring the second touch operation to enable the calibration frame to maintain the coordinates and the size;
receiving a third touch operation for adjusting the focus on the detection interface;
ignoring the third touch operation to maintain focusing on the focus.
4. The method of claim 1, wherein calculating a difference between the feature image data of a current cycle and the feature image data of a previous cycle to obtain an incremental crack comprises:
performing difference operation on the characteristic image data of the period and the characteristic image data of the previous period to obtain difference image data;
detecting a connected region in the differential image data as a candidate object;
extracting the geometrical characteristics of the candidate object;
and if the characteristics meet preset target conditions, determining the candidate object to be an incremental crack.
5. The method of claim 4, wherein the extracting the geometric features of the candidate objects comprises:
counting the total number of pixel points in the candidate object;
connecting any two pixel points on the edge of the candidate object into a first candidate line segment;
taking the first candidate line segment with the maximum length as a first target line segment;
connecting any two pixel points on the edge of the candidate object as a second candidate line segment in the direction vertical to the first target line segment;
taking the second candidate line segment with the maximum length as a second target line segment;
calculating a ratio between the first target line segment and the second target line segment;
if the characteristic meets a preset target condition, determining that the candidate object is an incremental crack, including:
and if the total number is greater than or equal to a preset first threshold value and the ratio is greater than or equal to a preset second threshold value, determining that the candidate object is an incremental crack.
6. The method of claim 1, wherein the comparing the incremental crack to the characteristic image data of a previous cycle to determine whether the incremental crack is a newly added crack or a crack that expands on an existing crack in the power device comprises:
inquiring the original cracks of the power equipment in the characteristic image data of the previous period;
calculating a distance between the incremental crack and the existing crack;
if the distance is smaller than or equal to a preset third threshold value, determining the incremental crack as a crack expanded on an original crack in the power equipment;
and if the distance is larger than a preset third threshold value, determining the incremental crack as a newly-increased crack in the power equipment.
7. The method according to any one of claims 1-6, further comprising:
in a first period, generating target image data in response to a determination operation received on the detection interface;
and generating shooting parameters aiming at the target image data, and establishing a relation that the codes and the angle codes are mapped to the shooting parameters together.
8. The method of claim 7, wherein the two-dimensional code has anchor points therein; the generating of the shooting parameters for the target image data includes:
recording a focal length of the camera for generating the target image data;
measuring the size and the coordinates of the outline of the two-dimensional code to be used as the size and the coordinates of a calibration frame;
querying a positioning point of the two-dimensional code as a positioning point in a positioning frame;
and inquiring the position of the crack in the target image data as a focus.
9. A computer device, characterized in that the computer device comprises:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a crack detection method for an electrical power device as recited in any of claims 1-8.
10. A computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, implements a crack detection method of an electric power device according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210711823.XA CN114972314A (en) | 2022-06-22 | 2022-06-22 | Crack detection method for power equipment, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210711823.XA CN114972314A (en) | 2022-06-22 | 2022-06-22 | Crack detection method for power equipment, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114972314A true CN114972314A (en) | 2022-08-30 |
Family
ID=82965531
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210711823.XA Pending CN114972314A (en) | 2022-06-22 | 2022-06-22 | Crack detection method for power equipment, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114972314A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743830A (en) * | 2023-12-28 | 2024-03-22 | 张家港保税区金港建设工程质量检测有限公司 | Bridge crack detection method and system |
-
2022
- 2022-06-22 CN CN202210711823.XA patent/CN114972314A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117743830A (en) * | 2023-12-28 | 2024-03-22 | 张家港保税区金港建设工程质量检测有限公司 | Bridge crack detection method and system |
| CN117743830B (en) * | 2023-12-28 | 2024-07-12 | 张家港保税区金港建设工程质量检测有限公司 | Bridge crack detection method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110866496B (en) | Robot positioning and mapping method and device based on depth image | |
| CN112016638B (en) | Method, device and equipment for identifying steel bar cluster and storage medium | |
| CN112330751B (en) | Line deviation detection method and device for structured light camera | |
| CN110956131B (en) | Single-target tracking method, device and system | |
| CN111124863B (en) | Intelligent device performance testing method and device and intelligent device | |
| WO2022100068A1 (en) | Image processing method and apparatus, electronic device, and storage medium | |
| CN109934873B (en) | Method, device and equipment for acquiring marked image | |
| CN113763466B (en) | Loop detection method and device, electronic equipment and storage medium | |
| CN110807416A (en) | Digital instrument intelligent recognition device and method suitable for mobile detection device | |
| JP2022185143A (en) | Text detection method, and text recognition method and device | |
| CN114972314A (en) | Crack detection method for power equipment, computer equipment and storage medium | |
| KR102440198B1 (en) | VIDEO SEARCH METHOD AND APPARATUS, COMPUTER DEVICE, AND STORAGE MEDIUM | |
| CN110111018B (en) | Method, device, electronic equipment and storage medium for evaluating vehicle sensing capability | |
| CN116824609B (en) | Document format detection method and device and electronic equipment | |
| CN112258541A (en) | Video boundary detection method, system, device and storage medium | |
| CN117314863A (en) | Defect output method, device, equipment and storage medium | |
| CN109934185B (en) | Data processing method and device, medium and computing equipment | |
| CN110162362B (en) | Dynamic control position detection and test method, device, equipment and storage medium | |
| CN117237681A (en) | Image processing method, device and related equipment | |
| CN117351505A (en) | Information code identification method, device, equipment and storage medium | |
| CN115393616A (en) | Target tracking method, device, equipment and storage medium | |
| CN111124862B (en) | Intelligent device performance testing method and device and intelligent device | |
| CN113762017B (en) | Action recognition method, device, equipment and storage medium | |
| US20150169973A1 (en) | Incomplete patterns | |
| CN111753625B (en) | Pedestrian detection method, device, equipment and medium |
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 |