CN110929707A - Converter station scanning detection method, system and medium based on image processing - Google Patents
Converter station scanning detection method, system and medium based on image processing Download PDFInfo
- Publication number
- CN110929707A CN110929707A CN201910940544.9A CN201910940544A CN110929707A CN 110929707 A CN110929707 A CN 110929707A CN 201910940544 A CN201910940544 A CN 201910940544A CN 110929707 A CN110929707 A CN 110929707A
- Authority
- CN
- China
- Prior art keywords
- image
- converter station
- image processing
- monitoring
- data
- 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 48
- 238000012545 processing Methods 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 48
- 238000012544 monitoring process Methods 0.000 claims abstract description 45
- 230000011218 segmentation Effects 0.000 claims description 27
- 238000007781 pre-processing Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000004891 communication Methods 0.000 claims description 10
- 238000012937 correction Methods 0.000 claims description 9
- 238000003702 image correction Methods 0.000 claims description 9
- 238000010801 machine learning Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003708 edge detection Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 230000010339 dilation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 4
- 238000002955 isolation Methods 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 5
- 230000018109 developmental process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 4
- 230000002441 reversible effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000007774 longterm Effects 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004134 energy conservation Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J13/00—Controls for manipulators
- B25J13/08—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices
- B25J13/087—Controls for manipulators by means of sensing devices, e.g. viewing or touching devices for sensing other physical parameters, e.g. electrical or chemical properties
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1674—Programme controls characterised by safety, monitoring, diagnostic
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1679—Programme controls characterised by the tasks executed
- B25J9/1689—Teleoperation
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
- B25J9/1697—Vision controlled systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/70—
-
- G06T5/80—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Abstract
The invention discloses a converter station scanning detection method, a system and a medium based on image processing, which obtains data detection results from real-time photos of a field display screen of a converter station through a series of image processing processes, can be finally displayed on mobile phone and computer client, can completely not affect the work of the current monitoring system of the convertor station, can realize the networked output of the monitoring data under the condition of ensuring the isolation of the internal network and the external network of the current monitoring system of the convertor station, prevents the current monitoring system of the convertor station from exposing security holes due to the output of network data, provides a novel idea for the artificial intelligent monitoring of the convertor station, the method has the advantages that the labor cost is reduced, the monitoring accuracy is guaranteed, the safe and stable operation of the converter stations is facilitated, the method is suitable for monitoring and alarming of each converter station, and the method can be widely applied to a plurality of scenes of power systems except the converter stations.
Description
Technical Field
The invention belongs to the field of converter station fault detection, and particularly relates to a converter station scanning detection method, a converter station scanning detection system and a converter station scanning detection medium based on image processing.
Background
With the rapid development of information technology and the increasing public safety concerns of society, the intelligent scanning monitoring system has been widely applied in national defense and military, traffic monitoring, sensitive important occasions and common civil fields. The massive information brought by the rapid development of the intelligent scanning monitoring system exceeds the range of the processing capacity of manpower, and the intellectualization is the inevitable trend of the development of the intelligent scanning technology.
The current intelligent scanning technology has matured in a whole day after ten years of development, but still is in a static scanning stage, and two defects mainly exist: firstly, static scanning and secondly, the analysis and evaluation function is weak. The traditional static scanning analysis is based on syntax analysis or compiler, and the defects of the analysis codes are analyzed by using a rule pattern (patterns) matched with the codes to evaluate the codes, and the codes are reported as long as the patterns are matched or similar, so that the truth and falsity of the codes need to be manually distinguished. Simple code would not be a problem or acceptable in the case of a small amount of code, but if the code is a large amount of code, complex code, the traditional scanning technology would be hardly feasible, because it would waste a lot of time for development and security auditors, and sometimes the human eye is unable to do so.
At the present stage, long-term safe and stable operation of the converter station needs long-term real-time monitoring of workers, alarm information needs to be processed in time, only a few or even no serious fault information exists in one day, but the workers need to monitor the station in the whole process, huge working cost is spent, and a great amount of labor is wasted.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: aiming at the problems in the prior art, the method, the system and the medium for scanning and detecting the convertor station based on image processing are provided, real-time pictures of a field display screen of the convertor station are processed by a series of image processing processes to obtain data detection results, can be finally displayed on mobile phone and computer client, can completely not affect the work of the current monitoring system of the convertor station, can realize the networked output of the monitoring data under the condition of ensuring the isolation of the internal network and the external network of the current monitoring system of the convertor station, prevents the current monitoring system of the convertor station from exposing security holes due to the output of network data, provides a novel idea for the artificial intelligent monitoring of the convertor station, the method has the advantages that the labor cost is reduced, the monitoring accuracy is guaranteed, the safe and stable operation of the converter stations is facilitated, the method is suitable for monitoring and alarming of each converter station, and the method can be widely applied to a plurality of scenes of power systems except the converter stations.
In order to solve the technical problems, the invention adopts the technical scheme that:
a converter station scanning detection method based on image processing comprises the following implementation steps:
1) acquiring a monitoring image of a monitoring center display screen of a converter station;
2) carrying out image preprocessing, image correction, image denoising and edge information extraction on a monitored image, wherein the image preprocessing specifically refers to carrying out image graying processing;
3) and performing character segmentation and character recognition on the monitored image to obtain a detection result.
Optionally, after the detection result is obtained in step 3), a step of performing early warning detection is further included, and the detailed steps include: and aiming at each kind of data in the detection result, finding out a corresponding early warning threshold value from a preset early warning threshold value database, judging whether the data exceeds the corresponding early warning threshold value, and if the data exceeds the corresponding early warning threshold value, pushing an alarm message to a specified mobile terminal device or a monitoring center.
Optionally, the step 1) of obtaining the monitoring image of the monitoring center display screen of the converter station is specifically realized by a mobile trolley provided with a camera on a mechanical arm, and the mobile trolley moves along a track laid on the ground or a table near the monitoring center display screen to adjust the shooting angle of the monitoring center display screen so as to realize picture quality adjustment.
Optionally, the image correction in step 2) specifically refers to correction by using a reverse mapping method, where the correction by using the reverse mapping method refers to deriving coordinates of a corresponding original image through coordinates of a target image, and determining gray levels of non-integer coordinate points by using a linear interpolation method to implement non-linear correction on a distorted image; the gray scale of the non-integer coordinate point is shown as the following formula:
in the above formula, y is the gray scale of the non-integer coordinate point, (x)0,y0)、(x1,y1) For known coordinates, (x, y) is [ x ]0,x1]Some value in the interval, α, is represented as an interpolation coefficient.
Optionally, the image denoising in step 2) specifically includes denoising the image by using a mean filtering method, and a function expression of denoising the image by using the mean filtering method is shown as follows:
g(x,y)＝1/m∑f(x,y)
in the above formula, g (x, y) is the gray level of the processed image on the pixel point, m is the total number of pixels including the current pixel in the de-noised image template, and f (x, y) is the gray level of the original image on the pixel point.
Optionally, the extracting of the edge information in step 2) specifically refers to extracting the image edge information by using a sobel operator, where the sobel operator is shown as follows:
in the above formula, GxRepresenting a lateral edge detection image; gyExpressed as a longitudinal edge detection image; g represents the gradient magnitude; θ represents the gradient direction.
Optionally, the detailed steps of step 3) include:
3.1) performing expansion operation on the monitored image by using a mathematical morphology method, dividing the image into a plurality of communicated areas, and marking to complete label positioning;
3.2) carrying out character segmentation on the determined connected region, utilizing a vertical projection method to carry out segmentation, accumulating gray values of all lines of the monitoring image, adopting self-adaptive threshold segmentation to find out an optimal threshold segmentation point, converting the gray image into a binary image, and finally utilizing a horizontal vertical projection method to find out boundary points between characters so as to segment each data character;
3.3) identifying the characters of each kind of data by using a machine learning model to obtain the detection result of each kind of data.
Optionally, step 3.3) is preceded by a step of training a machine learning model, and the detailed steps include:
s1) obtaining a monitoring image sample of a monitoring center display screen of the converter station;
s2) performing sample expansion on the monitoring image sample, wherein the expansion comprises one or more of rotation, inclination, deformation, noise addition and width change;
s3) carrying out image preprocessing, image correction, image denoising and edge information extraction on the monitored image sample after the sample, wherein the image preprocessing specifically refers to carrying out image graying processing;
s4) performing dilation operation on the monitored image by a mathematical morphology method, dividing the image into a plurality of communicated areas, and marking to complete label positioning;
s5) carrying out character segmentation on the determined connected region, carrying out segmentation by using a vertical projection method, accumulating gray values of all lines of the monitored image, finding out an optimal threshold segmentation point by adopting self-adaptive threshold segmentation, converting the gray image into a binary image, finally finding out boundary points between characters by using a horizontal vertical projection method so as to segment each data character, and setting a label for each segmented data character so as to establish a training data set;
s6) completing training of the machine learning model through the training data set.
In addition, the invention also provides a convertor station scanning detection system based on image processing, which comprises a mobile trolley, wherein a camera is mounted on a mechanical arm, a control terminal is arranged in the mobile trolley, the control terminal comprises a data acquisition module, a microprocessor, a communication module and a power module, the camera is connected with the microprocessor through the data acquisition module, the microprocessor is connected with the communication module, the power module is respectively connected with the data acquisition module, the microprocessor, the communication module and the camera, the microprocessor is programmed or configured to execute the steps of the convertor station scanning detection method based on image processing, or a computer program which is programmed or configured to execute the convertor station scanning detection method based on image processing is stored in a storage medium of the microprocessor.
Furthermore, the present invention also provides a computer readable storage medium having stored thereon a computer program programmed or configured to execute the image processing based converter station scan detection method.
Compared with the prior art, the invention has the following advantages:
the invention obtains the data detection result by the real-time picture of the field display screen of the convertor station through a series of image processing processes, and the data detection result can be finally displayed on a mobile phone and a computer client, so that the work of the existing monitoring system of the convertor station can be completely not influenced, the networked output of the monitoring data can be realized under the condition of really isolating the internal network and the external network of the existing monitoring system of the convertor station, the safety leak of the existing monitoring system of the convertor station due to the network data output is prevented, a novel thought is provided for the artificial intelligent monitoring of the convertor station, the monitoring accuracy is ensured while the labor cost is reduced, the safe and stable operation of the convertor station is facilitated, and the system is not only suitable for monitoring and alarming of each convertor station, but also can be widely applied to a plurality of scenes of electric.
Drawings
FIG. 1 is a basic flow diagram of a method according to an embodiment of the present invention.
Fig. 2 is a schematic structural diagram of a main view (facing a monitored display screen) according to an embodiment of the present invention.
FIG. 3 is a schematic side view of the embodiment of the present invention.
Fig. 4 is a schematic top view of the embodiment of the invention.
FIG. 5 is a schematic structural diagram of a button activation device according to an embodiment of the present invention.
Detailed Description
As shown in fig. 1, the implementation steps of the image processing-based converter station scan detection method of the embodiment include:
1) acquiring a monitoring image of a monitoring center display screen of a converter station;
2) carrying out image preprocessing, image correction, image denoising and edge information extraction on the monitored image, wherein the image preprocessing specifically refers to carrying out image graying processing to reduce the data processing amount of the image;
3) and performing character segmentation and character recognition on the monitored image to obtain a detection result.
In this embodiment, the step 1) of obtaining the monitoring image of the monitoring center display screen of the converter station is specifically realized by a mobile trolley provided with a camera on a mechanical arm, and the mobile trolley moves along a track laid on the ground or a table surface near the monitoring center display screen to adjust the shooting angle of the monitoring center display screen so as to realize picture quality adjustment. The movable trolley moves back and forth, and the scanning camera continuously shoots the field display screen.
As shown in fig. 2, fig. 3 and fig. 4, the device (intelligent monitoring robot) for acquiring the monitoring image of the monitoring center display screen of the converter station in step 1) of this embodiment includes a track 1 and a mobile trolley 2 having a function of traveling on the track 1, a control component is arranged inside the mobile trolley 2, an image acquisition device 3 for monitoring the operation data screen of the main control room of the transformer substation is arranged on the mobile trolley 2, the mobile trolley 2 is further connected with a button touch device 4 for touching the adjustment button of the operation data screen of the main control room of the transformer substation, and both the image acquisition device 3 and the button touch device 4 are connected with the control component. The mobile trolley 2 is provided with the image acquisition device 3 for monitoring the operation data screen of the transformer substation master control room, and data acquisition can be realized by monitoring the operation data screen of the transformer substation master control room through the camera on the premise of not interfering the transformer substation master control system to realize internal and external network isolation. The embodiment comprises a track 1 and a movable trolley 2 walking on the track 1, so that the position of the movable trolley on the track can be adjusted as required, the interference of illumination on the operation data screen of the transformer substation master control room can be overcome, and the image acquisition quality of the operation data screen of the transformer substation master control room is ensured. The moving trolley 2 is also connected with a button touch device 4 for touching an adjusting button of a running data screen of a main control room of the transformer substation, and on one hand, the brightness and contrast of the running data screen of the main control room of the transformer substation can be adjusted through the button touch device 4 for adjusting the button, so that the image acquisition quality of the running data screen of the main control room of the transformer substation is ensured; on the other hand, the on-off state of the operation data screen of the substation master control room can be controlled according to needs to realize energy conservation.
In this embodiment, the control assembly includes a power module, a controller and a data communication module that are connected in sequence, and the image acquisition device 3 and the button touching device 4 are connected with the controller.
As shown in fig. 2, the bottom of the mobile trolley 2 is provided with a walking wheel 21 and a walking motor for controlling the walking wheel 21 to move, the walking wheel 21 is arranged on the track 1, the walking wheel 21 is provided with a brake 22, the walking motor and the brake 22 are both connected with the output end of the control component, the walking and braking of the mobile trolley 2 on the track 1 can be conveniently controlled through the structure, and the mobile trolley 2 can be conveniently controlled to stop through the brake 22, so that the imaging quality is ensured; in this embodiment, the brake 22 is specifically an HDDDWX micro electromagnetic brake.
As shown in fig. 3, the image capturing device 3 includes a mechanical arm assembly 31 and a camera 32 installed at an end of the mechanical arm assembly 31, so that the camera 32 can be adjusted to a proper position, and the image capturing quality of the operation data screen of the substation main control room is ensured. In this embodiment, the mechanical arm assembly 31 comprises a plurality of sections of sequentially hinged mechanical arms, a rotation driving steering engine is arranged between the mechanical arm assembly 31 and the movable trolley 2, a rotation driving steering engine is arranged between adjacent mechanical arms, the rotation driving steering engine is connected with the output end of the control assembly, and the output end of the camera 32 is connected with the control assembly.
As shown in FIG. 3, the end of the robot arm assembly 31 is further provided with an infrared distance measuring sensor array 33, the infrared distance measuring sensor array 33 comprises a plurality of infrared distance measuring sensors, and output ends of the infrared distance measuring sensors are connected with the control assembly. The transformer substation master control room operation data screen can be conveniently scanned through the infrared distance measuring sensor array 33, so that the accurate position of the screen center of the transformer substation master control room operation data screen can be determined according to the blocking condition of the transformer substation master control room operation data screen on infrared rays.
In order to increase the angle of the moving trolley 2 walking on the track 1 relative to the running data screen of the transformer substation main control room and reduce the stroke of the moving trolley 2, as shown in fig. 4, the track 1 is an arc-shaped track, and the running data screen of the transformer substation main control room is positioned in the direction of the circle center side of the arc-shaped track, so that the stroke of the moving trolley 2 can be reduced to the maximum extent, the distance change of the moving trolley 2 relative to the running data screen of the transformer substation main control room is ensured to be smaller, and the image acquisition quality can be adjusted quickly.
As shown in fig. 5, the button activating device 4 includes a base 42 having a clamping groove 41, a clamping bolt 43 is disposed on a side wall of the base 42 located on at least one side of the clamping groove 41, a sliding groove 44 disposed along a length direction of the clamping groove 41 is disposed on one side of the base 42 located on one side of the clamping groove 41, a linear reciprocating motor 45 is disposed on one side of the sliding groove 44, a through hole is disposed in a middle portion of a sliding block 451 of the linear reciprocating motor 45, a telescopic motor 46 is mounted on the sliding block 451, a telescopic shaft of the telescopic motor 46 is inserted into the through hole and a pressing head of an adjusting button for touching an operation data screen of a main control room of a transformer substation is mounted on an end portion of the telescopic shaft, and control ends of the linear reciprocating motor 45 and the telescopic. The operating principle of the button actuation device 4 is as follows: the clamping groove 41 is sleeved at the bottom of the operation data screen of the transformer substation main control room at a proper height in advance, so that the sliding groove 44 and the bottom adjusting button of the operation data screen of the transformer substation main control room are at the same height, and then the clamping bolts 43 at two sides are adjusted (through inner hexagons on the surfaces of the clamping bolts 43) to clamp the operation data screen of the transformer substation main control room, so that the operation data screen of the transformer substation main control room is fixedly installed. Under the monitoring of the camera 32, the sliding block 451 can slide above the designated adjusting button of the running data screen of the corresponding transformer substation main control room through the linear reciprocating motor 45, and then the adjusting button of the running data screen of the transformer substation main control room can be touched by the stretching motor 46 to work so that the pressing head extends out, so that on one hand, the brightness and contrast of the running data screen of the transformer substation main control room can be adjusted, and the image acquisition quality of the running data screen of the transformer substation main control room is ensured; on the other hand, the on-off state of the operation data screen of the main control room of the transformer substation can be controlled according to needs to achieve energy saving, the telescopic motor 46 can start a plurality of adjusting buttons, and the use is flexible and convenient.
Because the screen has more distortion and noise points during imaging, the image correction in step 2) in this embodiment specifically refers to correction by using a reverse mapping method, where the correction by using the reverse mapping method refers to deriving coordinates of a corresponding original image through coordinates of a target image, and determining gray levels of non-integer coordinate points by using a linear interpolation method to implement nonlinear correction on a distorted image; the gray scale of the non-integer coordinate point is shown as the following formula:
in the above formula, y is the gray scale of the non-integer coordinate point, (x)0,y0)、(x1,y1) For known coordinates, (x, y) is [ x ]0,x1]Some value in the interval, α is denoted as an insertionA value coefficient.
In order to achieve the image smoothing effect, the image denoising in step 2) in this embodiment specifically means denoising an image by using a mean filtering method, and a function expression of denoising the image by using the mean filtering method is shown as follows:
g(x,y)＝1/m∑f(x,y)
in the above formula, g (x, y) is the gray level of the processed image on the pixel point, m is the total number of pixels including the current pixel in the de-noised image template, and f (x, y) is the gray level of the original image on the pixel point.
In this embodiment, the extracting of the edge information in step 2) specifically refers to extracting the image edge information by using a sobel operator, where the sobel operator is shown as follows:
in the above formula, GxRepresenting a lateral edge detection image; gyExpressed as a longitudinal edge detection image; g represents the gradient magnitude; θ represents the gradient direction.
In this embodiment, the graying processing of the image in step 2) selects a weighted average value method, and the expression is as follows:
in the above formula, R, G, B represents three basic colors of red, green and blue, respectively, WR、WG、WBRespectively R, G, B.
In this embodiment, the detailed steps of step 3) include:
3.1) performing expansion operation on the monitored image by using a mathematical morphology method, dividing the image into a plurality of communicated areas, and marking to complete label positioning; in this embodiment, the specific expression of the expansion calculation is as follows:
in the above formula, A, B represents two different structures; (x, y) are denoted image elements. The equation shows that expanding a with structure B translates the origin of structure element B to the image pixel (x, y) location. If the intersection of B and A at the image pixel (x, y) is not empty (that is, at least one of the image values corresponding to A at the element position of B being 1 is 1), the pixel (x, y) corresponding to the output image is assigned to 1, otherwise, the pixel is assigned to 0.
3.2) carrying out character segmentation on the determined connected region, utilizing a vertical projection method to carry out segmentation, accumulating gray values of all lines of the monitored image, adopting self-adaptive threshold segmentation (OTSU, also called Otsu method) to find out an optimal threshold segmentation point, converting the gray image into a binary image, and finally utilizing a horizontal vertical projection method to find out boundary points between characters so as to segment each data character;
3.3) identifying the characters of each kind of data by using a machine learning model to obtain the detection result of each kind of data.
In this embodiment, the detailed step of segmenting by using the vertical projection method in step 3.2) includes:
3.2.1) obtaining a convertor station display screen image which is only provided with characters after positioning according to the finished label positioning, obtaining the total number of pixel values in the column direction through calculation, and performing vertical projection on the pixel values;
3.2.2) selecting a smaller pixel and a smaller threshold value, scanning the image to find the left end of the character, and then finding the right end of the character according to the height-width ratio of the display screen of the convertor station;
3.2.3) repeating the step 3.2.2) to sequentially cut out other characters in the display screen of the convertor station, and finishing the determination of the left and right boundaries of the characters and storing the characters in a set array;
3.2.4) horizontally projecting the character segmented in the step 3.2.3) to find the upper and lower boundaries of the character;
3.2.5) output a standard character sub-graph (the previous steps resulted in an array of characters whose elements are not uniform in size and the character size used for different character recognition libraries is not uniform).
In this embodiment, step 3.3) is preceded by a step of training a machine learning model, and the detailed steps include:
s1) obtaining a monitoring image sample of a monitoring center display screen of the converter station;
s2) performing sample expansion on the monitoring image sample, wherein the expansion comprises one or more of rotation, inclination, deformation, noise addition and width change;
s3) carrying out image preprocessing, image correction, image denoising and edge information extraction on the monitored image sample after the sample, wherein the image preprocessing specifically refers to carrying out image graying processing;
s4) performing dilation operation on the monitored image by a mathematical morphology method, dividing the image into a plurality of communicated areas, and marking to complete label positioning;
s5) carrying out character segmentation on the determined connected region, carrying out segmentation by using a vertical projection method, accumulating gray values of all lines of the monitored image, finding out an optimal threshold segmentation point by adopting self-adaptive threshold segmentation, converting the gray image into a binary image, finally finding out boundary points between characters by using a horizontal vertical projection method so as to segment each data character, and setting a label for each segmented data character so as to establish a training data set;
s6) completing training of the machine learning model through the training data set.
In this embodiment, the step of performing early warning detection is further included after the detection result is obtained in step 3), and the detailed steps include: and aiming at each kind of data in the detection result, finding out a corresponding early warning threshold value from a preset early warning threshold value database, judging whether the data exceeds the corresponding early warning threshold value, and if the data exceeds the corresponding early warning threshold value, pushing an alarm message to a specified mobile terminal device or a monitoring center.
In addition, this embodiment further provides a converter station scanning detection system based on image processing, including a mobile cart having a camera mounted on a mechanical arm, the mobile cart being provided with a control terminal, the control terminal including a data acquisition module, a microprocessor, a communication module and a power module, the camera being connected to the data acquisition module and the microprocessor, the microprocessor being connected to the communication module, the power module being connected to the data acquisition module, the microprocessor, the communication module and the camera, respectively, the microprocessor being programmed or configured to execute the steps of the converter station scanning detection method based on image processing, or a storage medium of the microprocessor being stored with a computer program programmed or configured to execute the converter station scanning detection method based on image processing.
In this embodiment, the camera includes a surface scanning camera, a line scanning camera, and a matching light source, and the selection of the surface scanning camera, the line scanning camera, and the matching light source needs to be determined according to actual conditions. The system adopts a high-speed camera with 320 ten thousand pixels (2048 x 1080), the precision can reach 0.03mm/Pixel, the frame rate can reach 70fps or more, such as DALSA G2-GM10-T1921, and the light source adopts an annular shadowless light source, so that the system has the advantages of large irradiation area, small volume and good illumination uniformity. The line scan camera adopts a line scan camera with horizontal resolution 2048, vertical resolution 2 and line frequency of 100 KHZ; the precision can reach 0.03mm/Pixel, the frame rate can reach 30fps or more, such as DALSA P4-CM-02K10D, the light source is a high-brightness linear light source, and the illumination intensity is high and the illumination uniformity is good.
Furthermore, the present embodiment also provides a computer readable storage medium having stored thereon a computer program programmed or configured to execute the aforementioned image processing-based converter station scan detection method.
The above description is only a preferred embodiment of the present invention, and the protection scope of the present invention is not limited to the above embodiments, and all technical solutions belonging to the idea of the present invention belong to the protection scope of the present invention. It should be noted that modifications and embellishments within the scope of the invention may occur to those skilled in the art without departing from the principle of the invention, and are considered to be within the scope of the invention.
Claims (10)
1. A converter station scanning detection method based on image processing is characterized by comprising the following implementation steps:
1) acquiring a monitoring image of a monitoring center display screen of a converter station;
2) carrying out image preprocessing, image correction, image denoising and edge information extraction on a monitored image, wherein the image preprocessing specifically refers to carrying out image graying processing;
3) and performing character segmentation and character recognition on the monitored image to obtain a detection result.
2. The image processing based converter station scanning detection method according to claim 1, wherein the step of performing early warning detection after the detection result is obtained in step 3), and the detailed steps include: and aiming at each kind of data in the detection result, finding out a corresponding early warning threshold value from a preset early warning threshold value database, judging whether the data exceeds the corresponding early warning threshold value, and if the data exceeds the corresponding early warning threshold value, pushing an alarm message to a specified mobile terminal device or a monitoring center.
3. The image processing-based scanning detection method for the converter station according to claim 1, wherein the step 1) of obtaining the monitoring image of the monitoring center display screen of the converter station is realized by a mobile trolley with a camera mounted on a mechanical arm, and the mobile trolley moves along a track laid on the ground or a table surface near the monitoring center display screen to adjust the shooting angle of the monitoring center display screen so as to realize picture quality adjustment.
4. The image processing-based scanning detection method for the converter station according to claim 1, wherein the image correction in the step 2) specifically means correction by using an inverse mapping method, and the correction by using the inverse mapping method means deriving coordinates of a corresponding original image through coordinates of a target image and determining gray levels of non-integer coordinate points by using a linear interpolation method to realize non-linear correction of a distorted image; the gray scale of the non-integer coordinate point is shown as the following formula:
in the above formula, y isGray scale of non-integer coordinate point, (x)0,y0)、(x1,y1) For known coordinates, (x, y) is [ x ]0,x1]Some value in the interval, α, is represented as an interpolation coefficient.
5. The image processing-based converter station scanning detection method according to claim 1, wherein the image denoising in step 2) specifically means denoising the image by using a mean value filtering method, and a function expression of denoising the image by using the mean value filtering method is as follows:
g(x,y)＝1/m∑f(x,y)
in the above formula, g (x, y) is the gray level of the processed image on the pixel point, m is the total number of pixels including the current pixel in the de-noised image template, and f (x, y) is the gray level of the original image on the pixel point.
6. The image processing-based scanning detection method for the converter station according to claim 1, wherein the step 2) of extracting the edge information specifically includes extracting the image edge information by using a sobel operator, and the sobel operator is expressed as follows:
in the above formula, GxRepresenting a lateral edge detection image; gyExpressed as a longitudinal edge detection image; g represents the gradient magnitude; θ represents the gradient direction.
7. The image processing based converter station scan detection method according to claim 1, wherein the detailed step of step 3) comprises:
3.1) performing expansion operation on the monitored image by using a mathematical morphology method, dividing the image into a plurality of communicated areas, and marking to complete label positioning;
3.2) carrying out character segmentation on the determined connected region, utilizing a vertical projection method to carry out segmentation, accumulating gray values of all lines of the monitoring image, adopting self-adaptive threshold segmentation to find out an optimal threshold segmentation point, converting the gray image into a binary image, and finally utilizing a horizontal vertical projection method to find out boundary points between characters so as to segment each data character;
3.3) identifying the characters of each kind of data by using a machine learning model to obtain the detection result of each kind of data.
8. The image processing based converter station scan detection method according to claim 7, characterized in that step 3.3) is preceded by a step of training a machine learning model, and the detailed steps comprise:
s1) obtaining a monitoring image sample of a monitoring center display screen of the converter station;
s2) performing sample expansion on the monitoring image sample, wherein the expansion comprises one or more of rotation, inclination, deformation, noise addition and width change;
s3) carrying out image preprocessing, image correction, image denoising and edge information extraction on the monitored image sample after the sample, wherein the image preprocessing specifically refers to carrying out image graying processing;
s4) performing dilation operation on the monitored image by a mathematical morphology method, dividing the image into a plurality of communicated areas, and marking to complete label positioning;
s5) carrying out character segmentation on the determined connected region, carrying out segmentation by using a vertical projection method, accumulating gray values of all lines of the monitored image, finding out an optimal threshold segmentation point by adopting self-adaptive threshold segmentation, converting the gray image into a binary image, finally finding out boundary points between characters by using a horizontal vertical projection method so as to segment each data character, and setting a label for each segmented data character so as to establish a training data set;
s6) completing training of the machine learning model through the training data set.
9. A convertor station scanning detection system based on image processing is characterized by comprising a mobile trolley with a camera arranged on a mechanical arm, the mobile trolley is internally provided with a control terminal, the control terminal comprises a data acquisition module, a microprocessor, a communication module and a power supply module, the camera is connected with the microprocessor through the data acquisition module, the microprocessor is connected with the communication module, the power module is respectively connected with the data acquisition module, the microprocessor, the communication module and the camera, the microprocessor being programmed or configured to perform the steps of the image processing based converter station scan detection method according to any of claims 1-8, or a storage medium of the microprocessor, having stored thereon a computer program programmed or configured to execute the image processing based scan detection method for a converter station according to any of claims 1 to 8.
10. A computer readable storage medium, characterized in that the computer readable storage medium has stored thereon a computer program programmed or configured to execute the image processing based converter station scan detection method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910940544.9A CN110929707A (en) | 2019-09-30 | 2019-09-30 | Converter station scanning detection method, system and medium based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910940544.9A CN110929707A (en) | 2019-09-30 | 2019-09-30 | Converter station scanning detection method, system and medium based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110929707A true CN110929707A (en) | 2020-03-27 |
Family
ID=69848876
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910940544.9A Pending CN110929707A (en) | 2019-09-30 | 2019-09-30 | Converter station scanning detection method, system and medium based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110929707A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113524194A (en) * | 2021-04-28 | 2021-10-22 | 重庆理工大学 | Target grabbing method of robot vision grabbing system based on multi-mode feature deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130089263A1 (en) * | 2011-10-11 | 2013-04-11 | Tandent Vision Science, Inc. | System and method for digital image signal compression using intrinsic images |
| CN103886294A (en) * | 2014-03-24 | 2014-06-25 | 北京国网富达科技发展有限责任公司 | Method and system for recognizing number of movement times of arrester for convertor station based on images |
| CN105321289A (en) * | 2015-12-04 | 2016-02-10 | 中国建筑设计院有限公司 | Intelligent analyzing and alarming system and method of all-day monitored image |
| CN108573261A (en) * | 2018-04-17 | 2018-09-25 | 国家电网公司 | A kind of read out instrument recognition methods suitable for Intelligent Mobile Robot |
| CN207965544U (en) * | 2017-12-06 | 2018-10-12 | 中国能源建设集团云南省电力设计院有限公司 | A kind of smart substation equipment fault pre-alarming mechanism |
| CN109308447A (en) * | 2018-07-29 | 2019-02-05 | 国网上海市电力公司 | The method of equipment operating parameter and operating status is automatically extracted in remote monitoriong of electric power |
-
2019
- 2019-09-30 CN CN201910940544.9A patent/CN110929707A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130089263A1 (en) * | 2011-10-11 | 2013-04-11 | Tandent Vision Science, Inc. | System and method for digital image signal compression using intrinsic images |
| CN103886294A (en) * | 2014-03-24 | 2014-06-25 | 北京国网富达科技发展有限责任公司 | Method and system for recognizing number of movement times of arrester for convertor station based on images |
| CN105321289A (en) * | 2015-12-04 | 2016-02-10 | 中国建筑设计院有限公司 | Intelligent analyzing and alarming system and method of all-day monitored image |
| CN207965544U (en) * | 2017-12-06 | 2018-10-12 | 中国能源建设集团云南省电力设计院有限公司 | A kind of smart substation equipment fault pre-alarming mechanism |
| CN108573261A (en) * | 2018-04-17 | 2018-09-25 | 国家电网公司 | A kind of read out instrument recognition methods suitable for Intelligent Mobile Robot |
| CN109308447A (en) * | 2018-07-29 | 2019-02-05 | 国网上海市电力公司 | The method of equipment operating parameter and operating status is automatically extracted in remote monitoriong of electric power |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113524194A (en) * | 2021-04-28 | 2021-10-22 | 重庆理工大学 | Target grabbing method of robot vision grabbing system based on multi-mode feature deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108827316B (en) | Mobile robot visual positioning method based on improved Apriltag | |
| CN107705288B (en) | Infrared video detection method for dangerous gas leakage under strong interference of pseudo-target motion | |
| CN106157310B (en) | The TFT LCD mura defect inspection methods combined with multichannel based on mixed self-adapting Level Set Models | |
| CN104050446B (en) | Meter pointer image identification method based on pointer width character | |
| CN107014294B (en) | Contact net geometric parameter detection method and system based on infrared image | |
| CN112304954A (en) | Part surface defect detection method based on line laser scanning and machine vision | |
| CN107506760A (en) | Traffic signals detection method and system based on GPS location and visual pattern processing | |
| CN107347151A (en) | binocular camera occlusion detection method and device | |
| CN106707674A (en) | Automatic focusing method of projection equipment and the projection equipment | |
| CN106952280B (en) | A kind of spray gun paint amount uniformity detection method based on computer vision | |
| CN106250820B (en) | A kind of staircase mouth passenger flow congestion detection method based on image procossing | |
| CN109687382B (en) | Relay protection pressing plate switching state identification method based on color template matching | |
| CN105893944A (en) | Depth information static gesture segmentation method | |
| CN106228541A (en) | The method and device of screen location in vision-based detection | |
| CN108921881A (en) | A kind of across camera method for tracking target based on homography constraint | |
| CN109584258A (en) | Meadow Boundary Recognition method and the intelligent mowing-apparatus for applying it | |
| CN109190742A (en) | A kind of coding/decoding method of the coding characteristic point based on gray feature | |
| CN110929707A (en) | Converter station scanning detection method, system and medium based on image processing | |
| CN103533332B (en) | A kind of 2D video turns the image processing method of 3D video | |
| CN106558044A (en) | The resolution measuring method of image module | |
| CN109658441A (en) | Foreground detection method and device based on depth information | |
| CN109165605A (en) | Method of data center's crusing robot for control cabinet plate pressing equipment state recognition | |
| CN110644334B (en) | Detection method and detection system for three-dimensional texture morphology of pavement and storage medium | |
| KR101733028B1 (en) | Method For Estimating Edge Displacement Againt Brightness | |
| CN110334727B (en) | Intelligent matching detection method for tunnel cracks |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200327 |
|
| RJ01 | Rejection of invention patent application after publication |