CN109001597A - A kind of electric spark determines method and device - Google Patents
A kind of electric spark determines method and device Download PDFInfo
- Publication number
- CN109001597A CN109001597A CN201711030137.1A CN201711030137A CN109001597A CN 109001597 A CN109001597 A CN 109001597A CN 201711030137 A CN201711030137 A CN 201711030137A CN 109001597 A CN109001597 A CN 109001597A
- Authority
- CN
- China
- Prior art keywords
- brightness region
- area
- bow net
- region
- net arcing
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1218—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing using optical methods; using charged particle, e.g. electron, beams or X-rays
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Analysis (AREA)
Abstract
The present embodiments relate to bow net arcing detection technique fields, and in particular to a kind of electric spark determines that method and device, method include: the image for obtaining pantograph；Determine that at least one high-brightness region in described image, the high-brightness region are the region that gray value is greater than that the pixel of preset threshold forms；Gray value and predetermined bow net arcing classifier based on all pixels in each high-brightness region, determine the corresponding high-brightness region of electric spark.The embodiment of the present invention is by handling pantograph image, determine to may be the region as corresponding to the electric spark of bow net arcing generation in pantograph image, and then according to the gray value in each region, determine region corresponding to the electric spark of bow net arcing generation, so that staff can determine that bow net produces bow net arcing, elimination bow net arcing is taken timely measure for staff and is laid the foundation.
Description
Technical field
The present embodiments relate to bow net arcing detection technique fields, and in particular to a kind of electric spark determines method and dress
It sets.
Background technique
The electric system that bow net is made of contact net and pantograph, wherein contact net is the master of railway electrification project
Framework is set up along railroad track overhead "the" shape, the high voltage transmission line powered to power train；Pantograph is electric power column
By the device of obtaining current from contact net, pantograph is mounted on power train roof vehicle, by contacting with contact net by electric power
It is transferred on train from contact net.
Contact net and the good Mechanical Contact performance of pantograph are the premise guarantees for guaranteeing power train and operating normally.But it connects
It touches net and the good Mechanical Contact of pantograph is limited to many influence factors, such as overhead contact line, contact line material, pantograph
Slide plate defect and track are unequal.Any above-mentioned influence factor if it exists, make contact line with pantograph is slightly bad contacts, bend
Net may generate arcing.Bow net arcing is not only degrading pantograph by the quality of obtaining current, but also causes electrically to grind to bow net
Consumption, greatly reduces the bow net service life.
Therefore, it is urgent to provide a kind of electric sparks to determine method, to determine whether bow net generates arcing so that staff and
When take measures to eliminate bow net arcing.
Summary of the invention
In order to determine whether bow net generates arcing, the embodiment of the invention provides a kind of electric sparks to determine method and device.
In a first aspect, the embodiment of the present invention, which discloses a kind of electric spark, determines method, comprising:
Obtain the image of pantograph；
Determine that at least one high-brightness region in described image, the high-brightness region are that gray value is greater than preset threshold
Pixel composition region；
Gray value and predetermined bow net arcing classifier based on all pixels in each high-brightness region,
Determine the corresponding high-brightness region of electric spark.
Optionally, the gray value and predetermined bow net based on all pixels in each high-brightness region
Arcing classifier determines the corresponding high-brightness region of electric spark, comprising:
Gray scale interval belonging to the gray value of all pixels in each high-brightness region is counted respectively；The gray area
Between to divide the obtained section of gray scale value range；
For each high-brightness region, ratio shared by number of pixels that each gray scale interval includes is determined respectively,
Obtain the grey value profile of each high-brightness region；
Grey value profile and predetermined bow net arcing classifier based on each high-brightness region determine electricity
The corresponding high-brightness region of spark.
Optionally, the method also includes:
If high-brightness region is the corresponding region of electric spark, it is determined that the area of the high-brightness region；
Based on the area, the corresponding bow net arcing power of the high-brightness region is determined；
Based on the bow net arcing power, it is determined whether carry out bow net arcing early warning.
Optionally, the area of the determination high-brightness region, comprising:
Determine the minimum external contact zone of the high-brightness region；
Determine the area of the minimum external contact zone；
The area for determining the high-brightness region is the area of the minimum external contact zone.
Optionally, described to be based on the area, determine the corresponding bow net arcing power of the high-brightness region, comprising:
Based on the corresponding relationship between the area and predetermined area and bow net arcing power, determine that this is highlighted
Spend the corresponding bow net arcing power in region；The corresponding relationship is as follows:
Bow net arcing power=a × area2+ b × area+c
Wherein, a, b and c are the constant determining by fitting.
A kind of electric spark determining device is also disclosed in second aspect, the embodiment of the present invention, comprising:
Acquiring unit, for obtaining the image of pantograph；
First determination unit, for determining that at least one high-brightness region in described image, the high-brightness region be
Gray value is greater than the region that the pixel of preset threshold forms；
Second determination unit for the gray value based on all pixels in each high-brightness region and predefines
Bow net arcing classifier, determine the corresponding high-brightness region of electric spark.
Optionally, second determination unit, is specifically used for:
Gray scale interval belonging to the gray value of all pixels in each high-brightness region is counted respectively；The gray area
Between to divide the obtained section of gray scale value range；
For each high-brightness region, ratio shared by number of pixels that each gray scale interval includes is determined respectively,
Obtain the grey value profile of each high-brightness region；
Grey value profile and predetermined bow net arcing classifier based on each high-brightness region determine electricity
The corresponding high-brightness region of spark.
Optionally, described device further include:
Third determination unit, for second determination unit determine high-brightness region be the corresponding region of electric spark after,
Determine the area of the high-brightness region；
4th determination unit determines the corresponding bow net arcing power of the high-brightness region for being based on the area；
5th determination unit, for being based on the bow net arcing power, it is determined whether carry out bow net arcing early warning.
Optionally, the third determination unit, is specifically used for:
Determine the minimum external contact zone of the high-brightness region；
Determine the area of the minimum external contact zone；
The area for determining the high-brightness region is the area of the minimum external contact zone.
Optionally, the 4th determination unit, is specifically used for:
Based on the corresponding relationship between the area and predetermined area and bow net arcing power, determine that this is highlighted
Spend the corresponding bow net arcing power in region；The corresponding relationship is as follows:
Bow net arcing power=a × area2+ b × area+c
Wherein, a, b and c are the constant determining by fitting.
As it can be seen that the electric spark that the embodiment of the present invention proposes determines method and device, by handling pantograph image,
Determine to may be the region as corresponding to the electric spark of bow net arcing generation in pantograph image, and then according to the ash in each region
Angle value determines region corresponding to the electric spark of bow net arcing generation, so that staff can determine that bow net produces
Bow net arcing takes timely measure elimination bow net arcing for staff and lays the foundation.
Detailed description of the invention
In order to illustrate the technical solution of the embodiments of the present invention more clearly, below will be in embodiment or description of the prior art
Required attached drawing is briefly described, it should be apparent that, the accompanying drawings in the following description is only some realities of the invention
Example is applied, it for those of ordinary skill in the art, without any creative labor, can also be attached according to these
Figure obtains other attached drawings.
Fig. 1 is that a kind of electric spark provided in an embodiment of the present invention determines method flow diagram；
Fig. 2 is a kind of block diagram of electric spark determining device provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiments of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
Member's every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
As shown in Figure 1, the embodiment of the present invention, which discloses a kind of electric spark, determines method, it may include following steps 101~103:
101, the image of pantograph is obtained.
In the present embodiment, the executing subject of this method, which can be, executes the processor that electric spark determines method, the processor
It is arranged inside train, the executing subject of this method is also possible to the mobile unit of train (Vehicle on board
Control, VOBC) include: vehicle-mounted automatic protective system (vehicle-mounted ATP, Automatic Train Protection), it is vehicle-mounted from
Dynamic control loop (vehicle-mounted ATO, Automatic Train Operation) etc..
In the present embodiment, the executing subject of this method will obtain the image of pantograph, it is necessary first to which image capture device is adopted
Collect the image of pantograph, then the executing subject of this method interacts again with image capture device to obtain the image of pantograph.
102, determine that at least one high-brightness region in described image, the high-brightness region are gray value greater than default
The region of the pixel composition of threshold value.
In the present embodiment, step 102 specifically may include unshowned following steps 1021 to 1023 in Fig. 1:
1021, gray processing handles described image, obtains the first image.
In the present embodiment, it is contemplated that the pantograph image of acquisition is color image, and amount of image information is big, is not easy to determine electricity
Therefore the operation that spark process is related to carries out gray processing processing to the pantograph image of acquisition, so that every in pantograph image
A pixel only has a gray value, reduces amount of image information convenient for operation.Component method, maximum value can be used in gray processing processing
Method, mean value method or weighted mean method, these methods belong to the mature technology of this field, and this embodiment is not repeated.
1022, binary conversion treatment the first image obtains the second image.
In the present embodiment, using the first image of binary conversion treatment, other than being further reduced amount of image information convenient for operation,
Prior purpose is to remove the irrelevant information in the first image, reservation effective information.
In the present embodiment, it is contemplated that the most common binarization method: threshold binarization is by defining a gray scale threshold
The gray value of the pixel is set as 0 (i.e. black) if the gray value of pixel is less than the gray threshold by value, otherwise is set as 255
(i.e. white), but the limitation of threshold binarization is very big, because gray threshold is unique, if the illumination of pantograph image may not
It is even, then pantograph image some regions energy separating background, and in addition region may cannot separating background, therefore, no matter gray scale
Threshold value setting is high or low, it is possible that effective information is removed.It is therefore desirable to be taken for the pixel in different regions different
Gray threshold, in the present embodiment, it is preferred to use adaptive threshold binary conversion treatment the first image.
Adaptive threshold, such as gray threshold is determined by each pixel and the gray value relationship of surrounding pixel.It is adaptive
It answers the process of threshold binarization treatment as follows: for some pixel, calculating the rectangle region of N × N size centered on this pixel
The summation of the gray value of all pixels obtains the average gray value in the region again divided by region area in domain, if the ash of the pixel
Angle value is less than the average gray value, then the gray value of the pixel is set as 0 (i.e. black), otherwise is set as 255 (i.e. white),
In, N is positive integer, indicates the pixel number that every row or each column include in rectangular area.Adaptive threshold binary conversion treatment can also adopt
In other ways, this embodiment is not repeated.
1023, at least one high-brightness region in the first image, the high-brightness region and described second are determined
White area in image corresponds.
Pass through in the present embodiment, in step 1022 includes at least one white area in the second image that binary conversion treatment obtains
Domain, the gray value of each pixel is 255 in white area.These white areas may be the electric spark generated due to bow net arcing
Caused, therefore, the region in the first image corresponding to these white areas is as high-brightness region, namely highlights
It is identical as the position of white area in the second region to spend position of the region in the first image, and high-brightness region
It is identical with the shape size of corresponding white area.
103, gray value and predetermined bow net arcing point based on all pixels in each high-brightness region
Class device determines the corresponding high-brightness region of electric spark.
In the present embodiment, step 103 specifically includes unshowned following steps 1031 and 1032 in Fig. 1:
1031, the grey value profile of each high-brightness region is counted.
In the present embodiment, since the gray value of all pixels in high-brightness region is not exactly the same namely high-brightness region
In have multiple gray values, therefore, each high-brightness region can be directed to, count the gray value point of each high-brightness region respectively
Cloth.
1032, grey value profile and predetermined bow net arcing classifier based on each high-brightness region,
Determine the corresponding high-brightness region of electric spark.
In the present embodiment, bow net arcing classifier can by Training Support Vector Machines (Support Vector Machine,
SVM it) obtains, specifically, can be gone based on the grey value profile in region corresponding to the electric spark for having been determined as bow net arcing generation
The unknown SVM of training parameter, so that it is determined that the parameter value of SVM, obtains bow net arcing classifier.In turn by each high brightness
The output of input of the grey value profile in region as bow net arcing classifier, bow net arcing classifier can determine high luminance area
Whether domain is region corresponding to the electric spark of bow net arcing generation.
As it can be seen that electric spark disclosed by the embodiments of the present invention determines method, by handling pantograph image, determine by
It may be region corresponding to the electric spark that is generated as bow net arcing in pantograph image, and then according to the gray value in each region,
Region corresponding to the electric spark of bow net arcing generation is determined, so that staff can determine that bow net produces bow net combustion
Arc takes timely measure elimination bow net arcing for staff and lays the foundation.
Gray scale in a specific example, based on all pixels in each high-brightness region described in step 103
Value and predetermined bow net arcing classifier, determine the corresponding high-brightness region of electric spark, specifically include in following Fig. 1 not
The step 1031 shown ' to 1033 ':
1031 ', gray scale interval belonging to the gray value of all pixels in each high-brightness region is counted respectively；It is described
Gray scale interval is the section for dividing gray scale value range and obtaining.
In the present embodiment, gray scale value range is: 0~255, divide gray scale value range for example are as follows: by 0~255 gray scale
It is divided into 16 groups, the gray scale interval after division are as follows: 0~15,16~31 ..., 240~255.So, pixel in high-brightness region
Gray value is that the gray value of any value belongs to gray scale interval 0~15 in 0~15, in high-brightness region the gray value of pixel be 16~
The gray value of any value belongs to gray scale interval 16~31 in 31 ..., and the gray value of pixel is in 240~255 in high-brightness region
The gray value of any value belongs to gray scale interval 240~255.It should be appreciated that gray scale value range can be divided according to actual needs.
In the present embodiment, for each high-brightness region, step 1031 ' execute after, also determined that each gray area
Between corresponding number of pixels.
1032 ', it is directed to each high-brightness region, is determined shared by number of pixels that each gray scale interval includes respectively
Ratio obtains the grey value profile of each high-brightness region.
In the present embodiment, ratio shared by the number of pixels that gray scale interval includes is the high brightness that the gray scale interval includes
The ratio of the number of middle all pixels between number of pixels and the high luminance area in section.Step 1032 ' obtained gray value point
Cloth can realize that as histogram, the grey value profile and histogram of high-brightness region correspond, and in histogram, abscissa is gray scale
Section, 16 gray scale intervals represent 16 dimensions；Ordinate is the value of grey value profile namely dimension, and the value of each dimension is equal
It is 1 more than or equal to zero and less than the sum of value of 1,16 dimension.
1033 ', grey value profile and predetermined bow net arcing classifier based on each high-brightness region,
Determine the corresponding high-brightness region of electric spark.
It, can be based on the grey value profile in region corresponding to the electric spark for having been determined as bow net arcing generation in the present embodiment
The SVM that the value of 16 dimensions in corresponding histogram goes training parameter unknown, so that it is determined that the parameter value of SVM, obtains bow net
Arcing classifier.And then can be using step 1032 ' the obtained value of 16 dimensions as in step 106 bow net arcing classifier it is defeated
Enter, the output of bow net arcing classifier can determine whether high-brightness region is area corresponding to the electric spark of bow net arcing generation
Domain.
In a specific example, electric spark shown in FIG. 1 determines that method further includes unshowned following steps in Fig. 1
104~106:
If 104, high-brightness region is region corresponding to electric spark, it is determined that the area of the high-brightness region.
In the present embodiment, it is contemplated that bow net will do it loss test in design, and the bow net to put into effect allows generation one
The bow net arcing of power (power is less than or equal to preset power threshold) is determined without impacting to bow net.Therefore, in step
After 103 determine region corresponding to electric spark of the high-brightness region for bow net arcing generation, need to consider whether to be bent
Net arcing early warning, the key of early warning are bow net arcing power, if bow net arcing power is less than predetermined power threshold value, illustrate bow net
Arcing power does not need to carry out bow net arcing early warning in the power bracket that bow net can be born.
In the present embodiment, region corresponding to electric spark of the high-brightness region for bow net arcing generation is determined in step 103
Afterwards, it is first determined the area of the high-brightness region, and then lay the foundation for bow net arcing early warning.
105, it is based on the area, determines the corresponding bow net arcing power of the high-brightness region.
In the present embodiment, bow net arcing power is determined using area, compared to the prior art by Current Voltage come really
Determine the mode of power, and electric current and voltage need additional equipment to detect, and electric current and voltage are transient changes, increase
The difficulty of determining power.Therefore, the present embodiment determines that bow net arcing power not only reduces determining power using area
Cost, and reduce the difficulty of determining power.
106, it is based on the bow net arcing power, it is determined whether carry out bow net arcing early warning.
In the present embodiment, after determining bow net arcing power, so that it may determine whether to carry out bow net arcing early warning, specifically
Ground carries out early warning if bow net arcing power is greater than preset power threshold；If bow net arcing power is less than or equal to preset function
Rate threshold value, then without early warning.
In a specific example, the area of the high-brightness region is determined described in step 104, is specifically included in Fig. 1 not
The following steps 1041~1043 shown:
1041, the minimum external contact zone of the high-brightness region is determined.
In the present embodiment, it is contemplated that high-brightness region is irregular shape, is not easy to reference area, therefore, first really
The minimum external contact zone of the fixed high-brightness region, because the area of polygon is easier to determine.Optionally, polygon is square
Shape.
1042, the area of the minimum external contact zone is determined.
In the present embodiment, the prior art is can be used in the determination of the area of polygon, and this embodiment is not repeated.Optionally,
When polygon is rectangle, the area of polygon is more convenient for determining.
1043, the area for determining the high-brightness region is the area of the minimum external contact zone.
In the present embodiment, using the area of minimum external contact zone as the area of high-brightness region, there are certain errors, but
Determine that error can be ignored by the test of applicant repeatedly.
In a specific example, it is based on the area described in step 105, determines the corresponding bow net of the high-brightness region
Arcing power, specific as follows:
Based on the corresponding relationship between the area and predetermined area and bow net arcing power, determine that this is highlighted
Spend the corresponding bow net arcing power in region；The corresponding relationship is as follows:
Bow net arcing power=a × area2+ b × area+c
Wherein, a, b and c are the constant determining by fitting.
In the present embodiment, it is contemplated that be nonlinear relationship between area and bow net arcing power, therefore, provide ginseng first
The unknown corresponding relationship of number: bow net arcing power=a × area2Then+b × area+c is produced by having been determined as bow net arcing
The corresponding relationship that the area and bow net arcing power in region corresponding to raw electric spark go fitting above-mentioned parameter unknown, thus
It can be fitted to obtain the value of a, b and c, the method for fitting uses the prior art, such as least square method, and this embodiment is not repeated.
As shown in Fig. 2, the embodiment of the present invention discloses a kind of electric spark determining device, it may include such as lower unit: acquiring unit
21, the first determination unit 22 and the second determination unit 23, each unit is described as follows:
Acquiring unit 21, for obtaining the image of pantograph；
First determination unit 22, for determining at least one high-brightness region in described image, the high-brightness region
The region formed for the pixel that gray value is greater than preset threshold；
Second determination unit 23, for based on all pixels in each high-brightness region gray value and in advance really
Fixed bow net arcing classifier determines the corresponding high-brightness region of electric spark.
In a specific example, second determination unit 23 is specifically used for:
Gray scale interval belonging to the gray value of all pixels in each high-brightness region is counted respectively；The gray area
Between to divide the obtained section of gray scale value range；
For each high-brightness region, ratio shared by number of pixels that each gray scale interval includes is determined respectively,
Obtain the grey value profile of each high-brightness region；
Grey value profile and predetermined bow net arcing classifier based on each high-brightness region determine electricity
The corresponding high-brightness region of spark.
In a specific example, described device may also include unshowned such as lower unit in Fig. 2: third determination unit
24, the 4th determination unit 25 and the 5th determination unit 26, each unit are described as follows:
Third determination unit 24 determines that high-brightness region is the electricity that bow net arcing generates for second determination unit 23
Behind region corresponding to spark, the area of the high-brightness region is determined；
4th determination unit 25 determines the corresponding bow net arcing power of the high-brightness region for being based on the area；
5th determination unit 26, for being based on the bow net arcing power, it is determined whether carry out bow net arcing early warning.
In a specific example, the third determination unit 24 is specifically used for:
Determine the minimum external contact zone of the high-brightness region；
Determine the area of the minimum external contact zone；
The area for determining the high-brightness region is the area of the minimum external contact zone.
In a specific example, the 4th determination unit 25 is specifically used for:
Based on the corresponding relationship between the area and predetermined area and bow net arcing power, determine that this is highlighted
Spend the corresponding bow net arcing power in region；The corresponding relationship is as follows:
Bow net arcing power=a × area 2+b × area+c
Wherein, a, b and c are the constant determining by fitting.
It is true that electric spark determining device disclosed in above embodiments can be realized electric spark disclosed in the relevant each embodiment of Fig. 1
Determine the process of method, to avoid repeating, which is not described herein again.
It is understood that embodiments described herein can with hardware, software, firmware, middleware, microcode or its
Combination is to realize.For hardware realization, processing unit be may be implemented in one or more specific integrated circuit (Application
Specific Integrated Circuits, ASIC), digital signal processor (Digital Signal Processing,
DSP), digital signal processing appts (DSP Device, DSPD), programmable logic device (Programmable Logic
Device, PLD), field programmable gate array (Field-Programmable Gate Array, FPGA), general processor,
In controller, microcontroller, microprocessor, other electronic units for executing herein described function or combinations thereof.
For software implementations, the techniques described herein can be realized by executing the unit of function described herein.Software generation
Code is storable in memory and is executed by processor.Memory can in the processor or portion realizes outside the processor.
Those of ordinary skill in the art may be aware that list described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, the specific application and design constraint depending on technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
The scope of the present invention.
In embodiment provided herein, it should be understood that disclosed device and method can pass through others
Mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of the unit, only
A kind of logical function partition, there may be another division manner in actual implementation, for example, multiple units or components can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.Another point, shown or discussed is mutual
Between coupling, direct-coupling or communication connection can be through some interfaces, the INDIRECT COUPLING or communication link of device or unit
It connects, can be electrical property, mechanical or other forms.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, the technical solution of the embodiment of the present invention is substantially
The part of the part that contributes to existing technology or the technical solution can embody in the form of software products in other words
Come, which is stored in a storage medium, including some instructions are used so that a computer equipment (can
To be personal computer, server or the network equipment etc.) execute all or part of each embodiment the method for the present invention
Step.And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, ROM, RAM, magnetic or disk etc. are various can store program
The medium of code.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the device that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or device institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or device.
It should be noted that, in this document, the relational terms of such as " first " and " second " or the like are used merely to one
A entity or operation with another entity or operate distinguish, without necessarily requiring or implying these entities or operation it
Between there are any actual relationship or orders.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of electric spark determines method characterized by comprising
Obtain the image of pantograph；
Determine that at least one high-brightness region in described image, the high-brightness region are the picture that gray value is greater than preset threshold
The region of element composition；
Gray value and predetermined bow net arcing classifier based on all pixels in each high-brightness region determine
The corresponding high-brightness region of electric spark.
2. the method according to claim 1, wherein described based on all pixels in each high-brightness region
Gray value and predetermined bow net arcing classifier, determine the corresponding high-brightness region of electric spark, comprising:
Gray scale interval belonging to the gray value of all pixels in each high-brightness region is counted respectively；The gray scale interval is
Divide the section that gray scale value range obtains；
For each high-brightness region, ratio shared by number of pixels that each gray scale interval includes is determined respectively, is obtained
The grey value profile of each high-brightness region；
Grey value profile and predetermined bow net arcing classifier based on each high-brightness region, determine electric spark
Corresponding high-brightness region.
3. method according to claim 1 or 2, which is characterized in that the method also includes:
If high-brightness region is the corresponding region of electric spark, it is determined that the area of the high-brightness region；
Based on the area, the corresponding bow net arcing power of the high-brightness region is determined；
Based on the bow net arcing power, it is determined whether carry out bow net arcing early warning.
4. according to the method described in claim 3, it is characterized in that, the area of the determination high-brightness region, comprising:
Determine the minimum external contact zone of the high-brightness region；
Determine the area of the minimum external contact zone；
The area for determining the high-brightness region is the area of the minimum external contact zone.
5. according to the method described in claim 3, it is characterized in that, it is described be based on the area, determine the high-brightness region pair
The bow net arcing power answered, comprising:
Based on the corresponding relationship between the area and predetermined area and bow net arcing power, the high luminance area is determined
The corresponding bow net arcing power in domain；The corresponding relationship is as follows:
Bow net arcing power=a × area2+ b × area+c
Wherein, a, b and c are the constant determining by fitting.
6. a kind of electric spark determining device characterized by comprising
Acquiring unit, for obtaining the image of pantograph；
First determination unit, for determining that at least one high-brightness region in described image, the high-brightness region are gray scale
Value is greater than the region that the pixel of preset threshold forms；
Second determination unit, for gray value and predetermined bow based on all pixels in each high-brightness region
Net arcing classifier determines the corresponding high-brightness region of electric spark.
7. device according to claim 6, which is characterized in that second determination unit is specifically used for:
Gray scale interval belonging to the gray value of all pixels in each high-brightness region is counted respectively；The gray scale interval is
Divide the section that gray scale value range obtains；
For each high-brightness region, ratio shared by number of pixels that each gray scale interval includes is determined respectively, is obtained
The grey value profile of each high-brightness region；
Grey value profile and predetermined bow net arcing classifier based on each high-brightness region, determine electric spark
Corresponding high-brightness region.
8. device according to claim 6 or 7, which is characterized in that described device further include:
Third determination unit determines high-brightness region for second determination unit to determine behind the corresponding region of electric spark
The area of the high-brightness region；
4th determination unit determines the corresponding bow net arcing power of the high-brightness region for being based on the area；
5th determination unit, for being based on the bow net arcing power, it is determined whether carry out bow net arcing early warning.
9. device according to claim 8, which is characterized in that the third determination unit is specifically used for:
Determine the minimum external contact zone of the high-brightness region；
Determine the area of the minimum external contact zone；
The area for determining the high-brightness region is the area of the minimum external contact zone.
10. device according to claim 8, which is characterized in that the 4th determination unit is specifically used for:
Based on the corresponding relationship between the area and predetermined area and bow net arcing power, the high luminance area is determined
The corresponding bow net arcing power in domain；The corresponding relationship is as follows:
Bow net arcing power=a × area2+ b × area+c
Wherein, a, b and c are the constant determining by fitting.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711030137.1A CN109001597A (en) | 2017-10-30 | 2017-10-30 | A kind of electric spark determines method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711030137.1A CN109001597A (en) | 2017-10-30 | 2017-10-30 | A kind of electric spark determines method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109001597A true CN109001597A (en) | 2018-12-14 |
Family
ID=64573638
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711030137.1A Pending CN109001597A (en) | 2017-10-30 | 2017-10-30 | A kind of electric spark determines method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109001597A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112185069A (en) * | 2020-09-29 | 2021-01-05 | 浙江工业职业技术学院 | Circuit early warning system |
| CN113487543A (en) * | 2021-06-16 | 2021-10-08 | 成都唐源电气股份有限公司 | Contact net arcing firing detection method, device, computer equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013644A (en) * | 2002-05-27 | 2007-08-08 | 株式会社日立制作所 | Plasma display panel and imaging device using the same |
| CN105469420A (en) * | 2016-01-25 | 2016-04-06 | 成都国铁电气设备有限公司 | Overhead line-pantograph arcing defect identification method and system thereof |
| CN105571508A (en) * | 2016-01-25 | 2016-05-11 | 成都国铁电气设备有限公司 | Deformation detecting method and deformation detecting system for pantograph of overhead contact system |
| CN105652154A (en) * | 2016-01-25 | 2016-06-08 | 成都国铁电气设备有限公司 | Safety monitoring analysis system for contact net running state |
| CN106991417A (en) * | 2017-04-25 | 2017-07-28 | 华南理工大学 | A kind of visual projection's interactive system and exchange method based on pattern-recognition |
-
2017
- 2017-10-30 CN CN201711030137.1A patent/CN109001597A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101013644A (en) * | 2002-05-27 | 2007-08-08 | 株式会社日立制作所 | Plasma display panel and imaging device using the same |
| CN105469420A (en) * | 2016-01-25 | 2016-04-06 | 成都国铁电气设备有限公司 | Overhead line-pantograph arcing defect identification method and system thereof |
| CN105571508A (en) * | 2016-01-25 | 2016-05-11 | 成都国铁电气设备有限公司 | Deformation detecting method and deformation detecting system for pantograph of overhead contact system |
| CN105652154A (en) * | 2016-01-25 | 2016-06-08 | 成都国铁电气设备有限公司 | Safety monitoring analysis system for contact net running state |
| CN106991417A (en) * | 2017-04-25 | 2017-07-28 | 华南理工大学 | A kind of visual projection's interactive system and exchange method based on pattern-recognition |
Non-Patent Citations (4)
| Title |
|---|
| 李志锋: "《世界轨道交通技术及解决方案系列丛书 铁路供电运行安全与技术研究 2014版》", 31 August 2015, 西南交通大学出版社 * |
| 王兴梅 等: "《基于水平集的水下声呐图像目标检测 黑龙江省精品图书出版工程》", 30 June 2017, 哈尔滨工程大学出版社 * |
| 王胜辉: "基于紫外成像的污秽悬式绝缘子放电检测及评估", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
| 郝兵 等: "《After Effects 4.1》", 30 April 2001, 人民邮电出版社 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112185069A (en) * | 2020-09-29 | 2021-01-05 | 浙江工业职业技术学院 | Circuit early warning system |
| CN113487543A (en) * | 2021-06-16 | 2021-10-08 | 成都唐源电气股份有限公司 | Contact net arcing firing detection method, device, computer equipment and storage medium |
| CN113487543B (en) * | 2021-06-16 | 2023-08-04 | 成都唐源电气股份有限公司 | Contact net arcing burning detection method, device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105092598A (en) | Method and system for rapidly recognizing defects of big-breadth PCB on basis of connected areas | |
| CN105469420B (en) | bow net arcing defect identification method and system | |
| CN109001597A (en) | A kind of electric spark determines method and device | |
| CN103645822B (en) | The foreign matter detecting method of touch-screen and touch-screen | |
| CN102547365B (en) | Black edge detection method and device for video image | |
| CN104282011A (en) | Method and device for detecting interference stripes in video images | |
| Shareef et al. | An image processing based method for power quality event identification | |
| CN103903008A (en) | Power transmission line fog level recognition method and system based on images | |
| CN112164086B (en) | Method, system and electronic equipment for determining refined image edge information | |
| RU2014139838A (en) | THREE-DIMENSION OBJECT DETECTION DEVICE | |
| CN102521606B (en) | Method for classifying pixel blocks of JPEG images and image falsification detecting and falsified area positioning methods based on same | |
| JP2010271987A5 (en) | ||
| CN104866865A (en) | DHOG and discrete cosine transform-based overhead line system equilibrium line fault detection method | |
| CN109447074A (en) | A kind of licence plate recognition method and terminal device | |
| CN108645354A (en) | The structured light three-dimensional imaging method and system of high reflective subject surface | |
| CN103679732A (en) | Noise-detection-based high density impulse noise self-adaptive filtering algorithm | |
| CN107392889A (en) | A kind of power equipment running state monitoring method and system based on infrared image | |
| CN110618366A (en) | Direct current arc detection method and device | |
| CN110782409A (en) | Method for removing shadow of multi-motion object | |
| CN102509311B (en) | Motion detection method and device | |
| CN103996177A (en) | Snow noise removing algorithm free of reference detection | |
| US20140161349A1 (en) | Straight line detection apparatus and straight line detection method | |
| CN203825644U (en) | Image identification power transmission line-based fog level system | |
| KR20160039646A (en) | Method and device for enhancing edge of image and digital camera | |
| Chen et al. | A no-reference blocking artifacts metric using selective gradient and plainness measures |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181214 |