CN110378897A - A kind of pantograph running state real-time monitoring method and device based on video - Google Patents
A kind of pantograph running state real-time monitoring method and device based on video Download PDFInfo
- Publication number
- CN110378897A CN110378897A CN201910677782.5A CN201910677782A CN110378897A CN 110378897 A CN110378897 A CN 110378897A CN 201910677782 A CN201910677782 A CN 201910677782A CN 110378897 A CN110378897 A CN 110378897A
- Authority
- CN
- China
- Prior art keywords
- information
- pantograph
- image information
- contact point
- obtains
- 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
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000012544 monitoring process Methods 0.000 title claims abstract description 40
- 238000006073 displacement reaction Methods 0.000 claims abstract description 60
- 239000013307 optical fiber Substances 0.000 claims abstract description 57
- 238000001514 detection method Methods 0.000 claims abstract description 44
- 230000002159 abnormal effect Effects 0.000 claims abstract description 17
- 238000003708 edge detection Methods 0.000 claims abstract description 17
- 238000012549 training Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 8
- 230000010339 dilation Effects 0.000 claims description 7
- 230000003628 erosive effect Effects 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 230000007797 corrosion Effects 0.000 claims description 6
- 238000005260 corrosion Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 5
- 238000005530 etching Methods 0.000 claims description 5
- 230000001052 transient effect Effects 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 abstract description 7
- 238000004891 communication Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013095 identification testing Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000035939 shock Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013523 data management Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000009415 formwork Methods 0.000 description 1
- 230000007257 malfunction Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000002688 persistence Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000006641 stabilisation Effects 0.000 description 1
- 238000011105 stabilization Methods 0.000 description 1
- 238000013526 transfer learning Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- 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 using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Current-Collector Devices For Electrically Propelled Vehicles (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention provides a kind of pantograph running state real-time monitoring method and device based on video, this method comprises: obtaining bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and foreign matter recognition detection result information；If any information is abnormal in Spark plug optical fiber sensor information, bow net contact point lateral displacement statistical information or foreign matter recognition result information, alarm signal is issued；Wherein, it obtains bow net contact point lateral displacement statistical information to specifically include: edge detection is carried out to pantograph gray level image information, obtain edge image information, straight-line detection is carried out to edge image information, obtain contact line information, bow net contact point information is obtained, it is for statistical analysis to bow net contact point information to obtain bow net contact point lateral displacement statistical information；Angle information Spark plug optical fiber sensor information and the realization of foreign matter recognition detection result information are deflected for the real-time monitoring of pantograph operating status by bow net contact point lateral displacement statistical information, bow.
Description
Technical field
The present invention relates to malfunction monitoring technical fields more particularly to a kind of pantograph operating status based on video to supervise in real time
Survey method and device.
Background technique
All rail transit trains all pass through the sliding contact between train pantograph and contact net and obtain electric energy from outside,
Contact relation is most important to train safety, normal operation between bow net.Due to pantograph and the special contact relation of contact net and
Design feature is not easy to install test equipment in operation train pantograph or contact net, moreover, operation train once occurs sternly
The contact extremely of heavy bow net or attachment foreign matter are also not easy to step on top inspection by bus in track section, need by means of specially adhering to
Equipment steps on top inspection or train by bus and changes bow maintenance operation, directly influences train running on scheduled time operation.
In the prior art, the maintenance and monitoring of pantograph operating status are mainly after daily train storage by know-how
Personnel's manual inspection, registration, judge whether pantograph contour structure size, jacking condition are normal.But this maintenance mode is only
It can ensure that whether pantograph itself significant exception occurs, cannot ensure that can be realized normal bow net contact after putting into effect closes
System.In addition pantograph state in train travelling process can also be recorded, but can only be led to by installing high-definition camera in roof
It crosses artificial video playback mode and checks whether to occur abnormal, bow net contact relation condition can not be assessed in real time, whether hit or attached
Foreign matter.
Therefore how to realize and real-time monitoring, which has become industry technology urgently to be resolved, to be realized for pantograph operating status
Problem.
Summary of the invention
The embodiment of the present invention provides a kind of pantograph running state real-time monitoring method and device based on video, more than
It states the technical issues of proposing in background technique or at least partly solves technical problem mentioned above in the background art.
In a first aspect, the embodiment of the present invention provides a kind of pantograph running state real-time monitoring method based on video, packet
It includes:
Obtain bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and foreign matter identification
Testing result information；
Know if the Spark plug optical fiber sensor information, bow deflect angle information, bow net contact point lateral displacement statistical information or foreign matter
Any information is abnormal in other result information, then issues alarm signal；
Wherein, the acquisition bow net contact point lateral displacement statistical information specifically includes: to pantograph gray level image information
Edge detection is carried out, edge image information is obtained, straight-line detection is carried out to the edge image information, obtains contact line information,
Bow net contact point information is obtained according to pantograph collector head area information and the contact line information, bow net contact point information is carried out
Statistical analysis obtains bow net contact point lateral displacement statistical information.
Wherein, angle information, Spark plug optical fiber sensor information are deflected in the acquisition bow net contact point lateral displacement statistical information, bow
Before the step of foreign matter recognition detection result information, the method also includes:
Pantograph gray level image information is pre-processed, pretreatment pantograph image is obtained；
Image binaryzation is carried out to the pretreatment pantograph image, obtains binaryzation pantograph image information；
The binaryzation pantograph image information is analyzed and processed, Spark plug optical fiber sensor information is obtained.
Wherein, the step of pantograph gray level image information being pre-processed described, obtaining pretreatment pantograph image
Before, the method also includes:
Pantograph video information is obtained, pantograph image information is obtained according to the pantograph video information,
Gray proces are carried out to the pantograph image information, obtain pantograph gray level image information；
Template matching is carried out to the pantograph gray level image information, obtains pantograph collector head area information.
Wherein, described that the binaryzation pantograph image information is analyzed and processed, obtain the step of Spark plug optical fiber sensor information
Suddenly, it specifically includes:
The simply connected region pixel point areas in the binaryzation pantograph image information is counted, and is rejected pre- less than first
If the area pixel point of threshold value, obtains remaining area area information；
If the remaining area area information is greater than the second preset threshold, and the remaining area area information leans on adosculation
Line region is then determined as spark information, obtains the Spark plug optical fiber sensor information according to the spark information.
Wherein, described the step of edge detection is carried out to the pantograph gray level image information, obtains edge image information,
It specifically includes:
Expansion and etching operation are carried out to the pantograph gray level image information, obtain expanding image information and corrosion image
Information；
Expanding image information is subtracted into corrosion image information, obtains dilation erosion image information, dilation erosion image is believed
Breath presses pixel inversion operation, obtains inverse operations image information；
The inverse operations image information is changed into edge image information by self-adaption binaryzation.
Wherein, described the step of straight-line detection is carried out to the edge image information, obtains contact line information, specific to wrap
It includes:
Straight-line detection is carried out to the edge image information, obtains edge image straight line information；
Identifying processing is carried out to the edge image straight line information according to the constraint relationship between pantograph and contact net, is connect
Touch line information.
Wherein, angle information, Spark plug optical fiber sensor information are deflected in the acquisition bow net contact point lateral displacement statistical information, bow
Before the step of foreign matter recognition detection result information, the method also includes:
Multiple groups training sample will be obtained with foreign matter pantograph collector head area image as one group of training sample；
Multiple groups training sample is inputted default convolutional neural networks to be trained, until meet preset condition, deconditioning,
Obtain the common foreign matter identification preset model in pantograph collector head region；
Identification point is carried out to pantograph video information according to the common foreign matter identification preset model in the pantograph collector head region
Analysis, obtains foreign matter recognition detection result information.
Second aspect, the embodiment of the present invention provide a kind of pantograph running state real-time monitoring device based on video, packet
It includes:
Module is obtained, for obtaining bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor letter
Breath and foreign matter recognition detection result information；
Monitoring modular, if for the Spark plug optical fiber sensor information, bow deflection angle information, bow net contact point lateral displacement statistics
Any information is abnormal in information or foreign matter recognition result information, then issues alarm signal；
Wherein, the acquisition bow net contact point lateral displacement statistical information specifically includes: to pantograph gray level image information
Edge detection is carried out, edge image information is obtained, straight-line detection is carried out to the edge image information, obtains contact line information,
Bow net contact point information is obtained according to pantograph collector head area information and the contact line information, bow net contact point information is carried out
Statistical analysis obtains bow net contact point lateral displacement statistical information.
The third aspect, the embodiment of the present invention provides a kind of electronic equipment, including memory, processor and is stored in memory
Computer program that is upper and can running on a processor, the processor realize base as described in relation to the first aspect when executing described program
In the pantograph running state real-time monitoring method of video the step of.
Fourth aspect, the embodiment of the present invention provide a kind of non-transient computer readable storage medium, are stored thereon with calculating
Machine program realizes that the pantograph operating status based on video is real as described in relation to the first aspect when the computer program is executed by processor
When monitoring method the step of.
Pantograph running state real-time monitoring method and device provided in an embodiment of the present invention based on video, by by
Pantograph video information is analyzed, so that accurate judgement Spark plug optical fiber sensor information, realizes Spark plug optical fiber sensor；Pass through straight-line detection and edge
It detects and determines contact line information, bow net contact point lateral displacement statistics can be accurately counted in conjunction with pantograph collector head area information
Information realizes the monitoring of pantograph misalignment；And identify the foreign matter in pantograph image information；When the Spark plug optical fiber sensor is believed
Breath, bow net contact point lateral displacement statistical information and foreign matter recognition result Information abnormity then issue alarm signal, realization pair automatically
In the real-time monitoring of pantograph operating status.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is this hair
Bright some embodiments for those of ordinary skill in the art without creative efforts, can be with root
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is the pantograph running state real-time monitoring method flow based on video described in one embodiment of the invention
Figure；
Fig. 2 is real-time monitoring flow chart described in one embodiment of the invention；
Fig. 3 is that the pantograph running state real-time monitoring apparatus structure based on video described in one embodiment of the invention shows
It is intended to.
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 embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without creative efforts, shall fall within the protection scope of the present invention.
Fig. 1 is the pantograph running state real-time monitoring method flow based on video described in one embodiment of the invention
Figure, as shown in Figure 1, comprising:
Step S1 obtains bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and different
Object recognition detection result information；
Step S2, if the Spark plug optical fiber sensor information, bow deflection angle information, bow net contact point lateral displacement statistical information or
Any information is abnormal in foreign matter recognition result information, then issues alarm signal；
Wherein, the acquisition bow net contact point lateral displacement statistical information specifically includes: to pantograph gray level image information
Edge detection is carried out, edge image information is obtained, straight-line detection is carried out to the edge image information, obtains contact line information,
Bow net contact point information is obtained according to pantograph collector head area information and the contact line information, bow net contact point information is carried out
Statistical analysis obtains bow net contact point lateral displacement statistical information.
Specifically, acquisition Spark plug optical fiber sensor information described in the embodiment of the present invention specifically refers to believe pantograph gray level image
Breath is pre-processed, and pretreatment pantograph image is obtained, and then by image binaryzation, obtains binaryzation pantograph image letter
Breath；The binaryzation pantograph image information for meeting Spark plug optical fiber sensor rule is marked, and the binaryzation pantograph image is believed
Breath carries out continuing tracking, and then obtains spark information and spark duration, and by spark number information and spark duration
As Spark plug optical fiber sensor information.
Foreign matter recognition detection result information described in the embodiment of the present invention, primarily with respect to pantograph in normal use
The common foreign matter such as the bird, polybag and the rope that often arrive in the process is identified.
Foreign matter recognition detection result information in the embodiment of the present invention can be through preparatory trained pantograph collector head
The common foreign matter identification preset model in region obtains.
Bow deflection angle information described in the embodiment of the present invention is according to where the bow upper surface of bow region both ends
Linear position, obtain slide plate upper surface, the angle between the straight line and image bottom surface be bow deflection angle information, count every frame
The bow of image deflects angle information.
Pantograph collector head area information described in the embodiment of the present invention can be through pantograph gray level image information
Template matching is carried out, so that it is determined that pantograph collector head area information.
Bow net contact point lateral displacement statistical information described in the embodiment of the present invention refers to pantograph and contact line
Displacement data of the contact point relative to scale contact point.
Bow net contact point lateral displacement statistical information described in the embodiment of the present invention is abnormal, can refer to bow net contact
Displacement data in point lateral displacement statistical information has exceeded predetermined threshold, and preset threshold herein can be ± 2 σ, then herein
Alarm signal is issued, and issues pantograph lateral displacement early warning.
Spark plug optical fiber sensor Information abnormity described in the embodiment of the present invention can refer to that the spark in Spark plug optical fiber sensor information is held
The continuous time is more than preset time or spark number information is more than preset threshold, then it is assumed that Spark plug optical fiber sensor Information abnormity is issued and accused
Alert signal, and issue spark early warning；Such as obtaining the video frame rate of acquisition is 25FPS, then can get every frame image persistence
About 40ms marks and tracks the pantograph gray level image information for spark occur, and the record duration is more than the spark of 100ms
The several and duration, to obtain spark number information and spark duration information.
Foreign matter recognition detection results abnormity described in the embodiment of the present invention can refer to, detect in pantograph region
It detects that foreign matter exists, then issues alarm at this time, and issue foreign matter early warning.
The embodiment of the present invention is by analyzing pantograph video information, so that accurate judgement Spark plug optical fiber sensor information, real
Existing Spark plug optical fiber sensor；Contact line information is determined by straight-line detection and edge detection, it can be quasi- in conjunction with pantograph collector head area information
True statistics bow net contact point lateral displacement statistical information realizes the monitoring of pantograph misalignment；And identify pantograph image
Foreign matter in information；When the Spark plug optical fiber sensor information, bow net contact point lateral displacement statistical information and foreign matter recognition result information
It is abnormal, then alarm signal is issued automatically, realizes the real-time monitoring for pantograph operating status.
On the basis of the above embodiments, believe in the acquisition bow net contact point lateral displacement statistical information, Spark plug optical fiber sensor
Before the step of breath and foreign matter recognition detection result information, the method also includes:
Pantograph gray level image information is pre-processed, pretreatment pantograph image is obtained；
Image binaryzation is carried out to the pretreatment pantograph image, obtains binaryzation pantograph image information；
The binaryzation pantograph image information is analyzed and processed, Spark plug optical fiber sensor information is obtained.
It pretreatment is carried out to pantograph gray level image information specifically includes pair specifically, described in the embodiment of the present invention
The processing such as the rotation of pantograph gray level image machine core, Gaussian Blur filtering and sharpening operation, to obtain being more advantageous to image procossing
Pretreatment pantograph image.
The step of binaryzation pantograph image information is analyzed and processed described in the embodiment of the present invention specifically,
Simply connected region pixel occupied area is counted to pantograph image information after binaryzation respectively, rejects the area for being less than certain threshold value
Domain sorts to remaining connected region by size, and area is bigger and is spark close to the contact line band of position, from
And obtain Spark plug optical fiber sensor information；Wherein threshold size described herein can count to obtain by historical data.
After the embodiment of the present invention is by pre-processing pantograph gray level image information, obtain being more advantageous to image procossing
Pretreatment pantograph image, binary conversion treatment then is carried out to pretreatment pantograph image, and to binaryzation pantograph image
Information is analyzed, to identify spark, obtains Spark plug optical fiber sensor information, can effectively be realized for occurring in train operation state
The state of spark is identified.
On the basis of the above embodiments, pantograph gray level image information is pre-processed described, is pre-processed
Before the step of pantograph image, the method also includes:
Pantograph video information is obtained, pantograph image information is obtained according to the pantograph video information,
Gray proces are carried out to the pantograph image information, obtain pantograph gray level image information；
Template matching is carried out to the pantograph gray level image information, obtains pantograph collector head area information.
Specifically, pantograph video information described in the embodiment of the present invention, which can refer to, is mounted on car body top center
Position, and certain distance is kept with pantograph, the camera of entire pantograph motion range in train travelling process can be taken
The video information of acquisition, the frame per second of the video information can be 25FPS.
Gray proces described in the embodiment of the present invention, which refer to, is transformed to gray image for the color image of acquisition, reduces
Operand in image recognition processes.
Template matching described in the embodiment of the present invention refers to that obtaining pantograph collector head both ends bow angle in advance is template, right
Every width pantograph gray level image information carries out two bow angle matchings, to obtain pantograph collector head area information.
The embodiment of the present invention is by carrying out gray proces to pantograph image information, so as to effectively reduce subsequent processing
Operand, and the pantograph collector head area information identified in the embodiment of the present invention is conducive to the progress of subsequent step.
On the basis of the above embodiments, described that the binaryzation pantograph image information is analyzed and processed, it obtains
It the step of Spark plug optical fiber sensor information, specifically includes:
The simply connected region pixel point areas in the binaryzation pantograph image information is counted, and is rejected pre- less than first
If the area pixel point of threshold value, obtains remaining area area information；
If the remaining area area information is greater than the second preset threshold, and the remaining area area information leans on adosculation
Line region is then determined as spark information, obtains the Spark plug optical fiber sensor information according to the spark information.
Specifically, the first preset threshold described in the embodiment of the present invention and the second preset threshold may each be by going through
What history data statistics determined.
Binaryzation pantograph image information in the embodiment of the present invention refer to by pixel gray value on image be set as 0 or
255, so that whole picture pantograph gray level image information shows apparent black and white effect, this processing will make in image information
Data volume greatly reduces, and highlights the profile of target in image.
Simply connected region pixel occupied area is counted to pantograph image information after binaryzation respectively, rejects and is less than centainly
The region of threshold value sorts to remaining connected region by size, and the bigger and close contact line band of position of area is
Spark, to obtain Spark plug optical fiber sensor information.
The embodiment of the present invention passes through the simply connected region pixel point areas counted in the binaryzation pantograph image information,
Rejecting does not meet the first preset threshold pixel point areas, and will be close to the remaining area that contact line region is greater than the second preset threshold
Area is determined as spark, is conducive to subsequent Spark plug optical fiber sensor.
On the basis of the above embodiments, described that edge detection is carried out to the pantograph gray level image information, obtain side
It the step of edge image information, specifically includes:
Expansion and etching operation are carried out to the pantograph gray level image information, obtain expanding image information and corrosion image
Information；
Expanding image information is subtracted into corrosion image information, obtains dilation erosion image information, dilation erosion image is believed
Breath presses pixel inversion operation, obtains inverse operations image information；
The inverse operations image information is changed into edge image information by self-adaption binaryzation.
Specifically, expansion described in the embodiment of the present invention and etching operation are the routine techniques in image procossing,
It can be conducive to the subsequent edge image information for obtaining each component of pantograph with etching operation by hitting.
The embodiment of the present invention obtains edge image information, is conducive to subsequent step by dilation erosion and inversion operation
It carries out.
On the basis of the above embodiments, described that straight-line detection is carried out to the edge image information, obtain contact line letter
The step of breath, specifically includes:
Straight-line detection is carried out to the edge image information, obtains edge image straight line information；
Identifying processing is carried out to the edge image straight line information according to the constraint relationship between pantograph and contact net, is connect
Touch line information.
Specifically, straight-line detection described in the embodiment of the present invention can specifically refer to Hough straight-line detection, detecting
Edge image straight line information after straight line in the available image.
The constraint relationship specifically refers to search for and retain all between pantograph described in the embodiment of the present invention and contact net
The straight line contacted with image border；Straight slope where contact line is both less than carrier cable, excludes the biggish straight line of slope；Contact
Line slope all changes in a certain range, can be set to [- 1,1], removes the straight line of slope not in the range, thus
Obtain contact line information.
The embodiment of the present invention can obtain contact line by straight-line detection and by the constraint relationship between pantograph and contact net
Information is conducive to the progress of subsequent step.
On the basis of the above embodiments, believe in the acquisition bow net contact point lateral displacement statistical information, Spark plug optical fiber sensor
Before the step of breath and foreign matter recognition detection result information, the method also includes:
Multiple groups training sample will be obtained with foreign matter pantograph collector head area image as one group of training sample；
Multiple groups training sample is inputted default convolutional neural networks to be trained, until meet preset condition, deconditioning,
Obtain the common foreign matter identification preset model in pantograph collector head region；
Identification point is carried out to pantograph video information according to the common foreign matter identification preset model in the pantograph collector head region
Analysis, obtains foreign matter recognition detection result information.
Specifically, the band foreign matter pantograph collector head area image packet described in the embodiment of the present invention as training sample
Include the video image that the pantograph collector head that operation scene obtains hits bird, attachment polybag or rope.
Preset condition described in the embodiment of the present invention can refer to the default frequency of training of satisfaction, such as complete 200 times
Training, preset condition may also mean that default convolutional neural networks model meets preset condition, such as cross entropy loss function becomes
In stabilization, terminate to train at this time.
It is described in the embodiment of the present invention to be trained the default convolutional neural networks of multiple groups training sample input specifically
Refer to the machine learning by there is applications well achievement in field of image recognition, retain the characteristic extraction part in the model, uses
It is aforementioned default when meeting with several layers of full articulamentums for classification last in foreign matter pantograph collector head area image training pattern
When condition, training stops, and obtains the common foreign matter identification preset model in pantograph collector head region；Training is not participated in when using another section
The test of shock bird video image, shock can be recognized accurately in the common foreign matter in pantograph collector head region identification preset model
Bird.
The embodiment of the present invention will be by that will realize and bend to pantograph with foreign matter pantograph collector head area image as training sample
The training of the common foreign matter identification preset model of head region, can accurately identify the foreign matter situation in pantograph region, obtain foreign matter knowledge
Other testing result information, to realize the timely early warning when foreign matter occurs.
Fig. 2 is real-time monitoring flow chart described in one embodiment of the invention, as shown in Figure 2, comprising:
Video is obtained by camera, image is obtained by video frequency collection card, to image gray processing, both ends is carried out and bends Angle formwork
Matching obtains pantograph collector head working region, then carries out the filtering of image Gaussian Blur, edge detection and pantograph respectively and hits bird
Image data prepares.
After the filtering of image Gaussian Blur, image binaryzation is carried out by pixel and calculates single connection domain area, is filtered out small
It in the region of certain area, sorts by size, selects close to contact line and area maximum region is spark, calculate spark and hold
Continuous time, frequency, Spark plug optical fiber sensor information is obtained, is alerted if abnormal.
It after edge detection, carries out straight-line detection and marks, contact line is positioned by position constraint relationship, in bow area
Domain, by with contact line Relation acquisition bow net contact point, by contact point location of pixels can be calculated contact point displacement, calculate knot
Fruit storage calculates one piece of data displacement statistical parameter and obtains bow net contact point lateral displacement statistical information, alerts if abnormal.
After pantograph hits the preparation of bird image data, carries out bow net attachment polybag image data and prepare with pantograph just
Often image data prepares, and head-on collision bird, attachment foreign matter image carry out plus make an uproar, rotation and translation operates, and then use transfer learning, right
Machine learning is trained, deconditioning after loss function is stablized, and model deployment obtains foreign matter recognition detection knot by the model
If fruit information alerts abnormal.
The embodiment of the present invention is by analyzing pantograph video information, so that accurate judgement Spark plug optical fiber sensor information, real
Existing Spark plug optical fiber sensor；Contact line information is determined by straight-line detection and edge detection, it can be quasi- in conjunction with pantograph collector head area information
True statistics bow net contact point lateral displacement statistical information realizes the monitoring of pantograph misalignment；And identify pantograph image
Foreign matter in information；When the Spark plug optical fiber sensor information, bow net contact point lateral displacement statistical information and foreign matter recognition result information
It is abnormal, then alarm signal is issued automatically, realizes the real-time monitoring for pantograph operating status.
Fig. 3 is that the pantograph running state real-time monitoring apparatus structure based on video described in one embodiment of the invention shows
It is intended to, as shown in Figure 3, comprising: obtain module 310 and monitoring modular 320, wherein obtain module 310 for obtaining bow net contact
Point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and foreign matter recognition detection result information；Wherein, it supervises
Angle information, bow net contact point lateral displacement statistical information or different are deflected for the Spark plug optical fiber sensor information, bow if surveying module 320
Any information is abnormal in object recognition result information, then issues alarm signal；
Wherein, the acquisition bow net contact point lateral displacement statistical information specifically includes: to pantograph gray level image information
Edge detection is carried out, edge image information is obtained, straight-line detection is carried out to the edge image information, obtains contact line information,
Bow net contact point information is obtained according to pantograph collector head area information and the contact line information, bow net contact point information is carried out
Statistical analysis obtains bow net contact point lateral displacement statistical information.
Device described in the embodiment of the present invention is the device for executing above-described embodiment the method, specific implementation
Example please refers to above method embodiment, and details are not described herein again.
The embodiment of the present invention is by analyzing pantograph video information, so that accurate judgement Spark plug optical fiber sensor information, real
Existing Spark plug optical fiber sensor；Contact line information is determined by straight-line detection and edge detection, it can be quasi- in conjunction with pantograph collector head area information
True statistics bow net contact point lateral displacement statistical information realizes the monitoring of pantograph misalignment；And identify pantograph image
Foreign matter in information；When the Spark plug optical fiber sensor information, bow net contact point lateral displacement statistical information and foreign matter recognition result information
It is abnormal, then alarm signal is issued automatically, realizes the real-time monitoring for pantograph operating status.
The embodiment of the present invention discloses a kind of electronic equipment, and the electronic equipment includes: power module, CPU module, video flowing
Data Management Analysis module, input/output interface and communication module, memory module and motherboard communication bus；CPU module, video
Flow data handles analysis module, input/output interface and communication module, memory module is completed with each other by motherboard communication bus
Communication, CPU module complete computing resource, storage resource management and task schedule, power module by external power supply power supply turn
It is changed to voltage source required for other modules such as CPU work, video stream data handles analysis module and completes the decoding of video flowing, fortune
Row pantograph condition monitoring model program, and result is transmitted to CPU module, memory module storage model calculated result and works as
It video data, input/output interface and communication module complete video stream data and the model calculation data such as to the ground
Central transmission and system debug；The program of the pantograph running state real-time monitoring method based on video is stored in memory module
Instruction, when described program instruction is computer-executed, computer is able to carry out method provided by above-mentioned each method embodiment,
For example, obtain bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and foreign matter identification
Testing result information；If the Spark plug optical fiber sensor information, bow net contact point lateral displacement statistical information or foreign matter recognition result information
Middle any information is abnormal, then issues alarm signal；Wherein, the acquisition bow net contact point lateral displacement statistical information is specifically wrapped
It includes: edge detection being carried out to pantograph gray level image information, obtains edge image information, the edge image information is carried out straight
Line detection, obtains contact line information, obtains bow net contact point letter according to pantograph collector head area information and the contact line information
Breath, it is for statistical analysis to bow net contact point information to obtain bow net contact point lateral displacement statistical information.
The embodiment of the present invention provides a kind of non-transient computer readable storage medium, the non-transient computer readable storage medium
Matter storage server instruction, the computer instruction make computer execute provided by above-described embodiment it is a kind of based on video by electricity
Bend running state real-time monitoring method, for example, obtain bow net contact point lateral displacement statistical information, Spark plug optical fiber sensor information and
Foreign matter recognition detection result information；If the Spark plug optical fiber sensor information, bow net contact point lateral displacement statistical information or foreign matter identification
Any information is abnormal in result information, then issues alarm signal；Wherein, the acquisition bow net contact point lateral displacement statistical information
It specifically includes: edge detection being carried out to pantograph gray level image information, edge image information is obtained, to the edge image information
Straight-line detection is carried out, contact line information is obtained, obtains bow net according to pantograph collector head area information and the contact line information and connect
Contact information, it is for statistical analysis to bow net contact point information to obtain bow net contact point lateral displacement statistical information.
System embodiment described above is only schematical, wherein described, unit can as illustrated by the separation member
It is physically separated with being or may not be, component shown as a unit may or may not be physics list
Member, it can it is in one place, or may be distributed over multiple network units.It can be selected according to the actual needs
In some or all of the modules achieve the purpose of the solution of this embodiment.Those of ordinary skill in the art are not paying creativeness
Labour in the case where, it can understand and implement.
Through the above description of the embodiments, those skilled in the art can be understood that each embodiment can
It realizes by means of software and necessary general hardware platform, naturally it is also possible to pass through hardware.Based on this understanding, on
Stating technical solution, substantially the part that contributes to existing technology can be embodied in the form of software products in other words, should
Computer software product may be stored in a computer readable storage medium, such as ROM/RAM, magnetic disk, CD, including several fingers
It enables and using so that a computer equipment (can be personal computer, server or the network equipment etc.) executes each implementation
Method described in certain parts of example or embodiment.
Finally, it should be noted that the above embodiments are merely illustrative of the technical solutions of the present invention, rather than its limitations；Although
Present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that: it still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features；
And these are modified or replaceed, technical solution of various embodiments of the present invention that it does not separate the essence of the corresponding technical solution spirit and
Range.
Claims (10)
1. a kind of pantograph running state real-time monitoring method based on video characterized by comprising
Obtain bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and foreign matter recognition detection
Result information；
If the Spark plug optical fiber sensor information, bow net contact point lateral displacement statistical information, bow deflect angle information or foreign matter identification knot
Any information is abnormal in fruit information, then issues alarm signal；
Wherein, the acquisition bow net contact point lateral displacement statistical information specifically includes: carrying out to pantograph gray level image information
Edge detection obtains edge image information, carries out straight-line detection to the edge image information, obtains contact line information, according to
Pantograph collector head area information and the contact line information obtain bow net contact point information, count to bow net contact point information
Analysis obtains bow net contact point lateral displacement statistical information.
2. the pantograph running state real-time monitoring method based on video according to claim 1, which is characterized in that described
Obtain bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and foreign matter recognition detection result
Before the step of information, the method also includes:
Pantograph gray level image information is pre-processed, pretreatment pantograph image is obtained；
Image binaryzation is carried out to the pretreatment pantograph image, obtains binaryzation pantograph image information；
The binaryzation pantograph image information is analyzed and processed, Spark plug optical fiber sensor information is obtained.
3. the pantograph running state real-time monitoring method based on video according to claim 2, which is characterized in that described
Before the step of being pre-processed to pantograph gray level image information, obtaining pretreatment pantograph image, the method also includes:
Pantograph video information is obtained, pantograph image information is obtained according to the pantograph video information,
Gray proces are carried out to the pantograph image information, obtain pantograph gray level image information；
Template matching is carried out to the pantograph gray level image information, obtains pantograph collector head area information.
4. the pantograph running state real-time monitoring method based on video according to claim 2, which is characterized in that described right
The step of binaryzation pantograph image information is analyzed and processed, obtains Spark plug optical fiber sensor information, specifically includes:
The simply connected region pixel point areas in the binaryzation pantograph image information is counted, and is rejected less than the first default threshold
The area pixel point of value, obtains remaining area area information；
If the remaining area area information is greater than the second preset threshold, and the remaining area area information is close to contact line area
Domain is then determined as spark information, obtains the Spark plug optical fiber sensor information according to the spark information.
5. the pantograph running state real-time monitoring method based on video according to claim 3, which is characterized in that described right
The step of pantograph gray level image information carries out edge detection, obtains edge image information, specifically includes:
Expansion and etching operation are carried out to pantograph gray level image information, obtain expanding image information and corrosion image information；
Expanding image information is subtracted into corrosion image information, obtains dilation erosion image information, dilation erosion image information is pressed
Pixel inversion operation obtains inverse operations image information；
The inverse operations image information is changed into edge image information by self-adaption binaryzation.
6. the pantograph running state real-time monitoring method based on video according to claim 3, which is characterized in that described right
The step of edge image information carries out straight-line detection, obtains contact line information, specifically includes:
Straight-line detection is carried out to the edge image information, obtains edge image straight line information；
Identifying processing is carried out to the edge image straight line information according to the constraint relationship between pantograph and contact net, obtains contact line
Information.
7. the pantograph running state real-time monitoring method based on video according to claim 3, which is characterized in that described
Obtain bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and foreign matter recognition detection result
Before the step of information, the method also includes:
Multiple groups training sample will be obtained with foreign matter pantograph collector head area image as one group of training sample；
Multiple groups training sample is inputted default convolutional neural networks to be trained, until meeting preset condition, deconditioning is obtained
The common foreign matter in pantograph collector head region identifies preset model；
Discriminance analysis is carried out to pantograph video information according to the common foreign matter identification preset model in the pantograph collector head region, is obtained
To foreign matter recognition detection result information.
8. a kind of pantograph running state real-time monitoring device based on video characterized by comprising
Obtain module, for obtain bow net contact point lateral displacement statistical information, bow deflection angle information, Spark plug optical fiber sensor information and
Foreign matter recognition detection result information；
Monitoring modular, if deflecting angle information, bow net contact point lateral displacement statistical information for the Spark plug optical fiber sensor information, bow
Or any information is abnormal in foreign matter recognition result information, then issues alarm signal；
Wherein, the acquisition bow net contact point lateral displacement statistical information specifically includes: carrying out to pantograph gray level image information
Edge detection obtains edge image information, carries out straight-line detection to the edge image information, obtains contact line information, according to
Pantograph collector head area information and the contact line information obtain bow net contact point information, count to bow net contact point information
Analysis obtains bow net contact point lateral displacement statistical information.
9. a kind of electronic equipment including memory, processor and stores the calculating that can be run on a memory and on a processor
Machine program, which is characterized in that the processor is realized as described in any one of claim 1 to 7 when executing described program based on view
The step of pantograph running state real-time monitoring method of frequency.
10. a kind of non-transient computer readable storage medium, is stored thereon with computer program, which is characterized in that the computer
Realize that the pantograph operating status as described in any one of claim 1 to 7 based on video is supervised in real time when program is executed by processor
The step of survey method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910677782.5A CN110378897A (en) | 2019-07-25 | 2019-07-25 | A kind of pantograph running state real-time monitoring method and device based on video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910677782.5A CN110378897A (en) | 2019-07-25 | 2019-07-25 | A kind of pantograph running state real-time monitoring method and device based on video |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110378897A true CN110378897A (en) | 2019-10-25 |
Family
ID=68256105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910677782.5A Pending CN110378897A (en) | 2019-07-25 | 2019-07-25 | A kind of pantograph running state real-time monitoring method and device based on video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110378897A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091565A (en) * | 2020-01-02 | 2020-05-01 | 西南交通大学 | Self-adaptive motion characteristic matching and recognition bow net contact point detection method |
| CN111273136A (en) * | 2020-02-20 | 2020-06-12 | 山东万腾智能科技有限公司 | Online overhead line system arc discharge detection system and method based on image processing |
| CN111666947A (en) * | 2020-05-26 | 2020-09-15 | 成都唐源电气股份有限公司 | Pantograph head offset measurement method and system based on 3D imaging |
| CN111738342A (en) * | 2020-06-24 | 2020-10-02 | 西南交通大学 | Pantograph foreign matter detection method, storage medium and computer equipment |
| CN112749650A (en) * | 2020-12-31 | 2021-05-04 | 桂林海威科技股份有限公司 | Track pantograph electric spark detection system, method, medium and equipment |
| CN112784805A (en) * | 2021-02-02 | 2021-05-11 | 郑州地铁集团有限公司 | Pantograph video analysis system and method based on image recognition |
| CN112819776A (en) * | 2021-01-28 | 2021-05-18 | 中车青岛四方机车车辆股份有限公司 | Pantograph structure abnormality recognition method and system, electronic device, and storage medium |
| CN112991318A (en) * | 2021-03-31 | 2021-06-18 | 中车青岛四方机车车辆股份有限公司 | Motor train unit pantograph fault detection method and device and storage medium |
| CN113487561A (en) * | 2021-07-02 | 2021-10-08 | 成都唐源电气股份有限公司 | Pantograph foreign matter detection method and device based on gray gradient abnormal voting |
| CN113658112A (en) * | 2021-07-27 | 2021-11-16 | 北京交通大学 | Bow net anomaly detection method based on template matching and neural network algorithm |
| CN113837992A (en) * | 2021-07-14 | 2021-12-24 | 福建电子口岸股份有限公司 | Carbon brush box operation detection method and device based on example segmentation and readable medium |
| CN114185624A (en) * | 2021-12-30 | 2022-03-15 | 深圳前海微众银行股份有限公司 | Report loading update detection method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104316782A (en) * | 2014-09-26 | 2015-01-28 | 苏州华兴致远电子科技有限公司 | Pantograph monitoring method and system |
| CN104848792A (en) * | 2015-04-24 | 2015-08-19 | 苏州华兴致远电子科技有限公司 | Vehicle-mounted contact net measuring method and system |
| CN206074832U (en) * | 2016-08-02 | 2017-04-05 | 易讯科技股份有限公司 | A kind of railcar roof pantograph foreign matter detection system |
| CN107588720A (en) * | 2017-08-21 | 2018-01-16 | 南京理工大学 | A kind of municipal rail train pantograph disalignment on-line measuring device and method |
| CN108334842A (en) * | 2018-02-02 | 2018-07-27 | 成都国铁电气设备有限公司 | A method of identification pantograph-catenary current collection arcing size |
| CN109141255A (en) * | 2018-10-18 | 2019-01-04 | 北京华开领航科技有限责任公司 | A kind of bow net monitoring method |
| CN109143001A (en) * | 2018-10-18 | 2019-01-04 | 北京华开领航科技有限责任公司 | pantograph detection system |
| CN208476803U (en) * | 2018-09-25 | 2019-02-05 | 北京华开领航科技有限责任公司 | Pantograph electric spark detection system |
-
2019
- 2019-07-25 CN CN201910677782.5A patent/CN110378897A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104316782A (en) * | 2014-09-26 | 2015-01-28 | 苏州华兴致远电子科技有限公司 | Pantograph monitoring method and system |
| CN104848792A (en) * | 2015-04-24 | 2015-08-19 | 苏州华兴致远电子科技有限公司 | Vehicle-mounted contact net measuring method and system |
| CN206074832U (en) * | 2016-08-02 | 2017-04-05 | 易讯科技股份有限公司 | A kind of railcar roof pantograph foreign matter detection system |
| CN107588720A (en) * | 2017-08-21 | 2018-01-16 | 南京理工大学 | A kind of municipal rail train pantograph disalignment on-line measuring device and method |
| CN108334842A (en) * | 2018-02-02 | 2018-07-27 | 成都国铁电气设备有限公司 | A method of identification pantograph-catenary current collection arcing size |
| CN208476803U (en) * | 2018-09-25 | 2019-02-05 | 北京华开领航科技有限责任公司 | Pantograph electric spark detection system |
| CN109141255A (en) * | 2018-10-18 | 2019-01-04 | 北京华开领航科技有限责任公司 | A kind of bow net monitoring method |
| CN109143001A (en) * | 2018-10-18 | 2019-01-04 | 北京华开领航科技有限责任公司 | pantograph detection system |
Non-Patent Citations (3)
| Title |
|---|
| 中国农业工程学会: "《2005年中国农业工程学会学术会议论文集 农业工程科技创新与建设现代化 第3分册》", 31 December 2005 * |
| 赵俊杰 等: "基于图像处理的微波干燥设备物料火情报警***研究", 《计算机时代》 * |
| 郭卡 等: "《Python数据爬取技术与实战手册》", 31 August 2018 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111091565B (en) * | 2020-01-02 | 2022-02-08 | 西南交通大学 | Self-adaptive motion characteristic matching and recognition bow net contact point detection method |
| CN111091565A (en) * | 2020-01-02 | 2020-05-01 | 西南交通大学 | Self-adaptive motion characteristic matching and recognition bow net contact point detection method |
| CN111273136A (en) * | 2020-02-20 | 2020-06-12 | 山东万腾智能科技有限公司 | Online overhead line system arc discharge detection system and method based on image processing |
| CN111666947A (en) * | 2020-05-26 | 2020-09-15 | 成都唐源电气股份有限公司 | Pantograph head offset measurement method and system based on 3D imaging |
| CN111666947B (en) * | 2020-05-26 | 2023-08-04 | 成都唐源电气股份有限公司 | Pantograph head offset measuring method and system based on 3D imaging |
| CN111738342A (en) * | 2020-06-24 | 2020-10-02 | 西南交通大学 | Pantograph foreign matter detection method, storage medium and computer equipment |
| CN111738342B (en) * | 2020-06-24 | 2022-06-28 | 西南交通大学 | Pantograph foreign matter detection method, storage medium and computer equipment |
| CN112749650A (en) * | 2020-12-31 | 2021-05-04 | 桂林海威科技股份有限公司 | Track pantograph electric spark detection system, method, medium and equipment |
| CN112819776A (en) * | 2021-01-28 | 2021-05-18 | 中车青岛四方机车车辆股份有限公司 | Pantograph structure abnormality recognition method and system, electronic device, and storage medium |
| CN112784805A (en) * | 2021-02-02 | 2021-05-11 | 郑州地铁集团有限公司 | Pantograph video analysis system and method based on image recognition |
| CN112991318A (en) * | 2021-03-31 | 2021-06-18 | 中车青岛四方机车车辆股份有限公司 | Motor train unit pantograph fault detection method and device and storage medium |
| CN113487561A (en) * | 2021-07-02 | 2021-10-08 | 成都唐源电气股份有限公司 | Pantograph foreign matter detection method and device based on gray gradient abnormal voting |
| CN113487561B (en) * | 2021-07-02 | 2023-06-30 | 成都唐源电气股份有限公司 | Pantograph foreign matter detection method and device based on gray gradient abnormal voting |
| CN113837992A (en) * | 2021-07-14 | 2021-12-24 | 福建电子口岸股份有限公司 | Carbon brush box operation detection method and device based on example segmentation and readable medium |
| CN113837992B (en) * | 2021-07-14 | 2023-06-02 | 福建电子口岸股份有限公司 | Carbon brush box operation detection method and device based on example segmentation and readable medium |
| CN113658112A (en) * | 2021-07-27 | 2021-11-16 | 北京交通大学 | Bow net anomaly detection method based on template matching and neural network algorithm |
| CN113658112B (en) * | 2021-07-27 | 2024-03-01 | 北京交通大学 | Bow net anomaly detection method based on template matching and neural network algorithm |
| CN114185624A (en) * | 2021-12-30 | 2022-03-15 | 深圳前海微众银行股份有限公司 | Report loading update detection method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110378897A (en) | A kind of pantograph running state real-time monitoring method and device based on video | |
| Sampedro et al. | Deep learning-based system for automatic recognition and diagnosis of electrical insulator strings | |
| CN108985041B (en) | Verification code identification input method and system based on sliding verification | |
| CN101957325B (en) | Substation equipment appearance abnormality recognition method based on substation inspection robot | |
| CN112183313A (en) | SlowFast-based power operation field action identification method | |
| CN112016409A (en) | Deep learning-based process step specification visual identification determination method and system | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN101738998B (en) | System and method for monitoring industrial process based on local discriminatory analysis | |
| CN110717542A (en) | Emotion recognition method, device and equipment | |
| CN109635823B (en) | Method and device for identifying winding disorder rope and engineering machinery | |
| CN113192037B (en) | Belt conveyor monitoring method, system, medium and electronic terminal | |
| CN116308300B (en) | Power equipment state monitoring evaluation and command method and system | |
| CN114820626B (en) | Intelligent detection method for automobile front face part configuration | |
| CN116012762A (en) | Traffic intersection video image analysis method and system for power equipment | |
| CN111062364A (en) | Deep learning-based assembly operation monitoring method and device | |
| CN115146726A (en) | KPI abnormity early warning method in intelligent operation and maintenance based on machine learning | |
| CN116152202A (en) | Equipment appearance detection system based on image recognition technology and infrared thermal imaging technology | |
| CN116976865B (en) | Ship maintenance device allocation management system based on big data analysis | |
| CN113639685A (en) | Displacement detection method, device, equipment and storage medium | |
| CN117331802A (en) | Middle-station data monitoring and analyzing system based on industrial Internet | |
| CN111415326A (en) | Method and system for detecting abnormal state of railway contact net bolt | |
| CN117330582A (en) | Polymer PE film surface crystal point detecting system | |
| Batapati et al. | Video analysis for traffic anomaly detection using support vector machines | |
| CN114757905A (en) | Vision-based rope winding abnormity detection device and method | |
| KR102265461B1 (en) | Abnormal Data Detection System in Manufacturing Process |
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: 20191025 |