CN110414351A - The intelligent scissor and recognition methods, system and storage medium of substation - Google Patents
The intelligent scissor and recognition methods, system and storage medium of substation Download PDFInfo
- Publication number
- CN110414351A CN110414351A CN201910561596.5A CN201910561596A CN110414351A CN 110414351 A CN110414351 A CN 110414351A CN 201910561596 A CN201910561596 A CN 201910561596A CN 110414351 A CN110414351 A CN 110414351A
- Authority
- CN
- China
- Prior art keywords
- substation
- point cloud
- identified
- classification
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for ac mains or ac distribution networks
-
- 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
- G06T2207/10028—Range image; Depth image; 3D point clouds
Abstract
The invention discloses the intelligent scissor of substation and recognition methods, system and storage medium, method includes: to be scanned modeling to substation, obtains the point cloud data of substation；Intelligent scissor and classification are carried out to the point cloud data of substation, the point cloud after obtaining the object classification of substation；Point cloud after the object classification of substation is converted into model, and stores and arrives deep learning model library；The data of to be identified cloud of substation and deep learning model library are subjected to match cognization, the name for obtaining to be identified cloud is referred to as recognition result.The present invention is obtained the title of the point cloud of the point objects such as cloud and each equipment of the objects such as each equipment in substation by the intelligent scissor and classification of the point cloud data to substation and stored after conversion to deep learning model library, be conducive to the condition monitoring of each equipment and fine-grained management in subsequent realization three-dimensional transformer substation, and more efficiently, intelligence degree is higher.It the composite can be widely applied to substation's three-dimensional applications field.
Description
Technical field
The present invention relates to the three-dimensional applications field of substation, especially a kind of intelligent scissor of substation and recognition methods,
System and storage medium.
Background technique
Substation is the important node of power transmission, and station equipment enormous amount, device category is various, and management requires very
The substation of height, especially voltage levels.
Three-dimensional transformer substation be with computer technology, 3-D scanning technology development and gradually replace Two-dimensional Drawing Administrative
A kind of emerging technology, its biggest characteristic is that substation field environment can be really restored, visualized management substation equipment assets.Together
When, the speed of three-dimensional modeling greatly improved in the development of the technology of threedimensional model production, so that by substation management two-dimensional stage
Upgrade to three-dimensional tube platform to be possibly realized.
In three-dimensional transformer substation, each equipment being partitioned into substation one by one and the title for correctly identifying each equipment,
The condition monitoring and fine-grained management of each equipment in subsequent realization three-dimensional transformer substation are had a very important significance.At present
In the industry to this still without effective solution, it would be highly desirable to further improve and improve.
Summary of the invention
In order to solve the above technical problems, the purpose of the embodiment of the present invention is: provide the intelligent scissor of substation a kind of with
Recognition methods, system and storage medium.
First aspect of the embodiment of the present invention is adopted the technical scheme that:
The intelligent scissor of substation and recognition methods, comprising the following steps:
Modeling is scanned to substation, obtains the point cloud data of substation；
Intelligent scissor and classification are carried out to the point cloud data of substation, the point cloud after obtaining the object classification of substation；
Point cloud after the object classification of substation is converted into model, and stores and arrives deep learning model library；
The data of to be identified cloud of substation and deep learning model library are subjected to match cognization, obtain point to be identified
The name of cloud is referred to as recognition result.
Further, described the step for modeling is scanned to substation, obtains the point cloud data of substation, specific to wrap
It includes:
Using the three-dimensional data of scanning device scanning substation, the scanning device includes take photo by plane scanner and spacescan
Instrument；
It is modeled according to the three-dimensional data of substation, obtains the threedimensional model of substation；
The point cloud data of substation is obtained from the threedimensional model of substation.
Further, the point cloud data to substation carries out intelligent scissor and classification, obtains the object classification of substation
It the step for rear point cloud, specifically includes:
Intelligent scissor is carried out to the point cloud data of substation, obtains the point cloud of the object of substation；
Classify to the point cloud of the object of substation, the point cloud after obtaining the object classification of substation.
Further, the point cloud data to substation carries out intelligent scissor, obtain the object of substation point cloud this
Step, specifically:
According to the incidence relation between point cloud data, the point cloud of each object, institute are partitioned into from the point cloud data of substation
Stating the incidence relation between point cloud data includes that point is similar to color similarity relation, shape similarity relation, the size between consecutive points
Relationship, size similarity relation and distance relation.
Further, the point cloud of the object to substation is classified, the point cloud after obtaining the object classification of substation
The step for, it specifically includes:
Classify to the point cloud of the object of substation, obtain the first classification results, first classification results are power transformation
The room objects stood point cloud title, the room objects include floor, wall, stabilization control device, Electric capacity compensation device and
Integrated protection automation equipment；
Classify to the point cloud of the object of substation, obtain the second classification results, second classification results are power transformation
The title of the point cloud for the outdoor object stood, the outdoor object includes transformer, disconnecting switch, grounding switch, breaker, ground connection
Arrester, current transformer, voltage transformer, coupling capacitor, fuse, power capacitor, reactor, on-site personnel
With field operation equipment.
Further, described that the data of to be identified cloud of substation and deep learning model library are subjected to match cognization, it obtains
The step for being referred to as recognition result to the name of to be identified cloud, specifically includes:
To be identified cloud of substation is converted into model to be identified；
Model to be identified and the model of deep learning model library are subjected to match cognization, thus by deep learning model library
In title with the most matched model name of model to be identified as to be identified cloud.
Second aspect of the embodiment of the present invention is adopted the technical scheme that:
The intelligent scissor and identifying system of substation, comprising:
Point cloud data obtains module and obtains the point cloud data of substation for being scanned modeling to substation；
Intelligent scissor and categorization module carry out intelligent scissor and classification for the point cloud data to substation, obtain power transformation
Point cloud after the object classification stood；
Library module is converted and entered, is converted to model for the point cloud after the object classification by substation, and store and arrive depth
Learning model library；
Match cognization module, for the data of to be identified cloud of substation and deep learning model library to be carried out matching knowledge
Not, the name for obtaining to be identified cloud is referred to as recognition result.
Further, the match cognization module specifically includes:
Converting unit, for be identified cloud of substation to be converted to model to be identified；
Recognition unit, for the model of model to be identified and deep learning model library to be carried out match cognization, thus will
Title in deep learning model library with the most matched model name of model to be identified as to be identified cloud.
The third aspect of the embodiment of the present invention is adopted the technical scheme that:
The intelligent scissor and identifying system of substation, comprising:
At least one processor；
At least one processor, for storing at least one program；
When at least one described program is executed by least one described processor, so that at least one described processor is realized
The intelligent scissor of substation of the present invention and recognition methods.
Fourth aspect of the embodiment of the present invention is adopted the technical scheme that:
Storage medium, wherein being stored with the executable instruction of processor, the executable instruction of the processor is by handling
Intelligent scissor and recognition methods when device executes for realizing substation of the present invention.
One or more technical solutions in the embodiments of the present invention have the advantages that the embodiment of the present invention by pair
The intelligent scissor of the point cloud data of substation and classification obtain the point cloud of the objects such as each equipment and each equipment in substation
The title of the point cloud of equal objects simultaneously stores after conversion into deep learning model library, is conducive to subsequent realization three-dimensional transformer substation
The condition monitoring of interior each equipment and fine-grained management, and the deep learning model library that continuous renewal and self-teaching is utilized is come
The Auto-matching identification for completing to be identified cloud of substation, eliminates artificial participation, more efficiently, intelligence degree is more
It is high.
Detailed description of the invention
Fig. 1 is the flow chart of the intelligent scissor and recognition methods of substation provided in an embodiment of the present invention；
Fig. 2 is the intelligent scissor of substation provided in an embodiment of the present invention and a kind of structural block diagram of identifying system；
Fig. 3 is the intelligent scissor of substation provided in an embodiment of the present invention and another structural block diagram of identifying system.
Specific embodiment
The present invention will be further explained with specific embodiment with reference to the accompanying drawings of the specification.For following implementation
Step number in example, is arranged only for the purposes of illustrating explanation, does not do any restriction to the sequence between step, embodiment
In each step execution sequence can be adaptively adjusted according to the understanding of those skilled in the art.
Referring to Fig.1, the embodiment of the invention provides a kind of intelligent scissor of substation and recognition methods, including following step
It is rapid:
S100, modeling is scanned to substation, obtains the point cloud data of substation；
Specifically, when being scanned modeling to substation, reconstruction entire power transformation can be obtained while scanning or after scanning
The threedimensional model stood.And what the threedimensional model of whole transformer station was made of multiple clouds, therefore after rebuilding obtained threedimensional model
It can provide corresponding point cloud data, in order to subsequent intelligent scissor and classification.
S101, intelligent scissor and classification are carried out to the point cloud data of substation, the point after obtaining the object classification of substation
Cloud；
Specifically, the present embodiment can use the incidence relation (relationship such as point with Neighbor Points) between point cloud data to power transformation
The point cloud data stood carries out intelligent scissor, obtains the point cloud of each object in substation.It, can be right after obtaining the point cloud of each object
The point cloud of each object carries out Classification and Identification, identifies the title (title of i.e. each object) of the point cloud of each object.Wherein,
Object includes the intrinsic equipment (such as transformer, capacitor, switch, disconnecting link) inside and outside substation, further includes on-site personnel
(maintenance personal of such as substation) and field operation equipment (such as maintenance car).And Classification and Identification can pass through point of training in advance
Class device carries out, and trained classifier can be known according to title (i.e. label) using the artificial aptitude manner such as neural network in advance
Training sample build.
S102, the point cloud after the object classification of substation is converted to model, and stores and arrives deep learning model library；
Specifically, after intelligent scissor and classification obtain the title (i.e. the title of each object) of point cloud of each object,
The point cloud of each object can be converted into corresponding model (completing the singulation of model) by way of space coordinate transformation,
It is then stored in deep learning model library (being put in storage).And deep learning model library has the ability of deep learning, it can be constantly
Self-teaching and the rule (reflecting point cloud and the mapping relations between corresponding title) for updating model known to each title.
S103, the data of to be identified cloud of substation and deep learning model library are subjected to match cognization, obtained wait know
The name of other cloud is referred to as recognition result.
Specifically, to be identified cloud can be obtained by way of scanning substation.
Since deep learning model library is obtained between a cloud and corresponding title by continuous self-teaching and update
Mapping relations, the cloud can be converted to corresponding model after obtaining to be identified cloud, then in deep learning model
Matched and searched is carried out in the data in library, finally obtains the title of the cloud, to complete the automatic identification of single object-point cloud.
By the above content as it can be seen that the present embodiment obtains power transformation by the intelligent scissor and classification of the point cloud data to substation
In standing the title of the point cloud of the point objects such as cloud and each equipment of the objects such as each equipment and after conversion storage to depth
Learning model library is conducive to the condition monitoring of each equipment and fine-grained management in subsequent realization three-dimensional transformer substation, and is utilized
It constantly updates and the deep learning model library of self-teaching identifies to complete the Auto-matching of to be identified cloud of substation, save
Artificial participation, more efficiently, intelligence degree is higher.
It is further used as preferred embodiment, it is described that modeling is scanned to substation, obtain the point cloud number of substation
According to the step for, specifically include:
S1001, the three-dimensional data that substation is scanned using scanning device, the scanning device include take photo by plane scanner and sky
Between scanner；
Specifically, it takes photo by plane scanner, can be aerial photography aircraft etc. and take photo by plane equipment, for scanning substation's perimeter range
The three-dimensional data of (such as outside whole transformer station).Space scan, for scanning substation's indoor and outdoor surroundings (inside such as substation
Integrated protection automation equipment etc.) three-dimensional data.Three-dimensional data includes the data such as two-dimension picture and depth information.It is preferred that
Ground, scanning device can be integrated with edge GPU chip, can local to the data such as the two-dimension picture of acquisition and depth information into
Two-dimension picture (is such as carried out preliminary splicing by depth information) by the preliminary processing of row, alleviates the processing load of server.
S1002, it is modeled according to the three-dimensional data of substation, obtains the threedimensional model of substation；
Specifically, modeling include model reparation, editing, cut, subtract face, subtract mould, compression, processing material, processing textures and
Handle light.Preferably, the link (such as URL link) of the threedimensional model of substation can also be generated when modeling, it is any in this way
Support calculating equipment (including smart phone, tablet computer, laptop, smartwatch, smart television, the calculating of browser
Machine etc.) links and accesses threedimensional model can be passed through.
S1003, the point cloud data that substation is obtained from the threedimensional model of substation.
Specifically, the threedimensional model of whole transformer station is made of multiple clouds, therefore after rebuilding obtained threedimensional model
Corresponding point cloud data is provided, in order to subsequent intelligent scissor and classification.
It is further used as preferred embodiment, the point cloud data to substation carries out intelligent scissor and classification, obtains
The step for point cloud after to the object classification of substation S101, specifically include:
S1011, intelligent scissor is carried out to the point cloud data of substation, obtains the point cloud of the object of substation；
S1012, classify to the point cloud of the object of substation, the point cloud after obtaining the object classification of substation.
Specifically, the object in substation may include the objects such as multiple equipment, personage.Correspondingly, to the point cloud of substation
Data carry out intelligent scissor, and the point cloud for obtaining the object of substation also contains multiple clouds, the tool of these point clouds being partitioned into
You can get it after the classifier identification that body title is constructed through the method for artificial intelligence.
It is further used as preferred embodiment, the point cloud data to substation carries out intelligent scissor, obtains power transformation
The step for point cloud for the object stood S1011, specifically:
According to the incidence relation between point cloud data, the point cloud of each object, institute are partitioned into from the point cloud data of substation
Stating the incidence relation between point cloud data includes that point is similar to color similarity relation, shape similarity relation, the size between consecutive points
Relationship, size similarity relation and distance relation.
Specifically, the relationship between point cloud data midpoint and Neighbor Points reflects association between points in point cloud data.
The present embodiment can be based on the relationship, and the point for meeting the criteria for classifying is divided into the point cloud of same name.For example, can will with certain
Point of the distance in preset threshold between point is included into point cloud belonging to the point.It will be appreciated by persons skilled in the art that drawing
Minute mark will definitely be with not only according to distance, other standards (such as color, shape, size, size attribute) are equally applicable to this
Embodiment.
It is further used as preferred embodiment, the point cloud of the object to substation is classified, and substation is obtained
Object classification after point cloud the step for S1012, specifically include:
S10121, classify to the point cloud of the object of substation, obtain the first classification results, first classification results
For the title of the point cloud of the room objects of substation, the room objects include floor, wall, stabilization control device, capacitance compensation
Device and integrated protection automation equipment；
Specifically, the present embodiment, can be right by the interior of pre-training when carrying out Classification and Identification to substation's room objects
The point cloud identification model of elephant identifies the titles of the objects such as indoor object, very convenient and quick.
S10122, classify to the point cloud of the object of substation, obtain the second classification results, second classification results
For the title of the point cloud of the outdoor object of substation, the outdoor object includes transformer, disconnecting switch, grounding switch, open circuit
Device, earth arrester, current transformer, voltage transformer, coupling capacitor, fuse, power capacitor, reactor, scene
Operating personnel and field operation equipment.
Specifically, the present embodiment, can be right by the outdoor of pre-training when carrying out Classification and Identification to outside transformer substation object
The point cloud identification model of elephant identifies the titles of the objects such as indoor object, very convenient and quick.
It is further used as preferred embodiment, the number by substation's cloud and deep learning model library to be identified
According to match cognization is carried out, the step for name of to be identified cloud is referred to as recognition result S103 is obtained, is specifically included:
S1031, to be identified cloud of substation is converted into model to be identified；
S1032, model to be identified and the model of deep learning model library are subjected to match cognization, thus by deep learning
Title in model library with the most matched model name of model to be identified as to be identified cloud.
Specifically, deep learning model library can constantly obtain the name of the point cloud models of objects such as the various equipment of substation
Claim, and rule is formed by deep learning, in this way when scanning gets the new point cloud of substation, even if its title is unknown
, it also can use the rule by carrying out match cognization with the data of deep learning model library, to learn the new point cloud
Title, intelligence degree is high and very convenient.
Referring to Fig. 2, the embodiment of the invention also provides a kind of intelligent scissor of substation and identifying systems, comprising:
Point cloud data obtains module 201 and obtains the point cloud data of substation for being scanned modeling to substation；
Intelligent scissor and categorization module 202 carry out intelligent scissor and classification for the point cloud data to substation, are become
Point cloud after the object classification in power station；
Library module 203 is converted and entered, is converted to model for the point cloud after the object classification by substation, and store to deep
Spend learning model library；
Match cognization module 204, for carrying out the data of to be identified cloud of substation and deep learning model library
With identification, the name for obtaining to be identified cloud is referred to as recognition result.
Referring to Fig. 2, it is further used as preferred embodiment, the match cognization module 204 specifically includes:
Converting unit 2041, for be identified cloud of substation to be converted to model to be identified；
Recognition unit 2042, for the model of model to be identified and deep learning model library to be carried out match cognization, from
And using in deep learning model library with the most matched model name of model to be identified as the title of to be identified cloud.
Suitable for this system embodiment, this system embodiment is implemented content in above method embodiment
Function is identical as above method embodiment, and the beneficial effect reached and above method embodiment beneficial effect achieved
It is identical.
Referring to Fig. 3, the embodiment of the invention also provides a kind of intelligent scissor of substation and identifying systems, comprising:
At least one processor 301；
At least one processor 302, for storing at least one program；
When at least one described program is executed by least one described processor 301, so that at least one described processor
301 realize the intelligent scissor of substation of the present invention and recognition methods.
Suitable for this system embodiment, this system embodiment is implemented content in above method embodiment
Function is identical as above method embodiment, and the beneficial effect reached and above method embodiment beneficial effect achieved
It is identical.
The embodiment of the invention also provides a kind of storage mediums, wherein being stored with the executable instruction of processor, the place
The executable instruction of device is managed when executed by the processor for realizing the intelligent scissor of substation of the present invention and identification side
Method.
It is to be illustrated to preferable implementation of the invention, but the present invention is not limited to the embodiment above, it is ripe
Various equivalent deformation or replacement can also be made on the premise of without prejudice to spirit of the invention by knowing those skilled in the art, this
Equivalent deformation or replacement are all included in the scope defined by the claims of the present application a bit.
Claims (10)
1. intelligent scissor and the recognition methods of substation, it is characterised in that: the following steps are included:
Modeling is scanned to substation, obtains the point cloud data of substation；
Intelligent scissor and classification are carried out to the point cloud data of substation, the point cloud after obtaining the object classification of substation；
Point cloud after the object classification of substation is converted into model, and stores and arrives deep learning model library；
The data of to be identified cloud of substation and deep learning model library are subjected to match cognization, obtain to be identified cloud
Name is referred to as recognition result.
2. intelligent scissor and the recognition methods of substation according to claim 1, it is characterised in that: it is described to substation into
Row scanning modeling, specifically includes the step for obtaining the point cloud data of substation:
Using the three-dimensional data of scanning device scanning substation, the scanning device includes take photo by plane scanner and space scan；
It is modeled according to the three-dimensional data of substation, obtains the threedimensional model of substation；
The point cloud data of substation is obtained from the threedimensional model of substation.
3. intelligent scissor and the recognition methods of substation according to claim 1, it is characterised in that: described to substation
The step for point cloud data carries out intelligent scissor and classification, point cloud after obtaining the object classification of substation, specifically includes:
Intelligent scissor is carried out to the point cloud data of substation, obtains the point cloud of the object of substation；
Classify to the point cloud of the object of substation, the point cloud after obtaining the object classification of substation.
4. intelligent scissor and the recognition methods of substation according to claim 3, it is characterised in that: described to substation
The step for point cloud data carries out intelligent scissor, obtains the point cloud of the object of substation, specifically:
According to the incidence relation between point cloud data, the point cloud of each object, the point are partitioned into from the point cloud data of substation
Incidence relation between cloud data include point consecutive points between color similarity relation, shape similarity relation, size similarity relation,
Size similarity relation and distance relation.
5. intelligent scissor and the recognition methods of substation according to claim 3, it is characterised in that: described to substation
It the step for point cloud of object is classified, point cloud after obtaining the object classification of substation, specifically includes:
Classify to the point cloud of the object of substation, obtain the first classification results, first classification results are substation
The title of the point cloud of room objects, the room objects include floor, wall, stabilization control device, Electric capacity compensation device and synthesis
Protect automation equipment；
Classify to the point cloud of the object of substation, obtain the second classification results, second classification results are substation
The title of the point cloud of outdoor object, the outdoor object include transformer, disconnecting switch, grounding switch, breaker, are grounded and take shelter from the thunder
Device, current transformer, voltage transformer, coupling capacitor, fuse, power capacitor, reactor, on-site personnel and existing
Field operating equipment.
6. intelligent scissor and the recognition methods of substation according to claim 1, it is characterised in that: described to wait for substation
The point cloud of identification and the data of deep learning model library carry out match cognization, and the name for obtaining to be identified cloud is referred to as identifying knot
The step for fruit, specifically includes:
To be identified cloud of substation is converted into model to be identified；
The model of model to be identified and deep learning model library is subjected to match cognization, thus by deep learning model library with
Title of the most matched model name of model to be identified as to be identified cloud.
7. the intelligent scissor and identifying system of substation, it is characterised in that: include:
Point cloud data obtains module and obtains the point cloud data of substation for being scanned modeling to substation；
Intelligent scissor and categorization module carry out intelligent scissor and classification for the point cloud data to substation, obtain substation
Point cloud after object classification；
Library module is converted and entered, is converted to model for the point cloud after the object classification by substation, and store and arrive deep learning
Model library；
Match cognization module, for the data of to be identified cloud of substation and deep learning model library to be carried out match cognization,
The name for obtaining to be identified cloud is referred to as recognition result.
8. the intelligent scissor and identifying system of substation according to claim 7, it is characterised in that: the match cognization mould
Block specifically includes:
Converting unit, for be identified cloud of substation to be converted to model to be identified；
Recognition unit, for the model of model to be identified and deep learning model library to be carried out match cognization, thus by depth
Title in learning model library with the most matched model name of model to be identified as to be identified cloud.
9. the intelligent scissor and identifying system of substation, it is characterised in that: include:
At least one processor；
At least one processor, for storing at least one program；
When at least one described program is executed by least one described processor, so that at least one described processor is realized as weighed
Benefit requires intelligent scissor and the recognition methods of the described in any item substations of 1-6.
10. storage medium, wherein being stored with the executable instruction of processor, it is characterised in that: the executable finger of the processor
It enables when executed by the processor for realizing the intelligent scissor of substation as claimed in any one of claims 1 to 6 and identification side
Method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910561596.5A CN110414351A (en) | 2019-06-26 | 2019-06-26 | The intelligent scissor and recognition methods, system and storage medium of substation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910561596.5A CN110414351A (en) | 2019-06-26 | 2019-06-26 | The intelligent scissor and recognition methods, system and storage medium of substation |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110414351A true CN110414351A (en) | 2019-11-05 |
Family
ID=68358295
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910561596.5A Pending CN110414351A (en) | 2019-06-26 | 2019-06-26 | The intelligent scissor and recognition methods, system and storage medium of substation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110414351A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310845A (en) * | 2020-02-26 | 2020-06-19 | 广东电网有限责任公司电力科学研究院 | Substation equipment identification method, device and equipment |
| CN111412833A (en) * | 2020-03-30 | 2020-07-14 | 广东电网有限责任公司电力科学研究院 | Alarming method, system and equipment for positioning safe distance of three-dimensional scene of transformer substation |
| CN111521256A (en) * | 2020-04-13 | 2020-08-11 | 国家电网有限公司 | Main transformer surface vibration visualization detection method based on data mapping |
| CN112862910A (en) * | 2021-04-26 | 2021-05-28 | 广东电网有限责任公司东莞供电局 | Method for compressing data of three-dimensional model of transformer substation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150009214A1 (en) * | 2013-07-08 | 2015-01-08 | Vangogh Imaging, Inc. | Real-time 3d computer vision processing engine for object recognition, reconstruction, and analysis |
| CN106951860A (en) * | 2017-03-20 | 2017-07-14 | 河南腾龙信息工程有限公司 | A kind of three-dimensional data intelligent identification Method based on a cloud |
| CN107025323A (en) * | 2016-12-29 | 2017-08-08 | 南京南瑞信息通信科技有限公司 | A kind of transformer station's fast modeling method based on ATL |
| CN107045733A (en) * | 2017-03-21 | 2017-08-15 | 国网湖北省电力公司检修公司 | The method being modeled based on cloud data to transformer station's GIS device |
-
2019
- 2019-06-26 CN CN201910561596.5A patent/CN110414351A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150009214A1 (en) * | 2013-07-08 | 2015-01-08 | Vangogh Imaging, Inc. | Real-time 3d computer vision processing engine for object recognition, reconstruction, and analysis |
| CN107025323A (en) * | 2016-12-29 | 2017-08-08 | 南京南瑞信息通信科技有限公司 | A kind of transformer station's fast modeling method based on ATL |
| CN106951860A (en) * | 2017-03-20 | 2017-07-14 | 河南腾龙信息工程有限公司 | A kind of three-dimensional data intelligent identification Method based on a cloud |
| CN107045733A (en) * | 2017-03-21 | 2017-08-15 | 国网湖北省电力公司检修公司 | The method being modeled based on cloud data to transformer station's GIS device |
Non-Patent Citations (2)
| Title |
|---|
| QIAOYUN WU 等: "Automatic 3D reconstruction of electrical substation scene from LiDAR point cloud", 《ELSEVIER》 * |
| 纪勇 等: "基于霍夫投票的变电站设备三维点云识别算法", 《基于霍夫投票的变电站设备三维点云识别算法》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111310845A (en) * | 2020-02-26 | 2020-06-19 | 广东电网有限责任公司电力科学研究院 | Substation equipment identification method, device and equipment |
| CN111412833A (en) * | 2020-03-30 | 2020-07-14 | 广东电网有限责任公司电力科学研究院 | Alarming method, system and equipment for positioning safe distance of three-dimensional scene of transformer substation |
| CN111412833B (en) * | 2020-03-30 | 2021-07-30 | 广东电网有限责任公司电力科学研究院 | Alarming method, system and equipment for positioning safe distance of three-dimensional scene of transformer substation |
| CN111521256A (en) * | 2020-04-13 | 2020-08-11 | 国家电网有限公司 | Main transformer surface vibration visualization detection method based on data mapping |
| CN112862910A (en) * | 2021-04-26 | 2021-05-28 | 广东电网有限责任公司东莞供电局 | Method for compressing data of three-dimensional model of transformer substation |
| CN112862910B (en) * | 2021-04-26 | 2021-07-27 | 广东电网有限责任公司东莞供电局 | Method for compressing data of three-dimensional model of transformer substation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110414351A (en) | The intelligent scissor and recognition methods, system and storage medium of substation | |
| CN114241282B (en) | Knowledge distillation-based edge equipment scene recognition method and device | |
| CN110033453B (en) | Power transmission and transformation line insulator aerial image fault detection method based on improved YOLOv3 | |
| EP3940638A1 (en) | Image region positioning method, model training method, and related apparatus | |
| Huang et al. | Point cloud labeling using 3d convolutional neural network | |
| WO2022161380A1 (en) | Model training method and apparatus, and image retrieval method and apparatus | |
| CN112232425B (en) | Image processing method, device, storage medium and electronic equipment | |
| CN109934249A (en) | Data processing method, device, medium and calculating equipment | |
| CN109870983A (en) | Handle the method, apparatus of pallet stacking image and the system for picking of storing in a warehouse | |
| JP7412847B2 (en) | Image processing method, image processing device, server, and computer program | |
| CN107077487A (en) | Personal photo is tagged using depth network | |
| CN109918506A (en) | A kind of file classification method and device | |
| KR20210108044A (en) | Video analysis system for digital twin technology | |
| CN109697451A (en) | Similar image clustering method and device, storage medium, electronic equipment | |
| CN112070135A (en) | Power equipment image detection method and device, power equipment and storage medium | |
| CN110223297A (en) | Segmentation and recognition methods, system and storage medium based on scanning point cloud data | |
| CN113641797A (en) | Data processing method, device, equipment, storage medium and computer program product | |
| CN110275919A (en) | Data integrating method and device | |
| CN114565916A (en) | Target detection model training method, target detection method and electronic equipment | |
| CN114550053A (en) | Traffic accident responsibility determination method, device, computer equipment and storage medium | |
| Katsumata et al. | Spcomapgan: Spatial concept formation-based semantic mapping with generative adversarial networks | |
| CN113312499B (en) | Power safety early warning method and system based on knowledge graph | |
| CN107273478B (en) | A kind of semi-supervised hashing image searching method based on Group Lasso | |
| CN113128431A (en) | Video clip retrieval method, device, medium and electronic equipment | |
| Liu et al. | Helmet wearing detection based on YOLOv4-MT |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |
|
| RJ01 | Rejection of invention patent application after publication |