CN116524240A - Electric power operation scene violation behavior identification model, method, device and storage medium - Google Patents
Electric power operation scene violation behavior identification model, method, device and storage medium Download PDFInfo
- Publication number
- CN116524240A CN116524240A CN202310331575.0A CN202310331575A CN116524240A CN 116524240 A CN116524240 A CN 116524240A CN 202310331575 A CN202310331575 A CN 202310331575A CN 116524240 A CN116524240 A CN 116524240A
- Authority
- CN
- China
- Prior art keywords
- electric power
- layer
- power operation
- operation scene
- violation
- 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 36
- 238000003860 storage Methods 0.000 title claims abstract description 19
- 230000006399 behavior Effects 0.000 claims abstract description 48
- 238000011176 pooling Methods 0.000 claims abstract description 31
- 230000015654 memory Effects 0.000 claims description 26
- 238000012549 training Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 claims description 2
- 238000013527 convolutional neural network Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000009826 distribution Methods 0.000 description 9
- 238000003745 diagnosis Methods 0.000 description 7
- 238000013135 deep learning Methods 0.000 description 4
- 238000010276 construction Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- 230000001149 cognitive effect Effects 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000011664 signaling Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a model, a method, a device and a storage medium for identifying electric power operation scene violation behaviors, wherein the model comprises the following components: the convolution layer is used for extracting the characteristics of the input electric power operation scene pictures to obtain a plurality of characteristic pictures; the saliency maximization layer is used for carrying out maximization operation on the plurality of feature graphs; the saliency component positioning learning layer is used for carrying out weighted summation on the pooling result to obtain a summation result; and the classification layer is used for outputting the identification result according to the summation result. By implementing the invention, the full-connection layer is replaced by the saliency maximum pooling layer in the model, the problems of overlarge parameter quantity and easy overfitting in the convolutional neural network are solved, the saliency maximum pooling layer is connected with the convolutional layer, the practical category meaning of each channel is directly endowed, the characteristics of black boxes in the full-connection layer are removed, and the network structure has interpretability. And a significance component learning layer is arranged, so that the recognition of the illegal behaviors in the power operation scene becomes traceable.
Description
Technical Field
The invention relates to the technical field of electric power operation violation detection, in particular to an electric power operation scene violation behavior identification model, an electric power operation scene violation behavior identification method, an electric power operation scene violation behavior identification device and a storage medium.
Background
The construction environment is relatively complex in the power grid operation scene, and a plurality of unsafe factors exist, such as the fact that safety helmets are not correctly worn according to regulations when entering an operation site, the fact that fences are not arranged on the operation site according to requirements, and the like, and the unsafe factors form potential threats to the personal safety of personnel on the operation site.
Meanwhile, with the continuous improvement of the deep learning method, the artificial intelligence system achieves a level exceeding that of human on more and more complex tasks, and the deep learning-based system is widely applied to the fields of power grids, medical treatment, automatic driving and the like. However, while these algorithms perform well in most tasks, the results produced in the identification of violations in the power job scenario are unexplainable, traceable, and even in some cases uncontrollable.
Disclosure of Invention
In view of the above, the embodiment of the invention provides a model, a method, a device and a storage medium for identifying the behavior of the violations of the power operation scene, so as to solve the technical problem of poor interpretation of the result when the behavior of the violations of the power operation scene is identified by deep learning in the prior art.
The technical scheme provided by the invention is as follows:
an embodiment of the present invention provides a power operation scene violation behavior recognition model, including: the convolution layer is used for extracting the characteristics of the input electric power operation scene pictures to obtain a plurality of characteristic pictures; the saliency maximum pooling layer is used for carrying out maximum pooling operation on the plurality of feature images to obtain pooling results; the saliency component positioning learning layer is used for carrying out weighted summation on the pooling results to obtain summation results; and the classification layer is used for outputting a violation behavior identification result of the electric power operation scene picture according to the summation result.
In combination with the first aspect of the embodiment of the present invention, in a first implementation manner of the first aspect, the operation of the saliency maximum pooling layer is expressed by the following formula:
F k ＝Max(f k (x,y))
wherein f k (x, y) represents the value of the (x, y) position on the kth feature map.
With reference to the first implementation manner of the first aspect of the embodiment of the present invention, in a second implementation manner of the first aspect, the operation of the salient component positioning learning layer is expressed by the following formula:
where c represents the category and w represents the weight of the kth feature map.
With reference to the second implementation manner of the first aspect of the embodiment of the present invention, in a third implementation manner of the first aspect, the operation of the classification layer is expressed by the following formula:
wherein P is c The classification value corresponding to the category c is indicated.
With reference to the second implementation manner of the first aspect of the embodiment of the present invention, in a fourth implementation manner of the first aspect, the weight of each feature map is determined by training the electric power operation scene violation identification model by using a marked electric power operation scene picture.
The second aspect of the embodiment of the invention provides a method for identifying the illegal behaviors of an electric power operation scene, which comprises the following steps: acquiring a power operation scene picture to be identified; inputting the electric power operation scene picture to be identified into the electric power operation scene violation behavior identification model according to the first aspect of the embodiment of the invention to obtain an identification result.
With reference to the second aspect of the embodiment of the present invention, in a first implementation manner of the second aspect, the identification result includes a category of the offending behavior.
A third aspect of the embodiment of the present invention provides an apparatus for identifying a violation behavior in a power operation scenario, including: the image acquisition module is used for acquiring an image of the power operation scene to be identified; the identification module is used for inputting the to-be-identified electric power operation scene picture into the electric power operation scene violation identification model according to the first aspect and any one of the first aspect of the embodiment of the invention to obtain an identification result.
A fourth aspect of the embodiment of the present invention provides a computer readable storage medium, where computer instructions are stored, where the computer instructions are configured to cause the computer to execute the method for identifying electric power job scenario violations according to the second aspect of the embodiment of the present invention and the first implementation manner of the second aspect.
A fifth aspect of an embodiment of the present invention provides an electronic device, including: the system comprises a memory and a processor, wherein the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions so as to execute the electric power operation scene violation identification method according to the second aspect of the embodiment and the first implementation mode of the second aspect.
The technical scheme provided by the invention has the following effects:
aiming at the problem that the related models are insufficient in application reliability in the fields of equipment fault diagnosis, distribution network load prediction, power standard specification search query and the like due to the lack of interpretability research of the current special artificial intelligent cognitive model for electric power, the embodiment of the invention provides the electric power operation scene violation behavior recognition model comprising a convolution layer, a saliency maximum pooling layer, a saliency component positioning learning layer and a classification layer, and can greatly improve the application reliability and practicability of the model in the fields of equipment fault diagnosis, distribution network load prediction, power standard specification search query and the like while practically improving the performance of the special artificial intelligent model for electric power. Meanwhile, the saliency maximum pooling layer is adopted to replace the full-connection layer in the model, so that the problems of overlarge parameter quantity and easiness in fitting existing in the full-connection layer in the convolutional neural network are solved, meanwhile, the saliency maximum pooling layer is adopted to connect the convolutional layer, the category can be better corresponding to the characteristic diagram of the last convolutional layer, the actual category meaning of each channel is directly given to each channel (each channel corresponds to one category, each characteristic diagram can be regarded as a category confidence diagram corresponding to the category), and the characteristics of black boxes in the full-connection layer are removed, so that the network structure has interpretability. In addition, on the basis of the saliency maximum pooling layer, a saliency component learning layer is arranged, so that the recognition of the illegal behaviors in the power operation scene becomes traceable.
According to the method and the device for identifying the electric power operation scene violation behaviors, the electric power operation scene violation behaviors are identified by adopting the electric power operation scene violation behavior identification model, and the hidden layer of the violation behaviors is visualized based on the significant component positioning layer in the model, so that the result becomes interpretable. The recognition accuracy of the electric power operation scene violation behavior recognition model is practically improved, and meanwhile, the application reliability and the practicability of the model in the fields of equipment fault diagnosis, distribution network load prediction, electric power standard specification search query and the like are greatly improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
FIG. 1 is a block diagram of a power job scenario violation identification model according to an embodiment of the present invention;
FIG. 2 is a flow chart of a method for identifying violations of a power job scenario in accordance with an embodiment of the present invention;
FIG. 3 is a block diagram of a power job scenario violation identification device according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a computer-readable storage medium provided according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
The terms first, second, third, fourth and the like in the description and in the claims and in the above drawings are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate such that the embodiments described herein may be implemented in other sequences than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
An embodiment of the present invention provides a model for identifying a violation behavior in an electric power operation scene, as shown in fig. 1, including: the convolution layer 10 is used for extracting the characteristics of the input electric power operation scene pictures to obtain a plurality of characteristic pictures; a saliency maximum pooling layer 20, configured to perform a maximum pooling operation on the plurality of feature maps, so as to obtain a pooling result; a saliency component positioning learning layer 30, configured to perform weighted summation on the pooled results to obtain a summation result; and the classification layer 40 is used for outputting the identification result of the electric power operation scene picture according to the summation result.
Specifically, the convolution layer, the saliency maximization pooling layer and the classification layer constitute a prototype learning network structure. The convolution layer is used for performing deeper analysis on the input picture so as to obtain features with higher abstraction degree. The specific number of layers for the convolution layer can be set according to the actual situation. After the saliency maximum pooling layer is connected to the last layer in the convolution layers, so that the position information of the convolution layers can be reserved, and the network structure has interpretability. Meanwhile, saliency maximum pooling is adopted instead of average pooling, because the saliency target is clear in the power operation scene, and the saliency maximum pooling layer in the model can be used for realizing more accurate capture of the target in the power operation scene, so that the final recognition result is more accurate. The saliency component positioning learning layer is used for obtaining a saliency component positioning map corresponding to a specific category by carrying out weighted overlapping on the feature maps, and the saliency component positioning learning layer can display the feature maps which are mainly from a plurality of feature maps according to which classification decision the model makes, namely, the final recognition result becomes traceable. The classification layer is essentially a normalized network, the purpose of which is to map multiple scalar quantities into a probability distribution, with each value range of the classification layer output between 0-1. Therefore, probability distribution conditions belonging to different categories in the electric power operation scene picture can be obtained through the classification layer.
Aiming at the problem that the related models are insufficient in application reliability in the fields of equipment fault diagnosis, distribution network load prediction, power standard specification search query and the like due to the lack of interpretability research of the current special artificial intelligent cognitive model for electric power, the embodiment of the invention provides the electric power operation scene violation behavior recognition model comprising a convolution layer, a saliency maximum pooling layer, a saliency component positioning learning layer and a classification layer, and can greatly improve the application reliability and practicability of the model in the fields of equipment fault diagnosis, distribution network load prediction, power standard specification search query and the like while practically improving the performance of the special artificial intelligent model for electric power. Meanwhile, the saliency maximum pooling layer is adopted to replace the full-connection layer in the model, so that the problems of overlarge parameter quantity and easiness in fitting existing in the full-connection layer in the convolutional neural network are solved, meanwhile, the saliency maximum pooling layer is adopted to connect the convolutional layer, the category can be better corresponding to the characteristic diagram of the last convolutional layer, the actual category meaning of each channel is directly given to each channel (each channel corresponds to one category, each characteristic diagram can be regarded as a category confidence diagram corresponding to the category), and the characteristics of black boxes in the full-connection layer are removed, so that the network structure has interpretability. In addition, on the basis of the saliency maximum pooling layer, a saliency component learning layer is arranged, so that the recognition of the illegal behaviors in the power operation scene becomes traceable.
In one embodiment, the operation of the saliency maximization pooling layer is expressed by the following formula:
F k ＝Max(f k (x, y)) formula (1)
Wherein f k (x, y) represents the value of the (x, y) position on the kth feature map.
The operation of the salient component positioning learning layer is expressed by the following formula:
where c represents the category and w represents the weight of the kth feature map.
Specifically, based on the above formula (1), the expansion of formula (2) yields:
based on equation (3), a saliency map belonging to a certain class c is defined as:
as can be seen from equation (4), M c (x, y) represents the sum of weights of different saliency component feature images to identify a certain class c. M to be generated c (x, y) is enlarged to the size of the original image, and a saliency component positioning chart corresponding to a certain category c is obtained. The weight w is used as a parameter of the model, and may be adjusted and determined in the model training process. Specifically, the marked electric power operation scene picture is adopted to train a network structure comprising a convolution layer, a saliency maximum pooling layer, a saliency component positioning learning layer and a classification layer, and the weight w is adjusted and determined in the training process.
The operation of the classification layer is expressed by the following formula:
wherein P is c The classification value corresponding to the category c is indicated. Specifically, the result S after weighted summation by the saliency component positioning learning layer c And inputting the specific scores into a classification layer, wherein the classification layer adopts a formula (5) pair to calculate the specific scores belonging to the category c.
According to an embodiment of the present invention, there is also provided a method for identifying violations of a power job scenario, it being noted that the steps illustrated in the flowchart of the figures may be performed in a computer system, such as a set of computer-executable instructions, and that although a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different from that illustrated herein.
In this embodiment, a method for identifying a violation behavior of a power operation scene is provided, which may be used in an electronic device, such as a computer, a mobile phone, a tablet computer, etc., fig. 2 is a flowchart of the method for identifying a violation behavior of a power operation scene according to an embodiment of the present invention, as shown in fig. 2, and the method includes the following steps:
step S101: acquiring a power operation scene picture to be identified; specifically, the power operation scenario includes an operation scenario such as power construction or power production. Pictures of the construction or production of the workers of the power operation scene can be acquired through equipment such as an image sensor or a camera arranged on the operation scene.
Step S102: and inputting the electric power operation scene picture to be identified into the electric power operation scene violation identification model described in the embodiment, so as to obtain an identification result. Specifically, the electric power operation scene picture to be identified is input into the trained electric power operation scene violation behavior identification model, and an identification result comprising specific violation behaviors is obtained. For example, entering a job site does not properly wear a helmet as specified, the job site does not provide a fence as required, and so on.
In addition, fine-granularity violations can be identified by adopting the electric power operation scene violation identification model, for example, the violations of a safety helmet which is not correctly worn and a mandibular belt which is not correctly tied are both common violations in the electric power operation scene, but are difficult to accurately identify by adopting a traditional deep learning method because the two violations are difficult to distinguish. By adopting the electric power operation scene violation behavior recognition model, the hidden layer of the violation behavior is visualized based on the significance component positioning learning layer, so that the model performance is improved, and the accuracy of model recognition is improved.
According to the electric power operation scene violation behavior recognition method provided by the embodiment of the invention, the electric power operation scene violation behavior recognition model is adopted to recognize the violation behavior in the electric power operation scene, and the hidden layer of the violation behavior is visualized based on the significant component positioning layer in the model, so that the result becomes interpretable. The recognition accuracy of the electric power operation scene violation behavior recognition model is practically improved, and meanwhile, the application reliability and the practicability of the model in the fields of equipment fault diagnosis, distribution network load prediction, electric power standard specification search query and the like are greatly improved.
The embodiment of the invention also provides a device for identifying the electric power operation scene violation behavior, as shown in fig. 3, which comprises the following steps:
the image acquisition module is used for acquiring an image of the power operation scene to be identified; the specific content refers to the corresponding parts of the above method embodiments, and will not be described herein.
The identification module is used for inputting the power operation scene picture to be identified into the power operation scene violation behavior identification model described in the embodiment, and obtaining an identification result. The specific content refers to the corresponding parts of the above method embodiments, and will not be described herein.
According to the electric power operation scene violation behavior recognition device provided by the embodiment of the invention, the electric power operation scene violation behavior recognition model is adopted to recognize the violation behavior in the electric power operation scene, and the hidden layer of the violation behavior is visualized based on the significant component positioning layer in the model, so that the result becomes interpretable. The recognition accuracy of the electric power operation scene violation behavior recognition model is practically improved, and meanwhile, the application reliability and the practicability of the model in the fields of equipment fault diagnosis, distribution network load prediction, electric power standard specification search query and the like are greatly improved.
The function description of the electric power operation scene violation identification device provided by the embodiment of the invention refers to the description of the electric power operation scene violation identification method in the embodiment in detail.
The embodiment of the present invention further provides a storage medium, as shown in fig. 4, on which a computer program 601 is stored, which when executed by a processor, implements the steps of the electric power job scenario violation identification method in the above embodiment. The storage medium also stores audio and video stream data, characteristic frame data, interactive request signaling, encrypted data, preset data size and the like. The storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a random access Memory (Random Access Memory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), or a Solid State Drive (SSD); the storage medium may also comprise a combination of memories of the kind described above.
It will be appreciated by those skilled in the art that implementing all or part of the above-described embodiment method may be implemented by a computer program to instruct related hardware, where the program may be stored in a computer readable storage medium, and the program may include the above-described embodiment method when executed. Wherein the storage medium may be a magnetic Disk, an optical Disk, a Read-Only Memory (ROM), a random access Memory (RandomAccessMemory, RAM), a Flash Memory (Flash Memory), a Hard Disk (HDD), a Solid State Drive (SSD), or the like; the storage medium may also comprise a combination of memories of the kind described above.
The embodiment of the present invention further provides an electronic device, as shown in fig. 5, where the electronic device may include a processor 51 and a memory 52, where the processor 51 and the memory 52 may be connected by a bus or other means, and in fig. 5, the connection is exemplified by a bus.
The processor 51 may be a central processing unit (Central Processing Unit, CPU). The processor 51 may also be other general purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate arrays (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations thereof.
The memory 52 serves as a non-transitory computer readable storage medium that may be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as corresponding program instructions/modules in embodiments of the present invention. The processor 51 executes various functional applications of the processor and data processing by running non-transitory software programs, instructions, and modules stored in the memory 52, that is, implements the electric power job scenario violation identification method in the above-described method embodiment.
The memory 52 may include a memory program area that may store an operating device, an application program required for at least one function, and a memory data area; the storage data area may store data created by the processor 51, etc. In addition, memory 52 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some embodiments, memory 52 may optionally include memory located remotely from processor 51, which may be connected to processor 51 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The one or more modules are stored in the memory 52, which when executed by the processor 51, performs the power job scenario violation identification method in the embodiment shown in fig. 2.
The details of the electronic device may be understood correspondingly with respect to the corresponding relevant descriptions and effects in the embodiment shown in fig. 2, which are not repeated herein.
Although embodiments of the present invention have been described in connection with the accompanying drawings, various modifications and variations may be made by those skilled in the art without departing from the spirit and scope of the invention, and such modifications and variations fall within the scope of the invention as defined by the appended claims.
Claims (10)
1. An electric power operation scene violation behavior recognition model, which is characterized by comprising:
the convolution layer is used for extracting the characteristics of the input electric power operation scene pictures to obtain a plurality of characteristic pictures;
the saliency maximum pooling layer is used for carrying out maximum pooling operation on the plurality of feature images to obtain pooling results;
the saliency component positioning learning layer is used for carrying out weighted summation on the pooling results to obtain summation results;
and the classification layer is used for outputting a violation behavior identification result of the electric power operation scene picture according to the summation result.
2. The power job scenario violation identification model according to claim 1, wherein the operation of the saliency maximization pooling layer is expressed by the following formula:
F k ＝Max(f k (x,y))
wherein f k (x, y) represents the value of the (x, y) position on the kth feature map.
3. The power job scenario violation identification model according to claim 2, wherein the operation of the saliency component positioning learning layer is expressed by the following formula:
where c represents the category and w represents the weight of the kth feature map.
4. A power job scenario violation identification model according to claim 3, characterized in that the operation of the classification layer is expressed by the following formula:
wherein P is c The classification value corresponding to the category c is indicated.
5. A power job scenario violation identification model according to claim 3, characterized in that the weight of each feature map is determined by training the power job scenario violation identification model with annotated power job scenario pictures.
6. The electric power operation scene violation behavior identification method is characterized by comprising the following steps of:
acquiring a power operation scene picture to be identified;
inputting the electric power operation scene picture to be identified into the electric power operation scene violation behavior identification model according to any one of claims 1-5 to obtain an identification result.
7. The power job scenario violation identification method according to claim 6, wherein the identification result includes a category of violation.
8. An electric power operation scene behavior recognition device is characterized by comprising:
the image acquisition module is used for acquiring an image of the power operation scene to be identified;
the identification module is used for inputting the electric power operation scene picture to be identified into the electric power operation scene violation behavior identification model according to any one of claims 1-5 to obtain an identification result.
9. A computer-readable storage medium storing computer instructions for causing the computer to execute the electric power job scene violation identification method according to claim 6 or 7.
10. An electronic device, comprising: a memory and a processor, the memory and the processor are in communication connection, the memory stores computer instructions, and the processor executes the computer instructions, thereby executing the electric power operation scene violation identification method according to claim 6 or 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310331575.0A CN116524240A (en) | 2023-03-30 | 2023-03-30 | Electric power operation scene violation behavior identification model, method, device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310331575.0A CN116524240A (en) | 2023-03-30 | 2023-03-30 | Electric power operation scene violation behavior identification model, method, device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116524240A true CN116524240A (en) | 2023-08-01 |
Family
ID=87389459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310331575.0A Pending CN116524240A (en) | 2023-03-30 | 2023-03-30 | Electric power operation scene violation behavior identification model, method, device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116524240A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729819A (en) * | 2017-09-22 | 2018-02-23 | 华中科技大学 | A kind of face mask method based on sparse full convolutional neural networks |
| CN110569814A (en) * | 2019-09-12 | 2019-12-13 | 广州酷狗计算机科技有限公司 | Video category identification method and device, computer equipment and computer storage medium |
| CN112613454A (en) * | 2020-12-29 | 2021-04-06 | 国网山东省电力公司建设公司 | Electric power infrastructure construction site violation identification method and system |
| CN112861524A (en) * | 2021-04-07 | 2021-05-28 | 中南大学 | Deep learning-based multilevel Chinese fine-grained emotion analysis method |
| CN112883889A (en) * | 2021-03-02 | 2021-06-01 | 江苏省电力试验研究院有限公司 | Method suitable for detecting violation behaviors in power construction scene |
| CN113947161A (en) * | 2021-10-28 | 2022-01-18 | 广东工业大学 | Attention mechanism-based multi-label text classification method and system |
| CN114881173A (en) * | 2022-05-31 | 2022-08-09 | 中国人民解放军国防科技大学 | Resume classification method and device based on self-attention mechanism |
-
2023
- 2023-03-30 CN CN202310331575.0A patent/CN116524240A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107729819A (en) * | 2017-09-22 | 2018-02-23 | 华中科技大学 | A kind of face mask method based on sparse full convolutional neural networks |
| CN110569814A (en) * | 2019-09-12 | 2019-12-13 | 广州酷狗计算机科技有限公司 | Video category identification method and device, computer equipment and computer storage medium |
| CN112613454A (en) * | 2020-12-29 | 2021-04-06 | 国网山东省电力公司建设公司 | Electric power infrastructure construction site violation identification method and system |
| CN112883889A (en) * | 2021-03-02 | 2021-06-01 | 江苏省电力试验研究院有限公司 | Method suitable for detecting violation behaviors in power construction scene |
| CN112861524A (en) * | 2021-04-07 | 2021-05-28 | 中南大学 | Deep learning-based multilevel Chinese fine-grained emotion analysis method |
| CN113947161A (en) * | 2021-10-28 | 2022-01-18 | 广东工业大学 | Attention mechanism-based multi-label text classification method and system |
| CN114881173A (en) * | 2022-05-31 | 2022-08-09 | 中国人民解放军国防科技大学 | Resume classification method and device based on self-attention mechanism |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145759B (en) | Vehicle attribute identification method, device, server and storage medium | |
| US20170213081A1 (en) | Methods and systems for automatically and accurately detecting human bodies in videos and/or images | |
| CN110533950A (en) | Detection method, device, electronic equipment and the storage medium of parking stall behaviour in service | |
| CN104134364B (en) | Real-time traffic sign identification method and system with self-learning capacity | |
| CN109657564A (en) | A kind of personnel detection method, device, storage medium and terminal device on duty | |
| CN109993031A (en) | A kind of animal-drawn vehicle target is driven against traffic regulations behavioral value method, apparatus and camera | |
| CN112052837A (en) | Target detection method and device based on artificial intelligence | |
| CN110781980B (en) | Training method of target detection model, target detection method and device | |
| CN109815884A (en) | Unsafe driving behavioral value method and device based on deep learning | |
| CN111008576B (en) | Pedestrian detection and model training method, device and readable storage medium | |
| CN109800682A (en) | Driver attributes' recognition methods and Related product | |
| WO2022078216A1 (en) | Target recognition method and device | |
| CN116186770A (en) | Image desensitizing method, device, electronic equipment and storage medium | |
| CN112562159B (en) | Access control method and device, computer equipment and storage medium | |
| CN105405130A (en) | Cluster-based license image highlight detection method and device | |
| US20240135710A1 (en) | Systems and methods for video analysis | |
| CN112101114B (en) | Video target detection method, device, equipment and storage medium | |
| WO2023279799A1 (en) | Object identification method and apparatus, and electronic system | |
| CN110390226B (en) | Crowd event identification method and device, electronic equipment and system | |
| CN114359618A (en) | Training method of neural network model, electronic equipment and computer program product | |
| CN116524240A (en) | Electric power operation scene violation behavior identification model, method, device and storage medium | |
| CN109035686B (en) | Loss prevention alarm method and device | |
| CN116823884A (en) | Multi-target tracking method, system, computer equipment and storage medium | |
| CN113177917B (en) | Method, system, equipment and medium for optimizing snap shot image | |
| JP2024516642A (en) | Behavior detection method, electronic device and computer-readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |