CN112183265A - Electric power construction video monitoring and alarming method and system based on image recognition - Google Patents
Electric power construction video monitoring and alarming method and system based on image recognition Download PDFInfo
- Publication number
- CN112183265A CN112183265A CN202010980558.6A CN202010980558A CN112183265A CN 112183265 A CN112183265 A CN 112183265A CN 202010980558 A CN202010980558 A CN 202010980558A CN 112183265 A CN112183265 A CN 112183265A
- Authority
- CN
- China
- Prior art keywords
- information
- image
- image recognition
- power construction
- 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
Images
Classifications
-
- 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
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
- G06F18/24133—Distances to prototypes
- G06F18/24137—Distances to cluster centroïds
- G06F18/2414—Smoothing the distance, e.g. radial basis function networks [RBFN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/0202—Child monitoring systems using a transmitter-receiver system carried by the parent and the child
- G08B21/0261—System arrangements wherein the object is to detect trespassing over a fixed physical boundary, e.g. the end of a garden
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/182—Level alarms, e.g. alarms responsive to variables exceeding a threshold
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Business, Economics & Management (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Emergency Management (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Child & Adolescent Psychology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an electric power construction video monitoring and alarming method and system based on image recognition, wherein the method specifically comprises the following steps: firstly, acquiring image information of a power construction site in real time, labeling the image information including character information, and performing data processing on the labeled image information to obtain image data; secondly, the trained neural network is used as a pre-training model, and the pre-training model is retrained according to violation data to obtain an image recognition model; and finally, inputting the image data into a trained image recognition model, determining whether the personnel on the electric power construction site have illegal behaviors, and sending an alarm prompt signal when the illegal behaviors occur. The behaviors of the personnel entering the construction site are identified by adopting an image identification technology, whether the behaviors of the personnel entering the construction site are illegal or not is judged, and different alarm signals can be sent according to the illegal levels, so that the security supervision level of the transformer substation is improved, and the occurrence of security events is reduced.
Description
Technical Field
The invention relates to an electric power construction video monitoring and alarming method and system based on image recognition.
Background
Along with the increasing demand of electricity for people, the power grid scale is continuously enlarged, the number of transformer substations is also sharply increased, and in order to improve the labor efficiency and reasonably distribute human resources, the transformer substations are generally in an unattended mode. With the continuous development of video monitoring technology, the functions of monitoring the whole station and assisting security protection are achieved to a certain extent through continuous real-time monitoring of the environment inside and outside the transformer substation. However, at present, due to the fact that the intelligent level of the transformer substation is not very high, real unattended operation is not achieved, videos shot back by a large number of monitoring cameras need to be checked manually one by one, and waste of human resources and low working efficiency are caused.
Illegal things caused by people in the transformer station area are various, and common problems can be classified into the following problems: firstly, artificial damage, wherein some lawbreakers try to cross a transformer substation barrier and steal and damage various facility resources in the substation, and particularly under the condition of insufficient security measures, the substation is easy to damage; secondly, entering the interval by mistake, and when a professional enters a transformer substation to carry out related maintenance operation, due to the fact that certain similarity exists between the transformer equipment, the conditions such as entering the interval by mistake often occur, and certain misoperation caused by the conditions can bring great hidden danger to personal safety and equipment safety; and thirdly, the non-professional personnel are allowed to enter the transformer substation due to the reasons of visiting, construction and the like, but the non-professional personnel are not allowed to approach and enter the transformer substation, and the traditional warning board in the transformer substation can play a warning role but is easy to ignore.
Disclosure of Invention
The invention aims to provide an electric power construction video monitoring and alarming method and system based on image recognition, which can automatically recognize illegal behaviors of personnel entering a construction site, improve the security supervision level of a transformer substation and reduce the occurrence of security events.
In order to solve the technical problem, the invention provides an electric power construction video monitoring and alarming method based on image recognition, which comprises the following steps:
s1: acquiring image information of a power construction site in real time, labeling the acquired image information including character information, and performing data processing on the labeled image information to obtain image data;
s4: the trained neural network is used as a pre-training model, and the pre-training model is retrained according to violation data to obtain an image recognition model;
s5: and (4) inputting the image data obtained in the step (S1) into a trained image recognition model, determining whether the personnel on the electric power construction site have illegal behaviors, and sending out an alarm prompt signal when the illegal behaviors occur.
Further, the method further comprises:
when the fact that the violation behaviors exist in the electric power construction site personnel is determined, the violation behaviors of the personnel are compared with preset violation categories, the violation level of the violation behaviors of the personnel is judged, and different warning prompt signals are sent according to the violation level corresponding to the violation behaviors of the personnel.
Further, the step S4 specifically includes:
s41: downloading a trained neural network from ImageNet as a pre-training model;
s42: and freezing parameters of the shallow layer of the pre-training model, then informing the modification of the network structure of the output layer of the pre-training model, and retraining the pre-training model according to violation data to obtain an image recognition model root.
Further, the kernel parameter of the algorithm for retraining the pre-training model is a characteristic loss function of the picture, where the characteristic loss function is:
wherein (t)x,ty) As the center point of the prediction box, (t)w,th) The width and height of the prediction box are shown, C is the confidence coefficient of the prediction box, and p is the probability of the predicted object class.
Further, the method further comprises:
s2: establishing a constructor information base, wherein the constructor information base comprises basic identity information and face information of constructors;
s3: according to the image data obtained in the step S1, carrying out face recognition on the characters in the collected image information of the construction site, comparing the face recognition result with the face information in the constructor information base, judging whether the characters in the image information of the construction site are constructor information, if so, matching the basic identity information, the violation and the illegal behaviors in the constructor and constructor information base, and storing the matching result; otherwise, determining that a person enters the system, and sending an alarm prompt.
Further, the basic identity information of the constructor comprises name, attribution unit, post responsibility and communication information.
And further, forming a statistical report according to the violation records of the constructors according to a preset template and storing the statistical report.
Further, the method further comprises:
acquiring real-time running state and positioning information of each interval device in the transformer substation;
and judging whether the distance between the constructor and the electrified spacing equipment is smaller than a preset threshold value or not according to the personnel position information of the constructor, and if so, sending false entry spacing early warning information.
In addition, this application still provides an electric power construction video monitoring alarm system based on image recognition, includes
The image acquisition unit is used for acquiring image information of a power construction site in real time;
the data annotation unit is used for performing annotation processing on the acquired image information including the figure information;
the data processing unit is used for carrying out data processing on the marked image information to obtain image data;
the image recognition unit is used for inputting the image data into a trained image recognition model and determining whether the personnel on the electric power construction site have illegal behaviors;
and the warning unit is used for sending a warning prompt signal when the image recognition unit judges that the violation behavior occurs.
Further, the image recognition model is obtained by retraining the pre-training model according to violation data, and the pre-training model is a trained neural network.
The invention has the beneficial effects that: the behaviors of the personnel entering the construction site are identified by adopting an image identification technology, whether the behaviors of the personnel entering the construction site are illegal or not is judged, and different alarm signals can be sent according to the illegal levels, so that the security supervision level of the transformer substation is improved, the safety of the personnel is protected, and the occurrence of security events is reduced.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a data flow diagram of one embodiment of the present invention.
FIG. 2 is a schematic block diagram of one embodiment of the present invention.
Detailed Description
A power construction video monitoring and alarming method based on image recognition comprises the following steps:
s1: acquiring image information of a power construction site in real time, labeling the acquired image information including character information, and performing data processing on the labeled image information to obtain image data; the image information at the data labeling mark position comprises the image information of the character information, and then the labeled image information is subjected to data processing, so that the data processing strength can be reduced;
s2: establishing a constructor information base, wherein the constructor information base comprises basic identity information and face information of constructors; basic identity information of the constructor may include name, affiliation unit, post responsibility and communication information, etc. When a constructor enters a construction site, the identity of the constructor is identified through an image identification technology, and corresponding identity information is allocated to the constructor; setting post responsibility and communication information for subsequent notification and alarm information issuing;
s3: according to the image data obtained in the step S1, carrying out face recognition on the characters in the collected image information of the construction site, comparing the face recognition result with the face information in the constructor information base, judging whether the characters in the image information of the construction site are constructor information, if so, matching the basic identity information, the violation and the illegal behaviors in the constructor and constructor information base, and storing the matching result; otherwise, if the fact that non-constructors enter is determined, an alarm prompt is sent to the monitoring center in time to remind relevant managers that the non-constructors enter, and therefore the managers can take corresponding measures;
s4: the trained neural network is used as a pre-training model, and the pre-training model is retrained according to violation data to obtain an image recognition model; when the fact that the violation behaviors exist in the electric power construction site personnel is determined, the violation behaviors of the personnel are compared with preset violation categories, the violation level of the violation behaviors of the personnel is judged, and different warning prompt signals are sent according to the violation level corresponding to the violation behaviors of the personnel.
S5: and (4) inputting the image data obtained in the step (S1) into a trained image recognition model, determining whether the personnel on the electric power construction site have illegal behaviors, and sending out an alarm prompt signal when the illegal behaviors occur.
The step S4 specifically includes:
s41: downloading a trained neural network from ImageNet as a pre-training model;
s42: and freezing parameters of the shallow layer of the pre-training model, then informing the modification of the network structure of the output layer of the pre-training model, and retraining the pre-training model according to violation data to obtain an image recognition model root.
The pre-training model can select inception V3, Xception, VGG16, VGG19, ResNet50, MobileNet V2 and other models as the pre-training model, taking MobileNet V2 as an example, the size of the input picture is converted into (224, 224, 3), then the size is input into a MobileNet V2 model, a maximum pooling layer and a full connection layer are connected behind the MobileNet V2, the maximum pooling layer and the full connection layer are consistent with a shallow neural network, RMSprop is used as an optimizer to optimize cross entropy, and the pre-training model is re-trained by generally using a smaller learning rate. The image recognition basic algorithm model is a shallow neural network, an input picture firstly passes through three convolutional layers and a maximum pooling layer respectively, then two layers of fully-connected neural networks are connected, and RMSprop is selected as an optimizer to optimize the overall cross entropy. The method is a simple shallow neural network, is suitable for scenes with small data volume, can be used for recognizing scenes with large data volume by retraining the pre-training model by adopting a transfer learning method, and improves the recognition efficiency and the accuracy of recognition results.
The kernel parameter of the algorithm for retraining the pre-training model is a characteristic loss function of the picture, wherein the characteristic loss function is as follows:
wherein (t)x,ty) As the center point of the prediction box, (t)w,th) And C is the confidence coefficient of the prediction frame, the inspection effect can be controlled by adjusting the ratio between obj confidence coefficient loss and nonobj confidence coefficient loss, and p is the probability of the predicted object class.
The construction site can divide the violation into four levels according to the damage degree to the personnel, and the specific steps are as follows:
1. first-level violation: events which can cause the life safety of personnel, such as live working, lifting work and the like in the fence, a red fence is needed to be used, and any idle personnel is strictly forbidden to enter, which is defined as red first-level alarm;
2. second-level violation: an orange fence is needed in an event that personnel are seriously injured possibly, such as a pot hole in the fence, and an orange secondary alarm needs to be given after idle personnel (namely non-constructors) cross;
3. three-level violation behaviors: the event which can cause personal injury, such as a common construction event, needs a yellow fence, and needs to give a yellow three-level alarm after idle personnel cross.
For convenience of management, violation records of constructors can be stored by forming a statistical report according to a preset template, so that related responsible persons and construction units can conveniently count violation events of the constructors, follow-up punishment and management training can be carried out, and the safety management level can be effectively improved.
In addition, the application also provides an electric power construction video monitoring and warning system based on image identification, and as shown in fig. 2, the system comprises an image acquisition unit, a data annotation unit, a data processing unit, an image identification unit and a warning unit; the image acquisition unit is used for acquiring image information of a power construction site in real time; the data annotation unit is used for performing annotation processing on the acquired image information including the figure information; the data processing unit is used for carrying out data processing on the marked image information to obtain image data; the image recognition unit is used for inputting the image data into a trained image recognition model and determining whether the personnel on the electric power construction site have illegal behaviors; the warning unit is used for sending a warning prompt signal when the image recognition unit judges that the violation behavior occurs; the image recognition model is obtained by retraining the pre-training model according to violation data, and the pre-training model is a trained neural network.
Finally, the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all of them should be covered in the claims of the present invention.
Claims (10)
1. A power construction video monitoring and alarming method based on image recognition is characterized by comprising the following steps:
s1: acquiring image information of a power construction site in real time, labeling the acquired image information including character information, and performing data processing on the labeled image information to obtain image data;
s4: the trained neural network is used as a pre-training model, and the pre-training model is retrained according to violation data to obtain an image recognition model;
s5: and (4) inputting the image data obtained in the step (S1) into a trained image recognition model, determining whether the personnel on the electric power construction site have illegal behaviors, and sending out an alarm prompt signal when the illegal behaviors occur.
2. The video monitoring and warning method for power construction based on image recognition is characterized by further comprising the following steps of:
when the fact that the violation behaviors exist in the electric power construction site personnel is determined, the violation behaviors of the personnel are compared with preset violation categories, the violation level of the violation behaviors of the personnel is judged, and different warning prompt signals are sent according to the violation level corresponding to the violation behaviors of the personnel.
3. The image identification-based power construction video monitoring and warning method according to claim 1 or 2, wherein the step S4 specifically includes:
s41: downloading a trained neural network from ImageNet as a pre-training model;
s42: and freezing parameters of the shallow layer of the pre-training model, then informing the modification of the network structure of the output layer of the pre-training model, and retraining the pre-training model according to violation data to obtain an image recognition model root.
4. The image recognition-based power construction video monitoring and warning method according to claim 3, wherein the algorithm core parameter retraining the pre-trained model is a characteristic loss function of a picture, and the characteristic loss function is:
wherein (t)x,ty) As the center point of the prediction box, (t)w,th) To prepareAnd (3) measuring the width and the height of the frame, wherein C is the confidence coefficient of the prediction frame, and p is the probability of the class of the predicted object.
5. The video monitoring and warning method for power construction based on image recognition is characterized by further comprising the following steps of:
s2: establishing a constructor information base, wherein the constructor information base comprises basic identity information and face information of constructors;
s3: according to the image data obtained in the step S1, carrying out face recognition on the characters in the collected image information of the construction site, comparing the face recognition result with the face information in the constructor information base, judging whether the characters in the image information of the construction site are constructor information, if so, matching the basic identity information, the violation and the illegal behaviors in the constructor and constructor information base, and storing the matching result; otherwise, determining that a person enters the system, and sending an alarm prompt.
6. The video monitoring and warning method for power construction based on image recognition as claimed in claim 5, wherein the basic identity information of the constructor includes name, attribution unit, post responsibility and communication information.
7. The image recognition-based electric power construction video monitoring and warning method according to claim 6, wherein violation records of constructors are stored by forming a statistical form according to a preset template.
8. The video monitoring and warning method for power construction based on image recognition is characterized by further comprising the following steps:
acquiring real-time running state and positioning information of each interval device in the transformer substation;
and judging whether the distance between the constructor and the electrified spacing equipment is smaller than a preset threshold value or not according to the personnel position information of the constructor, and if so, sending false entry spacing early warning information.
9. An electric power construction video monitoring and alarming system based on image recognition is characterized by comprising
The image acquisition unit is used for acquiring image information of a power construction site in real time;
the data annotation unit is used for performing annotation processing on the acquired image information including the figure information;
the data processing unit is used for carrying out data processing on the marked image information to obtain image data;
the image recognition unit is used for inputting the image data into a trained image recognition model and determining whether the personnel on the electric power construction site have illegal behaviors;
and the warning unit is used for sending a warning prompt signal when the image recognition unit judges that the violation behavior occurs.
10. The image recognition-based power construction video monitoring and warning system of claim 1, wherein the image recognition model is obtained by retraining the pre-trained model according to violation data, and the pre-trained model is a trained neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010980558.6A CN112183265A (en) | 2020-09-17 | 2020-09-17 | Electric power construction video monitoring and alarming method and system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010980558.6A CN112183265A (en) | 2020-09-17 | 2020-09-17 | Electric power construction video monitoring and alarming method and system based on image recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112183265A true CN112183265A (en) | 2021-01-05 |
Family
ID=73920302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010980558.6A Pending CN112183265A (en) | 2020-09-17 | 2020-09-17 | Electric power construction video monitoring and alarming method and system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112183265A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949511A (en) * | 2021-03-08 | 2021-06-11 | 中国建筑一局(集团)有限公司 | Construction site personnel management method based on machine learning and image recognition |
| CN113052125A (en) * | 2021-04-09 | 2021-06-29 | 内蒙古科电数据服务有限公司 | Construction site violation image recognition and alarm method |
| CN113052137A (en) * | 2021-04-25 | 2021-06-29 | 烟台大迈物联科技有限公司 | Identification and judgment method for construction site environment |
| CN113128876A (en) * | 2021-04-22 | 2021-07-16 | 北京房江湖科技有限公司 | Image-based object management method, device and computer-readable storage medium |
| CN113191699A (en) * | 2021-06-11 | 2021-07-30 | 广东电网有限责任公司 | Power distribution construction site safety supervision method |
| CN113269233A (en) * | 2021-04-29 | 2021-08-17 | 国网福建省电力有限公司 | Intelligent monitoring and early warning system and method for subcontracting and subcontracting of building engineering |
| CN113787053A (en) * | 2021-09-15 | 2021-12-14 | 深圳市奥德兰科技有限公司 | Method and device for processing monitoring video |
| CN114040164A (en) * | 2021-11-09 | 2022-02-11 | 南通中安高科电子有限公司 | Personnel operation safety supervision cloud platform based on image video real-time monitoring |
| CN115082861A (en) * | 2022-07-06 | 2022-09-20 | 国网江苏省电力有限公司南通市通州区供电分公司 | Personnel identity and safety violation identification method and system |
| CN115601709A (en) * | 2022-11-07 | 2023-01-13 | 北京万理软件开发有限公司（Cn） | Coal mine employee violation statistical system, method and device and storage medium |
| CN116311541A (en) * | 2023-05-22 | 2023-06-23 | 泰坦(天津)能源技术有限公司 | Intelligent inspection method and system for identifying illegal behaviors of workers |
| CN117557201A (en) * | 2024-01-12 | 2024-02-13 | 国网山东省电力公司菏泽供电公司 | Intelligent warehouse safety management system and method based on artificial intelligence |
| CN117710832A (en) * | 2024-01-04 | 2024-03-15 | 广州智寻科技有限公司 | Intelligent identification method for power grid satellite, unmanned aerial vehicle and video monitoring image |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105745908A (en) * | 2013-11-20 | 2016-07-06 | 皇家飞利浦有限公司 | Method and device for validating user behaviour |
| CN105869066A (en) * | 2016-03-25 | 2016-08-17 | 国网福建省电力有限公司 | Switching operation system and method based on digital image processing and recognition |
| CN107332149A (en) * | 2017-08-15 | 2017-11-07 | 中国能源建设集团江苏省电力设计院有限公司 | A kind of transforming plant main transformer low-pressure side place and its method for arranging |
| CN107369295A (en) * | 2017-08-03 | 2017-11-21 | 国网安徽省电力公司检修公司 | 1000kV extra-high-voltage alternating current station mistaken collision preventing methods |
| CN107742101A (en) * | 2017-10-12 | 2018-02-27 | 珠海长园共创软件技术有限公司 | A kind of site operation personnel verification method |
| CN108805137A (en) * | 2018-04-17 | 2018-11-13 | 平安科技（深圳）有限公司 | Extracting method, device, computer equipment and the storage medium of livestock feature vector |
| CN209357188U (en) * | 2018-12-29 | 2019-09-06 | 国网山东省电力公司泰安供电公司 | Safety warning device device and system are maked an inspection tour by power plant |
| CN110211329A (en) * | 2019-07-01 | 2019-09-06 | 云南电力技术有限责任公司 | A kind of power distribution network personal security protective device |
| CN110674772A (en) * | 2019-09-29 | 2020-01-10 | 国家电网有限公司技术学院分公司 | Intelligent safety control auxiliary system and method for electric power operation site |
| CN110795991A (en) * | 2019-09-11 | 2020-02-14 | 西安科技大学 | Mining locomotive pedestrian detection method based on multi-information fusion |
| CN110807429A (en) * | 2019-10-23 | 2020-02-18 | 西安科技大学 | Construction safety detection method and system based on tiny-YOLOv3 |
| CN110826522A (en) * | 2019-11-15 | 2020-02-21 | 广州大学 | Method and system for monitoring abnormal human behavior, storage medium and monitoring equipment |
| CN111507320A (en) * | 2020-07-01 | 2020-08-07 | 平安国际智慧城市科技股份有限公司 | Detection method, device, equipment and storage medium for kitchen violation behaviors |
-
2020
- 2020-09-17 CN CN202010980558.6A patent/CN112183265A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105745908A (en) * | 2013-11-20 | 2016-07-06 | 皇家飞利浦有限公司 | Method and device for validating user behaviour |
| CN105869066A (en) * | 2016-03-25 | 2016-08-17 | 国网福建省电力有限公司 | Switching operation system and method based on digital image processing and recognition |
| CN107369295A (en) * | 2017-08-03 | 2017-11-21 | 国网安徽省电力公司检修公司 | 1000kV extra-high-voltage alternating current station mistaken collision preventing methods |
| CN107332149A (en) * | 2017-08-15 | 2017-11-07 | 中国能源建设集团江苏省电力设计院有限公司 | A kind of transforming plant main transformer low-pressure side place and its method for arranging |
| CN107742101A (en) * | 2017-10-12 | 2018-02-27 | 珠海长园共创软件技术有限公司 | A kind of site operation personnel verification method |
| CN108805137A (en) * | 2018-04-17 | 2018-11-13 | 平安科技（深圳）有限公司 | Extracting method, device, computer equipment and the storage medium of livestock feature vector |
| CN209357188U (en) * | 2018-12-29 | 2019-09-06 | 国网山东省电力公司泰安供电公司 | Safety warning device device and system are maked an inspection tour by power plant |
| CN110211329A (en) * | 2019-07-01 | 2019-09-06 | 云南电力技术有限责任公司 | A kind of power distribution network personal security protective device |
| CN110795991A (en) * | 2019-09-11 | 2020-02-14 | 西安科技大学 | Mining locomotive pedestrian detection method based on multi-information fusion |
| CN110674772A (en) * | 2019-09-29 | 2020-01-10 | 国家电网有限公司技术学院分公司 | Intelligent safety control auxiliary system and method for electric power operation site |
| CN110807429A (en) * | 2019-10-23 | 2020-02-18 | 西安科技大学 | Construction safety detection method and system based on tiny-YOLOv3 |
| CN110826522A (en) * | 2019-11-15 | 2020-02-21 | 广州大学 | Method and system for monitoring abnormal human behavior, storage medium and monitoring equipment |
| CN111507320A (en) * | 2020-07-01 | 2020-08-07 | 平安国际智慧城市科技股份有限公司 | Detection method, device, equipment and storage medium for kitchen violation behaviors |
Non-Patent Citations (1)
| Title |
|---|
| 王凯等: "基于人工智能的图像识别技术在抽水蓄能电站中的应用研究", 《水电与抽水蓄能》, pages 18 - 20 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112949511A (en) * | 2021-03-08 | 2021-06-11 | 中国建筑一局(集团)有限公司 | Construction site personnel management method based on machine learning and image recognition |
| CN113052125A (en) * | 2021-04-09 | 2021-06-29 | 内蒙古科电数据服务有限公司 | Construction site violation image recognition and alarm method |
| CN113128876A (en) * | 2021-04-22 | 2021-07-16 | 北京房江湖科技有限公司 | Image-based object management method, device and computer-readable storage medium |
| CN113052137A (en) * | 2021-04-25 | 2021-06-29 | 烟台大迈物联科技有限公司 | Identification and judgment method for construction site environment |
| CN113269233A (en) * | 2021-04-29 | 2021-08-17 | 国网福建省电力有限公司 | Intelligent monitoring and early warning system and method for subcontracting and subcontracting of building engineering |
| CN113191699A (en) * | 2021-06-11 | 2021-07-30 | 广东电网有限责任公司 | Power distribution construction site safety supervision method |
| CN113787053A (en) * | 2021-09-15 | 2021-12-14 | 深圳市奥德兰科技有限公司 | Method and device for processing monitoring video |
| CN114040164A (en) * | 2021-11-09 | 2022-02-11 | 南通中安高科电子有限公司 | Personnel operation safety supervision cloud platform based on image video real-time monitoring |
| CN115082861A (en) * | 2022-07-06 | 2022-09-20 | 国网江苏省电力有限公司南通市通州区供电分公司 | Personnel identity and safety violation identification method and system |
| CN115601709A (en) * | 2022-11-07 | 2023-01-13 | 北京万理软件开发有限公司（Cn） | Coal mine employee violation statistical system, method and device and storage medium |
| CN115601709B (en) * | 2022-11-07 | 2023-10-27 | 北京万理软件开发有限公司 | Colliery staff violation statistics system, method, device and storage medium |
| CN116311541A (en) * | 2023-05-22 | 2023-06-23 | 泰坦(天津)能源技术有限公司 | Intelligent inspection method and system for identifying illegal behaviors of workers |
| CN116311541B (en) * | 2023-05-22 | 2023-08-04 | 泰坦(天津)能源技术有限公司 | Intelligent inspection method and system for identifying illegal behaviors of workers |
| CN117710832A (en) * | 2024-01-04 | 2024-03-15 | 广州智寻科技有限公司 | Intelligent identification method for power grid satellite, unmanned aerial vehicle and video monitoring image |
| CN117557201A (en) * | 2024-01-12 | 2024-02-13 | 国网山东省电力公司菏泽供电公司 | Intelligent warehouse safety management system and method based on artificial intelligence |
| CN117557201B (en) * | 2024-01-12 | 2024-04-12 | 国网山东省电力公司菏泽供电公司 | Intelligent warehouse safety management system and method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112183265A (en) | Electric power construction video monitoring and alarming method and system based on image recognition | |
| CN110298278B (en) | Underground parking garage pedestrian and vehicle monitoring method based on artificial intelligence | |
| CN104318732B (en) | Transformer substation field worker monitoring and management system and method based on video analysis and RFID | |
| CN114973140A (en) | Dangerous area personnel intrusion monitoring method and system based on machine vision | |
| CN111127830A (en) | Alarm method, alarm system and readable storage medium based on monitoring equipment | |
| CN112560745B (en) | Method for discriminating personnel on electric power operation site and related device | |
| CN106707939A (en) | Power substation overhaul site intelligent control device | |
| CN116563797B (en) | Monitoring management system for intelligent campus | |
| CN109359712A (en) | Electric operating information dynamic collection monitoring device and its application method | |
| CN112798979A (en) | System and method for detecting state of grounding wire of transformer substation based on deep learning technology | |
| CN113469654B (en) | Multi-level safety control system of transformer substation based on intelligent algorithm fuses | |
| CN115620471A (en) | Image identification security system based on big data screening | |
| CN113191273A (en) | Oil field well site video target detection and identification method and system based on neural network | |
| CN109345787A (en) | A kind of anti-outer damage monitoring and alarming system of the transmission line of electricity based on intelligent image identification technology | |
| CN113743725B (en) | Ascending qualification detection method and system for ascending operators based on edge calculation | |
| CN115496640A (en) | Intelligent safety system of thermal power plant | |
| CN114170644A (en) | Early warning method for pedestrian survival behaviors of police based on video structuring | |
| CN118038021A (en) | Transformer substation operation site foreign matter intrusion detection method based on improvement yolov4 | |
| CN116385925A (en) | Intelligent safety management method and system for production site | |
| CN115953815A (en) | Monitoring method and device for infrastructure site | |
| CN113177453A (en) | Intelligent monitoring system for intelligent community based on image recognition | |
| CN208969695U (en) | Electric operating information dynamic collection monitoring device | |
| CN113297976A (en) | Base station intrusion detection method and system based on deep learning | |
| CN118450087B (en) | Intelligent security monitoring method and system | |
| CN113569709A (en) | Campus security image recognition early warning method based on convolutional neural network |
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 |