CN114241400A - Monitoring method and device of power grid system and computer readable storage medium - Google Patents
Monitoring method and device of power grid system and computer readable storage medium Download PDFInfo
- Publication number
- CN114241400A CN114241400A CN202111276252.3A CN202111276252A CN114241400A CN 114241400 A CN114241400 A CN 114241400A CN 202111276252 A CN202111276252 A CN 202111276252A CN 114241400 A CN114241400 A CN 114241400A
- Authority
- CN
- China
- Prior art keywords
- image
- target object
- site
- candidate regions
- target
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000010276 construction Methods 0.000 claims abstract description 64
- 238000001514 detection method Methods 0.000 claims abstract description 32
- 238000000605 extraction Methods 0.000 claims abstract description 26
- 230000004927 fusion Effects 0.000 claims abstract description 19
- 238000012549 training Methods 0.000 claims description 40
- 238000012545 processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 11
- 238000012806 monitoring device Methods 0.000 claims description 4
- 238000010586 diagram Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 7
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 230000010365 information processing Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001960 triggered effect Effects 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Economics (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
Abstract
本发明公开了一种电网系统的监控方法及其装置、计算机可读存储介质。其中，该方法包括：采集电力施工监控现场内的原始现场图像；对原始现场图像进行特征提取，得到原始现场图像中的特征图像，其中，特征图像包含电力施工监控现场内的目标对象；提取特征图像中的多个候选区域；预测多个候选区域中目标对象的类别；基于预测结果对多个候选区域中的部分候选区域进行窗口融合，得到融合后的目标窗口，其中，部分候选区域包含相同的检测目标；确定目标窗口中目标对象的类别，并基于目标对象的类别对目标对象进行监控。本发明解决了针对相关技术中对于现场施工人员的监控手段单一导致监督结果无法达到预期的技术问题。
The invention discloses a monitoring method of a power grid system, a device thereof, and a computer-readable storage medium. Wherein, the method includes: collecting an original on-site image in a power construction monitoring site; performing feature extraction on the original on-site image to obtain a feature image in the original on-site image, wherein the feature image includes a target object in the power construction monitoring site; extracting features Multiple candidate regions in the image; predict the category of the target object in the multiple candidate regions; perform window fusion on some candidate regions in the multiple candidate regions based on the prediction results to obtain the fused target window, wherein some candidate regions contain the same The detection target is determined; the category of the target object in the target window is determined, and the target object is monitored based on the category of the target object. The invention solves the technical problem in the related art that the monitoring result for the on-site construction personnel cannot reach the expectation due to the single monitoring method.
Description
Technical Field
The invention relates to the field of intelligent monitoring, in particular to a monitoring method and device of a power grid system and a computer readable storage medium.
Background
Among power systems, safety issues of personnel in power construction have always been a major concern. The violation phenomenon that non-constructors enter a construction site always exists, and how to avoid the non-constructors from entering the construction phenomenon is always an urgent problem to be solved. The traditional monitoring method adopts a personnel inspection mode for management, a special safety manager is equipped on a power construction site, and the safety inspection personnel regularly inspects the construction site and supervises whether non-construction personnel enter the construction phenomenon or not. However, the method consumes a lot of time, workers cannot monitor whether non-constructors enter the construction of the workers on the electric power construction site all weather, and limited human resources cannot meet the monitoring requirement of large-scale increase of the power grid. With the continuous development of monitoring videos, the electric power construction site mainly adopts a mode of combining manpower with the monitoring videos to monitor the site working conditions, real-time verification of monitoring camera shooting is realized through manpower, whether non-constructors enter the construction phenomenon or not under the electric power construction environment is observed through the intuitive vision of people, and therefore the personnel safety is monitored and guaranteed. Because the whole process uses manpower to monitor the site operation, the monitoring process becomes complicated, the safe construction of personnel can not be efficiently ensured, the monitoring screen is continuously and uninterruptedly watched, so that the supervisors are more fatigued, and the authenticity of the monitoring result is reduced. Meanwhile, with the enlargement of the video monitoring scale of the power grid, a single video monitoring center often needs to monitor hundreds of monitoring points simultaneously, and the manual monitoring mode is difficult to deal with at the moment. Therefore, an external force intrusion detection method capable of automatically performing image processing is urgently needed so as to automatically complete intrusion target detection and target judgment by using a computer, relieve manual monitoring pressure and improve monitoring efficiency.
Aiming at the problems that the reliability of a mode for monitoring a power grid system in the related technology is low and potential safety hazards exist, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a monitoring method and a monitoring device of a power grid system and a computer readable storage medium, which at least solve the technical problem that a monitoring result cannot reach an expected result due to a single monitoring means for field constructors in the related technology.
According to an aspect of an embodiment of the present invention, there is provided a monitoring method for a power grid system, including: collecting original site images in a power construction monitoring site; performing feature extraction on the original site image to obtain a feature image in the original site image, wherein the feature image comprises a target object in the electric power construction monitoring site; extracting a plurality of candidate regions in the characteristic image; predicting a category of a target object in the plurality of candidate regions; performing window fusion on partial candidate regions in the multiple candidate regions based on the prediction result to obtain a fused target window, wherein the partial candidate regions contain the same detection target; and determining the category of the target object in the target window, and monitoring the target object based on the category of the target object.
Optionally, acquiring an original site image in the power construction monitoring site includes: performing area division on the electric power construction monitoring site to obtain a safe area and an unsafe area in the electric power construction monitoring site, wherein the safe area is an area where the target object can exist, and the unsafe area is an area where the target object cannot exist; triggering an image acquisition device in the unsafe area to acquire the original live image.
Optionally, performing feature extraction on the original live image to obtain a feature image in the original live image, including: inputting the original live image into a target detection model, and processing the original live image by using the target detection model to obtain a feature image in the original live image, wherein the target detection model is obtained by using a plurality of groups of training data through machine learning training, and each group of training data in the plurality of groups of training data comprises: historical original live images and historical feature images corresponding to the historical original live images.
Optionally, extracting a plurality of candidate regions in the feature image includes: inputting the feature images into a regional suggestion network model to obtain the candidate regions based on the regional suggestion network model, wherein the regional suggestion model is obtained by machine learning training using a plurality of sets of training data, and each set of training data in the plurality of sets of training data includes: the image processing device comprises a historical feature image and a historical candidate region corresponding to the historical feature image.
Optionally, each of the plurality of candidate regions includes location information of the candidate region and an attribute score of the candidate region.
Optionally, predicting a category of a target object in the plurality of candidate regions comprises: and predicting a candidate window corresponding to each candidate region based on the attribute score of each candidate region in the candidate regions to obtain the category of the target object in the candidate window corresponding to the candidate regions.
According to another aspect of the embodiments of the present invention, there is provided a monitoring apparatus for a power grid system, including: the acquisition module is used for acquiring original site images in the power construction monitoring site; the first extraction module is used for extracting features of the original site image to obtain a feature image in the original site image, wherein the feature image comprises a target object in the electric power construction monitoring site; the second extraction module is used for extracting a plurality of candidate regions in the characteristic image; a prediction module to predict a category of a target object in the plurality of candidate regions; the fusion module is used for carrying out window fusion on partial candidate regions in the candidate regions based on the prediction result to obtain a fused target window, wherein the partial candidate regions comprise the same detection target; and the determining module is used for determining the category of the target object in the target window and monitoring the target object based on the category of the target object.
Optionally, the acquisition module includes: the dividing unit is used for performing region division on the electric power construction monitoring site to obtain a safe region and an unsafe region in the electric power construction monitoring site, wherein the safe region is a region where the target object can exist, and the unsafe region is a region where the target object cannot exist; and the triggering unit is used for triggering the image acquisition equipment in the non-safety area to acquire the original field image.
Optionally, the first extraction module includes: a first input unit, configured to input the original live image into a target detection model, so as to process the original live image by using the target detection model, so as to obtain a feature image in the original live image, where the target detection model is obtained by machine learning training using multiple sets of training data, and each set of training data in the multiple sets of training data includes: historical original live images and historical feature images corresponding to the historical original live images.
Optionally, the second extraction module includes: a second input unit, configured to input the feature image into a regional suggestion network model to obtain the candidate regions based on the regional suggestion network model, where the regional suggestion model is obtained through machine learning training using multiple sets of training data, and each of the multiple sets of training data includes: the image processing device comprises a historical feature image and a historical candidate region corresponding to the historical feature image.
Optionally, each of the plurality of candidate regions includes location information of the candidate region and an attribute score of the candidate region.
Optionally, the prediction module includes: and the predicting unit is used for predicting the candidate window corresponding to each candidate region based on the attribute score of each candidate region in the candidate regions to obtain the category of the target object in the candidate window corresponding to the candidate regions.
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is executed by a processor, the computer-readable storage medium controls an apparatus to execute the monitoring method for a power grid system according to any one of the above descriptions.
According to another aspect of the embodiment of the present invention, there is further provided a processor, configured to execute a computer program, where the computer program executes to perform the monitoring method for the power grid system according to any one of the above descriptions.
In the embodiment of the invention, the original site image in the power construction monitoring site is collected; extracting features of the original site image to obtain a feature image in the original site image, wherein the feature image comprises a target object in the electric power construction monitoring site; extracting a plurality of candidate regions in the characteristic image; predicting a category of a target object in a plurality of candidate regions; performing window fusion on partial candidate regions in the multiple candidate regions based on the prediction result to obtain a fused target window, wherein the partial candidate regions comprise the same detection target; and determining the category of the target object in the target window, and monitoring the target object based on the category of the target object. By the monitoring method of the power grid system, the purpose of monitoring the target object based on the prediction result of predicting the target object type in the candidate area in the original site characteristic image is achieved, the technical effect of improving the target tracking and monitoring capability of remote monitoring is achieved, and the technical problem that the monitoring result cannot reach the expectation due to the fact that the monitoring means for site constructors in the related technology is single is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
fig. 1 is a flow chart of a monitoring method of a power grid system according to an embodiment of the invention;
FIG. 2 is a diagram illustrating the effect of a candidate region after window fusion according to an embodiment of the present invention;
FIG. 3 is a flow diagram of a job site monitoring system according to an embodiment of the present invention;
fig. 4 is a schematic diagram of a monitoring method of a power grid system according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or 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.
Example 1
In accordance with an embodiment of the present invention, there is provided a method embodiment of a monitoring method for a power grid system, it is noted that the steps illustrated in the flowchart of the drawings may be performed in a computer system such as a set of computer executable instructions, and that while a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than here.
Fig. 1 is a flowchart of a monitoring method of a power grid system according to an embodiment of the present invention, as shown in fig. 1, the method includes the following steps:
and S102, acquiring an original site image in the power construction monitoring site.
Optionally, in the above step, a common camera or a 3D camera is used to monitor the construction site, so as to acquire an original construction image in the site.
And step S104, performing feature extraction on the original site image to obtain a feature image in the original site image, wherein the feature image comprises a target object in the electric power construction monitoring site.
Optionally, in the above step, feature extraction is performed on the original live image acquired in step S102, so as to obtain a feature image in the original live image, where the feature image includes a target object to be monitored (e.g., a constructor, a construction operation device, etc.).
In step S106, a plurality of candidate regions in the feature image are extracted.
Optionally, in the above step, the obtained feature image is input into an RPN (Region pro-potential Network) in a trained detection model, so as to obtain a plurality of candidate regions, which is convenient for further processing of the target object. The RPN is a network layer used for generating a candidate area in machine learning.
Step S108, predicting the category of the target object in the plurality of candidate areas.
Optionally, in the above step, the obtained target category in the candidate region is predicted, and the score is performed after the predicted category is predicted, where a higher score represents a higher category similarity in the machine algorithm recognition.
And step S110, performing window fusion on partial candidate regions in the multiple candidate regions based on the prediction result to obtain a fused target window, wherein the partial candidate regions comprise the same detection target.
Fig. 2 is a schematic diagram of the effect of candidate regions after window fusion according to an embodiment of the present invention, and as shown in fig. 2, the left diagram is a feature image of 4 candidate regions with the highest score in the constructor category candidate regions obtained through prediction of the image, and a right diagram, that is, an effect diagram after window fusion, can be obtained after processing by a predetermined algorithm. Note that, a Non-maximum suppression algorithm (NMS) is commonly used as the predetermined algorithm.
And step S112, determining the category of the target object in the target window, and monitoring the target object based on the category of the target object.
As can be seen from the above, in the embodiment of the present invention, the original site image in the power construction monitoring site may be collected first; then, feature extraction is carried out on the original site image to obtain a feature image in the original site image, wherein the feature image comprises a target object in the power construction monitoring site; then extracting a plurality of candidate regions in the characteristic image; then predicting the category of the target object in the candidate areas; then, window fusion is carried out on partial candidate areas in the candidate areas based on the prediction result to obtain a fused target window, wherein the partial candidate areas comprise the same detection target; and finally, determining the category of the target object in the target window, and monitoring the target object based on the category of the target object. By the monitoring method of the power grid system, the purpose of monitoring the target object based on the prediction result of predicting the target object type in the candidate area in the original site characteristic image is achieved, the technical effect of improving the target tracking and monitoring capability of remote monitoring is achieved, and the technical problem that the monitoring result cannot reach the expectation due to the fact that the monitoring means for site constructors in the related technology is single is solved.
As an alternative embodiment, the method for collecting original site images in the power construction monitoring site comprises the following steps: the method comprises the steps of performing region division on an electric power construction monitoring site to obtain a safe region and an unsafe region in the electric power construction monitoring site, wherein the safe region is a region where a target object can exist, and the unsafe region is a region where the target object cannot exist; triggering an image acquisition device in the non-safety area to acquire the original live image.
In the above optional embodiment, the collected images in the construction site are clustered and classified for the safe area and the unsafe area, and in the process of monitoring the target object, if the target object is always in the safe area, a safety alarm is not triggered; if the target object moves into the non-safety area, a safety alarm is triggered to prompt the target object to return to the safety area.
Furthermore, in the monitoring process, the types of the target objects may be divided, and after the regions are divided, the permissions of different portions are set, the permissions of the regions in which the target objects of different levels can move are different, and if the target objects move to a region higher than their permissions, operations such as triggering an alarm may also be performed.
As an alternative embodiment, performing feature extraction on the original live image to obtain a feature image in the original live image includes: inputting an original field image into a target detection model, processing the original field image by using the target detection model to obtain a characteristic image in the original field image, wherein the target detection model is obtained by using a plurality of groups of training data through machine learning training, and each group of training data in the plurality of groups of training data comprises: historical raw live images and historical feature images corresponding to the historical raw live images.
In the above-mentioned alternative embodiment, the original field image (e.g. the construction field image) is first input into the target detection model, and the target detection model extracts the feature information in the original field image, for example, extracts the target object therein, such as the constructor.
As an alternative embodiment, extracting a plurality of candidate regions in a feature image includes: inputting the feature images into a regional suggestion network model to obtain a plurality of candidate regions based on the regional suggestion network model, wherein the regional suggestion model is obtained by machine learning training using a plurality of sets of training data, and each set of training data in the plurality of sets of training data comprises: the image processing apparatus includes a history feature image and a history candidate region corresponding to the history feature image.
In the above optional embodiment, the feature image is input into the region suggestion network model to obtain a plurality of candidate regions, where the region suggestion model is used to perform frame selection on a plurality of features in the feature image by using a candidate frame and then perform more accurate candidate frame determination by using a training model.
As an alternative embodiment, each of the plurality of candidate regions includes the position information of the candidate region and the attribute score of the candidate region.
In the above alternative embodiment, each candidate region includes the position information of the current central point, the target category selected by the frame, and the corresponding category similarity score (i.e., attribute score), so that the target detection effect can be visually reflected.
As an alternative embodiment, predicting the category of the target object in the plurality of candidate regions includes: and predicting the candidate window corresponding to each candidate region based on the attribute score of each candidate region in the candidate regions to obtain the category of the target object in the candidate window corresponding to the candidate regions.
Fig. 3 is a flowchart of a construction site monitoring system according to an embodiment of the present invention, and as shown in fig. 3, in the embodiment of the present invention, after a site image of an electric power construction monitoring environment is input into a target detection model, features are extracted through a convolutional neural network, and then a set of candidate regions is obtained through a region suggestion network, where each candidate region includes position information of the candidate region and a score indicating whether the candidate region belongs to a foreground or a background. Then, the candidate window of the suspected target needs to be further predicted according to the category score of the candidate window, whether the candidate window belongs to a fence, a tripod, a signboard or a background is judged, and under the condition that the position information of each candidate area and the category score of the candidate area are known, the position information of the candidate area on the feature map can be obtained through mapping according to the position information of the candidate area on the original image and the position information of the candidate area on the feature map through the position mapping relation of the original image and the feature map, and then the feature map of the candidate area is obtained.
As can be seen from the above, in the embodiment of the present invention, the construction site image acquisition, the image processing, the feature extraction, and the classification of the target object are performed on the electric power construction site, the intelligent image processing technology is adopted to design the electric power construction site video monitoring system, the target tracking and identification on the electric power construction site are realized under the complex environmental condition, the remote monitoring and the real-time target tracking and detecting capability on the electric power construction site are improved, and the design of the electric power construction site video monitoring system is based on the image identification and the information processing, and the integrated information processing technology is combined to perform the target tracking and detecting of the remote monitoring on the electric power construction site, so that the positioning and detecting capability on the target is improved.
Example 2
According to another aspect of the embodiment of the present invention, there is also provided a monitoring apparatus for a power grid system, and fig. 4 is a schematic diagram of a monitoring method for a power grid system according to the embodiment of the present invention, as shown in fig. 4, including: an acquisition module 41, a first extraction module 43, a second extraction module 45, a prediction module 47, a fusion module 49, and a determination module 411. The following describes a monitoring device of the grid system.
And the acquisition module 41 is used for acquiring original site images in the power construction monitoring site.
The first extraction module 43 is configured to perform feature extraction on the original site image to obtain a feature image in the original site image, where the feature image includes a target object in the electric power construction monitoring site.
And a second extraction module 45, configured to extract a plurality of candidate regions in the feature image.
And the prediction module 47 is used for predicting the category of the target object in the candidate areas.
And a fusion module 49, configured to perform window fusion on a part of the candidate regions in the multiple candidate regions based on the prediction result to obtain a fused target window, where the part of the candidate regions includes the same detection target.
The determining module 411 is configured to determine a category of the target object in the target window, and monitor the target object based on the category of the target object.
It should be noted here that the above-mentioned acquisition module 41, first extraction module 43, second extraction module 45, prediction module 47, fusion module 49 and determination module 411 correspond to steps S102 to S112 in embodiment 1, and the above-mentioned modules are the same as the examples and application scenarios realized by the corresponding steps, but are not limited to the contents disclosed in embodiment 1. It should be noted that the modules described above as part of an apparatus may be implemented in a computer system such as a set of computer-executable instructions.
As can be seen from the above, in the embodiment of the present invention, the acquisition module 41 may be first used to acquire the original site image in the power construction monitoring site; then, a first extraction module 43 is used for extracting features of the original site image to obtain a feature image in the original site image, wherein the feature image comprises a target object in the electric power construction monitoring site; then, a second extraction module 45 is used for extracting a plurality of candidate regions in the characteristic image; then, the prediction module 47 is used for predicting the types of the target objects in the candidate areas; then, a fusion module 49 is used for carrying out window fusion on partial candidate regions in the multiple candidate regions based on the prediction result to obtain a fused target window, wherein the partial candidate regions comprise the same detection target; finally, the determining module 411 is used to determine the category of the target object in the target window and monitor the target object based on the category of the target object. The monitoring device of the power grid system achieves the purpose of monitoring the target object based on the prediction result of predicting the target object type in the candidate area in the original site characteristic image, thereby achieving the technical effect of improving the target tracking and monitoring capability of remote monitoring, and further solving the technical problem that the monitoring result cannot reach the expectation due to single monitoring means for site constructors in the related technology.
Optionally, the acquisition module comprises: the power construction monitoring system comprises a dividing unit, a monitoring unit and a monitoring unit, wherein the dividing unit is used for carrying out region division on a power construction monitoring site to obtain a safe region and an unsafe region in the power construction monitoring site, the safe region is a region where a target object can exist, and the unsafe region is a region where the target object cannot exist; and the triggering unit is used for triggering the image acquisition equipment in the non-safety area to acquire the original field image.
Optionally, the first extraction module includes: the system comprises a first input unit, a second input unit and a third input unit, wherein the first input unit is used for inputting an original field image into a target detection model so as to process the original field image by using the target detection model to obtain a feature image in the original field image, the target detection model is obtained by using a plurality of groups of training data through machine learning training, and each group of training data in the plurality of groups of training data comprises: historical raw live images and historical feature images corresponding to the historical raw live images.
Optionally, the second extraction module includes: a second input unit, configured to input the feature image into a regional suggestion network model to obtain a plurality of candidate regions based on the regional suggestion network model, where the regional suggestion model is obtained through machine learning training using a plurality of sets of training data, and each set of training data in the plurality of sets of training data includes: the image processing apparatus includes a history feature image and a history candidate region corresponding to the history feature image.
Optionally, each of the plurality of candidate regions includes location information of the candidate region and an attribute score of the candidate region.
Optionally, the prediction module comprises: and the predicting unit is used for predicting the candidate window corresponding to each candidate region based on the attribute score of each candidate region in the candidate regions to obtain the category of the target object in the candidate window corresponding to the candidate regions.
Example 3
According to another aspect of the embodiments of the present invention, there is also provided a computer-readable storage medium including a stored computer program, wherein when the computer program is executed by a processor, the apparatus where the computer-readable storage medium is located is controlled to execute the monitoring method of the power grid system of any one of the above.
Example 4
According to another aspect of the embodiments of the present invention, there is also provided a processor, configured to execute a computer program, where the computer program executes to perform the monitoring method for a power grid system according to any one of the foregoing methods.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (10)
1. A method for monitoring a power grid system, comprising:
collecting original site images in a power construction monitoring site;
performing feature extraction on the original site image to obtain a feature image in the original site image, wherein the feature image comprises a target object in the electric power construction monitoring site;
extracting a plurality of candidate regions in the characteristic image;
predicting a category of a target object in the plurality of candidate regions;
performing window fusion on partial candidate regions in the multiple candidate regions based on the prediction result to obtain a fused target window, wherein the partial candidate regions contain the same detection target;
and determining the category of the target object in the target window, and monitoring the target object based on the category of the target object.
2. The method of claim 1, wherein collecting raw site images within a power construction monitoring site comprises:
performing area division on the electric power construction monitoring site to obtain a safe area and an unsafe area in the electric power construction monitoring site, wherein the safe area is an area where the target object can exist, and the unsafe area is an area where the target object cannot exist;
triggering an image acquisition device in the unsafe area to acquire the original live image.
3. The method of claim 1, wherein extracting features from the original live image to obtain a feature image in the original live image comprises:
inputting the original live image into a target detection model, and processing the original live image by using the target detection model to obtain a feature image in the original live image, wherein the target detection model is obtained by using a plurality of groups of training data through machine learning training, and each group of training data in the plurality of groups of training data comprises: historical original live images and historical feature images corresponding to the historical original live images.
4. The method of claim 1, wherein extracting a plurality of candidate regions in the feature image comprises:
inputting the feature images into a regional suggestion network model to obtain the candidate regions based on the regional suggestion network model, wherein the regional suggestion model is obtained by machine learning training using a plurality of sets of training data, and each set of training data in the plurality of sets of training data includes: the image processing device comprises a historical feature image and a historical candidate region corresponding to the historical feature image.
5. The method of claim 1 or 4, wherein each of the candidate regions comprises location information of the candidate region and an attribute score of the candidate region.
6. The method of claim 5, wherein predicting the class of the target object in the plurality of candidate regions comprises:
and predicting a candidate window corresponding to each candidate region based on the attribute score of each candidate region in the candidate regions to obtain the category of the target object in the candidate window corresponding to the candidate regions.
7. A monitoring device for a power grid system, comprising:
the acquisition module is used for acquiring original site images in the power construction monitoring site;
the first extraction module is used for extracting features of the original site image to obtain a feature image in the original site image, wherein the feature image comprises a target object in the electric power construction monitoring site;
the second extraction module is used for extracting a plurality of candidate regions in the characteristic image;
a prediction module to predict a category of a target object in the plurality of candidate regions;
the fusion module is used for carrying out window fusion on partial candidate regions in the candidate regions based on the prediction result to obtain a fused target window, wherein the partial candidate regions comprise the same detection target;
and the determining module is used for determining the category of the target object in the target window and monitoring the target object based on the category of the target object.
8. The apparatus of claim 7, wherein the acquisition module comprises:
the dividing unit is used for performing region division on the electric power construction monitoring site to obtain a safe region and an unsafe region in the electric power construction monitoring site, wherein the safe region is a region where the target object can exist, and the unsafe region is a region where the target object cannot exist;
and the triggering unit is used for triggering the image acquisition equipment in the non-safety area to acquire the original field image.
9. A computer-readable storage medium, characterized in that the computer-readable storage medium comprises a stored computer program, wherein when the computer program is executed by a processor, the computer-readable storage medium controls an apparatus to execute the method for monitoring a power grid system according to any one of the preceding claims 1 to 6.
10. A processor for executing a computer program, wherein the computer program executes to perform the method for monitoring a power grid system according to any one of the preceding claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111276252.3A CN114241400A (en) | 2021-10-29 | 2021-10-29 | Monitoring method and device of power grid system and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111276252.3A CN114241400A (en) | 2021-10-29 | 2021-10-29 | Monitoring method and device of power grid system and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114241400A true CN114241400A (en) | 2022-03-25 |
Family
ID=80743481
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111276252.3A Pending CN114241400A (en) | 2021-10-29 | 2021-10-29 | Monitoring method and device of power grid system and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114241400A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116129350A (en) * | 2022-12-26 | 2023-05-16 | 广东高士德电子科技有限公司 | Intelligent monitoring method, device, equipment and medium for safety operation of data center |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140266698A1 (en) * | 2013-03-13 | 2014-09-18 | Qualcomm Incorporated | Systems and methods for monitoring a proximity of a personal item and automatically assigning safe and unsafe zones |
| CN110717456A (en) * | 2019-10-10 | 2020-01-21 | 北京百度网讯科技有限公司 | Object monitoring method, device, system, electronic equipment and 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 |
| CN112818758A (en) * | 2021-01-14 | 2021-05-18 | 广州穗能通能源科技有限责任公司 | Monitoring method, system and device for electric power construction site and storage medium |
-
2021
- 2021-10-29 CN CN202111276252.3A patent/CN114241400A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140266698A1 (en) * | 2013-03-13 | 2014-09-18 | Qualcomm Incorporated | Systems and methods for monitoring a proximity of a personal item and automatically assigning safe and unsafe zones |
| CN110717456A (en) * | 2019-10-10 | 2020-01-21 | 北京百度网讯科技有限公司 | Object monitoring method, device, system, electronic equipment and 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 |
| CN112818758A (en) * | 2021-01-14 | 2021-05-18 | 广州穗能通能源科技有限责任公司 | Monitoring method, system and device for electric power construction site and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 冯连强 等: "复杂工业现场智能监控系统中的人体检测方法", 《重型机械》, no. 05, 20 September 2013 (2013-09-20), pages 6 - 10 * |
| 高杨 等: "基于多层特征融合的小目标检测算法", 《计算机工程与设计》, no. 07, 16 July 2020 (2020-07-16), pages 1905 - 1909 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116129350A (en) * | 2022-12-26 | 2023-05-16 | 广东高士德电子科技有限公司 | Intelligent monitoring method, device, equipment and medium for safety operation of data center |
| CN116129350B (en) * | 2022-12-26 | 2024-01-16 | 广东高士德电子科技有限公司 | Intelligent monitoring method, device, equipment and medium for safety operation of data center |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116777713B (en) | Intelligent park safety management method and system based on data analysis | |
| WO2022160413A1 (en) | Electric power production anomaly monitoring method and apparatus, and computer device and storage medium | |
| CN110650316A (en) | Intelligent patrol and early warning processing method and device, electronic equipment and storage medium | |
| CN109063612A (en) | City intelligent red line management method and machine readable storage medium | |
| CN109298785A (en) | A man-machine joint control system and method for monitoring equipment | |
| CN103108159A (en) | Electric power intelligent video analyzing and monitoring system and method | |
| RU2713876C1 (en) | Method and system for detecting alarm events when interacting with self-service device | |
| CN115002414A (en) | Monitoring method, monitoring device, server and computer readable storage medium | |
| CN115099724A (en) | Monitoring and early warning method, device and equipment for construction scene and storage medium | |
| CN112528825A (en) | Station passenger recruitment service method based on image recognition | |
| CN115294528A (en) | Pedestrian safety monitoring method and device | |
| CN114236309A (en) | Transmission and transformation fault determination method | |
| CN111860187A (en) | High-precision worn mask identification method and system | |
| CN112381435A (en) | Gridding directional pushing management method for dynamic risk in hydropower station operation process | |
| US20230360402A1 (en) | Video-based public safety incident prediction system and method therefor | |
| CN114241400A (en) | Monitoring method and device of power grid system and computer readable storage medium | |
| CN106408000A (en) | Method and device for intelligent detection on personnel safety helmet | |
| CN113505704A (en) | Image recognition personnel safety detection method, system, equipment and storage medium | |
| CN116682162B (en) | A robot personnel detection method based on real-time video stream | |
| CN117456601A (en) | Tower crane safety state early warning method and system | |
| CN116886874A (en) | Ecological garden security monitoring and early warning data acquisition method and system | |
| CN116798074A (en) | Stranger identification method and device and electronic equipment | |
| Ma et al. | Scene understanding method utilizing global visual and spatial interaction features for safety production | |
| CN115546892A (en) | Method, device and storage medium for identifying operation violation | |
| CN111277745B (en) | Target person tracking methods, devices, electronic equipment and readable storage media |
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 |