CN111753712A - Method, system and equipment for monitoring safety of power production personnel - Google Patents
Method, system and equipment for monitoring safety of power production personnel Download PDFInfo
- Publication number
- CN111753712A CN111753712A CN202010576009.2A CN202010576009A CN111753712A CN 111753712 A CN111753712 A CN 111753712A CN 202010576009 A CN202010576009 A CN 202010576009A CN 111753712 A CN111753712 A CN 111753712A
- Authority
- CN
- China
- Prior art keywords
- dimensional
- target
- personnel
- image
- equipment
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 38
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012544 monitoring process Methods 0.000 title claims abstract description 32
- 239000011159 matrix material Substances 0.000 claims description 37
- 238000004364 calculation method Methods 0.000 claims description 29
- 238000001514 detection method Methods 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 15
- 230000005540 biological transmission Effects 0.000 claims description 13
- 230000010365 information processing Effects 0.000 claims description 11
- 238000010248 power generation Methods 0.000 claims description 11
- 230000009466 transformation Effects 0.000 claims description 11
- 230000006870 function Effects 0.000 claims description 8
- 230000003416 augmentation Effects 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 2
- 239000002994 raw material Substances 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 13
- 238000012545 processing Methods 0.000 description 5
- 230000005284 excitation Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013024 troubleshooting Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30244—Camera pose
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Multimedia (AREA)
- Biomedical Technology (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Emergency Alarm Devices (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a method, a system, equipment and a storage medium for monitoring the safety of power production personnel, which are used for identifying and positioning the coordinates of a measured object in a two-dimensional image through an image; further identifying three-dimensional models of personnel, equipment and environment by calculating the depth image; and finally, judging whether the maintainers exceed the safe distance and giving early warning in time through image recognition and safe distance analysis, and effectively improving the safety control level of the power grid enterprise on the staff in the production service scenes such as power infrastructure, operation and inspection and the like.
Description
Technical Field
The invention belongs to the technical field of electric power safety supervision, and relates to a method, a system and equipment for monitoring safety of electric power production personnel.
Background
Under the production service scenes of infrastructure, operation and inspection and the like in a power grid enterprise, workers need to go to a line and a transformer substation for completing construction tasks or timely troubleshooting hidden dangers to execute, but at present, the phenomena of low safety supervision level and extensive operation still exist in an electric power production field, and meanwhile, the problems of post management, unqualified operation, randomness and the like exist, so that the production services of infrastructure, operation and inspection and the like lack effective control over the safety of front-line workers, and the problems of over-range operation, mistaken entering of electrified intervals and the like exist objectively.
At present, the position information of the power energy enterprises to the personnel of the production operation of the same line is still mainly judged by background monitoring personnel through vision, and the position information of the personnel is collected by a small part of enterprises through methods such as a GPS/BDS positioning system, FRID and camera linkage positioning and the like. However, the above techniques have certain disadvantages: the distance between a person and equipment is difficult to accurately judge due to the fact that the depth cannot be measured in the visual positioning; the positioning of the GPS/BDS has meter-level errors and involves the capital investment of the portable equipment; the antenna in the RFID carries out distance alarm by feeding back external microwave excitation, however, the strength and the emission angle of an excitation signal influence the feedback of the RFID, thereby easily causing misjudgment and missed judgment.
Disclosure of Invention
The invention provides a method, a system and equipment for monitoring the safety of power production personnel, which are used for solving the problems in the prior art and improving the safety control level of power grid enterprises in China on the staff in the production service scenes such as power infrastructure, operation and inspection and the like from two aspects: firstly, realizing dynamic monitoring of three-dimensional space information of people and equipment; and secondly, diagnosis of abnormal behaviors of the maintainers is realized.
The invention provides a method for monitoring the safety of electric power production personnel, which is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
acquiring two-dimensional images of power production personnel, a power transmission line and power transformation equipment;
extracting target personnel and target equipment from the acquired two-dimensional image according to the target detection model;
respectively obtaining three-dimensional depth coordinates of the extracted target personnel and the extracted target equipment by using the parameter matrix, and respectively calculating three-dimensional frames of the target personnel and the target equipment by using the obtained three-dimensional depth coordinates;
and calculating the minimum Euclidean distance between the target personnel and the three-dimensional frame of the target equipment, comparing the obtained minimum Euclidean distance with a safety threshold value, and determining whether the power generation personnel are safe or not according to the comparison result.
Preferably, the two-dimensional image is acquired through the multi-view camera, specifically including calibrating an external parameter matrix of the multi-view camera, and calculating to obtain an internal parameter matrix of the multi-view camera according to the calibrated external parameter matrix; the external parameter matrix calibration process comprises calibration plate shooting, multi-camera external parameter estimation, multi-camera 3D point cloud acquisition and multi-camera external parameter calculation.
Further, the multi-view camera external parameter calculation adopts the following matrix:
in the formula (X)c,Yc,Zc) The coordinate of a certain point under a multi-view camera coordinate system; (X)w,Yw,Zw) Is the coordinate of the point in the external coordinate system, R3x3And T3x1Respectively are a rotation matrix and a translation vector from an external coordinate system to a multi-view camera coordinate system.
Further, the following formula is adopted for calculating the internal parameter matrix according to the calibrated external parameter matrix:
in the formula (I), the compound is shown in the specification,s is a proportionality coefficient and is,
is a two-dimensional augmentation vector, K is an internal parameter matrix, R and T are external parameter matrices,
is a three-dimensional augmentation vector.
Further, the construction process of the target detection model comprises the following steps:
s201, acquiring position images of electric power production personnel, a power transmission line and power transformation equipment by adopting a multi-view camera; marking the acquired position image to form an image database;
s202, inputting two-dimensional images in an image database, extracting targets of personnel and equipment by adopting a convolutional neural network, acquiring image features under multiple scales through a convolutional layer, further extracting the acquired image features by combining a pooling layer, and finally obtaining a depth image of the target through an activation function to realize the detection of the target.
Further, according to the inside and outside parameter matrix of the multi-view camera, the coordinates (x) in the color map are utilized through the alignment of the color map and the depth image1,y1)、(x2,y2) And obtaining the three-dimensional depth coordinate of the target object through the mapping relation between the three-dimensional depth coordinate and the coordinate (x, y, z) in the depth image.
Preferably, the minimum euclidean distance is calculated using the following equation:
wherein (X)1Y1Z1) Is the three-dimensional frame coordinate of the operator; (X)2Y2Z2) Is the three-dimensional frame coordinate of the detected power equipment.
Preferably, when the comparison result shows that the minimum Euclidean distance is smaller than the safety threshold, the target person is judged to mistakenly enter the electrified interval, the fact that the power generation personnel are unsafe is determined, alarm information is sent out, and the alarm information is converted into text data to be sent to a data background of the power enterprise.
A power production personnel safety monitoring system comprises an image acquisition module, an image identification calculation module, a depth information processing module, a three-dimensional calculation module and a comparison monitoring module;
the image acquisition module is used for acquiring two-dimensional images of electric power production personnel, the power transmission line and the power transformation equipment; sending the acquired two-dimensional image to an image recognition and calculation module for target detection;
the image identification calculation module is used for extracting target personnel and target equipment from the acquired two-dimensional image according to the target detection model; identifying target personnel and target equipment, and sending the identified target personnel and target equipment to a depth information processing module;
the depth information processing module is used for respectively obtaining three-dimensional depth coordinates by using the extracted target personnel and the extracted target equipment through a parameter matrix;
the three-dimensional calculation module is used for calculating three-dimensional frames of the target personnel and the target equipment respectively by using the obtained three-dimensional depth coordinates;
and the comparison monitoring module is used for calculating the minimum Euclidean distance between the target personnel and the three-dimensional frame of the target equipment, comparing the obtained minimum Euclidean distance with a safety threshold value, and determining whether the power generation personnel are safe or not according to the comparison result.
An electrical power production personnel safety monitoring apparatus comprising a memory for storing a computer program; and the processor is used for realizing any one of the above-mentioned electric power production personnel safety monitoring methods when executing the computer program.
According to the method, the system, the equipment and the storage medium for monitoring the safety of the power production personnel, disclosed by the invention, the visible light image data of the personnel, the equipment and the environment in a power production service scene is acquired based on the multi-view imaging sensing terminal; the coordinates of the measured object in the two-dimensional image are identified and positioned through the image; further identifying three-dimensional models of personnel, equipment and environment by calculating a depth image (also called a distance image); and finally, judging whether the maintainers exceed the safe distance and giving early warning in time through image recognition and safe distance analysis, and effectively improving the safety control level of the power grid enterprise on the staff in the production service scenes such as power infrastructure, operation and inspection and the like.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic diagram of a power production personnel safety monitoring method of the present invention;
FIG. 2 is a schematic structural diagram of a power generation personnel safety monitoring system of the present invention;
FIG. 3 is a block diagram of the electrical power production personnel safety monitoring system of the present invention;
FIG. 4 is a schematic diagram of a human body position three-dimensional calculation module of the power generation personnel safety monitoring system of the present invention;
fig. 5 is a schematic diagram of a safety distance early warning module of the power generation personnel safety monitoring system of the invention.
In the figure, 1, a multi-view camera, 2, an electric power production worker, 3, an electric power facility, 4, a depth image processing and early warning analysis terminal, C1, a multi-view vision sensing module, C2, an image recognition and calculation module, C3, a depth information processing module, C4, a human body position three-dimensional calculation module, C41, a human body three-dimensional frame calculation module, C42, an electric power equipment three-dimensional frame calculation module, C5, a safety distance early warning module, C51, an equipment type recognition module, C52, a distance early warning module, C53 and an information transmission module are arranged.
Detailed Description
The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The following detailed description is exemplary in nature and is intended to provide further details of the invention. Unless otherwise defined, all technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention.
As shown in fig. 1, the present invention provides a method for monitoring safety of power generation personnel, comprising the following steps:
s1, acquiring two-dimensional images of electric power production personnel, the power transmission line and the power transformation equipment in real time by using the multi-view camera, and sending the acquired two-dimensional images to a target detection model for target detection;
before the multi-view camera acquires the two-dimensional image, firstly calibrating an external parameter matrix of the multi-view camera, and calculating to obtain an internal parameter matrix according to the calibrated external parameter matrix; the external parameter calibration process comprises calibration plate shooting, multi-camera external parameter estimation, multi-camera 3D point cloud acquisition and multi-camera external parameter calculation.
Preferably, the following matrix is adopted to perform the multi-view camera external parameter calculation:
in the formula (X)c,Yc,Zc) The coordinate of a certain point under a multi-view camera coordinate system; (X)w,Yw,Zw) Is the coordinate of the point in the external coordinate system, R3x3And T3x1The method is characterized in that the method comprises the steps of respectively obtaining a rotation matrix and a translation vector from an external coordinate system to a coordinate system of the multi-view camera, namely an external parameter matrix of the multi-view camera.
Preferably, the following formula 1 is adopted to calculate the internal parameter matrix according to the calibrated external parameter matrix:
in the formula, s is a proportionality coefficient,
is a two-dimensional augmentation vector, K is an internal parameter matrix, R and TIn the form of a matrix of external parameters,
is a three-dimensional augmentation vector.
S2, detecting and extracting target personnel and target equipment from the two-dimensional image by the target detection model, respectively obtaining three-dimensional depth coordinates by the extracted target personnel and the extracted target equipment by using the parameter matrix, and respectively calculating three-dimensional frames of the target personnel and the target equipment by using the obtained three-dimensional depth coordinates;
in S2, the target detection model needs to be constructed in advance, and the construction process includes the following steps:
s201, acquiring position images of electric power production personnel, a power transmission line and power transformation equipment by adopting a multi-view camera; marking the acquired position image to form an image database;
s202, inputting two-dimensional images in an image database, extracting targets of personnel and equipment by adopting a convolutional neural network, acquiring image features under multiple scales through a convolutional layer, further extracting the acquired image features by combining a pooling layer, and finally obtaining a depth image of the target through an activation function to realize the detection of the target.
In an embodiment of the present invention, preferably, in S2, after the multi-view camera internal and external parameter matrix is obtained, the coordinates (x) in the color map are utilized by aligning the color map with the depth image1,y1)、(x2,y2) And obtaining the three-dimensional depth coordinate of the target object through the mapping relation between the three-dimensional depth coordinate and the coordinate (x, y, z) in the depth image.
S3, calculating the minimum Euclidean distance between the target person and the three-dimensional frame of the target device, comparing the obtained minimum Euclidean distance with a safety threshold value, and when the minimum Euclidean distance is smaller than the safety threshold value, judging that the target person mistakenly enters the electrified interval, and sending alarm information.
The minimum euclidean distance is calculated using the following equation 2:
wherein (X)1Y1Z1) Is the three-dimensional frame coordinate of the operator; (X)2Y2Z2) Is the three-dimensional frame coordinate of the detected power equipment.
In S3, when the alarm message is issued, the alarm message is converted into text data and sent to the data back-end of the power enterprise.
The invention provides a safety monitoring system for power production personnel, which is used for realizing the steps of the method and comprises a multi-view vision sensing module, an image recognition and calculation module, a depth information processing module, a human body position three-dimensional calculation module and a safety distance early warning module;
the multi-view vision sensing module C1 is used for acquiring two-dimensional images of power production personnel, power transmission lines and power transformation equipment in real time and sending the acquired two-dimensional images to the image recognition and calculation module for target detection; the multi-view vision sensing module C1 is used for adjusting the included angle of the shot target and calibrating the coordinates of the shot target, so that the three-dimensional depth information acquisition function of recording personnel images in multiple angles and supporting the power transmission line and the power transformation equipment is realized;
the image recognition computing module C2 is used for carrying out target recognition on the received two-dimensional image and sending the recognized two-dimensional image to the depth information processing module; the method comprises the steps of carrying out target identification on a two-dimensional image, and extracting three-dimensional coordinates of a target in a support three-dimensional depth image;
the depth information processing module C3 is used for respectively obtaining three-dimensional depth coordinates by using the extracted target personnel and target equipment through a parameter matrix; and acquiring three-dimensional depth information of the supported detected power transmission line and the power transformation equipment.
The human body position three-dimensional calculation module C4 comprises a human body three-dimensional frame calculation module C41 and an electric power equipment three-dimensional frame calculation module C42; the human body three-dimensional frame calculation module C41 calculates the human body three-dimensional frame in the depth image by using the relationship between the coordinates of several key parts of the human body and the internal and external parameters of the multi-view camera; the power equipment three-dimensional frame calculation module C42 calculates the power equipment three-dimensional frame in the depth image by using the relationship between the position coordinates of the power equipment and the internal and external parameters of the multi-view camera.
And the safe distance early warning module C5 is used for calculating the minimum Euclidean distance between the target personnel and the three-dimensional frame of the target equipment, comparing the obtained minimum Euclidean distance with a safe threshold value, and when the minimum Euclidean distance is smaller than the safe threshold value, judging that the target personnel mistakenly enters the electrified interval and sending out alarm information. The method specifically comprises the following steps: the device type identification module C51, the distance early warning module C52 and the information transmission module C53; the equipment type identification module C51 acquires information of each equipment in the area where the maintainers are located through the image identification technology of the depth information processing module, and provides corresponding safe distance for preparing early warning; the distance early warning module C52 judges whether each part of the three-dimensional personnel model exceeds a safe distance and gives an early warning in time; the information transfer module C53 returns the warning information to the data backend.
The invention also provides electric power production personnel safety monitoring equipment, which comprises a memory, a monitoring module and a monitoring module, wherein the memory is used for storing a computer program; a processor for implementing the steps of the above-mentioned method for monitoring safety of power generation personnel when executing the computer program.
The invention also provides a computer storage medium, which stores a computer program, and the computer program realizes the steps of the above method for monitoring the safety of the power generation personnel when being executed by a processor.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Claims (10)
1. A safety monitoring method for power production personnel is characterized by comprising the following steps: comprises the steps of (a) preparing a mixture of a plurality of raw materials,
acquiring two-dimensional images of power production personnel, a power transmission line and power transformation equipment;
extracting target personnel and target equipment from the acquired two-dimensional image according to the target detection model;
respectively obtaining three-dimensional depth coordinates of the extracted target personnel and the extracted target equipment by using the parameter matrix, and respectively calculating three-dimensional frames of the target personnel and the target equipment by using the obtained three-dimensional depth coordinates;
and calculating the minimum Euclidean distance between the target personnel and the three-dimensional frame of the target equipment, comparing the obtained minimum Euclidean distance with a safety threshold value, and determining whether the power generation personnel are safe or not according to the comparison result.
2. The method of claim 1, wherein: acquiring a two-dimensional image through a multi-view camera, specifically, calibrating an external parameter matrix of the multi-view camera, and calculating to obtain an internal parameter matrix of the multi-view camera according to the calibrated external parameter matrix; the external parameter matrix calibration process comprises calibration plate shooting, multi-camera external parameter estimation, multi-camera 3D point cloud acquisition and multi-camera external parameter calculation.
3. The method of claim 2, wherein: the multi-view camera external parameter calculation adopts the following matrix:
in the formula (X)c,Yc,Zc) The coordinate of a certain point under a multi-view camera coordinate system; (X)w,Yw,Zw) Is the coordinate of the point in the external coordinate system, R3x3And T3x1Respectively are a rotation matrix and a translation vector from an external coordinate system to a multi-view camera coordinate system.
4. The method of claim 2, wherein: calculating an internal parameter matrix according to the calibrated external parameter matrix by adopting the following formula:
in the formula, s is a proportionality coefficient,
is a two-dimensional augmentation vector, K is an internal parameter matrix, R and T are external parameter matrices,
is a three-dimensional augmentation vector.
5. The method of claim 2, wherein: the construction process of the target detection model comprises the following steps:
s201, acquiring position images of electric power production personnel, a power transmission line and power transformation equipment by adopting a multi-view camera; marking the acquired position image to form an image database;
s202, inputting two-dimensional images in an image database, extracting targets of personnel and equipment by adopting a convolutional neural network, acquiring image features under multiple scales through a convolutional layer, further extracting the acquired image features by combining a pooling layer, and finally obtaining a depth image of the target through an activation function to realize the detection of the target.
6. The method of claim 5, wherein: according to the inside and outside parameter matrix of the multi-view camera, the coordinates (x) in the color map are utilized through the alignment of the color map and the depth image1,y1)、(x2,y2) And obtaining the three-dimensional depth coordinate of the target object through the mapping relation between the three-dimensional depth coordinate and the coordinate (x, y, z) in the depth image.
7. The method of claim 1, wherein: the minimum euclidean distance is calculated using the following equation:
wherein (X)1Y1Z1) Is the three-dimensional frame coordinate of the operator; (X)2Y2Z2) Is the three-dimensional frame coordinate of the detected power equipment.
8. The method of claim 1, wherein: and when the comparison result shows that the minimum Euclidean distance is smaller than the safety threshold value, judging that the target personnel mistakenly enter the electrified interval, determining that the power production personnel are unsafe, sending alarm information, converting the alarm information into text data, and sending the text data to a data background of the power enterprise.
9. The utility model provides an electric power production personnel safety monitoring system which characterized in that: the system comprises an image acquisition module, an image recognition and calculation module, a depth information processing module, a three-dimensional calculation module and a comparison and monitoring module;
the image acquisition module is used for acquiring two-dimensional images of electric power production personnel, the power transmission line and the power transformation equipment; sending the acquired two-dimensional image to an image recognition and calculation module for target detection;
the image identification calculation module is used for extracting target personnel and target equipment from the acquired two-dimensional image according to the target detection model; identifying target personnel and target equipment, and sending the identified target personnel and target equipment to a depth information processing module;
the depth information processing module is used for respectively obtaining three-dimensional depth coordinates by using the extracted target personnel and the extracted target equipment through a parameter matrix;
the three-dimensional calculation module is used for calculating three-dimensional frames of the target personnel and the target equipment respectively by using the obtained three-dimensional depth coordinates;
and the comparison monitoring module is used for calculating the minimum Euclidean distance between the target personnel and the three-dimensional frame of the target equipment, comparing the obtained minimum Euclidean distance with a safety threshold value, and determining whether the power generation personnel are safe or not according to the comparison result.
10. The utility model provides an electric power production personnel safety monitoring equipment which characterized in that: comprising a memory for storing a computer program; a processor for implementing a method of electrical power production personnel safety monitoring according to any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010576009.2A CN111753712A (en) | 2020-06-22 | 2020-06-22 | Method, system and equipment for monitoring safety of power production personnel |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010576009.2A CN111753712A (en) | 2020-06-22 | 2020-06-22 | Method, system and equipment for monitoring safety of power production personnel |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111753712A true CN111753712A (en) | 2020-10-09 |
Family
ID=72675699
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010576009.2A Pending CN111753712A (en) | 2020-06-22 | 2020-06-22 | Method, system and equipment for monitoring safety of power production personnel |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111753712A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700403A (en) * | 2020-12-09 | 2021-04-23 | 国网宁夏电力有限公司检修公司 | Charged interval false-entry prevention detection method, medium and system |
| CN112750169A (en) * | 2021-01-13 | 2021-05-04 | 深圳瀚维智能医疗科技有限公司 | Camera calibration method, device and system and computer readable storage medium |
| CN112766129A (en) * | 2021-01-12 | 2021-05-07 | 云南电网有限责任公司电力科学研究院 | Power grid worker behavior real-time monitoring method and device |
| 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 |
| CN113283496A (en) * | 2021-05-21 | 2021-08-20 | 国网宁夏电力有限公司中卫供电公司 | Method applied to intelligent identification of dangerous actions of distribution network uninterrupted operation |
| CN113505667A (en) * | 2021-06-29 | 2021-10-15 | 浙江华是科技股份有限公司 | Transformer substation monitoring method, device and system and computer storage medium |
| CN113990034A (en) * | 2021-10-25 | 2022-01-28 | 国网四川省电力公司检修公司 | Transmission maintenance safety early warning method, system and terminal based on RTK positioning |
| CN115311831A (en) * | 2022-08-01 | 2022-11-08 | 太湖流域管理局苏州管理局 | Electrical cabinet monitoring system and method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120306876A1 (en) * | 2011-06-06 | 2012-12-06 | Microsoft Corporation | Generating computer models of 3d objects |
| US20180322648A1 (en) * | 2015-11-11 | 2018-11-08 | Zhejiang Dahua Technology Co., Ltd. | Methods and systems for binocular stereo vision |
| CN108846891A (en) * | 2018-05-30 | 2018-11-20 | 广东省智能制造研究所 | A kind of man-machine safety collaboration method based on three-dimensional framework detection |
| CN109084724A (en) * | 2018-07-06 | 2018-12-25 | 西安理工大学 | A kind of deep learning barrier distance measuring method based on binocular vision |
| CN109522935A (en) * | 2018-10-22 | 2019-03-26 | 易思维（杭州）科技有限公司 | The method that the calibration result of a kind of pair of two CCD camera measure system is evaluated |
| CN109801302A (en) * | 2018-12-14 | 2019-05-24 | 华南理工大学 | A kind of ultra-high-tension power transmission line foreign matter detecting method based on binocular vision |
| CN110307790A (en) * | 2019-07-04 | 2019-10-08 | 深圳市富源信息技术有限公司 | Camera shooting machine detecting device and method applied to safety monitoring slope |
| CN110363858A (en) * | 2019-06-18 | 2019-10-22 | 新拓三维技术(深圳)有限公司 | A kind of three-dimensional facial reconstruction method and system |
| CN110533773A (en) * | 2019-09-02 | 2019-12-03 | 北京华捷艾米科技有限公司 | A kind of three-dimensional facial reconstruction method, device and relevant device |
| CN111028271A (en) * | 2019-12-06 | 2020-04-17 | 浩云科技股份有限公司 | Multi-camera personnel three-dimensional positioning and tracking system based on human skeleton detection |
| CN111311728A (en) * | 2020-01-10 | 2020-06-19 | 华中科技大学鄂州工业技术研究院 | High-precision morphology reconstruction method, equipment and device based on optical flow method |
-
2020
- 2020-06-22 CN CN202010576009.2A patent/CN111753712A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120306876A1 (en) * | 2011-06-06 | 2012-12-06 | Microsoft Corporation | Generating computer models of 3d objects |
| US20180322648A1 (en) * | 2015-11-11 | 2018-11-08 | Zhejiang Dahua Technology Co., Ltd. | Methods and systems for binocular stereo vision |
| CN108846891A (en) * | 2018-05-30 | 2018-11-20 | 广东省智能制造研究所 | A kind of man-machine safety collaboration method based on three-dimensional framework detection |
| CN109084724A (en) * | 2018-07-06 | 2018-12-25 | 西安理工大学 | A kind of deep learning barrier distance measuring method based on binocular vision |
| CN109522935A (en) * | 2018-10-22 | 2019-03-26 | 易思维（杭州）科技有限公司 | The method that the calibration result of a kind of pair of two CCD camera measure system is evaluated |
| CN109801302A (en) * | 2018-12-14 | 2019-05-24 | 华南理工大学 | A kind of ultra-high-tension power transmission line foreign matter detecting method based on binocular vision |
| CN110363858A (en) * | 2019-06-18 | 2019-10-22 | 新拓三维技术(深圳)有限公司 | A kind of three-dimensional facial reconstruction method and system |
| CN110307790A (en) * | 2019-07-04 | 2019-10-08 | 深圳市富源信息技术有限公司 | Camera shooting machine detecting device and method applied to safety monitoring slope |
| CN110533773A (en) * | 2019-09-02 | 2019-12-03 | 北京华捷艾米科技有限公司 | A kind of three-dimensional facial reconstruction method, device and relevant device |
| CN111028271A (en) * | 2019-12-06 | 2020-04-17 | 浩云科技股份有限公司 | Multi-camera personnel three-dimensional positioning and tracking system based on human skeleton detection |
| CN111311728A (en) * | 2020-01-10 | 2020-06-19 | 华中科技大学鄂州工业技术研究院 | High-precision morphology reconstruction method, equipment and device based on optical flow method |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112700403A (en) * | 2020-12-09 | 2021-04-23 | 国网宁夏电力有限公司检修公司 | Charged interval false-entry prevention detection method, medium and system |
| CN112766129A (en) * | 2021-01-12 | 2021-05-07 | 云南电网有限责任公司电力科学研究院 | Power grid worker behavior real-time monitoring method and device |
| CN112750169A (en) * | 2021-01-13 | 2021-05-04 | 深圳瀚维智能医疗科技有限公司 | Camera calibration method, device and system and computer readable storage medium |
| CN112750169B (en) * | 2021-01-13 | 2024-03-19 | 深圳瀚维智能医疗科技有限公司 | Camera calibration method, device, system and computer readable storage medium |
| CN113283496A (en) * | 2021-05-21 | 2021-08-20 | 国网宁夏电力有限公司中卫供电公司 | Method applied to intelligent identification of dangerous actions of distribution network uninterrupted operation |
| CN113283496B (en) * | 2021-05-21 | 2022-07-29 | 国网宁夏电力有限公司中卫供电公司 | Method applied to intelligent identification of dangerous actions of distribution network uninterrupted operation |
| 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 |
| CN113505667A (en) * | 2021-06-29 | 2021-10-15 | 浙江华是科技股份有限公司 | Transformer substation monitoring method, device and system and computer storage medium |
| CN113505667B (en) * | 2021-06-29 | 2023-11-17 | 浙江华是科技股份有限公司 | Substation monitoring method, device and system and computer storage medium |
| CN113990034A (en) * | 2021-10-25 | 2022-01-28 | 国网四川省电力公司检修公司 | Transmission maintenance safety early warning method, system and terminal based on RTK positioning |
| CN115311831A (en) * | 2022-08-01 | 2022-11-08 | 太湖流域管理局苏州管理局 | Electrical cabinet monitoring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111753712A (en) | Method, system and equipment for monitoring safety of power production personnel | |
| CN107392247B (en) | Real-time detection method for ground object safety distance below power line | |
| CN107229930B (en) | Intelligent identification method for numerical value of pointer instrument | |
| CN110850723B (en) | Fault diagnosis and positioning method based on transformer substation inspection robot system | |
| US10488194B2 (en) | Motion measurement method and apparatus applied to large multi-paddle wave simulation system | |
| CN109977813A (en) | A kind of crusing robot object localization method based on deep learning frame | |
| CN107588855B (en) | Detection method, detection device and the terminal device of transformer equipment temperature | |
| CN109829908B (en) | Binocular image-based method and device for detecting safety distance of ground object below power line | |
| CN114241298A (en) | Tower crane environment target detection method and system based on laser radar and image fusion | |
| CN104091168A (en) | Method for automatically extracting and locating power line based on unmanned aerial vehicle image | |
| CN109357629A (en) | A kind of intelligent checking system and application method based on spatial digitizer | |
| CN110910460A (en) | Method and device for acquiring position information and calibration equipment | |
| CN105139384B (en) | The method and apparatus of defect capsule detection | |
| CN113688817A (en) | Instrument identification method and system for automatic inspection | |
| CN111064935B (en) | Intelligent construction site personnel posture detection method and system | |
| CN117498225B (en) | Unmanned aerial vehicle intelligent power line inspection system | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN116821409B (en) | Production safety management method and system based on image data processing | |
| CN113965733A (en) | Binocular video monitoring method, system, computer equipment and storage medium | |
| CN108898187A (en) | A kind of method and device of automatic identification power distribution room indicating equipment image | |
| CN111340884A (en) | Binocular heterogeneous camera and RFID dual target positioning and identity identification method | |
| CN116363397A (en) | Equipment fault checking method, device and inspection system | |
| CN115965579A (en) | Method and system for identifying and positioning three-dimensional defects in transformer substation inspection | |
| CN113778091A (en) | Method for inspecting equipment of wind power plant booster station | |
| CN116912721B (en) | Power distribution network equipment body identification method and system based on monocular stereoscopic vision |
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 |