CN110956652A - Early warning method for transformer substation personnel crossing line - Google Patents
Early warning method for transformer substation personnel crossing line Download PDFInfo
- Publication number
- CN110956652A CN110956652A CN201911139039.0A CN201911139039A CN110956652A CN 110956652 A CN110956652 A CN 110956652A CN 201911139039 A CN201911139039 A CN 201911139039A CN 110956652 A CN110956652 A CN 110956652A
- Authority
- CN
- China
- Prior art keywords
- img
- transformer substation
- foot
- dangerous area
- equation
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000004590 computer program Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 description 5
- 230000006399 behavior Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/277—Analysis of motion involving stochastic approaches, e.g. using Kalman filters
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/24—Reminder alarms, e.g. anti-loss alarms
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/30196—Human being; Person
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Multimedia (AREA)
- Emergency Management (AREA)
- Marketing (AREA)
- Social Psychology (AREA)
- Psychiatry (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Human Computer Interaction (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a transformer substation personnel line crossing early warning method, belongs to the technical field of computer vision, and aims to overcome the defect that the conventional transformer substation cannot give an early warning for the line crossing of workers. According to the transformer substation personnel early-line-crossing warning method, a camera is used for collecting an image set of a dangerous area in a transformer substation and establishing a coordinate system for the dangerous area, a foot track is predicted through Kalman filtering, a large amount of observation data does not need to be stored, a new parameter filtering value can be calculated at any time when new observation data are obtained, observation results can be processed conveniently in real time, early warning can be achieved for phenomena of mistakenly approaching a dangerous point, randomly traversing, mistakenly selecting a misoperation operation target and the like based on a Kalman filtering strategy, and the phenomena of preventing accidents are avoided in the bud.
Description
Technical Field
The invention belongs to the technical field of computer vision, and relates to a transformer substation personnel early line-crossing warning method.
Background
The transformer substation is used as an intermediate junction for connecting a power plant and a user, is the foundation and the support of a power grid system, and has no replaceable function in the whole power system. And a plurality of high-risk working areas exist in the transformer substation, and major accidents are easy to happen without paying attention to the high-risk working areas, so that a set of method is needed to effectively supervise and control operations in the areas, and early warning is carried out on the dangerous areas, so that the purpose of ensuring no accidents in safety production is achieved. At present, in order to improve the safety management level, in addition to establishing a series of regulations, a comprehensive automation system, a video monitoring system, a five-prevention system, an electrical equipment detection system and the like are configured in many substations. However, these electrical equipment monitoring systems are mainly used for monitoring electrical quantity and chemical quantity, and often only can provide a data recording and analyzing means for analyzing accident causes during or after an accident, and cannot prevent and warn human factors in advance, and human and equipment accidents caused by human factors such as violation of rules and regulations, insufficient patrol, and intrusion into dangerous areas frequently occur, and effective technical support is not obtained. Statistical data show that about one third of the safety accidents of the transformer substation are caused by human factors such as that operators do not carefully execute management procedures, over-regional operation, and on-site monitoring and investigation is not available, so that the enhancement of behavior supervision on the transformer substation personnel is particularly important.
Disclosure of Invention
The invention provides a transformer substation personnel line crossing early warning method aiming at the problems in the prior art and aims to overcome the defect that the conventional transformer substation cannot give an early warning for the line crossing of workers.
The invention is realized by the following steps:
the transformer substation personnel early line-crossing warning method is characterized by comprising the following steps of:
step (ii) of1. Collecting dangerous area image set IMG = { IMG) in transformer substation through camera1, img2, …, imgn}；
Step 2, taking the lower img boundary as the x axis of a plane rectangular coordinate system, taking the left img boundary as the y axis and taking the lower left img corner as the origin (0, 0); extracting the boundary of the dangerous area by combining Hough transform to obtain an equation set L = containing the n boundaries of the dangerous areal 1,l 2, …,l i, …,l n},lThe equation of (1) is as follows:
l 1=m1x+p1,l 2=m2x+ p2, …,l i=mix+ pi, …,l n=mnx+ pn;
step 3, collecting the human body of the worker through a camera, realizing human body two-dimensional attitude estimation by adopting human body attitude identification based on a convolutional neural network and supervised learning, continuously identifying feet, corresponding a front frame position and a rear frame position of the feet to the plane rectangular coordinate system established in the step 2, and setting the feet of the front frame to be (x)1, y1) The position of the rear frame foot is (x)2, y2) Obtaining a foot equation F, wherein the specific equation is as follows: f = { (y)2-y1)/(x2-x1)}(x-x1)+y1;
Step 4, correcting the predicted foot position of the previous frame according to the actual position of the current foot through Kalman filtering, and predicting the foot position (x) of the next frame2’, y2') current foot position (x)1’, y1') and predicted next frame foot position (x)2’, y2') is recorded as the foot predicted trajectory equation F ', where F ' = { (y)2’-y1’)/(x2’-x1’)}(x-x1’)+y1’;
Step 5, judging the intersection of the L and the F 'through computer program judgment, judging that the risk of entering a dangerous area exists in the staff when the L and the F' have coincident points, and sending an alarm; and when the coincidence points of L and F' do not exist, judging that the risk of entering the dangerous area does not exist in the staff.
According to the transformer substation personnel early-crossing alarming method provided by the invention, the foot part dynamics is predicted by adopting Kalman filtering, the Kalman filtering does not need to store a large amount of observation data during solving, and when new observation data are obtained, a new parameter filtering value can be calculated at any time, so that the observation result is conveniently processed in real time, and early warning can be realized on the phenomena of mistaken approaching of a dangerous point, random crossing, mistaken selection of a misoperation target and the like based on a Kalman filtering strategy, so that the transformer substation personnel early-crossing alarming method is prevented from getting in the bud.
Drawings
Fig. 1 is a flow chart of an alarm method.
Detailed Description
The following detailed description of the embodiments of the present invention is provided in connection with the accompanying drawings for the purpose of facilitating understanding and understanding of the technical solutions of the present invention. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The embodiment provides a transformer substation personnel early line-crossing warning method, which comprises the following steps:
step 1, collecting an image set IMG = { IMG = of a dangerous area in a transformer substation through a camera1, img2, …, imgn}. n is the number of dangerous area divisions, and may be 1, 2 or more.
Step 2, taking the lower img boundary as the x axis of a plane rectangular coordinate system, taking the left img boundary as the y axis and taking the lower left img corner as the origin (0, 0); extracting the boundary of the dangerous area by combining Hough transform to obtain an equation set L = containing the n boundaries of the dangerous areal 1,l 2,…,l i, …,l n},lThe equation of (1) is as follows:
l 1=m1x+p1,l 2=m2x+ p2, …,l i=mix+ pi, …,l n=mnx+ pn。
IMG refers to any one of the image sets IMG, and this step requires a coordinate system to be set for all the images in the image set IMG.
Step 3, collecting the human body of the worker through a camera, realizing human body two-dimensional attitude estimation by adopting human body attitude identification based on a convolutional neural network and supervised learning, continuously identifying feet, corresponding a front frame position and a rear frame position of the feet to the plane rectangular coordinate system established in the step 2, and setting the feet of the front frame to be (x)1, y1) The position of the rear frame foot is (x)2, y2) Obtaining a foot equation F, wherein the specific equation is as follows: f = { (y)2-y1)/(x2-x1)}(x-x1)+y1。
Step 4, correcting the predicted foot position of the previous frame according to the actual position of the current foot through Kalman filtering, and predicting the foot position (x) of the next frame2’, y2') current foot position (x)1’, y1') and predicted next frame foot position (x)2’,y2') is recorded as the foot predicted trajectory equation F ', where F ' = { (y)2’-y1’)/(x2’-x1’)}(x-x1’)+y1’。
Step 5, judging the intersection of the L and the F 'through computer program judgment, judging that the risk of entering a dangerous area exists in the staff when the L and the F' have coincident points, and sending an alarm; and when the coincidence points of L and F' do not exist, judging that the risk of entering the dangerous area does not exist in the staff.
When a person enters the capturing range of the camera, the camera can transmit the captured information to the computer, and the computer starts to judge. The warning can be carried out in a sound, light or character mode, the warning can be carried out on personnel entering the transformer substation, the warning can also be carried out on personnel in a monitoring room, and the warning is provided for prompting that people are about to break into a dangerous area. Typically steps 1 and 2 are performed once, while steps 3-5 are performed repeatedly.
Claims (1)
1. The transformer substation personnel early line-crossing warning method is characterized by comprising the following steps of:
step 1, byCamera acquires image set IMG = { IMG) of dangerous area in transformer substation1, img2, …, imgn}；
Step 2, taking the lower img boundary as the x axis of a plane rectangular coordinate system, taking the left img boundary as the y axis and taking the lower left img corner as the origin (0, 0); extracting the boundary of the dangerous area by combining Hough transform to obtain an equation set L = containing the n boundaries of the dangerous areal 1,l 2, …,l i, …,l n},lThe equation of (1) is as follows:
l 1=m1x+p1,l 2=m2x+ p2, …,l i=mix+ pi, …,l n=mnx+ pn;
step 3, collecting the human body of the worker through a camera, realizing human body two-dimensional attitude estimation by adopting human body attitude identification based on a convolutional neural network and supervised learning, continuously identifying feet, corresponding a front frame position and a rear frame position of the feet to the plane rectangular coordinate system established in the step 2, and setting the feet of the front frame to be (x)1, y1) The position of the rear frame foot is (x)2, y2) Obtaining a foot equation F, wherein the specific equation is as follows:
F={(y2-y1)/(x2-x1)}(x-x1)+y1;
step 4, correcting the predicted foot position of the previous frame according to the actual position of the current foot through Kalman filtering, and predicting the foot position (x) of the next frame2’, y2') current foot position (x)1’, y1') and predicted next frame foot position (x)2’, y2') is recorded as the foot predicted trajectory equation F ', where F ' = { (y)2’-y1’)/(x2’-x1’)}(x-x1’)+y1’;
Step 5, judging the intersection of the L and the F 'through computer program judgment, judging that the risk of entering a dangerous area exists in the staff when the L and the F' have coincident points, and sending an alarm; and when the coincidence points of L and F' do not exist, judging that the risk of entering the dangerous area does not exist in the staff.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911139039.0A CN110956652A (en) | 2019-11-20 | 2019-11-20 | Early warning method for transformer substation personnel crossing line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911139039.0A CN110956652A (en) | 2019-11-20 | 2019-11-20 | Early warning method for transformer substation personnel crossing line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110956652A true CN110956652A (en) | 2020-04-03 |
Family
ID=69977847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911139039.0A Pending CN110956652A (en) | 2019-11-20 | 2019-11-20 | Early warning method for transformer substation personnel crossing line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110956652A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489397A (en) * | 2020-11-19 | 2021-03-12 | 公安部第三研究所 | Radar early warning system and method for realizing prejudgment and track calibration processing aiming at illegal crossing behavior of pedestrians on expressway |
| CN112767647A (en) * | 2020-12-29 | 2021-05-07 | 深圳力维智联技术有限公司 | Danger early warning method, device, equipment and computer readable storage medium |
| CN112766034A (en) * | 2020-11-27 | 2021-05-07 | 东华大学 | Intelligent monitoring system for workshop operation safety |
| CN113382070A (en) * | 2021-06-09 | 2021-09-10 | 合肥中科星翰科技有限公司 | Personnel monitoring and positioning system for judicial management |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104008645A (en) * | 2014-06-12 | 2014-08-27 | 湖南大学 | Lane line predicating and early warning method suitable for city road |
| CN105260719A (en) * | 2015-10-16 | 2016-01-20 | 南京工程学院 | Railway platform line-crossing detection method |
| CN108596129A (en) * | 2018-04-28 | 2018-09-28 | 武汉盛信鸿通科技有限公司 | A kind of vehicle based on intelligent video analysis technology gets over line detecting method |
| CN108876822A (en) * | 2018-07-09 | 2018-11-23 | 山东大学 | A kind of behavior risk assessment method and household safety-protection nursing system |
-
2019
- 2019-11-20 CN CN201911139039.0A patent/CN110956652A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104008645A (en) * | 2014-06-12 | 2014-08-27 | 湖南大学 | Lane line predicating and early warning method suitable for city road |
| CN105260719A (en) * | 2015-10-16 | 2016-01-20 | 南京工程学院 | Railway platform line-crossing detection method |
| CN108596129A (en) * | 2018-04-28 | 2018-09-28 | 武汉盛信鸿通科技有限公司 | A kind of vehicle based on intelligent video analysis technology gets over line detecting method |
| CN108876822A (en) * | 2018-07-09 | 2018-11-23 | 山东大学 | A kind of behavior risk assessment method and household safety-protection nursing system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112489397A (en) * | 2020-11-19 | 2021-03-12 | 公安部第三研究所 | Radar early warning system and method for realizing prejudgment and track calibration processing aiming at illegal crossing behavior of pedestrians on expressway |
| CN112766034A (en) * | 2020-11-27 | 2021-05-07 | 东华大学 | Intelligent monitoring system for workshop operation safety |
| CN112767647A (en) * | 2020-12-29 | 2021-05-07 | 深圳力维智联技术有限公司 | Danger early warning method, device, equipment and computer readable storage medium |
| CN113382070A (en) * | 2021-06-09 | 2021-09-10 | 合肥中科星翰科技有限公司 | Personnel monitoring and positioning system for judicial management |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110956652A (en) | Early warning method for transformer substation personnel crossing line | |
| CN107911653B (en) | Intelligent video monitoring module, system, method and storage medium for residence | |
| CN106341661B (en) | Patrol robot | |
| CN108983806B (en) | Method and system for generating area detection and air route planning data and aircraft | |
| CN209543514U (en) | Monitoring and alarm system based on recognition of face | |
| CN110889339A (en) | Head and shoulder detection-based dangerous area grading early warning method and system | |
| CN116743970B (en) | Intelligent management platform with video AI early warning analysis | |
| CN111178424A (en) | Petrochemical production site safety compliance real-time detection system and method | |
| CN109243139A (en) | A kind of personnel safety monitoring method, terminal device, system and storage medium | |
| CN117079397B (en) | Wild human and animal safety early warning method based on video monitoring | |
| CN111652128B (en) | High-altitude power operation safety monitoring method, system and storage device | |
| CN115964645B (en) | Big data-based information processing method and system | |
| CN113506416A (en) | Engineering abnormity early warning method and system based on intelligent visual analysis | |
| CN112530144A (en) | Method and system for warning violation behaviors of thermal power plant based on neural network | |
| CN112349015A (en) | Shelter management and control system and method based on Internet of things | |
| CN115880722A (en) | Intelligent identification method, system and medium worn by power distribution operating personnel | |
| CN104574729A (en) | Alarming method, device and system | |
| CN113887310A (en) | Worker standard dressing identification method, system and medium | |
| CN110543809A (en) | Electric power operation site risk supervision intrusion video identification method | |
| CN111461655A (en) | Personnel management system | |
| CN112419091B (en) | Intelligent video safety control method for field operation of power distribution network driven by knowledge graph | |
| CN115909212A (en) | Real-time early warning method for typical violation behaviors of power operation | |
| CN116129340A (en) | Safety monitoring method for dangerous area based on action track prediction | |
| CN114241400A (en) | Monitoring method and device of power grid system and computer readable storage medium | |
| CN115474441A (en) | Obstacle detection method, apparatus, device, and computer storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200403 |