CN111914620A - Calibration-based disconnecting link state visual identification method - Google Patents
Calibration-based disconnecting link state visual identification method Download PDFInfo
- Publication number
- CN111914620A CN111914620A CN202010533450.2A CN202010533450A CN111914620A CN 111914620 A CN111914620 A CN 111914620A CN 202010533450 A CN202010533450 A CN 202010533450A CN 111914620 A CN111914620 A CN 111914620A
- Authority
- CN
- China
- Prior art keywords
- disconnecting link
- state
- calibration
- equipment
- image
- 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
- 230000000007 visual effect Effects 0.000 title claims abstract description 26
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims abstract description 12
- 238000005530 etching Methods 0.000 claims abstract description 3
- 238000010191 image analysis Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 239000003550 marker Substances 0.000 abstract description 2
- 238000012790 confirmation Methods 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000005611 electricity Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000003068 static 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
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a calibration-based disconnecting link state visual identification method, which comprises the following steps of: 1. etching a rectangular mark area on the movable knife gate, wherein the area is filled with red; 2. engineering configuration calibration: calibrating the relevant state position of the movable disconnecting link of the equipment, and automatically recording and storing the relevant data of the marker area at each disconnecting link state position; 3. and (3) running visual recognition: and performing visual identification of the state of the disconnecting link when the equipment is put into operation after debugging is completed, and automatically completing identification of the state of the disconnecting link according to the calibration data. The method has great adaptability, extremely high identification accuracy, stability and reliability, and meanwhile, the visual analysis method is simple, the system resource occupation is less, and the identification efficiency is higher.
Description
Technical Field
The invention relates to the field of disconnecting link detection, in particular to a method for visually identifying a disconnecting link state based on calibration.
Background
Along with the application of a large number of automatic devices in an electric power system (including rail transit), the efficiency and the safety of subway production are greatly improved. The knife switch is used for controlling the electricity consumption of the electric power equipment in a large number, the knife switch is a key component of the equipment, and meanwhile, the accuracy of the state of the knife switch is very important in relation to the safety of the electricity consumption.
At present, the state of the disconnecting link of these devices mainly depends on the disconnecting link switching-on and switching-off action to drive the attached mechanical travel switch, so that the state of the mechanical travel switch is changed and is transmitted out of the state of the disconnecting link switching-on and switching-off. However, when the equipment fails, the travel switch is abnormal, and the system and personnel cannot know the abnormal travel switch, the equipment is operated to cause power utilization safety accidents, and great loss is caused. In order to avoid the situation, at present, cameras are additionally arranged in a plurality of devices, the state of a disconnecting link can be transmitted to an operator through the cameras for manual confirmation, but when the devices are in failure, a travel switch is abnormal, and meanwhile, the operator does not perform manual video inspection confirmation, safety accidents can also be caused.
To solve this problem, some manufacturers have begun to use computer vision analysis techniques to automatically analyze the state of the knife switch instead of manual video confirmation. The used visual analysis technology is mainly based on full-picture characteristic search, and the opening and closing state of the disconnecting link is judged according to the characteristic. However, in terms of actual use, the currently used disconnecting link state visual analysis technology and method have the disadvantages of high system resource occupation, low recognition efficiency, easy environmental interference, low accuracy and reliability, and cannot replace manual video confirmation.
As shown in fig. 1, the feature area is an area etched in a specific color on the knife switch, and the shape and color of the area are different according to the algorithm used. The visual analysis process of the prior technical scheme mainly comprises the following steps: 1. connecting software and logging in a built-in camera of the equipment; 2. software obtains an image through a camera; 3. carrying out full-picture preprocessing on the image; 4. identifying a movable knife switch (or a characteristic region) in the full-picture image by different methods; 5. calculating the angle of the identified movable knife switch (or characteristic area); 6. and judging the opening and closing state according to the angle. The visual analysis technique used in the prior art is based on the calculation and processing of the whole image picture during the analysis of the state of the knife switch. In the image preprocessing stage, processing is required to be carried out based on the whole picture; the search based on the full image is also used for searching the movable knife switch (or the characteristic area). The intensity of external light easily influences the captured image, so that a movable knife switch (or a characteristic area) cannot be accurately found, the identification fails, and the identification accuracy and reliability are low; meanwhile, the processing process is based on the whole image, so that the calculation amount is large, the occupied resource is high, and the efficiency is low.
Disclosure of Invention
The invention aims to solve the technical problem of providing a calibration-based disconnecting link state visual identification method, which is greatly tolerant to environmental interference, has great adaptability, and is extremely high in identification accuracy, stable and reliable.
In order to solve the technical problems, the invention adopts the technical scheme that:
a visual identification method for a disconnecting link state based on calibration comprises the following steps:
step 1: etching a rectangular mark area on the movable knife gate, wherein the area is filled with red;
step 2: engineering configuration calibration, comprising:
1) determining equipment to be calibrated, and operating the equipment to change the state of the disconnecting link;
2) when the state of the disconnecting link of the equipment is changed, automatically acquiring a current image of the disconnecting link from a camera of the equipment;
3) manually marking a mark area in the image;
4) identifying the complete graph of the mark area through an image analysis algorithm, recording and storing relevant morphological data including position, size and angle of the mark area, and establishing association between the mark area data and the state of the disconnecting link;
5) operating the equipment again, switching the disconnecting link to the next state, and calibrating in the newly captured disconnecting link image;
6) completing the calibration of all the disconnecting link states in sequence;
and step 3: running a visual recognition comprising:
1) loading calibration data of all equipment and the states of all disconnecting links of the equipment;
2) connecting built-in cameras of each device;
3) acquiring a complete image of the disconnecting link from the camera;
4) intercepting corresponding sub-regions of the calibration region image from the captured complete image according to the mark region graphic data of each disconnecting link state of the equipment; the subarea is an image of the position of the mark area corresponding to each disconnecting link state;
5) carrying out visual analysis pretreatment on each subregion;
6) performing red identification on each subregion, and counting the proportion of red in the subregion;
7) and comparing the red proportion of each subarea, wherein the calibration disconnecting link state corresponding to the subarea with the largest red proportion is the current disconnecting link state.
Compared with the prior art, the invention has the beneficial effects that: the method has the advantages of great tolerance to environmental interference, great adaptability, high identification accuracy, stability and reliability; meanwhile, the visual analysis method is simple, the system resource occupation is less, the recognition efficiency is higher, and the method can replace the manual video confirmation step according to the use of actual projects.
Drawings
FIG. 1 is a model of knife gate state identification with etched regions.
Fig. 2 shows a knife switch state recognition model with red mark areas.
FIG. 3 is a schematic diagram of a calibration process in the identification method of the present invention.
Fig. 4 is a schematic diagram of the identification process of the state of the disconnecting link in the identification method of the present invention.
In the figure: a movable knife switch 1; a characteristic region 2; a wire inlet side base 3; a wire outlet side base 4; and a static contact 5.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
As shown in the knife switch state model of fig. 2, a rectangular mark area is etched on the movable knife switch 1, and the area is filled with red; the method of the invention divides the whole visual identification process into two stages: the engineering configuration calibration stage and the operation visual identification stage are as follows:
and in the engineering configuration calibration stage, when the equipment engineering is installed and debugged, a worker calibrates the relevant state position of the movable disconnecting link of the equipment, and automatically records and stores the relevant data of the marker area at each disconnecting link state position. The state position of each movable disconnecting link of each device is only calibrated once, and the calibration process is not needed in the visual identification stage, wherein the calibration process is shown in figure 3:
1. determining equipment to be calibrated, and operating the equipment to change the state of the disconnecting link;
2. when the state of the disconnecting link of the equipment changes, automatically acquiring a current image of the disconnecting link from a camera of the equipment;
3. manually marking a mark area in the image;
4. identifying the complete graph of the mark area through an image analysis algorithm, recording and storing relevant morphological data including position, size and angle of the mark area, and establishing association between the mark area data and the state of the disconnecting link;
5. and operating the equipment again, switching the disconnecting link to the next state, calibrating in the newly captured disconnecting link image, and completing calibration of all disconnecting link states in sequence.
And the operation visual identification stage is a stage of visually identifying the state of the disconnecting link when the equipment is put into operation after debugging is completed. In the stage, manual operation and intervention are not needed, the identification of the state of the disconnecting link is automatically completed according to the calibration data, and the working process of the identification stage is as shown in fig. 4:
1. loading calibration data of all equipment and the states of all disconnecting links of the equipment;
2. connecting and logging in a built-in camera of the equipment;
3. acquiring a complete image of the disconnecting link from the camera;
4. and intercepting corresponding image sub-regions from the captured complete image according to the calibration data of each disconnecting link state of the equipment. The subarea is an image of the position of the mark area corresponding to each disconnecting link state;
5. carrying out visual analysis pretreatment on each subregion;
6. performing red identification on each subregion, and counting the proportion of red in the subregion;
7. and comparing the red proportion of each subarea, wherein the calibration disconnecting link state corresponding to the subarea with the largest red proportion is the current disconnecting link state.
The visual identification of the state of the disconnecting link is divided into two stages of engineering configuration calibration and operation visual identification, and dynamic analysis and identification are carried out according to calibration data during operation on the basis of engineering calibration data. The engineering configuration calibration takes the characteristic area as a calibration object, and each disconnecting link state corresponds to a group of characteristic area calibration data. And (5) operating a visual identification stage, and only analyzing and identifying the images of all the characteristic areas marked by the engineering configuration.
Claims (1)
1. A visual identification method for a switch state based on calibration is characterized by comprising the following steps:
step 1: etching a rectangular mark area on the movable knife gate, wherein the area is filled with red;
step 2: engineering configuration calibration, comprising:
1) determining equipment to be calibrated, and operating the equipment to change the state of the disconnecting link;
2) when the state of the disconnecting link of the equipment is changed, automatically acquiring a current image of the disconnecting link from a camera of the equipment;
3) manually marking a mark area in the image;
4) identifying the complete graph of the mark area through an image analysis algorithm, recording and storing relevant morphological data including position, size and angle of the mark area, and establishing association between the mark area data and the state of the disconnecting link;
5) operating the equipment again, switching the disconnecting link to the next state, and calibrating in the newly captured disconnecting link image;
6) completing the calibration of all the disconnecting link states in sequence;
and step 3: running a visual recognition comprising:
1) loading calibration data of all equipment and the states of all disconnecting links of the equipment;
2) connecting built-in cameras of each device;
3) acquiring a complete image of the disconnecting link from the camera;
4) intercepting corresponding sub-regions of the calibration region image from the captured complete image according to the mark region graphic data of each disconnecting link state of the equipment; the subarea is an image of the position of the mark area corresponding to each disconnecting link state;
5) carrying out visual analysis pretreatment on each subregion;
6) performing red identification on each subregion, and counting the proportion of red in the subregion;
7) and comparing the red proportion of each subarea, wherein the calibration disconnecting link state corresponding to the subarea with the largest red proportion is the current disconnecting link state.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010533450.2A CN111914620A (en) | 2020-06-12 | 2020-06-12 | Calibration-based disconnecting link state visual identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010533450.2A CN111914620A (en) | 2020-06-12 | 2020-06-12 | Calibration-based disconnecting link state visual identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111914620A true CN111914620A (en) | 2020-11-10 |
Family
ID=73237507
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010533450.2A Pending CN111914620A (en) | 2020-06-12 | 2020-06-12 | Calibration-based disconnecting link state visual identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111914620A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348380A (en) * | 2019-07-10 | 2019-10-18 | 无锡地铁集团有限公司 | A kind of visualization grounding switch state video recognition system and method |
| CN111178395A (en) * | 2019-12-12 | 2020-05-19 | 平高集团有限公司 | Isolation switch state identification method and device |
-
2020
- 2020-06-12 CN CN202010533450.2A patent/CN111914620A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110348380A (en) * | 2019-07-10 | 2019-10-18 | 无锡地铁集团有限公司 | A kind of visualization grounding switch state video recognition system and method |
| CN111178395A (en) * | 2019-12-12 | 2020-05-19 | 平高集团有限公司 | Isolation switch state identification method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271844B (en) | Electrical cabinet electrical symbol recognition method based on OpenCV | |
| CN101893686B (en) | Digital radiography-based breaker operating characteristic on-line detection device and method | |
| WO2017084186A1 (en) | System and method for automatic monitoring and intelligent analysis of flexible circuit board manufacturing process | |
| CN112115927B (en) | Intelligent machine room equipment identification method and system based on deep learning | |
| CN109117764A (en) | Using the method for color threshold method identification target object region electrical symbol in power monitoring | |
| CN113723189B (en) | Intelligent power equipment fault diagnosis method based on single-order infrared image target detection | |
| CN109308448A (en) | A method of it prevents from becoming distribution maloperation using image processing techniques | |
| CN112100039B (en) | Equipment fault alarm method and system | |
| CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
| CN111639568A (en) | Navigation patrol method for intelligent robot of transformer substation | |
| CN116231504A (en) | Remote intelligent inspection method, device and system for booster station | |
| CN110148118B (en) | Switch cabinet grounding knife state non-contact monitoring method, system, medium and equipment | |
| CN110543809A (en) | Electric power operation site risk supervision intrusion video identification method | |
| CN113297913B (en) | Identification method for dressing specification of distribution network field operators | |
| CN111914620A (en) | Calibration-based disconnecting link state visual identification method | |
| CN116228778A (en) | Insulator rupture detection method and system based on multi-mode information fusion | |
| CN102866158A (en) | Detection method of power transmission and distribution cables for tunnel routing inspection | |
| CN113421233B (en) | Measuring method for disconnecting link in-place state and image acquisition and analysis equipment | |
| CN113837178A (en) | Deep learning-based automatic positioning and unified segmentation method for meter of transformer substation | |
| CN112750149A (en) | High-voltage isolating switch fault monitoring method based on moving target detection | |
| CN117095389B (en) | Image data processing method and system based on liquid crystal visual recognition unit | |
| CN117686516B (en) | Automatic chip appearance defect detection system based on machine vision | |
| EP4254325A1 (en) | Inspection of printed circuit board assemblies | |
| CN117686823B (en) | Automatic acceptance checking system for relay protection of transformer substation | |
| de Oliveira et al. | Development and experimental evaluation of a vision system for detecting defects of stator windings in induction motor assembly lines |
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 |
Application publication date: 20201110 |
|
| RJ01 | Rejection of invention patent application after publication |