CN115731380A - Computer vision-based positioning method, control method and device for four coke oven trucks - Google Patents
Computer vision-based positioning method, control method and device for four coke oven trucks Download PDFInfo
- Publication number
- CN115731380A CN115731380A CN202211458979.8A CN202211458979A CN115731380A CN 115731380 A CN115731380 A CN 115731380A CN 202211458979 A CN202211458979 A CN 202211458979A CN 115731380 A CN115731380 A CN 115731380A
- Authority
- CN
- China
- Prior art keywords
- image
- furnace number
- camera
- module
- locomotive
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention provides a computer vision-based positioning method, a control method and a device for four coke oven trucks, which comprises the steps of controlling a camera arranged on a locomotive to shoot images in real time, and extracting a first image shot by the camera when a furnace number marker is in a camera shooting range; comparing the first image with each second image in a pre-stored image library to determine the furnace number of the locomotive and determine the offset between the camera and the corresponding furnace number marker, wherein each second image in the image library is an image obtained by shooting each furnace number marker; and determining positioning information according to the furnace number and the offset. By implementing the technical scheme of the invention, both the positioning precision and the positioning cost can be considered.
Description
Technical Field
The invention belongs to the technical field of computer industrial application, and particularly relates to a computer vision-based positioning method, a computer vision-based control method and a computer vision-based control device for four coke ovens.
Background
The automatic system of the four locomotives of the coke oven aims to realize the coke pushing interlocking and coordination work of the four locomotives through the accurate measurement of the respective positions of the coke pusher, the coke guide, the coal charging car and the coke quenching car and the reliable data communication among the coke pusher, the coke guide, the coal charging car and the coke quenching car, and realize the automatic running, the automatic positioning and the automatic operation under the production control, thereby realizing the automatic production operation and the computer production management of the four locomotives and the unmanned driving of the final locomotive.
The locomotive positioning technology is a key technology for automation of a coke oven locomotive and is also a core problem for realizing unmanned operation of the locomotive. The current home and abroad positioning technologies mainly comprise rotary encoder position detection, code position detection of a code reader, an infrared positioning technology, coded cable position detection, bar code position detection, an electromagnetic induction technology and the like. The four-car positioning technology adopted by the coking plant at present has the following defects:
1) Rotary encoder position detection techniques: the accumulated error is large after long-term work, and the positioning precision is not high;
2) The code position detection and infrared positioning technology of the code reader: the method has the advantages of single-point positioning, low reliability, high failure rate and high maintenance cost;
3) And (3) coded cable position detection: the positioning accuracy is up to +/-5 mm, the positioning accuracy is not high, and once the whole coding cable is damaged, the maintenance cost is high.
Disclosure of Invention
In order to overcome at least one technical problem in the prior art, the invention provides a computer vision-based positioning method, a control method and a device for four coke oven cars, which can take precision and cost into consideration.
The technical scheme of the invention is as follows: the computer vision-based positioning method for the four coke oven trucks comprises the following steps:
controlling a camera installed on a locomotive to shoot images in real time, and extracting a first image shot by the camera when a furnace number marker is in a camera shooting range;
comparing the first image with each second image in a pre-stored image library to identify the furnace number of the locomotive, and extracting the offset between the camera and the corresponding furnace number marker, wherein each second image in the image library is an image obtained by shooting each furnace number marker;
and determining positioning information according to the furnace number and the offset.
Further, before comparing the first image with each of the second images in the pre-stored image library, the method further includes:
preprocessing a first image, and performing edge extraction processing on the preprocessed first image, wherein the edge-extracted first image is used for comparing with the second image.
Further, the preprocessing includes at least one of a noise removal processing and an image enhancement processing, and the edge extraction processing includes at least one of a binarization processing and a gradation value processing.
Further, the furnace number marker comprises a graduated scale, a color card or a digital furnace number signboard.
Further, the comparing the first image with each second image in a pre-stored image library to identify the furnace number in which the locomotive is located includes:
determining second images with the similarity exceeding a preset value with the first image according to the comparison result of comparing the first image with each second image in a pre-stored image library;
and taking the furnace number corresponding to the second image as the furnace number of the locomotive.
Further, the positioning information comprises the furnace number and the offset, or the positioning information comprises determining the relative position between the locomotive and the furnace number according to the furnace number and the offset.
The technical scheme of the control method is that the positioning information is sent to the central control module, and the central control module performs four-vehicle interlocking control.
The technical scheme of the positioning device comprises the following steps:
the system comprises an extraction module, a first storage module and a second storage module, wherein the extraction module is used for controlling a camera arranged on a locomotive to shoot images in real time and extracting a first image shot by the camera when a furnace number marker is in a camera shooting range;
the first determining module is used for comparing the first image with each second image in a pre-stored image library, identifying the furnace number of the locomotive and extracting the offset between the camera and the corresponding furnace number marker, wherein each second image in the image library is an image obtained by shooting each furnace number marker;
and the second determining module is used for determining positioning information according to the furnace number and the offset.
Further, the apparatus further comprises: and the processing module is used for preprocessing the first image and performing edge extraction processing on the preprocessed first image before comparing the first image with each second image in a pre-stored image library.
The technical scheme of the control device provided by the invention is as follows: comprises a sending module and a positioning device; the sending module is used for sending the positioning information determined by the second determining module to the PLC central control module; and the central control module is used for carrying out four-vehicle interlocking control according to the positioning information.
The invention has the following technical effects:
1) The positioning method has higher positioning precision, enables the four-car to run stably and safely by realizing the four-car interlocking control, avoids accidents caused by problems of the four-car in the production process due to the displacement, prolongs the service life of the coke oven locomotive and the coke oven body, ensures the strict execution of the operation according to the process, greatly improves the coke quality, improves the automation degree of the production, improves the production efficiency, lightens the labor intensity of operators, and can bring great economic benefits on the whole.
2) The invention can rapidly obtain a large amount of information by utilizing computer vision, has low cost and easy automatic processing, is successfully applied to the field of industrial production, and greatly improves the production automation level and the quality and reliability of products. The computer vision hardware configuration is simple, the industrial computer, the high-speed industrial camera and the furnace number marker can accurately position the target operation furnace number, and the hardware configuration cost is low.
3) The invention has high positioning precision and low later maintenance cost of equipment, and the application of the computer vision positioning technology in four-vehicle positioning in the coking industry is the world initiative.
Drawings
FIG. 1 is a flow chart of the present invention.
Detailed Description
The main equipment of the coke oven is coke oven heating exchange equipment (exchanger), and coke pushing cars, coke blocking cars, coke quenching cars and coal charging cars, which are collectively called "four-car one machine", and the latter is generally called "four-cart". The production operation of the coke oven is completed under the mutual cooperation of various machines. Under the condition that the mechanical level of the coke oven is gradually improved, the four large cars work in a coordinated mode, and a series of automatic technical problems such as mutual communication, address oven number alignment, coke pushing action interlocking, coal charging action interlocking and computer centralized joint control are finally achieved. Meanwhile, the realization of four-vehicle interlocking can ensure the production safety and the strict operation of production according to the plan.
The key technology for realizing four-vehicle interlocking is to accurately position the operating furnace numbers of the four vehicles. The application of the computer vision positioning technology is an effective method for realizing the accurate positioning of the target operation furnace numbers of the four big cars.
Example 1:
the computer vision-based positioning method for the four coke oven trucks comprises the following steps:
controlling a camera installed on a locomotive to shoot images in real time, and extracting a first image shot by the camera when a furnace number marker is in a camera shooting range;
comparing the first image with each second image in a pre-stored image library to identify the furnace number of the locomotive, and extracting the offset between the camera and the corresponding furnace number identifier, wherein each second image in the image library is an image obtained by shooting each furnace number identifier; and determining positioning information according to the furnace number and the offset.
For example: and calculating the offset between the center coordinate of the camera and the center coordinate of the corresponding furnace number marker to be used as the offset between the camera and the corresponding furnace number marker. The offset between the center coordinate of the camera and the center coordinate of the corresponding furnace number marker can be obtained by utilizing the existing offset calculation method between the center coordinate of the camera and the center coordinate of the image object which is matched and shot.
Further, before comparing the first image with each of the second images in the pre-stored image library, the method further includes:
preprocessing a first image, and performing edge extraction processing on the preprocessed first image, wherein the edge-extracted first image is used for comparing with the second image.
Further, the above-mentioned preprocessing includes at least one of noise removal processing and image enhancement processing, and the edge extraction processing includes at least one of binarization processing and gradation value processing.
Further, the furnace number marker comprises a graduated scale, a color card or a digital furnace number signboard.
Further, the comparing the first image with each second image in a pre-stored image library to identify the furnace number of the locomotive includes:
determining second images with similarity exceeding a preset value with the first image according to comparison results of the first images and all second images in a pre-stored image library;
and taking the furnace number corresponding to the second image as the furnace number of the locomotive.
Further, the positioning information includes the furnace number and the offset, or the positioning information includes determining a relative position between the locomotive and the furnace number according to the furnace number and the offset.
The technical scheme of the control method is that the positioning information is sent to the central control module, and the central control module performs four-vehicle interlocking control.
The technical scheme of the positioning device comprises the following steps:
the system comprises an extraction module, a first storage module and a second storage module, wherein the extraction module is used for controlling a camera arranged on a locomotive to shoot images in real time and extracting a first image shot by the camera when a furnace number marker is in a camera shooting range;
the first determining module is used for comparing the first image with each second image in a pre-stored image library, identifying the furnace number of the locomotive and extracting the offset between the camera and the corresponding furnace number marker, wherein each second image in the image library is an image obtained by shooting each furnace number marker;
and the second determining module is used for determining positioning information (which can be the furnace number and the offset) according to the furnace number and the offset. Further, the apparatus further comprises: and the processing module is used for preprocessing the first image and performing edge extraction processing on the preprocessed first image before comparing the first image with each second image in a pre-stored image library.
The invention discloses a control device, which comprises a sending module and a positioning device; the sending module is used for sending the positioning information determined by the second determining module to the PLC central control module; and the central control module is used for carrying out four-vehicle interlocking control according to the positioning information.
Example 2:
as shown in FIG. 1, before the system identifies the oven number, images of all oven number identification plates are taken to generate an image library. When the system works, the camera is opened and captures images in real time, when a camera vehicle runs and the furnace number signboard enters the range of the camera, the camera carries out image recognition and comparison on the number signboard, a Halcon visual graphic processing soft real-time analysis is used for analyzing a target furnace number, and the offset of the central coordinate of the camera and the central coordinate of the furnace number signboard is analyzed in real time. With the furnace number and the offset, the relative position of the locomotive relative to the center of the furnace number signboard can be determined. And after the industrial personal computer is analyzed and processed by software, the identified furnace number and coordinate offset are transmitted to the central control PLC in a wireless communication mode, the PLC controls walking, and four-vehicle interlocking control is carried out according to the positioning position.
The system comprises the following components: the computer vision positioning system for the four coke ovens comprises an industrial personal computer, a high-resolution variable-focus industrial high-speed camera, an image acquisition card, an oven number signboard, a stable light source, an AP + CPE wireless network, a central control PLC and the like.
The image recognition software system is the core and key technology of the whole computer vision positioning system, and the algorithm of the image recognition software system is directly related to the running speed and the recognition accuracy of the system. The image recognition software system mainly comprises: image preprocessing, edge extraction and image identification. The software flow chart of the image software identification software system is as follows:
(1) Image preprocessing:
the number signboard image shot by an industrial camera inevitably generates some noise in the transmission and conversion processes, so that the noise-removing and image-enhancing image preprocessing is required before the image processing. The noise brings many difficulties to image processing, and has direct influence on subsequent image processing such as image segmentation, edge extraction, image recognition and the like. Therefore, the number signboard image collected in real time needs to be filtered.
(2) Edge extraction:
in order to separate the furnace number signboard image from a complex background in the image identification processing, the obtained part edge image is subjected to binarization processing and gray value processing.
(3) Image recognition:
when the locomotive runs, the number plate number and the offset between the camera center and the furnace number signboard are analyzed by comparing the real-time collected image with the prestored signboard image. And transmitting the data to the central control PLC through wireless communication to perform interlocking control.
For the selection of the furnace number signboard in the technical scheme, the digital signboard is only used as one of the markers, and the furnace number signboard can also be replaced by a graduated scale, a color card and the like.
In a word, the invention has high positioning speed, can work for a long time and can run for 24 hours all day. In the production operation of a coke-oven plant, the furnace body number plate is mainly recognized by the naked eyes of a cart operator, the locomotive is driven to be aligned in the alignment, the eyes of the operator are easy to be tired after long-time operation, and the operator is easily influenced by emotion and can cause production accidents in severe cases. Each operator has slight difference in the judgment of the target operation furnace number center, and needs to be competent by operators with abundant experience. When the production rhythm is tense, the rapid positioning by manpower cannot be ensured. The computer vision positioning technology not only overcomes the defects of the traditional manual furnace number positioning method, but also plays the advantages of rapidness and accuracy.
Claims (10)
1. The computer vision-based positioning method for the four coke oven trucks is characterized by comprising the following steps:
controlling a camera installed on a locomotive to shoot images in real time, and extracting a first image shot by the camera when a furnace number marker is in a camera shooting range;
comparing the first image with each second image in a pre-stored image library to identify the furnace number of the locomotive, and extracting the offset between the camera and the corresponding furnace number identifier, wherein each second image in the image library is an image obtained by shooting each furnace number identifier;
and determining positioning information according to the furnace number and the offset.
2. The method of claim 1, wherein prior to comparing the first image to each of the second images in the pre-stored image library, the method further comprises:
preprocessing a first image, and performing edge extraction processing on the preprocessed first image, wherein the edge-extracted first image is used for comparing with the second image.
3. The method according to claim 2, wherein the preprocessing includes at least one of a noise removal processing and an image enhancement processing, and the edge extraction processing includes at least one of a binarization processing and a gradation value processing.
4. The method of claim 1, wherein the oven number identifier comprises a scale, a color card, or a digital oven number identifier plate.
5. The method of claim 1, wherein comparing the first image to each second image in a library of pre-stored images to identify a furnace number in which the locomotive is located comprises:
determining second images with similarity exceeding a preset value with the first image according to comparison results of the first images and all second images in a pre-stored image library;
and taking the furnace number corresponding to the second image as the furnace number of the locomotive.
6. The method of claim 1, wherein the locating information comprises the furnace number and the offset, or wherein the locating information comprises determining a relative position between the locomotive and the furnace number based on the furnace number and the offset.
7. A control method, characterized in that the positioning information determined according to the method of any one of claims 1 to 6 is transmitted to a central control module, and the central control module performs four-vehicle interlocking control.
8. A positioning device, comprising:
the system comprises an extraction module, a first storage module and a second storage module, wherein the extraction module is used for controlling a camera arranged on a locomotive to shoot images in real time and extracting a first image shot by the camera when a furnace number marker is in a camera shooting range;
the first determining module is used for comparing the first image with each second image in a pre-stored image library, identifying the furnace number of the locomotive and extracting the offset between the camera and the corresponding furnace number marker, wherein each second image in the image library is an image obtained by shooting each furnace number marker;
and the second determining module is used for determining positioning information according to the furnace number and the offset.
9. The apparatus of claim 8, further comprising:
and the processing module is used for preprocessing the first image and performing edge extraction processing on the preprocessed first image before comparing the first image with each second image in a pre-stored image library.
10. A control device, characterized by comprising a transmitting module and a positioning device according to claim 8 or 9;
the sending module is used for sending the positioning information determined by the second determining module to the PLC central control module;
and the central control module is used for carrying out four-vehicle interlocking control according to the positioning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211458979.8A CN115731380A (en) | 2022-11-17 | 2022-11-17 | Computer vision-based positioning method, control method and device for four coke oven trucks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211458979.8A CN115731380A (en) | 2022-11-17 | 2022-11-17 | Computer vision-based positioning method, control method and device for four coke oven trucks |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115731380A true CN115731380A (en) | 2023-03-03 |
Family
ID=85296948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211458979.8A Pending CN115731380A (en) | 2022-11-17 | 2022-11-17 | Computer vision-based positioning method, control method and device for four coke oven trucks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115731380A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117050760A (en) * | 2023-10-13 | 2023-11-14 | 山西中科冶金建设有限公司 | Intelligent coal charging and coke discharging system |
-
2022
- 2022-11-17 CN CN202211458979.8A patent/CN115731380A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117050760A (en) * | 2023-10-13 | 2023-11-14 | 山西中科冶金建设有限公司 | Intelligent coal charging and coke discharging system |
| CN117050760B (en) * | 2023-10-13 | 2023-12-15 | 山西中科冶金建设有限公司 | Intelligent coal charging and coke discharging system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111899288B (en) | Tunnel leakage water area detection and identification method based on infrared and visible light image fusion | |
| CN115731380A (en) | Computer vision-based positioning method, control method and device for four coke oven trucks | |
| CN108009484B (en) | Intelligent light bar collecting system and method based on machine vision technology | |
| CN105424330A (en) | Lorry shaft end bolt fault detecting method and lorry shaft end bolt fault detecting device | |
| CN105172842B (en) | A kind of train is driven to calibration method, equipment and system by station track | |
| CN107097813A (en) | One kind reorganizes and outfit a locomotive alignment system | |
| CN211401691U (en) | Different-sound rail bottom acoustic diagnosis device for driving mechanism of running part of motor train unit | |
| CN104320613A (en) | Monitoring method, monitoring system and positioning system for maintenance operation of motor car | |
| CN103595125A (en) | An electrical device on-line monitoring system based on an image identification technique | |
| CN111079734A (en) | Method for detecting foreign matters in triangular holes of railway wagon | |
| CN114581437A (en) | Visual inspection system for visual track guided by visual identification | |
| CN104298993A (en) | Pole number positioning and identification method suitable for railway line in complex scene | |
| CN111368833B (en) | Full-automatic steel loading method for detecting slab number based on machine vision | |
| CN112109769B (en) | Wheel tread damage detection method based on urban rail vehicle wheel tread damage detection system | |
| CN111681265B (en) | Online detection method for contact point of railway pantograph and contact network | |
| CN104850869A (en) | Automatic identification system and method for high-speed railway CPIII marker | |
| CN111144235B (en) | Switch tongue track crawling monitoring method based on video | |
| CN110909745A (en) | Train disinfection channel identification system | |
| CN204188798U (en) | A kind of positioning system of the real-time position information for obtaining motor car inspection and repair personnel | |
| CN103042822B (en) | Control system and method of double identification code dynamic digit of presswork | |
| CN108268812A (en) | A kind of device and method for being used to identify aluminium alloy compression casting wheel hub | |
| CN114771599A (en) | Method and system for positioning rail fault, storage medium and electronic equipment | |
| CN112082507A (en) | Intelligent detection system for subway vehicle faults | |
| CN102928093A (en) | Infrared-based billet surface temperature measurement device | |
| CN109754410B (en) | Railway vehicle carriage counting method based on machine 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 |