CN117744681B - Freight train type and number recognition method and device - Google Patents
Freight train type and number recognition method and device Download PDFInfo
- Publication number
- CN117744681B CN117744681B CN202410182405.5A CN202410182405A CN117744681B CN 117744681 B CN117744681 B CN 117744681B CN 202410182405 A CN202410182405 A CN 202410182405A CN 117744681 B CN117744681 B CN 117744681B
- Authority
- CN
- China
- Prior art keywords
- vehicle type
- number information
- type number
- carriage
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000003137 locomotive effect Effects 0.000 claims abstract description 33
- 238000001514 detection method Methods 0.000 claims abstract description 29
- 230000002159 abnormal effect Effects 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims description 21
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000001502 supplementing effect Effects 0.000 claims description 4
- 230000026676 system process Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000007 visual effect Effects 0.000 description 4
- 239000000463 material Substances 0.000 description 3
- 238000012015 optical character recognition Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 239000003245 coal Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention provides a freight train type number identification method and device, and relates to the technical field of freight train information detection, wherein the method comprises the following steps: acquiring first vehicle type number information and second vehicle type number information of any target carriage when a vision-based locomotive type number recognition system and a radio frequency identification tag type number recognition system respectively recognize each carriage of a freight train; when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal, the first vehicle type number information is used as target vehicle type number information of a target carriage; when the first vehicle type number information is the same as the second vehicle type number information, the first vehicle type number information or the second vehicle type number information is used as target vehicle type number information of a target carriage, so that a freight train type number recognition system and a radio frequency identification tag vehicle type number recognition system based on vision can timely and accurately provide vehicle type number information, and continuity of a loading process is guaranteed.
Description
Technical Field
The invention relates to the technical field of freight train information detection, in particular to a freight train type and number identification method and device.
Background
The device for identifying the train number of the freight train carriage is widely applied to places such as loading stations and ports and is used for identifying the train type and the train number of the freight train so as to judge the volume or the type of materials to be loaded, is a key step for realizing the intellectualization and the unmanned of a loading system of the freight train, and in the related technology, the train number identification system is generally based on an RFID technology, and needs manual correction when missed detection and false detection occur to influence the loading process, so that a more intelligent freight train type and train number identification method is needed.
Disclosure of Invention
The present invention aims to solve at least one of the technical problems in the related art to some extent.
Therefore, a first object of the present invention is to provide a freight train type and number recognition method, which is based on a visual freight train type and number recognition system and a radio frequency identification tag type and number recognition system, to timely and accurately provide information of the vehicle type and number, and to ensure continuity of the loading process.
A second object of the present invention is to provide a freight train type number recognition device.
A third object of the present invention is to propose an electronic device.
A fourth object of the present invention is to propose a non-transitory computer readable storage medium storing computer instructions.
To achieve the above object, an embodiment of a first aspect of the present invention provides a method for identifying a model number of a freight train, the method comprising:
Acquiring first vehicle number information of any target carriage when a vision-based locomotive type number recognition system recognizes each carriage of a freight train, wherein the vision-based locomotive type number recognition system consists of a video acquisition device, a lighting device, an correlation switch and an edge computing terminal;
acquiring second type car number information of the radio frequency identification tag car type car number identification system for identifying the target carriage;
when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal, the first vehicle type number information is used as target vehicle type number information of a target carriage;
And when the first vehicle type number information is the same as the second vehicle type number information, taking the first vehicle type number information or the second vehicle type number information as target vehicle type number information of a target carriage.
To achieve the above object, an embodiment of a second aspect of the present invention provides a freight train type number identification device, the device including:
The system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first vehicle type number information of any target carriage when a vision-based locomotive type number identification system identifies each carriage of a freight train, and the vision-based locomotive type number identification system consists of a video acquisition device, a lighting device, an correlation switch and an edge calculation terminal;
The second acquisition module is used for acquiring second vehicle number information of the radio frequency identification tag vehicle type and vehicle number identification system for identifying the target carriage;
the first judging module is used for taking the first vehicle type number information as target vehicle type number information of a target carriage when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal;
and the second judging module is used for taking the first vehicle type number information or the second vehicle type number information as target vehicle type number information of a target carriage when the first vehicle type number information is the same as the second vehicle type number information.
According to the freight train type number identification method, the device electronic equipment and the storage medium, the first type number information and the second type number information of any target carriage when the vision-based locomotive type number identification system and the radio frequency identification tag type number identification system respectively identify each carriage of the freight train are obtained; when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal, the first vehicle type number information is used as target vehicle type number information of a target carriage; when the first vehicle type number information is the same as the second vehicle type number information, the first vehicle type number information or the second vehicle type number information is used as target vehicle type number information of a target carriage, so that a freight train type number recognition system and a radio frequency identification tag vehicle type number recognition system based on vision can timely and accurately provide vehicle type number information, and continuity of a loading process is guaranteed.
To achieve the above object, an embodiment of a third aspect of the present invention provides an electronic device, including: at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of the first aspect.
To achieve the above object, an embodiment of a fourth aspect of the present invention proposes a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the method according to the first aspect.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The foregoing and/or additional aspects and advantages of the invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings, in which:
fig. 1 is a schematic flow chart of a method for identifying a freight train type and number according to an embodiment of the present invention;
FIG. 2 is a diagram illustrating an exemplary apparatus for a vision-based recognition system for a model number of a locomotive according to an embodiment of the present invention;
Fig. 3 is a schematic flow chart of another method for identifying a model number of a freight train according to an embodiment of the present invention;
Fig. 4 is an exemplary diagram of a method for identifying a model number of a freight train according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a freight train type number recognition device according to an embodiment of the present invention.
Detailed Description
Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to like or similar elements or elements having like or similar functions throughout. The embodiments described below by referring to the drawings are illustrative and intended to explain the present invention and should not be construed as limiting the invention.
The technical scheme of the application is to acquire, store, use, process and the like data, which all meet the relevant regulations of national laws and regulations.
The method and the device for identifying the model number of the freight train according to the embodiment of the invention are described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a method for identifying a freight train type and number according to an embodiment of the present invention.
As shown in fig. 1, the method comprises the steps of:
Step 101, obtaining first vehicle type number information of any target carriage when a vision-based locomotive type number recognition system recognizes each carriage of a freight train, wherein the vision-based locomotive type number recognition system consists of a video acquisition device, a lighting device, a correlation switch and an edge computing terminal.
Alternatively, the video capture device may be a video camera, but is not limited thereto.
Alternatively, the lighting device may be a light-compensating lamp, but is not limited thereto.
In some embodiments, one implementation manner of obtaining the first type number information of any target carriage when the vision-based locomotive type number recognition system recognizes each carriage of the freight train may be to collect a carriage surface image of any target carriage when recognizing each carriage of the freight train based on the video acquisition device, where the lighting device is used to supplement a light source when collecting the carriage surface image for the video acquisition device; the opposite-shooting switch is used for triggering the video acquisition device to acquire a carriage surface image of the target carriage when detecting the gap between two carriages corresponding to the freight train; the edge computing terminal is internally provided with a vehicle type number detection model and a character recognition model, character area detection is carried out on a carriage surface image of a target carriage through the vehicle type number detection model to obtain a character area image containing vehicle type number information, and character recognition is carried out on the character area image based on the character recognition model to obtain first vehicle type number information.
Specifically, as shown in fig. 2, an example of a device of the vision-based locomotive model number recognition system is shown, when a freight train corresponding to a coal conveyer passes through, a clearance trigger camera between two carriages is detected by an opposite-shooting switch to collect a carriage surface image of any one target carriage in each carriage, character region detection is performed on the carriage surface image of the target carriage by a built-in model number detection model in an edge calculation terminal to obtain a character region image containing model number information, and character recognition is performed on the character region image based on a built-in character recognition model in the edge calculation terminal to obtain first model number information (model number and number of the target carriage).
Wherein the camera may be installed at the side of the freight train running track, but is not limited thereto.
Further, since the information of the train carriage type and number is not rotated normally, the direction of the words of the information of the train carriage type and number collected by the fixedly installed camera is stable, a direction detection model can be omitted, and in the detection process, when the vision-based recognition system of the train carriage type and number processes the carriage surface images of a plurality of target carriages, each carriage surface image is used as the input of the model of the train carriage type and number detection model, so that a plurality of character area images corresponding to each carriage surface image are obtained; obtaining the spatial position relation of each character area image according to the coordinate relation of the plurality of character area images; and sequentially inputting the images of the character areas into a character recognition model based on the spatial position relationship to obtain first vehicle type number information of each target carriage.
Among them, the model for detecting the vehicle model and the number of the vehicle can use the target detection models commonly used by two-stage optical character recognition (Optical Character Recognition, OCR), such as a scene text detector (AN EFFICIENT AND Accurate Scene Text Detector, EAST), text detection (Real-TIME SCENE Text Detection with Differentiable Binarization, DB) and a progressive scale expansion network (progressive scale expansion network, PSENet); character recognition models may be used
A data generation Model (Reciprocal Feature Learning, RFL), a single Visual Model based scene Text Recognition algorithm (Scene Text Recognition WITH A SINGLE Visual Model, SVTR), and a Visual converter for fast and efficient scene Text Recognition (Vision Transformer for FAST AND EFFICIENT SCENE Text Recognition, viTSTR).
Step 102, obtaining second vehicle type number information for identifying the target carriage by the radio frequency identification tag vehicle type number identification system.
In some embodiments, the bottom of the freight train target carriage is provided with a radio frequency identification electronic tag describing the vehicle type and number information, and one implementation way of obtaining the second vehicle type and number information of the radio frequency identification tag vehicle type and number identification system for identifying the freight train may be to read the radio frequency identification electronic tag through a radio frequency identification antenna in the radio frequency identification tag vehicle type and number identification system, so that the read vehicle type and number information is used as the second vehicle type and number information.
Optionally, as shown in fig. 2, a radio frequency identification (Radio Frequency Identification, RFID) tag vehicle type number identification system is connected to an edge computing terminal of the vision-based locomotive type number identification system to transmit the second vehicle type number information to the edge computing terminal for processing.
Step 103, when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is determined to be abnormal, the first vehicle type number information is used as the target vehicle type number information of the target carriage.
Optionally, in a case where the first vehicle type number information includes first vehicle type information and first vehicle number information, and the second vehicle type number information includes second vehicle type information and second vehicle number information, a scene in which the first vehicle type number information is different from the second vehicle type number information may include that the first vehicle type information is the same as the second vehicle type information, and the first vehicle number information is different from the second vehicle number information; the first vehicle type information is different from the second vehicle type information, and the first vehicle number information is different from the second vehicle number information; the first vehicle type information is different from the second vehicle type information, and the first vehicle number information is the same as the second vehicle number information.
Alternatively, the second vehicle type number information abnormality may include, but is not limited to, the collected vehicle type number information when an RFID card (electronic tag) is lost or damaged.
Step 104, when the first vehicle type number information is the same as the second vehicle type number information, the first vehicle type number information or the second vehicle type number information is used as the target vehicle type number information of the target carriage.
Alternatively, in the case where the first vehicle type number information includes first vehicle type information and first vehicle number information, and the second vehicle type number information includes second vehicle type information and second vehicle number information, a scene in which the first vehicle type number information is identical to the second vehicle type number information may include that the first vehicle type information is identical to the second vehicle type information, and the first vehicle number information is identical to the second vehicle number information.
According to the freight train type number identification method, first car type number information and second car type number information of any target carriage when a vision-based locomotive type number identification system and a radio frequency identification tag type number identification system respectively identify each carriage of a freight train are obtained; when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal, the first vehicle type number information is used as target vehicle type number information of a target carriage; when the first vehicle type number information is the same as the second vehicle type number information, the first vehicle type number information or the second vehicle type number information is used as target vehicle type number information of a target carriage, so that a freight train type number recognition system and a radio frequency identification tag vehicle type number recognition system based on vision can timely and accurately provide vehicle type number information, and continuity of a loading process is guaranteed.
In order to clearly illustrate the above embodiment, the present embodiment provides a method for identifying a model number of a freight train, and fig. 3 is a schematic flow chart of another method for identifying a model number of a freight train according to the embodiment of the present invention.
As shown in fig. 3, the method may include the steps of:
Step 301, obtaining first vehicle type number information of any target carriage when a vision-based locomotive type number recognition system recognizes each carriage of a freight train, wherein the vision-based locomotive type number recognition system consists of a video acquisition device, a lighting device, a correlation switch and an edge computing terminal.
Step 302, second vehicle type number information of the radio frequency identification tag vehicle type number identification system for identifying the target carriage is obtained.
In step 303, when the first vehicle type number information is different from the second vehicle type number information and it is determined that the second vehicle type number information is abnormal, the first vehicle type number information is used as the target vehicle type number information of the target carriage.
Step 304, when the first vehicle type number information is the same as the second vehicle type number information, the first vehicle type number information or the second vehicle type number information is used as the target vehicle type number information of the target carriage.
It should be noted that, regarding the specific implementation of steps 301 to 304, reference may be made to the related description in the above embodiments.
In step 305, when the first vehicle type number information is different from the second vehicle type number information and it is determined that the first vehicle type number information is abnormal, the abnormal first vehicle type number information and the abnormal carriage surface image corresponding to the abnormal first vehicle type number information are used as a set of training data.
In some embodiments, the training data set and the test data set may be divided according to a preset proportion, training may be performed by the training data set, and then verification may be performed by the test data set, so as to improve reliability of the vehicle model number detection model and the character recognition model.
Step 306, based on the training data, training and optimizing the model for detecting the vehicle type and the character recognition model, so as to take the optimized model for detecting the vehicle type and the character recognition model as a model for detecting the target vehicle type and a model for recognizing the target character of the vision-based locomotive type and the character recognition system.
In some embodiments, the accuracy of the vision-based locomotive model number recognition system is further enhanced by training data. When the RFID card of the freight train purely in the carriage is lost and damaged, the correct information of the vehicle type and the vehicle number can be read through a vision-based locomotive type and vehicle number recognition system formed by the target vehicle type and vehicle number detection model and the target character recognition model, so that the normal operation of the loading process is ensured.
According to the freight train type number identification method, first car type number information and second car type number information of any target carriage when a vision-based locomotive type number identification system and a radio frequency identification tag type number identification system respectively identify each carriage of a freight train are obtained; when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal, the first vehicle type number information is used as target vehicle type number information of a target carriage; when the first vehicle type number information is the same as the second vehicle type number information, taking the first vehicle type number information or the second vehicle type number information as target vehicle type number information of a target carriage, and taking carriage surface images corresponding to the first vehicle type number information and the first vehicle type number information as a group of training data under the condition that the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be normal; based on training data, training and optimizing the model for detecting the vehicle model number and the model for recognizing the character, so that the model for detecting the vehicle model number and the model for recognizing the character after optimization are used as a model for detecting the target vehicle model number and a model for recognizing the target character of the system for recognizing the vehicle model number based on vision. Therefore, the freight train type number recognition system based on vision and the radio frequency identification tag type number recognition system can provide the information of the type number timely and accurately, simultaneously continuously optimize the freight train type number recognition system based on vision and improve the recognition precision of the freight train type number recognition system based on vision.
In summary, to better understand the present invention, the present invention further provides a flow chart of a freight train type number recognition method, as shown in fig. 4, in a freight train type number recognition system based on vision, based on a correlation switch and a light supplementing lamp, a carriage surface image of any one target carriage in each carriage is collected through a camera, character area detection is performed on the carriage surface image through a vehicle type number detection model, so as to obtain a character area image containing vehicle type number information, and character recognition is performed on the character area image based on the character recognition model, so as to obtain first vehicle type number information; in the radio frequency identification tag vehicle type and number identification system, a radio frequency identification antenna reads a radio frequency identification electronic tag of a target carriage to read second vehicle type and number information, and further the first vehicle type and the second vehicle type and number information can be compared through an edge computing terminal; based on the training data, training and optimizing the vehicle model and the character recognition model.
In order to achieve the above embodiment, the invention also provides a freight train type and number identification device.
Fig. 5 is a schematic structural diagram of a freight train type number recognition device according to an embodiment of the present invention.
As shown in fig. 5, the freight train model number recognition device 50 includes: the first acquisition module 51, the second acquisition module 52, the first judgment module 53, and the second judgment module 54.
The first obtaining module 51 is configured to obtain first vehicle type number information of any target carriage when the vision-based locomotive type number recognition system recognizes each carriage of the freight train, where the vision-based locomotive type number recognition system is composed of a video acquisition device, a lighting device, an correlation switch, and an edge computing terminal;
A second obtaining module 52, configured to obtain second vehicle type number information that is identified by the rfid tag vehicle type number identification system for the target vehicle compartment;
A first judging module 53, configured to, when the first vehicle type number information is different from the second vehicle type number information and it is judged that the second vehicle type number information is abnormal, take the first vehicle type number information as target vehicle type number information of a target carriage;
the second determining module 54 is configured to, when the first vehicle type number information is the same as the second vehicle type number information, use the first vehicle type number information or the second vehicle type number information as target vehicle type number information of a target carriage.
Further, in one possible implementation manner of the embodiment of the present invention, the first obtaining module 51 includes:
The system comprises a video acquisition device, an acquisition unit and a lighting device, wherein the video acquisition device is used for acquiring a carriage surface image of any target carriage when identifying each carriage of a freight train, and the lighting device is used for supplementing a light source when acquiring the carriage surface image for the video acquisition device; the opposite-shooting switch is used for triggering the video acquisition device to acquire a carriage surface image of a target carriage when detecting a gap between two carriages corresponding to the freight train;
The detection unit is used for carrying out character area detection on the carriage surface image of the target carriage through the vehicle type and number detection model to obtain a character area image containing vehicle type and number information, and carrying out character recognition on the character area image based on the character recognition model to obtain first vehicle type and number information.
Further, in one possible implementation manner of the embodiment of the present invention, the first obtaining module 51 further includes:
The input unit is used for taking each carriage surface image as the input of a vehicle type number detection model when the vision-based locomotive type number recognition system processes the carriage surface images of a plurality of target carriages so as to obtain a plurality of character area images corresponding to each carriage surface image;
the first generation unit is used for obtaining the spatial position relation of each character area image according to the coordinate relation of the plurality of character area images;
And the second generation unit is used for sequentially inputting the images of the character areas into the character recognition model based on the spatial position relation to obtain the first vehicle type number information of each target carriage.
Further, in one possible implementation manner of the embodiment of the present invention, the bottom of the freight train target compartment is installed with a radio frequency identification electronic tag describing the vehicle type number information, and the second obtaining module 52 is specifically configured to:
And reading the radio frequency identification electronic tag through a radio frequency identification antenna in the radio frequency identification tag vehicle type and number identification system so as to take the read vehicle type and number information as second vehicle type and number information.
Further, in one possible implementation manner of the embodiment of the present invention, the second determining module 54 is specifically configured to:
When the first vehicle type number information is different from the second vehicle type number information and the first vehicle type number information is judged to be abnormal, taking the abnormal first vehicle type number information and an abnormal carriage surface image corresponding to the abnormal first vehicle type number information as a group of training data;
Based on the training data, training and optimizing the model for detecting the vehicle type and the character recognition model, so that the optimized model for detecting the vehicle type and the character recognition model are used as a model for detecting the target vehicle type and a model for recognizing the target character recognition model of the system for recognizing the locomotive type and the character recognition based on vision.
According to the freight train type and number recognition device, a vision-based locomotive type and number recognition system and a radio frequency identification tag type and number recognition system are used for respectively recognizing first car type and second car type and number information of any target carriage when each carriage of a freight train is recognized; when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal, the first vehicle type number information is used as target vehicle type number information of a target carriage; when the first vehicle type number information is the same as the second vehicle type number information, the first vehicle type number information or the second vehicle type number information is used as target vehicle type number information of a target carriage, so that a freight train type number recognition system and a radio frequency identification tag vehicle type number recognition system based on vision can timely and accurately provide vehicle type number information, and continuity of a loading process is guaranteed.
In order to achieve the above embodiment, the present invention further provides an electronic device, including:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the aforementioned method.
To achieve the above embodiments, the present invention also proposes a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the aforementioned method.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms are not necessarily directed to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present invention, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps of the process, and additional implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order from that shown or discussed, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the embodiments of the present invention.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in the embodiments of the present invention may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. While embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the invention, and that variations, modifications, alternatives and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the invention.
Claims (7)
1. A method for identifying a model number of a freight train, the method comprising:
acquiring first vehicle type number information of any target carriage when a vision-based locomotive type number recognition system recognizes each carriage of a freight train, wherein the vision-based locomotive type number recognition system consists of a video acquisition device, a lighting device, an correlation switch and an edge computing terminal, wherein a vehicle type number detection model and a character recognition model are built in the edge computing terminal, character area detection is carried out on a carriage surface image of the target carriage through the vehicle type number detection model so as to obtain a character area image containing the vehicle type number information, and character recognition is carried out on the character area image based on the character recognition model so as to obtain first vehicle type number information;
acquiring second type car number information of the radio frequency identification tag car type car number identification system for identifying the target carriage;
when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal, the first vehicle type number information is used as target vehicle type number information of a target carriage;
When the first vehicle type number information is the same as the second vehicle type number information, the first vehicle type number information or the second vehicle type number information is used as target vehicle type number information of a target carriage;
The bottom of the freight train target carriage is provided with a radio frequency identification electronic tag for describing the vehicle type and number information, and the second vehicle type and number information for identifying the freight train by the radio frequency identification tag vehicle type and number identification system is obtained, and the radio frequency identification electronic tag comprises:
reading the radio frequency identification electronic tag through a radio frequency identification antenna in a radio frequency identification tag vehicle type and number identification system, so that the read vehicle type and number information is used as second vehicle type and number information;
When the first vehicle type number information is different from the second vehicle type number information and the first vehicle type number information is judged to be abnormal, taking the abnormal first vehicle type number information and an abnormal carriage surface image corresponding to the abnormal first vehicle type number information as a group of training data;
Based on the training data, training and optimizing the model for detecting the vehicle type and the character recognition model, so that the optimized model for detecting the vehicle type and the character recognition model are used as a model for detecting the target vehicle type and a model for recognizing the target character recognition model of the system for recognizing the locomotive type and the character recognition based on vision.
2. The method of claim 1, wherein the obtaining the first vehicle type number information of any target car when the vision-based locomotive type number recognition system recognizes each car of the freight train, wherein the vision-based locomotive type number recognition system is composed of a video acquisition device, a lighting device, an correlation switch, and an edge computing terminal, comprises:
Based on the video acquisition device, acquiring a carriage surface image of any target carriage when each carriage of the freight train is identified, wherein the lighting device is used for supplementing a light source when the video acquisition device acquires the carriage surface image; and the correlation switch is used for triggering the video acquisition device to acquire the carriage surface image of the target carriage when detecting the gap between two carriages corresponding to the freight train.
3. The method according to claim 2, characterized in that the method further comprises:
When the vision-based locomotive model number recognition system processes carriage surface images of a plurality of target carriages, taking each carriage surface image as input of a model for detecting the vehicle model number so as to obtain a plurality of character area images corresponding to each carriage surface image;
Obtaining the spatial position relation of each character area image according to the coordinate relation of the plurality of character area images;
and sequentially inputting the images of the character areas into the character recognition model based on the spatial position relation to obtain first vehicle type number information of each target carriage.
4. A freight train type number identification device, the device comprising:
The system comprises a first acquisition module, a second acquisition module and a third acquisition module, wherein the first acquisition module is used for acquiring first vehicle type number information of any target carriage when a vision-based locomotive type number identification system identifies each carriage of a freight train, and the vision-based locomotive type number identification system consists of a video acquisition device, a lighting device, an correlation switch and an edge calculation terminal;
The second acquisition module is used for acquiring second vehicle number information of the radio frequency identification tag vehicle type and vehicle number identification system for identifying the target carriage;
the first judging module is used for taking the first vehicle type number information as target vehicle type number information of a target carriage when the first vehicle type number information is different from the second vehicle type number information and the second vehicle type number information is judged to be abnormal;
The second judging module is used for taking the first vehicle type number information or the second vehicle type number information as target vehicle type number information of a target carriage when the first vehicle type number information is the same as the second vehicle type number information;
The first acquisition module includes:
The detection unit is used for carrying out character area detection on the carriage surface image of the target carriage through the vehicle type and number detection model to obtain a character area image containing vehicle type and number information, and carrying out character recognition on the character area image based on the character recognition model to obtain first vehicle type and number information;
The bottom of the freight train target carriage is provided with a radio frequency identification electronic tag for describing the vehicle type and number information, and the second acquisition module is specifically used for:
reading the radio frequency identification electronic tag through a radio frequency identification antenna in a radio frequency identification tag vehicle type and number identification system, so that the read vehicle type and number information is used as second vehicle type and number information;
The first judging module is further configured to, when the first vehicle type number information is different from the second vehicle type number information and the first vehicle type number information is judged to be abnormal, use the abnormal first vehicle type number information and an abnormal carriage surface image corresponding to the abnormal first vehicle type number information as a set of training data;
Based on the training data, training and optimizing the model for detecting the vehicle type and the character recognition model, so that the optimized model for detecting the vehicle type and the character recognition model are used as a model for detecting the target vehicle type and a model for recognizing the target character recognition model of the system for recognizing the locomotive type and the character recognition based on vision.
5. The apparatus of claim 4, wherein the first acquisition module comprises:
the system comprises a video acquisition device, an acquisition unit and a lighting device, wherein the video acquisition device is used for acquiring a carriage surface image of any target carriage when identifying each carriage of a freight train, and the lighting device is used for supplementing a light source when acquiring the carriage surface image for the video acquisition device; and the correlation switch is used for triggering the video acquisition device to acquire the carriage surface image of the target carriage when detecting the gap between two carriages corresponding to the freight train.
6. An electronic device, comprising:
at least one processor; and
A memory communicatively coupled to the at least one processor; wherein,
The memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method of any one of claims 1-3.
7. A non-transitory computer readable storage medium storing computer instructions for causing the computer to perform the method of any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410182405.5A CN117744681B (en) | 2024-02-19 | 2024-02-19 | Freight train type and number recognition method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410182405.5A CN117744681B (en) | 2024-02-19 | 2024-02-19 | Freight train type and number recognition method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117744681A CN117744681A (en) | 2024-03-22 |
| CN117744681B true CN117744681B (en) | 2024-05-07 |
Family
ID=90279872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410182405.5A Active CN117744681B (en) | 2024-02-19 | 2024-02-19 | Freight train type and number recognition method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117744681B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100134206A (en) * | 2009-06-15 | 2010-12-23 | (주) 알티솔루션 | The automatic vehicle identification system of non-trigger type based on image processing and that of using identification method |
| CN108171248A (en) * | 2017-12-29 | 2018-06-15 | 武汉璞华大数据技术有限公司 | A kind of method, apparatus and equipment for identifying train model |
| CN110619329A (en) * | 2019-09-03 | 2019-12-27 | 中国矿业大学 | Carriage number and loading state identification method of railway freight open wagon based on airborne vision |
| CN112132053A (en) * | 2020-09-24 | 2020-12-25 | 杭州海康威视数字技术股份有限公司 | Carriage identification method and device and computer storage medium |
| CN112613509A (en) * | 2020-12-25 | 2021-04-06 | 杭州智诺科技股份有限公司 | Railway wagon carriage number identification snapshot method and system |
| JP2023157152A (en) * | 2022-04-14 | 2023-10-26 | 三菱電機エンジニアリング株式会社 | Vehicle number reading device and vehicle number reading system |
| CN117132990A (en) * | 2023-08-29 | 2023-11-28 | 上海平奥供应链管理有限公司 | Railway carriage information identification method, device, electronic equipment and storage medium |
-
2024
- 2024-02-19 CN CN202410182405.5A patent/CN117744681B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20100134206A (en) * | 2009-06-15 | 2010-12-23 | (주) 알티솔루션 | The automatic vehicle identification system of non-trigger type based on image processing and that of using identification method |
| CN108171248A (en) * | 2017-12-29 | 2018-06-15 | 武汉璞华大数据技术有限公司 | A kind of method, apparatus and equipment for identifying train model |
| CN110619329A (en) * | 2019-09-03 | 2019-12-27 | 中国矿业大学 | Carriage number and loading state identification method of railway freight open wagon based on airborne vision |
| CN112132053A (en) * | 2020-09-24 | 2020-12-25 | 杭州海康威视数字技术股份有限公司 | Carriage identification method and device and computer storage medium |
| CN112613509A (en) * | 2020-12-25 | 2021-04-06 | 杭州智诺科技股份有限公司 | Railway wagon carriage number identification snapshot method and system |
| JP2023157152A (en) * | 2022-04-14 | 2023-10-26 | 三菱電機エンジニアリング株式会社 | Vehicle number reading device and vehicle number reading system |
| CN117132990A (en) * | 2023-08-29 | 2023-11-28 | 上海平奥供应链管理有限公司 | Railway carriage information identification method, device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117744681A (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103400500B (en) | Vehicle information data acquisition device and method | |
| EP2697738B1 (en) | Method and system of rail component detection using vision technology | |
| CN107743577B (en) | Method and apparatus for detecting vibration information of electric railway vehicle | |
| CN107273802B (en) | Method and device for detecting fault of brake shoe drill rod ring of railway train | |
| CN103512762A (en) | Image processing method and device and train fault detection system | |
| CN104567725A (en) | Vehicle operation fault detection system and method | |
| CN109242035B (en) | Vehicle bottom fault detection device and method | |
| CN111833302A (en) | Car number and case number identification association system | |
| CN105426894A (en) | Image detection method and device for railroad plug nails | |
| CN113788051A (en) | Train on-station running state monitoring and analyzing system | |
| CN113895481B (en) | Train positioning and tracking management method, device and medium based on pattern recognition | |
| CN117744681B (en) | Freight train type and number recognition method and device | |
| US20210397850A1 (en) | Fixed state inspection apparatus, fixed state inspection system, fixed state inspection method, and program | |
| CN112215222A (en) | License plate recognition method, device, equipment and storage medium | |
| CN115755000A (en) | Safety verification method and device for environment sensing equipment of obstacle detection system | |
| CN212302511U (en) | Car number and case number identification association system monitoring facilities | |
| JPH10105873A (en) | Device for recognizing number plate of vehicle | |
| CN110267231A (en) | It is a kind of based on the parking stall recognition methods of bluetooth RSSI, apparatus and system | |
| US20230342937A1 (en) | Vehicle image analysis | |
| CN106023600B (en) | A kind of vehicle speed detection method and device based on vehicle electron identifying | |
| CN109850596B (en) | Multi-target positioning method and system for train container and transport vehicle | |
| CN209835088U (en) | Train container multi-target positioning system and highway-railway transport vehicle | |
| CN113327337A (en) | Method for ensuring normal payment and departure of vehicle | |
| CN114005097A (en) | Train operation environment real-time detection method and system based on image semantic segmentation | |
| JP4552409B2 (en) | Image processing device |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |