A tunnel train visual positioning device, method, equipment and medium

Abstract

The application relates to a tunnel train visual positioning device, method, equipment and medium, which comprises a vehicle-mounted controller, a vehicle-mounted visual odometer, a train surface identification code, a trackside visual beacon, a trackside visual axle counter and feature points arranged at a set distance inside the tunnel; the vehicle-mounted visual odometer collects the trackside visual beacon and the feature points, and the trackside visual axle counter collects the train surface identification code; the vehicle-mounted controller obtains the current speed and the relative displacement from the vehicle-mounted visual odometer, calculates the current position in the line according to the trackside visual beacon and performs calibration positioning, simultaneously obtains the current position in the line from the trackside visual axle counter and performs calibration positioning, so that continuous train speed measurement and positioning are realized. Compared with the prior art, the application has the advantages of enhanced redundancy and availability of the positioning system, lower cost and the like.

Description

Technical Field

[0001] The present invention relates to a rail transit signal system, and in particular to a device, method, equipment and medium for visually positioning a train in a tunnel. Background Art

[0002] Currently, there are two common speed measurement and positioning methods in the rail transit signaling industry: one that uses photoelectric / Hall-effect speed sensors combined with ground beacons, and the other that uses satellite virtual transponders combined with speed sensors. The former relies on the density of beacon placement for accuracy, resulting in higher system costs. The latter, however, uses satellite signals that are easily obstructed by tunnels and buildings, has high requirements for terrain, and is less universal.

[0003] After searching, Chinese patent publication number CN111114593A discloses a subway train autonomous positioning device, system and method based on multi-information fusion, which specifically discloses an inertial navigation device for autonomous navigation and positioning of subway trains and calculation of inertial navigation positioning information; a visual device for monitoring image beacons set at fixed positions beside the subway track and calculating visual positioning information; a data processing device for receiving information reported by the inertial navigation device and the visual device, performing information fusion and obtaining fused positioning information; although the patent uses a visual device to achieve positioning, the visual device is used to measure the distance between the front of the vehicle and the marker, and the information collected by the visual device is only used as one of the fusion information sources, and its weight is not clear, and it does not involve operations when the on-board autonomous positioning system fails.

[0004] Meanwhile, Chinese Patent Publication No. CN116946214A discloses a train positioning and speed measurement system, method, device, and medium based on visual recognition. Specifically, the system includes: mileage signs with QR codes, placed at set distances along the track; a camera for capturing the QR code image on the mileage sign; and a security host connected to the camera for parsing the QR code image captured by the camera, identifying the mileage sign ahead, and using the positioning pattern on the QR code to calculate the distance from the vehicle to the mileage sign ahead through a distance measurement algorithm. Although the patent uses a visual device for positioning, the visual device is used for distance measurement and requires a kilometer mark within the viewing range to measure distance, which is a discontinuous distance measurement method.

[0005] Furthermore, Chinese Patent Publication No. CN116136404A discloses a low-cost, all-regional speed measurement and positioning method and apparatus for train control onboard equipment. Specifically, if the satellite signal status is in a failed state, a multi-sensor fusion method is used to establish an inertial sensor error model. The inertial sensor error is estimated using the difference between the inertial sensor and other sensor measurements, and feedback correction is performed to obtain final train status information. Although the patent uses a visual device for positioning, the specific positioning process of the visual device is not discussed. Furthermore, the information collected by the visual device is only used as one source of fusion information, and its weight is not clearly defined.

[0006] It can be seen from this that the speed measurement and positioning methods commonly used in the existing technology cannot take into account both cost and universality in the tunnel environment, and the publicly disclosed solutions using visual positioning cannot be used alone (there is a problem of inability to continuously position), and require the assistance of other types of speed measurement and positioning equipment, and lack countermeasures after failure. Summary of the Invention

[0007] The purpose of the present invention is to provide a device, method, equipment and medium for visual positioning of trains in tunnels in order to overcome the defects of the above-mentioned prior art.

[0008] The purpose of the present invention can be achieved by the following technical solutions:

[0009] According to a first aspect of the present invention, there is provided a visual positioning device for a train in a tunnel, the device comprising an onboard controller, an onboard visual odometer, a train surface identification code, a trackside visual beacon, a trackside visual axle counter, and feature points arranged at set distances inside the tunnel;

[0010] The on-board visual odometer collects trackside visual beacons and feature points, and the trackside visual axle counter collects train surface identification codes; the on-board controller obtains the current speed and relative displacement from the on-board visual odometer, calculates the current position on the line based on the trackside visual beacons and performs calibration positioning, and at the same time obtains the current position on the line from the trackside visual axle counter and performs calibration positioning, thereby realizing continuous speed measurement and positioning of the train.

[0011] As a preferred technical solution, the on-board controller includes a first computing unit and a first storage device. The first computing unit obtains an electronic route map containing trackside visual beacon information from the first storage device. The first storage device is used to store the electronic route map and train parameters.

[0012] As a preferred technical scheme, the vehicle-mounted visual odometer comprises a first camera and a first image processing unit, the first camera acquires a trackside image and a trackside visual beacon and sends them to the first image processing unit, and the first image processing unit calculates a relative running distance of the train according to the acquired trackside image and calibrates the position of the train according to the trackside visual beacon.

[0013] As a preferred technical scheme, the train surface identification code comprises a first two-dimensional code and a first bar code, both of which correspond to a unique identification code of the train.

[0014] As a preferred technical scheme, the trackside visual beacon comprises up-and-down direction identification and a second two-dimensional code and a second bar code, both of which correspond to a unique identification code of the visual beacon in an electronic line map.

[0015] As a preferred technical scheme, the trackside visual axle comprises a second camera, a second image processing unit and a communication device, the second camera acquires a train surface identification code and sends it to the second image processing unit, the second image processing unit identifies the train and calculates the position of the train, and sends a position message to the train through the communication device and sends a train position message to a control center.

[0016] As a preferred technical scheme, the characteristic points arranged at a set distance inside the tunnel comprise reflective letter and number patterns, and are not repeated throughout the line.

[0017] As a preferred technical scheme, the distance between every two characteristic points is determined by the field of view of the camera of the vehicle-mounted visual odometer, so as to ensure that at least one characteristic point is included in the image acquired by the train at a set speed in each cycle.

[0018] According to a second aspect of the present application, a positioning method using the train visual positioning device in the tunnel is provided, which comprises the following steps:

[0019] In step S1, a vehicle-mounted controller pre-stores an electronic line map containing trackside visual beacon information, and a trackside visual axle pre-stores identification codes of all possible running trains on the line;

[0020] In step S2, a train is positioned and initialized according to a trackside visual beacon;

[0021] In step S3, a vehicle-mounted visual odometer acquires a trackside image and calculates a relative running distance in each cycle, and a vehicle-mounted controller accumulates a running distance;

[0022] In step S4, when a trackside visual beacon is detected, a vehicle-mounted visual odometer is calibrated;

[0023] Step S5: When the trackside visual axle counter detects a train passing by, it identifies the train and continuously calculates the train's position, then sends a position message to the train and simultaneously sends a train position message to the control center;

[0024] Step S6: When a communication failure occurs on the train, or a failure occurs on the onboard controller, or a failure occurs on the onboard visual odometer, the trackside visual axle counter detects the train position and reports the faulty train position to the control center.

[0025] As a preferred technical solution, the trackside visual beacon information in step S1 includes a unique identification code of each visual beacon and its position on the track.

[0026] As a preferred technical solution, the specific process of positioning initialization in step S2 is as follows:

[0027] The on-board visual odometer detects the trackside visual beacon, identifies the unique identification code of the beacon based on the second QR code and the second barcode on the trackside visual beacon, obtains the basic position based on the position of the unique identification code on the route map, obtains the offset of the basic position based on the distance difference between the focal center of the first camera and the center of the beacon, and obtains the running direction based on the up and down direction identification on the beacon combined with the displacement direction of the beacon relative to the beacon in the previous and next two cycles, thereby calculating the initialization positioning of the train.

[0028] As a preferred technical solution, the relative running distance is calculated in step S3 as follows:

[0029] Step S301: training static image data of feature points in the tunnel to obtain an initialized model;

[0030] Step S302: Combine the dynamic image data captured at low, medium and high vehicle speeds to continue training the initialization model to obtain a basic model;

[0031] Step S304: adding noise data to the dynamic image data, training a basic model, and obtaining an application model;

[0032] Step S305 , in the field application, the application model is used to identify feature points in the collected image, and the relative distance between the same feature points in two consecutive cycles is calculated to obtain the relative running distance of the train.

[0033] As a preferred technical solution, the positioning calibration in step S4 is specifically as follows:

[0034] Step S401: The onboard controller calculates the train's position based on the position of the visual beacon, which is the same as the positioning initialization process in step S2.

[0035] Step S402: The onboard controller accumulates the relative displacement fed back by the visual odometer in each cycle to obtain the second train position;

[0036] Step S403, correcting the train position 2 according to the train position 1 to obtain the train position 3, that is, obtaining a more accurate train position.

[0037] As a preferred technical solution, the identification of the train and continuous calculation of the train position in step S5 are specifically as follows:

[0038] Step S501, training a model for trackside visual axle counting to identify trains;

[0039] Step S502: pre-marking and calibrating absolute position points within the viewing range of the second camera of the trackside visual axle counting system, which serve as reference points for locating the train position in subsequent processes;

[0040] Step S503: When a train is detected passing by (in two consecutive cycles, the train goes from not appearing in the image to appearing in the image), the train identification code is identified (and cross-checked) using the QR code and barcode on the train body to determine the train's identity, and the train's absolute position is calculated using pre-calibrated reference points.

[0041] Step S504: continuously update the train's position (using the same updating method as the calculation of the relative running distance in step S3) until the train leaves the camera's viewing range.

[0042] According to a third aspect of the present invention, an electronic device is provided, comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the method when executing the program.

[0043] According to a fourth aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0044] Compared with the prior art, the present invention has the following advantages:

[0045] 1) The train visual positioning technology of the present invention only uses onboard visual sensors and trackside visual tags and visual sensors. Compared with traditional beacons, odometers and axle counters, the equipment is simpler and the deployment, operation and maintenance costs are lower.

[0046] 2) The present invention fully considers the failure of onboard equipment and provides a backup positioning mode through trackside visual axle counting, thereby enhancing the redundancy and availability of the positioning system;

[0047] 3) The present invention uses visual sensors to achieve the positioning process. Compared with traditional speed measurement and positioning devices that are prone to idling slip errors and satellite positioning technology that is prone to signal interruption inside tunnels, the present invention can better achieve improved positioning accuracy and enhanced positioning availability. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flow chart of a method for visual positioning of a train in a tunnel provided by one embodiment of the present invention;

[0049] Figure 2 A diagram showing the structure of a visual positioning device for trains in tunnels according to one embodiment of the present invention;

[0050] Figure 3 A schematic diagram of the deployment of a visual positioning device for trains in a tunnel according to an embodiment of the present invention;

[0051] Figure 4 This is a flowchart of initialization positioning of a method for visual positioning of a train in a tunnel provided by one embodiment of the present invention;

[0052] Figure 5 This is a flow chart of the method for visual positioning of a train in a tunnel provided by one embodiment of the present invention, in which the trackside visual axle counting is used to detect the positioning of the train. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0054] Figure 1 This is a flow chart of a method for visual positioning of a train in a tunnel according to an embodiment of the present invention. The specific process is as follows:

[0055] Step S1: The onboard controller pre-stores an electronic route map containing trackside visual beacon information, and the trackside visual axle counter pre-stores identification codes of all trains that may run on the route, wherein the trackside visual beacon information includes a unique identification code of each visual beacon and its position on the route;

[0056] Step S2: Initialization of the train positioning based on the trackside visual beacon;

[0057] The positioning initialization process includes the on-board visual odometer detecting the trackside visual beacon, identifying the beacon's unique identification code based on the QR code and barcode on the beacon, obtaining the basic position based on the position of the unique identification code on the route map, obtaining the relative offset based on the distance difference between the camera focal center and the beacon center, and obtaining the running direction based on the up and down direction identification on the beacon and the displacement direction relative to the beacon in the previous and next two cycles, thereby calculating the train's initial positioning.

[0058] Step S3: The train's visual odometry periodically acquires trackside images and calculates the relative running distance, and the onboard controller accumulates the running distance;

[0059] Among them, the process of calculating the relative running distance includes training the static image data of the feature points in the tunnel in advance to obtain an initialization model; then combining the dynamic image data taken at low, medium and high speeds to continue training the initialization model to obtain a basic model; finally, adding noise data on the basis of the dynamic image data, training the basic model, and obtaining an application model; in field applications, the application model is used to identify the feature points in the collected images, calculate the relative distance of the same feature point in two consecutive cycles, and obtain the relative running distance of the train.

[0060] Step S4: When the trackside visual beacon is detected, the train's visual odometer performs positioning calibration;

[0061] The positioning calibration process includes: first, the on-board controller calculates the train's position 1 based on the position of the visual beacon, which is the same as the positioning initialization process in step S2; secondly, the on-board controller also accumulates the relative displacement feedback from the visual odometer every cycle to obtain the train's position 2; finally, the train's position 2 is corrected based on the train's position 1 to obtain the train's position 3, that is, a more accurate train position.

[0062] Step S5: When the trackside visual axle counter detects a train passing by, it identifies the train, continuously calculates the train's position, and sends a position message to the train and simultaneously sends a train position message to the control center;

[0063] Among them, the process of detecting, identifying the train and continuously updating the train position includes training a model for identifying trains for trackside axle counting in advance, and the training process is the same as the training process in step S3; pre-marking and calibrating absolute position points within the field of view of the trackside visual axle counting camera as reference points for locating the train position in subsequent processes; in formal engineering applications, when a train is recognized to pass (in two consecutive cycles, the train goes from not appearing in the picture to appearing in the picture), the train identification code is identified (and mutually verified) through the QR code and barcode on the train body, the train identity is determined, and the absolute position of the train is calculated through the pre-calibrated reference points; the train position is continuously updated (the update method is the same as the calculation of the relative running distance in step 3) until the train leaves the camera's field of view.

[0064] Step S6: When a communication failure occurs on the train, or a failure occurs on the train's onboard controller, or a failure occurs on the train's visual odometer equipment, the visual axle counter on the trackside detects the train's position and reports the faulty train's position to the control center.

[0065] Figure 4 This is a flowchart for initializing positioning of a method for visual positioning of a train in a tunnel according to an embodiment of the present invention. During the train's movement, the visual odometer detects a trackside visual beacon; the unique identification code of the beacon is identified by recognizing the QR code and the barcode; the beacon identification code corresponding to the QR code is determined to be consistent with the beacon identification code corresponding to the barcode; if they are inconsistent, the information of the visual beacon is discarded; if they are consistent, further processing is performed; the legality of the visual beacon is determined based on the stored electronic route map and the naming rules for the beacon identification code; if it is illegal, the visual beacon is discarded; if it is legal, further processing is performed; the position of the visual beacon in the electronic route map is searched; the offset between the center of the camera and the center of the visual beacon is calculated; the running direction of the train is determined based on the up and down signs of the visual beacon and the movement direction of the two previous and next cycles; the distance traveled by the train from capturing the visual beacon to completing the calculation is calculated; and the final initialization positioning of the train is obtained.

[0066] Figure 5The present invention provides a flow chart of a method for visual positioning of trains in tunnels using trackside visual axle counting to detect train positioning. The trackside visual axle counting method detects the passage of a train, i.e., the train changes from not appearing in the image to appearing in the image; identifies the QR code and barcode on the surface of the train, and identifies the unique train identification code corresponding to the two; determines whether the beacon identification code corresponding to the QR code is consistent with the beacon identification code corresponding to the barcode; if not, an alarm is sent to the control center and an image is uploaded; if consistent, further processing is performed; the validity of the train identification code is determined by combining the stored identification codes of all trains that may appear on the line and the naming rules for train identification codes; if not, an alarm is sent to the control center and an image is uploaded; if legal, further processing is performed; the offset between the reference point and the train identification code is calculated based on the position of a pre-calibrated reference point, thereby calculating the absolute position of the train; and the train positioning is reported to the control center.

[0067] The above is an introduction to a method embodiment. The following further illustrates the solution of the present invention through an apparatus embodiment.

[0068] Figure 2 This is a diagram illustrating the structure of a visual positioning device for trains in a tunnel according to an embodiment of the present invention. The device includes an onboard controller 50, an onboard visual odometer 400, a train surface identification code 40, a trackside visual beacon 100, a trackside visual axle counter 300, and feature points 200 arranged at set intervals within the tunnel. The onboard controller 50 includes a first computing unit 501 and a first storage device 502. The onboard visual odometer 400 includes a first camera 30 and a first image processing unit 60. The trackside visual axle counter 300 includes a second camera 70 and a second image processing unit 80, as well as communication equipment. The trackside visual beacon 100 includes up and down markings 20 and a QR code and barcode 10.

[0069] Figure 3This is a deployment diagram of a visual positioning device for trains in tunnels according to an embodiment of the present invention. An onboard controller 50 and an onboard visual odometry 400 are installed on the train, a train surface identification code 40 is spray-painted on the train surface, and trackside visual beacons 100, a trackside visual axle counter 300, and characteristic points 200 arranged at predetermined intervals within the tunnel are arranged on both sides of the trackside within the tunnel. The first computing unit in the onboard controller is used to calculate the train's positioning information based on the relative displacement obtained from the train's visual odometry, the visual beacon's identification code information, position calibration information obtained from the control center, and information such as an electronic map, visual beacon identification code, and location obtained from a first storage device. The image processing unit and communication device of the trackside visual axle counter capture the train identification code information from the camera, combine it with all pre-stored train identification codes that may appear on the line, pre-delineate and calibrate absolute position point information, calculate the position of passing trains, and transmit it to the control center 500.

[0070] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0071] An embodiment of the present invention further provides an electronic device including a central processing unit (CPU), which can perform various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) or computer program instructions loaded from a storage unit into a random access memory (RAM). In the RAM, various programs and data required for device operation can also be stored. The CPU, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0072] Many components in a device are connected to the I / O interface, including: input units, such as a keyboard and mouse; output units, such as various types of displays and speakers; storage units, such as magnetic disks and optical disks; and communication units, such as network cards, modems, and wireless communication transceivers. The communication unit allows the device to exchange information / data with other devices via computer networks such as the Internet and / or various telecommunication networks.

[0073] The processing unit performs the various methods and processes described above, such as methods S1 to S6. For example, in some embodiments, methods S1 to S6 may be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as a storage unit. In some embodiments, part or all of the computer program may be loaded and / or installed onto the device via a ROM and / or a communication unit. When the computer program is loaded into the RAM and executed by the CPU, one or more steps of methods S1 to S6 described above may be performed. Alternatively, in other embodiments, the CPU may be configured to execute methods S1 to S6 by any other appropriate means (e.g., by means of firmware).

[0074] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0075] The program code for implementing the method of the present invention can be written in any combination of one or more programming languages. Such program code can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0076] In the context of the present invention, machine-readable medium can be a tangible medium that can contain or store a program for use with an instruction execution system, device or equipment or used in combination with an instruction execution system, device or equipment. Machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. Machine-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. More specific examples of machine-readable storage media can include electrical connections based on one or more lines, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0077] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and such modifications or substitutions are intended to be within the scope of protection of the present invention. Therefore, the scope of protection of the present invention shall be subject to the scope of protection of the claims.

Claims

1. A visual positioning device for trains in tunnels, characterized in that: The device comprises an onboard controller (50), an onboard visual odometer (400), a train surface identification code (40), a trackside visual beacon (100), a trackside visual axle counter (300), and characteristic points arranged at set distances inside a tunnel; The on-board visual odometer (400) collects the trackside visual beacon (100) and feature points, and the trackside visual axle counter (300) collects the train surface identification code (40); the on-board controller (50) obtains the current speed and relative displacement from the on-board visual odometer (400), calculates the current position on the line based on the trackside visual beacon (100), and performs calibration positioning, and simultaneously obtains the current position on the line from the trackside visual axle counter (300) and performs calibration positioning, thereby achieving continuous speed measurement and positioning of the train; The on-board visual odometer (400) includes a first camera (30) and a first image processing unit (60), wherein the first camera (30) acquires a trackside image and a trackside visual beacon (100) and sends the acquired trackside image to the first image processing unit (60), and the first image processing unit (60) calculates the relative running distance of the train based on the acquired trackside image and performs positioning calibration on the train based on the trackside visual beacon (100); The trackside visual axle counter (300) comprises a second camera (70), a second image processing unit (80), and a communication device. The second camera (70) collects a train surface identification code (40) and sends it to the second image processing unit (80). The second image processing unit (80) identifies the train, calculates the train position, and sends a position message to the train via the communication device, while simultaneously sending the train position message to the control center. The method of calculating the relative running distance of the trains is specifically as follows: training the static image data of the feature points in the tunnel to obtain an initialization model; combining the dynamic image data taken at low, medium and high speeds to continue training the initialization model to obtain a basic model; Add noise data to the dynamic image data, train the basic model, and obtain the application model; In field applications, the application model is used to identify feature points in the collected images, and the relative distance between the same feature points in two consecutive cycles is calculated to obtain the relative running distance of the train.

2. A visual positioning device for trains in tunnels according to claim 1, characterized in that: The onboard controller (50) comprises a first computing unit (501) and a first storage device (502), wherein the first computing unit (501) obtains an electronic route map containing trackside visual beacon information from the first storage device (502), and the first storage device (502) is used to store the electronic route map and train parameters.

3. The visual positioning device for trains in tunnels according to claim 1, characterized in that: The train surface identification code (40) comprises a first two-dimensional code and a first bar code, both corresponding to the train's unique identification code.

4. The visual positioning device for trains in tunnels according to claim 1, characterized in that: The trackside visual beacon (100) comprises an up and down direction identifier (20), a second two-dimensional code, and a second barcode (10), wherein the second two-dimensional code and the second barcode (10) both correspond to a unique identification code of the visual beacon in an electronic route map.

5. The visual positioning device for trains in tunnels according to claim 1, characterized in that: The characteristic points arranged at set intervals inside the tunnel include reflective letter and number patterns, and are not repeated along the entire line.

6. The visual positioning device for trains in tunnels according to claim 5, characterized in that: The distance between each two feature points is determined by the viewing range of the camera of the onboard visual odometer (400), ensuring that at a set speed, the image collected in each cycle contains at least one feature point.

7. A positioning method using the visual positioning device for trains in tunnels according to claim 1, characterized in that: The method comprises the following steps: Step S1, the onboard controller (50) pre-stores an electronic route map containing trackside visual beacon information, and the trackside visual axle counter (300) pre-stores identification codes of all trains that may run on the route; Step S2, the train performs positioning initialization according to the trackside visual beacon (100); Step S3, the onboard visual odometer (400) periodically acquires the trackside image and calculates the relative running distance, and the onboard controller (50) accumulates the running distance; Step S4, when the trackside visual beacon (100) is detected, the onboard visual odometer (400) performs positioning calibration; Step S5, when the trackside visual axle counter (300) detects a train passing by, it identifies the train and continuously calculates the train position, then sends a position message to the train and simultaneously sends a train position message to the control center; Step S6, when a communication failure occurs in the train, or a failure occurs in the onboard controller (50), or a failure occurs in the onboard visual odometer (400), the trackside visual axle meter (300) detects the train position and reports the faulty train position to the control center.

8. The positioning method according to claim 7, characterized in that: The trackside visual beacon information in step S1 includes a unique identification code of each visual beacon and its position on the track.

9. The positioning method according to claim 7, characterized in that: The specific process of positioning initialization in step S2 is as follows: The on-board visual odometer (400) detects a trackside visual beacon (100), identifies a unique identification code of the beacon based on the second QR code and the second bar code on the trackside visual beacon (100), obtains a basic position based on the position of the unique identification code on the route map, obtains an offset of the basic position based on the distance difference between the focal length center of the first camera (30) and the center of the beacon, and obtains a running direction based on the up and down direction identification on the beacon combined with the displacement direction of the beacon in the previous and next two cycles, thereby calculating the initial positioning of the train.

10. The positioning method according to claim 7, characterized in that: The relative running distance is calculated in step S3 as follows: Step S301: training static image data of feature points in the tunnel to obtain an initialized model; Step S302: Combine the dynamic image data captured at low, medium and high vehicle speeds to continue training the initialization model to obtain a basic model; Step S304: adding noise data to the dynamic image data, training a basic model, and obtaining an application model; Step S305 , in the field application, the application model is used to identify feature points in the collected image, and the relative distance between the same feature points in two consecutive cycles is calculated to obtain the relative running distance of the train.

11. The positioning method according to claim 7, characterized in that: The positioning calibration in step S4 is specifically as follows: Step S401, the onboard controller calculates the position of the train according to the position of the visual beacon; Step S402: The onboard controller accumulates the relative displacement fed back by the visual odometer in each cycle to obtain the second train position; Step S403, correcting the train's position 2 according to the train's position 1 to obtain the train's position 3.

12. The positioning method according to claim 7, characterized in that: The train identification and continuous calculation of the train position in step S5 are specifically as follows: Step S501, training a model for identifying trains for the trackside visual axle counter (300); Step S502, pre-marking and calibrating absolute position points within the viewing range of the second camera of the trackside visual axle counter (300), which serve as reference points for locating the train position in subsequent processes; Step S503: When a train is detected passing by, the train identification code is identified through the QR code and barcode on the train body to determine the train identity, and the absolute position of the train is calculated through the pre-calibrated reference points; Step S504: continuously update the position of the train until the train leaves the camera's viewing range.

13. An electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the program, the method according to any one of claims 7 to 12 is implemented.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 7 to 12 is implemented.

Images