Track status monitoring method, device, electronic equipment and medium

Abstract

The present application relates to a method, device, electronic device and medium for monitoring the state of a track, and to the field of detection of the state of a track. The method comprises obtaining the outer image information of the railings corresponding to each of the two groups of railings at a crossing after they are closed, and the inner image information between the two groups of railings, performing vehicle recognition on the inner image information, and obtaining a recognition result. If there is a vehicle in the recognition result of the inner image information, the center position of the inner vehicle distribution of the two groups of railings and the model of each inner vehicle are determined based on the inner image information, the target railings that need to be opened in the two groups of railings are determined based on the outer image information and the center position, the opening angle and opening speed of the target railing are determined based on the center position and the model of each inner vehicle, and the target railing is controlled to move according to the opening angle and opening speed. The present application has the effect of enabling trapped vehicles to exit the crossing quickly and safely.

Description

Technical Field

[0001] The present application relates to the field of track status monitoring, and in particular to a track status monitoring method, device, electronic equipment and medium. Background Art

[0002] With the development of economy and transportation industry, the number of train tracks is increasing, and there are more and more urban roads. The situation of tracks and roads intersecting also appears. Setting up crossings at the intersection of tracks and roads can enable both routes to pass smoothly. Before the train passes through the crossing, the vehicles or pedestrians on the road are stopped by the railings on both sides of the track. After the train passes smoothly, the railings are opened to release the vehicles or pedestrians on the road. However, there may be vehicles or pedestrians rushing when the railings fall. If the vehicles or pedestrians fail to successfully exit the crossing when the railings fall, the pedestrians can get out under the railings, but the vehicles will be trapped in the railings, which will cause a collision between the train and the vehicle, resulting in major traffic accidents with casualties and vehicle damage. At present, the railings are usually lifted by manual control to allow the trapped vehicles to leave the crossing. However, since the time for the train to arrive at the crossing is short, there may be delays in manually controlling the lifting of the railings, which may result in the vehicles being unable to leave the crossing in time, thus causing accidents. Summary of the invention

[0003] In order to enable trapped vehicles to exit the intersection quickly and safely, the present application provides a track status monitoring method, device, electronic equipment and medium.

[0004] In a first aspect, the present application provides a track status monitoring method, which adopts the following technical solution:

[0005] A track condition monitoring method, comprising:

[0006] Acquire outer side image information of the respective corresponding railings of two sets of railings at the crossing after they are closed and inner side image information between the two sets of railings, wherein the two sets of railings include a first railing and a second railing;

[0007] Performing vehicle recognition on the inner image information to obtain a recognition result;

[0008] If there is a vehicle in the recognition result of the inner image information, determining the center position of the inner side vehicle distribution of the two groups of railings and the model of each inner side vehicle based on the inner image information;

[0009] Determine a target railing to be opened in the two groups of railings based on the outer image information and the center position;

[0010] determining an opening angle and an opening speed of the target barrier based on the center position and the model of each inner vehicle;

[0011] The target railing is controlled to move according to the opening angle and opening speed.

[0012] By adopting the above technical solution, the outer image information of the railings corresponding to each of the two groups of railings at the crossing after they are closed and the inner image information between the two groups of railings are obtained. The outer and inner image information can reflect the traffic conditions inside and outside the railings at the crossing. Vehicle recognition is performed on the inner image information to obtain a recognition result. If there is a vehicle in the recognition result of the inner image information, it means that a vehicle is trapped inside the railing. Then, based on the inner image information, the center position of the vehicle distribution inside the two groups of railings and the model of each inner vehicle are determined. The center position can show the overall distribution position of the vehicle. In order for the trapped vehicle to be able to drive out more quickly and easily, it is necessary to determine which side of the railing is more convenient to open, and determine the target railing that needs to be opened in the two groups of railings based on the outer image information and the center position, and determine the opening angle and opening speed of the target railing based on the center position and the model of each inner vehicle. Both the angle and speed are important factors in whether the trapped vehicle can safely and quickly drive out of the crossing after the railing is opened. The target railing is then controlled to move according to the opening angle and opening speed, reducing the delay time of manual control of lifting the railing, so that the trapped vehicle can safely and quickly drive out of the crossing.

[0013] In another possible implementation, determining the center position of the vehicle distribution and the model of each inner vehicle based on the inner image information includes:

[0014] Establishing a coordinate system based on the inner image information and determining coordinate information of each inner vehicle center point;

[0015] Determine a geometric figure composed of the coordinate information based on the coordinate information;

[0016] Determine the center point coordinates of the geometric figure, wherein the center point coordinates represent the center position of the vehicle distribution;

[0017] The vehicle type is identified by performing vehicle type recognition on the inner image information based on the trained network model to obtain the model of each inner vehicle.

[0018] In another possible implementation, the outer image information includes first image information outside the first railing and second image information outside the second railing, and determining the target railing to be opened in the two groups of railings based on the outer image information and the center position includes:

[0019] Performing feature recognition on the first image information and the second image information to determine the first number of vehicles and the first number of people outside the first railing, and the second number of vehicles and the second number of people outside the second railing;

[0020] If the first vehicle quantity is 0 and the second vehicle quantity is not 0, determining the first barrier as the target barrier;

[0021] If the second vehicle quantity is 0 and the first vehicle quantity is not 0, determining the second barrier as the target barrier;

[0022] If both the first number of vehicles and the second number of vehicles are not 0, determine the first vertical distance of the center position from the first railing and the second vertical distance from the second railing, determine the first density of people and vehicles outside the first railing based on the first image information, and determine the second density of people and vehicles outside the second railing based on the second image information; determine the target railing based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information.

[0023] In another possible implementation, determining the target barrier based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density, and the inner image information includes:

[0024] calculating a first score based on the first vertical distance, the first number of vehicles, the first number of people, the first density, and respective first coefficients;

[0025] calculating a second score based on the second vertical distance, the second number of vehicles, the second number of people, the second density, and respective second coefficients;

[0026] If the first score is less than the second score, determining the first railing as the target railing;

[0027] If the first score is greater than the second score, determining the second railing as the target railing;

[0028] If the first score is equal to the second score, the vehicle head direction is identified based on the inner image information, and the guardrail corresponding to the side with a larger number of vehicle head directions is determined as the target guardrail.

[0029] In another possible implementation, the first railing and the second railing are both composed of a first lifting rod that can rotate in a vertical plane and a second lifting rod that can rotate in a universal direction, and the determining of the opening angle and the opening speed of the target railing based on the center position and the model of each inner vehicle includes:

[0030] Determine the target vehicle with the highest height based on the model of each vehicle, and obtain the height and position of the target vehicle;

[0031] Determining a minimum opening angle of a first lifting bar of a target barrier based on the height and position of the target vehicle;

[0032] Obtaining the distance from the train to the crossing, and determining the opening speed of the first lifting bar based on the number of vehicles inside the two groups of barriers, the distance, and the vertical distance from the target barrier to the center position;

[0033] Determine the ratio of the number of vehicles to the number of people outside the target barrier;

[0034] The horizontal rotation angle of the second lifting rod is determined based on the center position, and the horizontal rotation speed of the second lifting rod is determined based on the density of the outer side of the target railing, the ratio, and the vertical distance from the target railing to the center position.

[0035] In another possible implementation, the method further includes:

[0036] If the distance from the train to the crossing reaches a preset distance threshold, determine the safe speed value to which the train needs to decelerate based on the number of inner vehicles and the distance from the train to the crossing;

[0037] A safe speed value to which the train needs to decelerate is sent.

[0038] In another possible implementation, the method further includes:

[0039] Obtaining the time it takes for the train to arrive at the crossing, and determining the maximum time between the inner vehicle leaving the two sets of railings based on the time;

[0040] The display device at the crossing is controlled to display the maximum time.

[0041] In a second aspect, the present application provides a track state monitoring device, which adopts the following technical solution:

[0042] A track state monitoring device, comprising:

[0043] An image acquisition module, used to acquire outer image information of the railings corresponding to the two groups of railings at the crossing after they are closed and inner image information between the two groups of railings, wherein the two groups of railings include a first railing and a second railing;

[0044] An image recognition module, used to perform vehicle recognition on the inner image information to obtain a recognition result;

[0045] A first determination module is used to determine the center position of the inner side vehicle distribution of the two groups of railings and the model of each inner side vehicle based on the inner side image information if there is a vehicle in the recognition result of the inner side image information;

[0046] A target railing determination module, used to determine a target railing to be opened in the two groups of railings based on the outer image information and the center position;

[0047] A second determination module, configured to determine an opening angle and an opening speed of the target barrier based on the center position and the model of each inner vehicle;

[0048] The opening module is used to control the target railing to move according to the opening angle and opening speed.

[0049] By adopting the above technical solution, the image acquisition module obtains the outer image information of the railings corresponding to each of the two groups of railings at the crossing after the two groups of railings are closed, and the inner image information between the two groups of railings. The image recognition module performs vehicle recognition on the inner image information to obtain a recognition result. If there is a vehicle in the recognition result of the inner image information, the first determination module determines the center position of the vehicle distribution inside the two groups of railings and the model of each inner vehicle based on the inner image information. The target railing determination module determines the target railing that needs to be opened in the two groups of railings based on the outer image information and the center position. The second determination module determines the opening angle and opening speed of the target railing based on the center position and the model of each inner vehicle. The opening module controls the target railing to move according to the opening angle and opening speed, shortens the lifting time, and enables the trapped vehicle to quickly and safely exit the crossing.

[0050] In another possible implementation, when the first determination module determines the center position of the distribution of vehicles inside the two groups of railings and the model of each inside vehicle based on the inside image information, it is specifically used to:

[0051] Establishing a coordinate system based on the inner image information and determining coordinate information of each inner vehicle center point;

[0052] Determine a geometric figure composed of the coordinate information based on the coordinate information;

[0053] Determine the center point coordinates of the geometric figure, wherein the center point coordinates represent the center position of the vehicle distribution;

[0054] The vehicle type is identified by performing vehicle type recognition on the inner image information based on the trained network model to obtain the model of each inner vehicle.

[0055] In another possible implementation, the target railing determination module, when determining the target railing to be opened in the two groups of railings based on the outer image information and the center position, is specifically configured to:

[0056] Performing feature recognition on the first image information and the second image information to determine the first number of vehicles and the first number of people outside the first railing, and the second number of vehicles and the second number of people outside the second railing;

[0057] If the first vehicle quantity is 0 and the second vehicle quantity is not 0, determining the first barrier as the target barrier;

[0058] If the second vehicle quantity is 0 and the first vehicle quantity is not 0, determining the second barrier as the target barrier;

[0059] If both the first number of vehicles and the second number of vehicles are not 0, determine the first vertical distance of the center position from the first railing and the second vertical distance from the second railing, determine the first density of people and vehicles outside the first railing based on the first image information, and determine the second density of people and vehicles outside the second railing based on the second image information; determine the target railing based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information.

[0060] In another possible implementation, the target barrier determination module, when determining the target barrier based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density, and the inner image information, is specifically configured to:

[0061] calculating a first score based on the first vertical distance, the first number of vehicles, the first number of people, the first density, and respective first coefficients;

[0062] calculating a second score based on the second vertical distance, the second number of vehicles, the second number of people, the second density, and respective second coefficients;

[0063] If the first score is less than the second score, determining the first railing as the target railing;

[0064] If the first score is greater than the second score, determining the second railing as the target railing;

[0065] If the first score is equal to the second score, the vehicle head direction is identified based on the inner image information, and the guardrail corresponding to the side with a larger number of vehicle head directions is determined as the target guardrail.

[0066] In another possible implementation, the second determination module, when determining the opening angle and opening speed of the target barrier based on the center position and the model of each inner vehicle, is specifically configured to:

[0067] Determine the target vehicle with the highest height based on the model of each vehicle, and obtain the height and position of the target vehicle;

[0068] Determining a minimum opening angle of a first lifting bar of a target barrier based on the height and position of the target vehicle;

[0069] Obtaining the distance from the train to the crossing, and determining the opening speed of the first lifting bar based on the number of vehicles inside the two groups of barriers, the distance, and the vertical distance from the target barrier to the center position;

[0070] Determine the ratio of the number of vehicles to the number of people outside the target barrier;

[0071] The horizontal rotation angle of the second lifting rod is determined based on the center position, and the horizontal rotation speed of the second lifting rod is determined based on the density of the outer side of the target railing, the ratio, and the vertical distance from the target railing to the center position.

[0072] In another possible implementation, the second determination module, when determining the opening angle and opening speed of the target barrier based on the center position and the model of each inner vehicle, is specifically configured to:

[0073] If the distance from the train to the crossing reaches a preset distance threshold, determine the safe speed value to which the train needs to decelerate based on the number of inner vehicles and the distance from the train to the crossing;

[0074] A safe speed value to which the train needs to decelerate is sent.

[0075] In another possible implementation, the device further includes:

[0076] A time determination module, which obtains the time length of the train arriving at the crossing, and determines the maximum time between the inner vehicle leaving the two sets of railings based on the time length;

[0077] A control display module controls the display device at the crossing to display the maximum time.

[0078] In a third aspect, the present application provides a track status monitoring system, which adopts the following technical solution:

[0079] A track condition monitoring system, the system comprising:

[0080] The first railing and the second railing are respectively arranged on both sides of the crossing and are parallel to the track, and the first railing and the second railing each include a first lifting rod that can rotate in a vertical plane and a second lifting rod that can universally rotate;

[0081] An image acquisition device, used for acquiring outer side image information of the first railing and the second railing and inner side image information between the two groups of railings;

[0082] An electronic device, used for obtaining outer image information of each corresponding railing after two groups of railings at a crossing are closed and inner image information between the two groups of railings, the two groups of railings comprising a first railing and a second railing; performing vehicle recognition on the inner image information to obtain a recognition result; if a vehicle is present in the recognition result of the inner image information, determining the center position of the inner vehicle distribution of the two groups of railings and the model of each inner vehicle based on the inner image information; determining a target railing to be opened in the two groups of railings based on the outer image information and the center position; determining an opening angle and an opening speed of the target railing based on the center position and the model of each inner vehicle; and controlling the target railing to move according to the opening angle and the opening speed.

[0083] In a fourth aspect, the present application provides an electronic device, which adopts the following technical solution:

[0084] An electronic device, comprising:

[0085] at least one processor;

[0086] Memory;

[0087] At least one application, wherein at least one application is stored in a memory and configured to be executed by at least one processor, and at least one is configured to: execute a track condition monitoring method shown in any possible implementation of the first aspect.

[0088] In summary, the present application includes at least one of the following beneficial technical effects:

[0089] The outer image information of the corresponding railings of the two groups of railings at the crossing after they are closed and the inner image information between the two groups of railings are obtained. The outer and inner image information can reflect the traffic conditions inside and outside the railings at the crossing. Vehicle recognition is performed on the inner image information to obtain a recognition result. If there is a vehicle in the recognition result of the inner image information, it means that a vehicle is trapped inside the railing. Then, the center position of the vehicle distribution inside the two groups of railings and the model of each inner vehicle are determined based on the inner image information. The center position can show the position of the overall distribution of the vehicle. In order to enable the trapped vehicle to drive out more quickly and easily, it is necessary to determine which side of the railing is more convenient to open. Based on the outer image information and the center position, the target railing to be opened in the two groups of railings is determined, and the opening angle and opening speed of the target railing are determined based on the center position and the model of each inner vehicle. The angle and speed are important factors for whether the trapped vehicle can safely and quickly drive out of the crossing after the railing is opened. Then, the target railing is controlled to move according to the opening angle and opening speed, which reduces the delay time of manually controlling the lifting of the railing, so that the trapped vehicle can safely and quickly drive out of the crossing. BRIEF DESCRIPTION OF THE DRAWINGS

[0090] Figure 1 It is a flow chart of a track status monitoring method according to an embodiment of the present application.

[0091] Figure 2 It is a schematic diagram of a process for determining the center position of the inner vehicle and the model of each inner vehicle in an embodiment of the present application.

[0092] Figure 3 It is a schematic diagram of a process for determining a target railing opening angle and opening speed in an embodiment of the present application.

[0093] Figure 4 It is a structural schematic diagram of a track status monitoring device in an embodiment of the present application.

[0094] Figure 5 It is a structural schematic diagram of a track status monitoring system according to an embodiment of the present application.

[0095] Figure 6 It is a structural schematic diagram of an electronic device according to an embodiment of the present application.

[0096] : 20, track status monitoring device; 201, image acquisition module; 202, image recognition module; 203, first determination module; 204, target railing determination module; 205, second determination module; 206, opening module; 30, track status monitoring system; 301, first railing; 302, second railing; 303, image acquisition device; 304, electronic device; 3041, processor; 3042, bus; 3043, memory; 3044, transceiver. DETAILED DESCRIPTION

[0097] The present application is further described in detail below in conjunction with the accompanying drawings.

[0098] After reading this specification, those skilled in the art may make non-creative modifications to this embodiment as needed, but such modifications are protected by patent law as long as they are within the scope of the claims of this application.

[0099] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0100] In addition, the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article, unless otherwise specified, generally means that the associated objects before and after are in an "or" relationship.

[0101] The embodiments of the present application are further described in detail below in conjunction with the drawings in the specification.

[0102] The embodiment of the present application provides a track status monitoring method, which is executed by an electronic device, which can be a server or a terminal device, wherein the server can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides cloud computing services. The terminal device can be a smart phone, a tablet computer, a laptop computer, a desktop computer, etc., but is not limited thereto. The terminal device and the server can be directly or indirectly connected via wired or wireless communication, which is not limited in the embodiment of the present application. The method includes steps S101, S102, S103, S104, S105, and S106. Figure 1 As shown,

[0103] S101, obtaining outer side image information of each corresponding railing after two sets of railings at a road crossing are closed and inner side image information between the two sets of railings.

[0104] The two groups of railings include a first railing and a second railing.

[0105] For the embodiment of the present application, two groups of railings are provided on both sides of the track, and the two groups of railings include a first railing on one side of the track and a second railing on the other side of the track. Camera devices are provided at both groups of railings, and the camera devices are connected to electronic devices for communication via wired or wireless communication. The camera devices collect outer image information of the two groups of railings and inner image information between the two groups of railings and send them to the electronic device. The electronic device obtains outer image information of the railings corresponding to each other and inner image information between the two groups of railings after the two groups of railings at the crossing are closed.

[0106] S102, performing vehicle recognition on the inner image information to obtain a recognition result.

[0107] In the embodiment of the present application, the electronic device inputs the inner image information into the trained network model to perform vehicle recognition and obtain a recognition result. The network model can be a convolutional neural network model, a recurrent neural network model, or other network models.

[0108] S103: If there is a vehicle in the recognition result of the inner image information, the center position of the distribution of the vehicles inside the two groups of railings and the model of each inner vehicle are determined based on the inner image information.

[0109] For the embodiment of the present application, the electronic device can obtain the recognition result to know whether there is a vehicle in the inner image information. If there is a vehicle, it means that the vehicle is trapped on the inside of the railing. The center position of the distribution of vehicles on the inside of the two groups of railings and the model of each inner vehicle can be determined through the inner image information. The center position can indicate which side of the railing the vehicle is closer to in the two groups of railings. Obtaining the vehicle model makes it easy to know the size of each inner vehicle. The size of the vehicle also affects whether the vehicle can quickly leave the intersection later.

[0110] S104: Determine the target railing to be opened in the two groups of railings based on the outer image information and the center position.

[0111] For the embodiment of the present application, the electronic device analyzes the outer image information to obtain the vehicle and personnel situation outside the two groups of railings, and comprehensively judges which side of the railing is the target railing that needs to be opened through the vehicle and personnel situation outside the railing and the center position, determines the target railing and controls the opening of the target railing, making it easier for trapped vehicles on the inside to drive out.

[0112] S105 , determining an opening angle and an opening speed of the target barrier based on the center position and the model of each inner vehicle.

[0113] For the embodiment of the present application, the opening angle and opening speed of the target barrier determine whether the inner vehicle can drive out quickly and safely, and can fall down quickly after driving out to reduce the possibility of other vehicles or people outside the barrier entering the inner side of the barrier. The closer the distance from the center position to the target barrier, the faster the opening speed. The height of the vehicle can be known by the vehicle model. The taller the vehicle, the larger the required opening angle. The electronic device determines the opening angle and opening speed of the target barrier more accurately and safely through multiple features such as the center position and the model of each inner vehicle.

[0114] S106, controlling the target railing to move according to the opening angle and opening speed.

[0115] For the embodiment of the present application, the electronic device is connected to the target railing via a wire or wirelessly, generates a control signal after determining the opening angle and opening speed, and sends the control signal to the target railing. The target railing controls the motor action according to the opening angle and opening speed, so that the target railing moves according to the opening angle and opening speed.

[0116] This method is used to identify the number of vehicles on the inside of the barrier and the people in the vehicles on the outside, and determine the target barrier. Then, the opening angle and speed of the target barrier are determined through a variety of features, and the electronic equipment controls the lifting of the barrier. This method shortens the time it takes to lift the barrier, allowing trapped vehicles to quickly and safely exit the intersection.

[0117] In a possible implementation of the embodiment of the present application, the center position of the vehicle distribution and the model of each inner vehicle are determined based on the inner image information in step S103, which specifically includes steps S1031, S1032, S1033 and S1034. Figure 2 As shown,

[0118] S1031, establishing a coordinate system based on the inner image information, and determining the coordinate information of each inner vehicle center point.

[0119] For the embodiment of the present application, the electronic device establishes a coordinate system based on the inner image information. The establishment of the coordinate system provides accurate spatial position information for the analysis and processing of the inner image information. The vehicle contour is the edge contour of the vehicle. Different vehicles have different contours. The electronic device determines the center point of each inner vehicle based on the vehicle contour shape, and obtains the coordinate information of the center point of each inner vehicle according to the two-dimensional coordinates of the center point in the coordinate system. The coordinate information can show the distribution of each inner vehicle in the inner image information.

[0120] S1032, determining a geometric figure composed of the coordinate information based on the coordinate information.

[0121] For the embodiment of the present application, the coordinate information of each inner vehicle center point is randomly distributed in the inner image information coordinate system, and the electronic device connects the coordinates of the outermost inner vehicle center points to form a geometric figure.

[0122] S1033, determining the center point coordinates of the geometric figure, where the center point coordinates represent the center position of the vehicle distribution.

[0123] For the embodiment of the present application, the electronic device calculates the average value of the coordinate information of the center point of the inner vehicles that make up the geometric figure to obtain the coordinates of the center point of the geometric figure. When there are two or more vehicles, the average value of the horizontal coordinate and the average value of the vertical coordinate of each vehicle are respectively calculated, which are the coordinates of the center point. If there is only one vehicle, the coordinates of the center point are the coordinate information of this vehicle. For example, the coordinate information of three vehicles are (3, 5), (2, 4), and (1, 6), the average value of the horizontal coordinate is (3+2+1) / 3=2, and the average value of the vertical coordinate is (5+4+6) / 3=5, then the coordinates of the center points of the three vehicles are (2, 5). Determining the coordinates of the center point can characterize the central position of the vehicle distribution.

[0124] S1034, performing vehicle type recognition on the inner image information based on the trained network model to obtain the model of each inner vehicle.

[0125] In the embodiment of the present application, the electronic device inputs the inner image information into the trained network model for vehicle model recognition, and obtains the model of each inner vehicle in the inner image information. Obtaining the vehicle model facilitates knowing the size of each inner vehicle. The network model can be a convolutional neural network model, a recurrent neural network model, or other network models.

[0126] In a possible implementation of the embodiment of the present application, the outer image information includes first image information outside the first railing and second image information outside the second railing. In step S104, the target railing to be opened in the two groups of railings is determined based on the outer image information and the center position, which specifically includes step 1, step 2, step 3 and step 4, wherein:

[0127] Step 1: Perform feature recognition on the first image information and the second image information to determine the first number of vehicles and the first number of people outside the first railing, and the second number of vehicles and the second number of people outside the second railing.

[0128] In the embodiment of the present application, the electronic device performs feature recognition on the first image information and the second image information, the features include vehicles and people, and obtains the first number of vehicles and the first number of people outside the first railing, and the second number of vehicles and the second number of people outside the second railing, and displays the situation of vehicles and people outside the two groups of railings through the size of each number. Specifically, feature recognition can be performed through a trained network model, which is a prior art and will not be repeated here.

[0129] Step 2: If the first vehicle quantity is 0 and the second vehicle quantity is not 0, the first barrier is determined as the target barrier.

[0130] For the embodiment of the present application, when the electronic device determines that the number of the first vehicles is 0 and the number of the second vehicles is not 0, it means that there is no vehicle outside the first railing, and it is more suitable to open the first railing to facilitate the inner vehicle to drive out. If there is a vehicle outside the second railing, more space is needed to make way for the inner vehicle, and it also takes a certain amount of time to move the car to make way, which is far less convenient than making way for the inner vehicle outside the first railing when there is no vehicle. Therefore, the first railing is determined as the target railing.

[0131] Step three: if the second vehicle quantity is 0 and the first vehicle quantity is not 0, the second barrier is determined as the target barrier.

[0132] For the embodiment of the present application, when the electronic device determines that the second vehicle number is 0 and the first vehicle number is not 0, it means that there is no vehicle outside the second railing, and it is more appropriate to open the second railing to facilitate the inner vehicle to drive out, so the second railing is determined as the target railing.

[0133] Step four: if both the first number of vehicles and the second number of vehicles are not 0, determine the first vertical distance of the center position from the first railing and the second vertical distance from the second railing, determine the first density of people and vehicles outside the first railing based on the first image information, and determine the second density of people and vehicles outside the second railing based on the second image information; determine the target railing based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information.

[0134] For the embodiment of the present application, if the electronic device determines that the first number of vehicles and the second number of vehicles are not 0, indicating that there are vehicles outside the two groups of railings, it is necessary to determine the target railing through other features. First, the electronic device determines the first vertical distance from the center position to the first railing and the second vertical distance from the second railing, and determines the first density of people and vehicles outside the first railing based on the first image information, and determines the second density of people and vehicles outside the second railing based on the second image information. The first density and the second density represent the density of vehicles and people outside the first railing and the second railing respectively. The center point of each vehicle and each person is determined, and the distance from each center point to other points is calculated, and then the average distance from each point to other points is calculated, and then the average distance of each point is averaged. The smaller the average value, the more crowded and the greater the density. It is more accurate to comprehensively determine the target railing based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information.

[0135] A possible implementation of the embodiment of the present application is to determine the target barrier based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information in step 4, specifically including steps 5, 6, 7, 8 and 9, wherein:

[0136] Step five, calculating a first score based on the first vertical distance, the first number of vehicles, the first number of people, the first density, and the respective first coefficients.

[0137] For the embodiment of the present application, the first vertical distance, the first number of vehicles, the first number of people, and the first density are all important factors affecting whether the first railing is suitable as a target railing. Therefore, the electronic device calculates the first score based on the first vertical distance, the first number of vehicles, the first number of people, the first density, and their respective first coefficients. Assuming that the first vertical distance is 8, the first number of vehicles is 3, the first number of people is 2, and the first density is 0.16, and the first coefficients of the first vertical distance, the first number of vehicles, the first number of people, and the first density are 0.6, 0.5, 0.3, and 6 respectively, the first score is 8×0.6+3×0.5+2×0.3+0.16×6=7.86 points.

[0138] Step six, calculating a second score based on the second vertical distance, the second number of vehicles, the second number of people, the second density, and the respective second coefficients.

[0139] For the embodiment of the present application, the second vertical distance, the second number of vehicles, the second number of people, and the second density are all important factors affecting whether the second railing is the target railing. Therefore, the electronic device calculates the second score based on the second vertical distance, the second number of vehicles, the second number of people, the second density, and their respective second coefficients. Assuming that the second vertical distance is 7, the second number of vehicles is 4, the second number of people is 3, and the second density is 0.23, the second coefficients of the second vertical distance, the second number of vehicles, the second number of people, and the second density are 0.6, 0.5, 0.3, and 6 respectively, then the second score is 7×0.6+4×0.5+3×0.3+0.23×6=8.48 points.

[0140] Step seven: if the first score is less than the second score, the first railing is determined to be the target railing.

[0141] For the embodiment of the present application, the electronic device determines whether the first score is less than the second score, and if so, determines that the first barrier is the target barrier. Taking into account various factors, the first barrier is more suitable as the target barrier, and vehicles on the inside can exit more quickly, and vehicles and people on the outside of the first barrier can also give way more conveniently.

[0142] Step eight: if the first score is greater than the second score, the second railing is determined to be the target railing.

[0143] For the embodiment of the present application, the electronic device determines whether the first score is greater than the second score, and if so, determines that the second barrier is the target barrier. Taking into account various factors, the second barrier is more suitable as the target barrier, and vehicles on the inside can exit more quickly, and vehicles and people on the outside of the second barrier can also give way more conveniently.

[0144] Step nine: if the first score is equal to the second score, the vehicle head direction is identified based on the inner image information, and the guardrail corresponding to the side with a larger number of vehicle head directions is determined as the target guardrail.

[0145] For the embodiment of the present application, if the electronic device determines that the first score is equal to the second score, the target barrier cannot be determined yet and needs to be determined based on other features. The electronic device identifies the head direction of each inner vehicle based on the inner image information, determines the number of vehicles facing the first barrier and the number of vehicles facing the second barrier, and determines the barrier corresponding to the side with more vehicles facing the head direction as the target barrier by comparison. Vehicles with more vehicles facing the head direction can drive out of the target barrier more conveniently and quickly, and other vehicles with opposite directions turn around and drive out of the target barrier. If the side with fewer vehicles facing the head direction is selected as the target barrier, more vehicles will need to turn around, which is inconvenient and takes longer time.

[0146] In a possible implementation of the embodiment of the present application, the first railing and the second railing are both composed of a first lifting rod that can rotate in a vertical plane and a second lifting rod that can rotate in a universal direction. In step S105, the opening angle and opening speed of the target railing are determined based on the center position and the model of each inner vehicle, specifically including steps S1051, S1052, S1053, S1054 and S1055. Figure 3 As shown,

[0147] S1051, determining the target vehicle with the highest height based on the model of each vehicle, and obtaining the height and position of the target vehicle.

[0148] For the embodiment of the present application, the electronic device obtains the height of each inner vehicle from a pre-stored vehicle model table according to the model of each inner vehicle, compares them to determine the target vehicle with the highest height, and obtains the height of the target vehicle. The height of the inner vehicle is a key factor in the opening angle of the target barrier. The higher the height of the target vehicle and the larger the model, the larger the angle at which the target barrier needs to be opened.

[0149] The electronic device determines the position of the target vehicle in the coordinate system based on the coordinate system of the inner image information.

[0150] S1052: Determine a minimum opening angle of a first lifting bar of a target barrier based on a height and a position of the target vehicle.

[0151] For the embodiment of the present application, the higher the height of the target vehicle, the larger the required opening angle of the first lifting bar; the closer the position of the target vehicle is to the rotation axis of the first lifting bar, the larger the required opening angle of the first lifting bar. The electronic device comprehensively determines the minimum opening angle of the first lifting bar of the target railing based on the height and position of the target vehicle.

[0152] S1053, obtaining the distance of the train to the crossing, and determining the opening speed of the first lifting bar based on the number and distance of vehicles inside the two sets of railings and the vertical distance from the target railing to the center position.

[0153] For the embodiment of the present application, the electronic device obtains the distance of the current train arriving at the crossing through the train warning system. The tracks on both sides of the crossing are installed with train warning systems, and the train warning systems are communicatively connected with the electronic device. For example, when the train arrives at a certain position in a certain section, the train position collected by the train warning system may be 500m+35m, and the distance of the train arriving at the crossing is 535m. The closer the distance, the shorter the time it takes for the train to arrive at the crossing, and the faster the opening speed is required. The fewer the number of vehicles on the inside of the two sets of railings, the faster the opening speed is. Similarly, the shorter the vertical distance from the target railing to the center position, the faster the opening speed is. The number of vehicles on the inside of the two sets of railings, the distance, and the vertical distance from the target railing to the center position are all related to the opening speed of the first lifting bar. , calculate the second score according to the three and their respective second coefficients, determine the first preset score interval in which the second score is located, and determine the first speed corresponding to the first preset score interval as the opening speed of the first lifting bar. Assume that the number of vehicles on the inner side of the two sets of railings is 3, the distance from the train to the crossing is 200 meters, and the vertical distance from the target railing to the center position is 6 meters. The number and distance of vehicles on the inner side of the two sets of railings and the second coefficients of the vertical distance from the target railing to the center position are 5, 0.06, and 3 respectively. The electronic device calculates the second score as 3×5+200×0.06+6×3=45. The first preset score interval in which 45 is located is (30, 50], and the first speed corresponding to this interval is 0.8s, that is, the opening speed of the first lifting bar is determined to be 0.8s.

[0154] S1054, determining the ratio of the number of vehicles to the number of people outside the target barrier.

[0155] For the embodiment of the present application, the electronic device determines the ratio of the number of vehicles to the number of people outside the target barrier. If the vehicle gives way to the inner vehicle, it will take time and it is not as convenient as for the people to give way directly to the left or right. Therefore, the larger the ratio, the longer the time required to give way.

[0156] S1055, determining the horizontal rotation angle of the second lifting bar based on the center position, and determining the horizontal rotation speed of the second lifting bar based on the density and ratio of the outer side of the target railing and the vertical distance from the target railing to the center position.

[0157] For the embodiment of the present application, the electronic device determines the horizontal rotation angle of the second lifting bar according to the distance between the center position and the second lifting bar rotation axis, calculates the third score based on the density, ratio, vertical distance from the target railing to the center position and the respective third coefficients of the outside of the target railing, determines the second preset score interval in which the third score is located, and determines the second speed corresponding to the second preset score interval as the opening speed of the second lifting bar. The density of the outside of the target railing is 0.16, the ratio is 0.5, the vertical distance from the target railing to the center position is 6 meters, the density, ratio, and third coefficients of the vertical distance from the outside of the target railing to the center position are 40, 6, and 0.3, respectively. The electronic device calculates the third score as 0.16×40+0.5×6+6×0.3=11.2, and the second preset score interval in which 11.2 is located is (8, 12], and the second speed corresponding to this interval is 1.5s, that is, the opening speed of the second lifting bar is determined to be 1.5s.

[0158] In a possible implementation manner of the embodiment of the present application, the method further includes step 10 and step 11, wherein step 10 may be performed after step S1053, wherein:

[0159] Step 10: If the distance from the train to the crossing reaches a preset distance threshold, determine the safe speed value to which the train needs to slow down based on the number of inner vehicles and the distance from the train to the crossing.

[0160] For the embodiment of the present application, the electronic device determines whether the distance from the train to the crossing has reached a preset distance threshold. If it has reached the threshold, it means that the distance to the crossing is very close, and the more the number of inner vehicles, the less likely it is that the inner vehicles will be able to safely exit the crossing before the train arrives. The electronic device calculates a fourth score based on the number of inner vehicles, the distance from the train to the crossing, and the respective fourth coefficients. The deceleration value corresponding to the third preset score interval where the fourth score is located is the deceleration value of the train. Assuming that the number of inner vehicles is 3, the distance from the train to the crossing is 500m, and the weights of the number of inner vehicles and the distance from the train to the crossing are 3 and 0.07 respectively, the fourth score is 3×3+500×0.07=44, and the third preset score interval is (35, 45], and the corresponding safe speed value that needs to be decelerated is 20km / h. The safe speed value that needs to be decelerated is determined, and the train is decelerated to allow the inner vehicles to exit safely and quickly.

[0161] Step 11: Send the safe speed value to which the train needs to decelerate.

[0162] In the embodiment of the present application, the electronic device sends the safe speed value to which the train needs to decelerate to the terminal system of the train, and the staff obtains the safe speed value to which the train needs to decelerate through the terminal system of the train.

[0163] In a possible implementation manner of the embodiment of the present application, the method further includes step 12 and step 13, wherein step 12 may be performed after step S106, wherein:

[0164] Step 12, obtaining the time it takes for the train to arrive at the crossing, and determining the maximum time between the inner vehicle leaving the two sets of railings based on the time;

[0165] For the embodiment of the present application, the electronic device calculates the time it takes for the train to arrive at the crossing based on the distance the train reaches the crossing and the speed of the train. The shorter the time, the faster it takes for the inner vehicle to exit the guardrail. Therefore, the electronic device determines the maximum time between the inner vehicle leaving the two sets of guardrails based on the preset time interval corresponding to the time.

[0166] Step 13, controlling the display device at the crossing to display the maximum time.

[0167] For the embodiment of the present application, the electronic device controls the display device at the crossing to display the maximum time, which can be displayed in the form of a countdown. For example, if the maximum time is 8s, the countdown starts from 8s and displays 8s, 7s, ..., 1s until 0s is displayed.

[0168] The above embodiment introduces a track state monitoring method from the perspective of method flow, and the following embodiment introduces a track state monitoring device from the perspective of a virtual module or a virtual unit. Please refer to the following embodiment for details.

[0169] The present application embodiment provides a track state monitoring device 20, such as Figure 4 As shown, the track state monitoring device 20 may specifically include:

[0170] An image acquisition module 201 is used to acquire outer image information of the railings corresponding to the two groups of railings at the crossing after they are closed and inner image information between the two groups of railings, wherein the two groups of railings include a first railing and a second railing;

[0171] The image recognition module 202 is used to perform vehicle recognition on the inner image information to obtain a recognition result;

[0172] The first determination module 203 is used to determine the center position of the inner side vehicle distribution of the two groups of guardrails and the model of each inner side vehicle based on the inner side image information if there is a vehicle in the recognition result of the inner side image information;

[0173] A target railing determination module 204 is used to determine the target railing to be opened in the two groups of railings based on the outer image information and the center position;

[0174] A second determination module 205 is used to determine the opening angle and opening speed of the target barrier based on the center position and the model of each inner vehicle;

[0175] The opening module 206 is used to control the target railing to move according to the opening angle and opening speed.

[0176] The embodiment of the present application discloses a track state monitoring device 20, wherein an image acquisition module 201 acquires outer image information of each corresponding railing after two groups of railings at a crossing are closed and inner image information between the two groups of railings, an image recognition module 202 performs vehicle recognition on the inner image information to obtain a recognition result, if there is a vehicle in the recognition result of the inner image information, a first determination module 203 determines the center position of the inner vehicle distribution of the two groups of railings and the model of each inner vehicle based on the inner image information, a target railing determination module 204 determines the target railing that needs to be opened in the two groups of railings based on the outer image information and the center position, a second determination module 205 determines the opening angle and opening speed of the target railing based on the center position and the model of each inner vehicle, and an opening module 206 controls the target railing to move according to the opening angle and opening speed, thereby shortening the lifting time, thereby enabling the trapped vehicle to quickly and safely exit the crossing.

[0177] In a possible implementation of the embodiment of the present application, the first determination module 203, when used to determine the center position of the distribution of vehicles inside the two groups of railings and the model of each inside vehicle based on the inside image information, is specifically used to:

[0178] Establishing a coordinate system based on the inner image information and determining the coordinate information of each inner vehicle center point;

[0179] Determine a geometric figure composed of the coordinate information based on the coordinate information;

[0180] Determine the center point coordinates of the geometric figure, where the center point coordinates represent the center position of the vehicle distribution;

[0181] Based on the trained network model, the vehicle model is identified from the inner image information to obtain the model of each inner vehicle.

[0182] In a possible implementation of the embodiment of the present application, the target railing determination module 204, when determining the target railing to be opened in the two groups of railings based on the outer image information and the center position, is specifically configured to:

[0183] Performing feature recognition on the first image information and the second image information to determine the first number of vehicles and the first number of people outside the first barrier, and the second number of vehicles and the second number of people outside the second barrier;

[0184] If the first vehicle quantity is 0 and the second vehicle quantity is not 0, the first barrier is determined as the target barrier;

[0185] If the second vehicle quantity is 0 and the first vehicle quantity is not 0, the second barrier is determined as the target barrier;

[0186] If both the first number of vehicles and the second number of vehicles are not 0, determine the first vertical distance of the center position from the first railing and the second vertical distance from the second railing, determine the first density of people and vehicles outside the first railing based on the first image information, and determine the second density of people and vehicles outside the second railing based on the second image information; determine the target railing based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information.

[0187] In a possible implementation of the embodiment of the present application, the target barrier determination module 204, when determining the target barrier based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information, is specifically used to:

[0188] Calculating a first score based on the first vertical distance, the first number of vehicles, the first number of people, the first density, and respective first coefficients;

[0189] calculating a second score based on the second vertical distance, the second number of vehicles, the second number of people, the second density, and respective second coefficients;

[0190] If the first score is less than the second score, the first railing is determined to be the target railing;

[0191] If the first score is greater than the second score, the second railing is determined to be the target railing;

[0192] If the first score is equal to the second score, the vehicle head direction is identified based on the inner image information, and the guardrail corresponding to the side with a larger number of vehicle head directions is determined as the target guardrail.

[0193] In a possible implementation of the embodiment of the present application, the second determination module 205, when determining the opening angle and opening speed of the target barrier based on the center position and the model of each inner vehicle, is specifically used to:

[0194] Determine the target vehicle with the highest height based on the model of each vehicle, and obtain the height and position of the target vehicle;

[0195] Determine a minimum opening angle of a first lifting bar of a target barrier based on a height and a position of the target vehicle;

[0196] Obtain the distance of the train to the crossing, and determine the opening speed of the first lifting bar based on the number and distance of vehicles inside the two sets of barriers and the vertical distance from the target barrier to the center position;

[0197] Determine the ratio of the number of vehicles to the number of people outside the target barrier;

[0198] The horizontal rotation angle of the second lifting rod is determined based on the center position, and the horizontal rotation speed of the second lifting rod is determined based on the density and ratio of the outer side of the target railing and the vertical distance from the target railing to the center position.

[0199] In a possible implementation of the embodiment of the present application, the second determination module 205, when determining the opening angle and opening speed of the target barrier based on the center position and the model of each inner vehicle, is specifically used to:

[0200] If the distance from the train to the crossing reaches a preset distance threshold, the safe speed value to which the train needs to slow down is determined based on the number of inner vehicles and the distance from the train to the crossing;

[0201] Send the train a safe speed value to which it needs to slow down.

[0202] In a possible implementation of the embodiment of the present application, the device 20 further includes:

[0203] The time determination module obtains the time it takes for the train to arrive at the crossing and determines the maximum time between the inner vehicle leaving the two sets of railings based on the time;

[0204] The control display module controls the display device at the crossing to display the maximum time.

[0205] The present application provides a track status monitoring system. Figure 5 As shown, Figure 5 The track state monitoring system shown specifically includes a first railing 301, a second railing 302, an image acquisition device 303, and an electronic device 304. The first railing 301 and the second railing 302 are respectively arranged on both sides of the crossing and are parallel to the track. The first railing 301 and the second railing 302 both include a first lifting rod that can rotate in a vertical plane and a second lifting rod that can rotate in a universal direction. The first lifting rod and the second lifting rod are arranged opposite to each other. Motors are arranged inside the first lifting rod and the second lifting rod. The motors are connected to the electronic device 304 by wire or wirelessly. The electronic device 304 can control the motor to rotate at a specified speed and can control the motor to rotate at a specified angle, thereby driving the lifting rod to rotate.

[0206] The image acquisition device 303 is connected to the camera device by wire or wirelessly, and is connected to the electronic device by wire or wirelessly, and is used to acquire the outer image information of the first railing and the second railing and the inner image information between the two groups of railings.

[0207] The electronic device 304 is used to execute the contents disclosed in the above method embodiment. When the train is about to arrive at the crossing, the first railing 301 and the second railing 302 are closed and in a state parallel to the horizontal plane to prevent vehicles or pedestrians outside the two groups of railings from entering the crossing. However, some vehicles or pedestrians may be trapped in the crossing because they force their way through or rush in. The image acquisition device 303 acquires outer image information of the railings corresponding to each of the two groups of railings at the crossing after they are closed and inner image information between the two groups of railings. The two groups of railings include the first railing 301 and the second railing 302. The electronic device 304 acquires the inner image information and performs vehicle recognition based on the inner image information to obtain a recognition result. If there is a vehicle in the recognition result of the inner image information, the center position of the inner vehicle distribution of the two groups of railings and the model of each inner vehicle are determined based on the inner image information. The target railing to be opened in the two groups of railings is determined based on the outer image information and the center position. The opening angle and opening speed of the target railing are determined based on the center position and the model of each inner vehicle. The electronic device 304 controls the target railing to move according to the opening angle and opening speed.

[0208] An electronic device is provided in an embodiment of the present application, such as Figure 6 As shown, Figure 6 The electronic device 304 shown includes: a processor 3041 and a memory 3043. The processor 3041 and the memory 3043 are connected, such as through a bus 3042. Optionally, the electronic device 304 may also include a transceiver 3044. It should be noted that in actual applications, the transceiver 3044 is not limited to one, and the structure of the electronic device 304 does not constitute a limitation on the embodiments of the present application.

[0209] Processor 3041 may be a CPU (Central Processing Unit), a general-purpose processor, a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. It may implement or execute various exemplary logic blocks, modules, and circuits described in conjunction with the disclosure of this application. Processor 3041 may also be a combination that implements computing functions, such as a combination of one or more microprocessors, a combination of a DSP and a microprocessor, and the like.

[0210] The bus 3042 may include a path to transmit information between the above components. The bus 3042 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus 3042 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one thick line is used in the diagram, but it does not mean that there is only one bus or only one type of bus.

[0211] The memory 3043 may be a ROM (Read Only Memory) or other types of static storage devices that can store static information and instructions, a RAM (Random Access Memory) or other types of dynamic storage devices that can store information and instructions, or an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, optical disk storage (including compressed optical disk, laser disk, optical disk, digital versatile disk, Blu-ray disk, etc.), a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to these.

[0212] The memory 3043 is used to store the application code for executing the solution of the present application, and the execution is controlled by the processor 3041. The processor 3041 is used to execute the application code stored in the memory 3043 to implement the contents shown in the above method embodiment.

[0213] The electronic devices include, but are not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), and fixed terminals such as digital TVs, desktop computers, etc. It can also be a server, etc. Figure 6 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0214] The embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer-readable storage medium is run on a computer, the computer can execute the corresponding contents in the aforementioned method embodiment. Compared with the related art, in the embodiment of the present application, the outer image information of the railings corresponding to each of the two groups of railings at the crossing after they are closed and the inner image information between the two groups of railings are obtained. The outer and inner image information can reflect the traffic conditions inside and outside the railings at the crossing. The inner image information is used to identify the vehicle and obtain the identification result. If there is a vehicle in the identification result of the inner image information, it means that a vehicle is trapped inside the railing. Then, based on the inner image information, the center position of the vehicle distribution inside the two groups of railings and the model of each inner vehicle are determined. The center position can show the overall distribution position of the vehicle. In order to enable the trapped vehicle to exit more quickly and easily, it is necessary to determine which side of the railing is more convenient to open, and determine the target railing that needs to be opened in the two groups of railings based on the outer image information and the center position, and determine the opening angle and opening speed of the target railing based on the center position and the model of each inner vehicle. The angle and speed are important factors in whether the trapped vehicle can exit the crossing safely and quickly after the railing is opened. The target railing is then controlled to move according to the opening angle and opening speed, reducing the delay time of manually controlling the lifting of the railing, so that the trapped vehicle can exit the crossing safely and quickly.

[0215] It should be understood that, although the steps in the flowchart of the accompanying drawings are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless otherwise specified herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least a part of the steps in the flowchart of the accompanying drawings may include multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be executed in turn or alternately with other steps or at least a part of the sub-steps or stages of other steps.

[0216] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A track condition monitoring method, characterized in that: include: Acquire outer side image information of the respective corresponding railings of two sets of railings at the crossing after they are closed and inner side image information between the two sets of railings, wherein the two sets of railings include a first railing and a second railing; Performing vehicle recognition on the inner image information to obtain a recognition result; If there is a vehicle in the recognition result of the inner image information, determining the center position of the inner side vehicle distribution of the two groups of railings and the model of each inner side vehicle based on the inner image information; Determine a target railing to be opened in the two groups of railings based on the outer image information and the center position; determining an opening angle and an opening speed of the target barrier based on the center position and the model of each inner vehicle; Controlling the target railing to move according to the opening angle and opening speed; The outer image information includes first image information outside the first railing and second image information outside the second railing, and determining the target railing to be opened in the two groups of railings based on the outer image information and the center position includes: Performing feature recognition on the first image information and the second image information to determine the first number of vehicles and the first number of people outside the first railing, and the second number of vehicles and the second number of people outside the second railing; If the first vehicle quantity is 0 and the second vehicle quantity is not 0, determining the first barrier as the target barrier; If the second vehicle quantity is 0 and the first vehicle quantity is not 0, determining the second barrier as the target barrier; If both the first number of vehicles and the second number of vehicles are not 0, determine the first vertical distance of the center position from the first railing and the second vertical distance from the second railing, determine the first density of people and vehicles outside the first railing based on the first image information, and determine the second density of people and vehicles outside the second railing based on the second image information; determine the target railing based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information.

2. A track condition monitoring method according to claim 1, characterized in that: The determining the center position of the vehicle distribution and the model of each inner vehicle based on the inner image information includes: Establishing a coordinate system based on the inner image information and determining coordinate information of each inner vehicle center point; Determine a geometric figure composed of the coordinate information based on the coordinate information; Determine the center point coordinates of the geometric figure, wherein the center point coordinates represent the center position of the vehicle distribution; The vehicle type is identified by performing vehicle type recognition on the inner image information based on the trained network model to obtain the model of each inner vehicle.

3. A track condition monitoring method according to claim 1, characterized in that: The determining the target barrier based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information comprises: calculating a first score based on the first vertical distance, the first number of vehicles, the first number of people, the first density, and respective first coefficients; calculating a second score based on the second vertical distance, the second number of vehicles, the second number of people, the second density, and respective second coefficients; If the first score is less than the second score, determining the first railing as the target railing; If the first score is greater than the second score, determining the second railing as the target railing; If the first score is equal to the second score, the vehicle head direction is identified based on the inner image information, and the guardrail corresponding to the side with a larger number of vehicle head directions is determined as the target guardrail.

4. A track condition monitoring method according to claim 1, characterized in that: The first railing and the second railing are both composed of a first lifting rod that can rotate in a vertical plane and a second lifting rod that can rotate in a universal direction. The method of determining the opening angle and opening speed of the target railing based on the center position and the model of each inner vehicle includes: Determine the target vehicle with the highest height based on the model of each vehicle, and obtain the height and position of the target vehicle; Determining a minimum opening angle of a first lifting bar of a target barrier based on the height and position of the target vehicle; Obtaining the distance from the train to the crossing, and determining the opening speed of the first lifting bar based on the number of vehicles inside the two groups of barriers, the distance, and the vertical distance from the target barrier to the center position; Determine the ratio of the number of vehicles to the number of people outside the target barrier; The horizontal rotation angle of the second lifting rod is determined based on the center position, and the horizontal rotation speed of the second lifting rod is determined based on the density of the outer side of the target railing, the ratio, and the vertical distance from the target railing to the center position.

5. A track condition monitoring method according to claim 4, characterized in that: The method further comprises: If the distance from the train to the crossing reaches a preset distance threshold, determine the safe speed value to which the train needs to decelerate based on the number of inner vehicles and the distance from the train to the crossing; A safe speed value to which the train needs to decelerate is sent.

6. A track condition monitoring method according to claim 1, characterized in that: The method further comprises: Obtaining the time it takes for the train to arrive at the crossing, and determining the maximum time between the inner vehicle leaving the two sets of railings based on the time; The display device at the crossing is controlled to display the maximum time.

7. A track status monitoring device, characterized in that: include: An image acquisition module, used to acquire outer image information of the railings corresponding to the two groups of railings at the crossing after they are closed and inner image information between the two groups of railings, wherein the two groups of railings include a first railing and a second railing; An image recognition module, used to perform vehicle recognition on the inner image information to obtain a recognition result; A first determination module is used to determine the center position of the inner side vehicle distribution of the two groups of railings and the model of each inner side vehicle based on the inner side image information if there is a vehicle in the recognition result of the inner side image information; A target railing determination module, used to determine a target railing to be opened in the two groups of railings based on the outer image information and the center position; A second determination module, configured to determine an opening angle and an opening speed of the target barrier based on the center position and the model of each inner vehicle; An opening module, used to control the target railing to move according to the opening angle and opening speed; The outer image information includes first image information outside the first railing and second image information outside the second railing. The target railing determination module, when determining the target railing to be opened in the two groups of railings based on the outer image information and the center position, is specifically used to: Performing feature recognition on the first image information and the second image information to determine the first number of vehicles and the first number of people outside the first railing, and the second number of vehicles and the second number of people outside the second railing; If the first vehicle quantity is 0 and the second vehicle quantity is not 0, determining the first barrier as the target barrier; If the second vehicle quantity is 0 and the first vehicle quantity is not 0, determining the second barrier as the target barrier; If both the first number of vehicles and the second number of vehicles are not 0, determine the first vertical distance of the center position from the first railing and the second vertical distance from the second railing, determine the first density of people and vehicles outside the first railing based on the first image information, and determine the second density of people and vehicles outside the second railing based on the second image information; determine the target railing based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information.

8. A track status monitoring system, characterized in that: include: The first railing and the second railing are respectively arranged on both sides of the crossing and are parallel to the track, and the first railing and the second railing each include a first lifting rod that can rotate in a vertical plane and a second lifting rod that can rotate in a universal direction; An image acquisition device, used for acquiring outer side image information of the first railing and the second railing and inner side image information between the two groups of railings; An electronic device, used for obtaining outer image information of railings corresponding to each of two groups of railings at a road crossing after they are closed and inner image information between the two groups of railings, the two groups of railings comprising a first railing and a second railing; performing vehicle recognition on the inner image information to obtain a recognition result; if a vehicle is present in the recognition result of the inner image information, determining the center position of the inner vehicle distribution of the two groups of railings and the model of each inner vehicle based on the inner image information; determining a target railing to be opened in the two groups of railings based on the outer image information and the center position; determining an opening angle and a opening speed; controlling the target railing to move according to the opening angle and the opening speed; the outside image information includes first image information outside the first railing and second image information outside the second railing, and determining the target railing to be opened in the two groups of railings based on the outside image information and the center position, including: performing feature recognition on the first image information and the second image information to determine the first number of vehicles and the first number of people outside the first railing, and the second number of vehicles and the second number of people outside the second railing; if the first number of vehicles is 0 and the second number of vehicles is not 0, then determining the first railing as the target railing; If the second number of vehicles is 0 and the first number of vehicles is not 0, the second guardrail is determined as the target guardrail; if the first number of vehicles and the second number of vehicles are both not 0, the first vertical distance of the center position from the first guardrail and the second vertical distance from the second guardrail are determined, and the first density of people and vehicles outside the first guardrail is determined based on the first image information, and the second density of people and vehicles outside the second guardrail is determined based on the second image information; the target guardrail is determined based on the first vertical distance, the second vertical distance, the first number of vehicles, the second number of vehicles, the first number of people, the second number of people, the first density, the second density and the inner image information.

9. An electronic device, characterized in that: It includes: at least one processor; Memory; At least one application, wherein the at least one application is stored in the memory and is configured to be executed by the at least one processor, and the at least one application is used to execute a track condition monitoring method according to any one of claims 1 to 6.

Images