Train operation control system and method based on image target detection and electronic equipment

Abstract

The invention discloses a train operation control system and method based on image target detection and electronic equipment, the train operation control system comprises a camera, an image processing unit and vehicle-mounted ATP / ATO equipment, the camera is used for obtaining video images along a track in front of train operation; the image processing unit is used for extracting a target along the track in the image and feature information thereof, and obtaining the distance between the train and the target; and the vehicle-mounted ATP / ATO equipment is used for calculating train movement authorization according to the distance between the train and the target, calculating a train protection speed curve according to the train movement authorization, and controlling the train to run according to the train protection speed curve. According to the invention, even if the wireless communication of the operation control system is interrupted or the ground ZC and the transponder break down, the train with the operation function can still be ensured to safely run to the safe area, so that the emergency stop time of the train due to the fault is reduced, and the influence on the subsequent train operation efficiency is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of automatic control of urban rail transit train operation, and in particular to a train operation control system, method and electronic equipment based on image target detection. Background Art

[0002] The train operation control system is the key to ensuring the driving safety of urban rail transit and improving the system's transportation capacity. The communication-based train operation control (CBTC) system is the mainstream technology in the field of urban rail transit and is the most widely used. The CBTC system uses continuous, real-time, and large-capacity wireless communication technology for two-way communication between the train and the ground. It dynamically calculates and updates the train's movement authorization based on the train's current position speed, route, train performance, and line parameters to complete the control of the train's real-time running speed, thereby realizing automatic control of the train's safe operation.

[0003] The CBTC system supports a variety of train driving modes, mainly divided into automatic driving mode and manual driving mode. The key to its train operation control is that the on-board automatic train protection / automatic train operation (ATP / ATO) system obtains accurate current position and movement authorization information, thereby calculating the ATP protection speed curve that can maintain the normal operation of the train. The on-board ATP / ATO uses the on-board speed measurement and positioning device and the ground transponder to obtain the current position information, while the movement authorization is calculated by the ground zone controller (ZC) and provided through the train-ground wireless communication. In the current train operation control method, if the current position of the train or the movement authorization is lost due to equipment failure, the train will be emergency braked and need to wait for manual disposal. If necessary, emergency evacuation of passengers is also required.

[0004] When the train-ground wireless communication is interrupted for some reason or the ground ZC or transponder fails, the onboard ATP / ATO of the train operation control system cannot obtain accurate movement authorization or location information, but it still has the operation function. If it is in manual driving mode, the driver can also use restricted or unrestricted driving mode to visually drive the train to a safe area. In the unattended automatic driving mode, although the train has the function of running, the "failure-safety" principle of the operation control system will determine that the train is in a dangerous state of driving and will not allow the train to continue running. At this time, the train operation is interrupted, and manual troubleshooting is required, and corresponding disposal measures are taken. Therefore, once a fault occurs, it is necessary to wait for staff to board the train for disposal, which has a great impact on the train operation efficiency, and the fault disposal time is long, which is easy to cause passengers to have bad emotions or panic, and there are also potential other dangerous factors.

[0005] In addition, the train automatic control system (TACS) based on vehicle-to-vehicle communication is one of the development directions of the train operation control system at this stage. The key to its train operation control is similar to that of the CBTC system, which is to obtain accurate current location and driving resource information for the on-board system equipment. The difference is that the TACS system obtains key driving information that the train's own on-board equipment does not have through wireless communication equipment, and then calculates the mobile authorization through the on-board equipment, which greatly reduces the equipment in the ground signal equipment room. However, when wireless communication is interrupted, ground key equipment or on-board speed measurement and positioning unit fails, the TACS system also faces the same problems as the CBTC system. Summary of the invention

[0006] The present invention aims to solve at least one of the technical problems existing in the prior art, and proposes a train operation control system, method and electronic equipment based on image target detection. The method allows a train with operation function to ensure that the train can safely travel to a safe area even when the wireless communication of the operation control system is interrupted or the ground ZC or transponder fails, thereby reducing the emergency stop time of the train due to failure, reducing the impact on the subsequent train operation efficiency to a certain extent, and also reducing the probability of adverse accidents caused by potential dangerous factors during the forced stop of the train.

[0007] In a first aspect, the present invention provides a train operation control system based on image target detection, comprising:

[0008] A camera, the camera is used to obtain video images along the track ahead of the train;

[0009] An image processing unit, the image processing unit is used to extract the target along the track in the image and its feature information, and obtain the distance between the train and the target;

[0010] The on-board ATP / ATO device is used to calculate the train movement authorization according to the distance between the train and the target, calculate the train protection speed curve according to the train movement authorization, and control the train operation according to the train protection speed curve.

[0011] The present invention provides a train operation control method based on image target detection, comprising the following steps:

[0012] S1: Acquire the image ahead of the train;

[0013] S2: Extract the target and its feature information along the track in the image and obtain the distance between the train and the target;

[0014] S3: Calculate train movement authorization;

[0015] S4: Calculate the train protection speed curve according to the train movement authorization;

[0016] S5: Control train operation according to the train protection speed curve.

[0017] Further, the distance between the train and the target is obtained, specifically including: establishing a camera coordinate system with the optical center origin of the vehicle-mounted camera as the center point c -X c Y c Z c , camera coordinate system Z c The X axis is consistent with the main optical axis of the camera. c O c Y c The plane is consistent with the lens plane; then establish the pixel coordinate system O uv -uv and image coordinate system O xy -xy, pixel coordinate system O uv -uv takes the upper left corner of the image as the origin, the right is the u axis, and the downward is the v axis; the image coordinate system O xy -xy takes the center of the image as the origin, the x-axis and y-axis are parallel to the u-axis and v-axis respectively. For point P along the track, its coordinates in the camera coordinate system are recorded as (x c ,y c ,z c ), the coordinates of the projection point P' on the image in the image coordinate system and the pixel coordinate system are (x, y) and (u, v), respectively, and the conversion relationship between the two is:

[0018]

[0019] Where, d x d y Respectively represent the width of the column pixel and the height of the row pixel, u0 and v0 represent the pixel coordinate position corresponding to the origin of the image coordinate system;

[0020] According to the similarity relationship, the transformation relationship of P' in the image coordinate system and the camera coordinate system is calculated as follows:

[0021]

[0022] Where f is the focal length;

[0023] Get the optical center origin of the vehicle camera and the distance L from point P to the center of the line c and L P , calculate the x of P in the camera coordinate system c The coordinate value is L P -L c , according to the x of P in the camera coordinate system c The coordinate values ​​calculate the distance from the camera to the target point and the camera coordinate system coordinates of the target point.

[0024] Furthermore, the targets include obstacles and visual labels on the trackside;

[0025] Calculate train movement authorization, including:

[0026] When there is an obstacle within the visible range, calculate the relative distance L from the current position of the train to the movement authorization point MAL =L o -L s or L MAL =L r -L s , L s is the safety protection distance, L o is the distance between the train and the obstacle, L r is the length of the track visible range of the image collected at the current position of the train, L o ≤L r ;

[0027] When the train position is not lost or the image collected at the train's current position has a visual label with mileage data, obtain the train's current position mileage S c , calculate the mobile authorization terminal mileage S MAL =S c +L MAL .

[0028] Furthermore, when the image collected at the current position of the train contains a visual tag with mileage data, the mileage S of the current position of the train is obtained. c Specifically, it includes: combining the camera coordinate system to calculate the position mileage of the camera origin on the line, and obtaining the train position mileage data S c =S vie -L vie , where S vie is the visual label mileage, L vie is the distance between the train and the visual label with mileage data.

[0029] Furthermore, the train protection speed curve is calculated, specifically including:

[0030] When the train position is obtained, the relative distance L between the train and the mobile authorization end point is known. MAL When the acceleration a under the most unfavorable conditions is calculated based on the mobile authorization endpoint and the current position line parameters in the vehicle electronic map s , calculate the train emergency braking speed curve MCB, and calculate the train's current position mileage S c The maximum speed v c , v c The calculation formula is:

[0031]

[0032] Among them, t r is the train braking delay time;

[0033] Combined with v c , calculate and obtain the basic train ATP speed protection curve MCBA;

[0034] According to v c , train and operation control system performance to calculate the maximum possible value of Δl, Δl is the distance generated by the train running at the ATO speed curve under the ATP speed protection curve for Δt, Δt is the image processing cycle, and the mileage S is calculated c +Δl to mileage S MAL The ATP speed protection curve DCM is used to calculate the train speed at mileage S. c +Δl speed v l Maximum value, v l The calculation formula is:

[0035]

[0036] According to the position S c +Δl and the acceleration a under the most unfavorable conditions corresponding to the route parameters in the on-board electronic map s ′, calculate the train emergency braking speed curve DEFG, and calculate the train's current position mileage S c The maximum speed v c ′,v c The calculation formula is:

[0037]

[0038] At this point, the train mileage S from the current position is obtained. c Depart from, with location mileage S MAL ATP speed protection curve GFEDCM for the mobile authorization endpoint.

[0039] Furthermore, if there is a speed limit in the area, the speed of the point position on the calculated ATP speed protection curve GFEDCM is compared with the speed limit of the corresponding position on the electronic map, and the lower speed value at the same position is taken to obtain a new ATP speed protection curve.

[0040] Furthermore, when the train position is missing and the image captured at the current position of the train does not include a visual label with mileage data, the train protection speed curve is calculated according to a preset value or the train operation is controlled according to a preset value.

[0041] Furthermore, the train operation is controlled according to the train protection speed curve. If the train does not run to the target point, the process returns to step S1. If the train runs to the target point, the control ends.

[0042] Furthermore, the train operation is controlled according to the train protection speed curve, specifically including: based on the calculated train ATP protection speed curve, the on-board ATP / ATO equipment controls the train speed not to exceed the train ATP protection speed curve.

[0043] In a third aspect, the present invention further provides an electronic device, comprising:

[0044] at least one processor; and

[0045] a memory communicatively connected to the at least one processor; wherein,

[0046] The memory stores one or more computer programs that can be executed by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can execute the train operation control method based on image target detection as described in the first aspect.

[0047] The present invention has at least the following beneficial effects: The present invention discloses a train autonomous operation control method applicable to urban rail transit, especially an unmanned fully automatic operation system. Compared with the existing technical solutions, the image target detection method based on this solution enables the train to obtain mobile authorization autonomously and calculate the corresponding ATP protection speed curve, so that even when the wireless communication of the operation control system is interrupted or the ground ZC or transponder fails, the train with operation function can still ensure the safe driving of the train to a safe area, reduce the time the train stops in the section for some reason, and reduce the impact on the subsequent train operation efficiency to a certain extent. At the same time, it also reduces the probability of adverse accidents caused by potential dangerous factors during the train stop, further improves the intelligence of train operation, and improves the level of urban rail transit operation service. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A schematic diagram of the basic structure of a train operation control system based on image target detection provided by an embodiment of the present invention;

[0049] Figure 2 A flow chart of a train operation control method based on image target detection provided by an embodiment of the present invention;

[0050] Figure 3 A schematic diagram of target distance recognition provided by an embodiment of the present invention;

[0051] Figure 4 A schematic diagram of calculating a train safety protection speed curve provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to enable those skilled in the art to better understand the technical solution of the present invention, the technical solution in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0053] With the rapid development of artificial intelligence and computer vision, the field of autonomous driving using machine vision has gradually become a research hotspot, and related technologies and algorithms have gradually matured. In view of the problems existing in the train operation control process in the existing technology, it is possible to consider using mature deep learning-based algorithms to detect and extract features from image targets, and realize autonomous train operation control under partial fault conditions.

[0054] The idea of ​​the train autonomous operation control scheme designed in the present invention is that the on-board equipment based on image target detection autonomously obtains movement authorization and calculates the ATP protection speed curve. First, a high-definition camera installed at the end of the train is used to collect video images of the track line range in front of the train. The target and feature information along the track in the image are extracted through the image processing unit, and the relative distance between the train and the target is obtained. Based on this, the train movement authorization and ATP protection speed curve are calculated, thereby controlling the train to continue running.

[0055] See also Figure 1 The embodiment of the present invention discloses a train operation control system based on image target detection, comprising:

[0056] A camera, the camera is used to obtain video images along the track ahead of the train;

[0057] An image processing unit, the image processing unit is used to extract the target along the track in the image and its feature information, and obtain the distance between the train and the target;

[0058] The on-board ATP / ATO device is used to calculate the train movement authorization according to the distance between the train and the target, calculate the train protection speed curve according to the train movement authorization, and control the train operation according to the train protection speed curve.

[0059] The targets are mainly obstacles in the track and visual labels beside the track.

[0060] The obstacle mainly refers to the forward train, but may also be a foreign object in the track that affects the safe operation of the train.

[0061] The visual labels on the trackside are equipment and signs installed on the trackside during the construction of rail transit, such as signal machines, turnouts, switch machines, civil air defense doors, flood prevention doors, fans, signal machine labels, turnout labels, mileage signs, speed limit signs, etc.; they can also be signs installed on the trackside specifically for providing train operation information.

[0062] Furthermore, the image processing unit is used to process the collected images, and can realize the recognition of obstacles and visual labels in the images, feature extraction and target distance measurement.

[0063] The on-board ATP / ATO device stores an electronic map of the route and has the functions of train speed protection and train running speed control. In combination with the obstacle target distance provided by the image processing unit, it also has the function of mobile authorization calculation.

[0064] The electronic route map contains route parameters and visual label parameters. The route parameters include the route slope, curve, and speed limit corresponding to each route mileage point; the visual label parameters mainly refer to the mileage information of unique visual labels, such as signal labels, switch labels, mileage signs, some speed limit signs, and special identification signs.

[0065] Figure 1 A schematic diagram of the basic structure of a train autonomous operation control system based on image target detection disclosed in an embodiment is shown in FIG. Figure 1 The "1" represents the train, that is, the overall equipment of the vehicle system, including all equipment such as traction, braking, and operation control of the train. Figure 1 The "2" in the figure indicates a high-definition camera used to obtain the image of the front of the train. Figure 1 The "3" in the figure represents the track on which the train runs. Figure 1 The "image processing unit" is used to process the image data in front of the track transmitted by the high-definition camera, and provide the processed target detection result information to the on-board ATP / ATO. The transmitted information includes the distance from the train to the obstacle, the distance from the train to the visual label, and the feature information of the visual label. Figure 1 "ATP / ATO" can calculate the train movement authorization based on the data transmitted by the image processing unit, realize the calculation of the train's safety protection speed and control the continuous operation of the train accordingly. Figure 1 The "positioning speed measuring device" is generally composed of a transponder antenna, a speed sensor, an accelerometer or a radar.

[0066] Figure 2 A flow chart of a train operation control method based on image target detection provided in an embodiment of the present invention; the implementation of this method mainly includes the following links: image target detection in front of the train, calculation of train position and movement authorization, calculation of train ATP protection speed curve, and autonomous operation of the train based on the protection speed curve.

[0067] An embodiment of the present invention provides a train operation control method based on image target detection, comprising the following steps:

[0068] S1: Acquire the image ahead of the train;

[0069] S2: Extract the target and its feature information along the track in the image and obtain the distance between the train and the target;

[0070] S3: Calculate train movement authorization;

[0071] S4: Calculate the train protection speed curve according to the train movement authorization;

[0072] S5: Control the train operation according to the train protection speed curve;

[0073] S6: If the target point has not been reached, the process returns to step S1; if the target point has been reached, the process ends.

[0074] Furthermore, obtaining the image ahead of the train specifically includes: collecting visual label images along the line.

[0075] For trains running on the same line, their visual labels are consistent. In order to obtain a more comprehensive image target recognition model training data set, the cameras of all trains on the line are set at the same calibration position, that is, when the trains stop at the same position, the cameras have the same world coordinate system, and the camera shooting angles of each train are consistent during operation, so a more comprehensive image data set can be obtained, and then massive data can be used to carry out deep learning target detection algorithm training, which needs to detect the obstacles and visual labels in the main target track.

[0076] Further, the distance between the train and the target is obtained, specifically including: For image processing, firstly establish a camera coordinate system with the optical center origin of the vehicle-mounted camera as the center point c -X c Y c Z c , camera coordinate system Z c The X axis is consistent with the main optical axis of the camera. c O c Y c The plane is consistent with the lens plane; then establish the pixel coordinate system O uv -uv and image coordinate system O xy -xy,O uv -uv takes the upper left corner of the image as the origin, the right is the u axis, and the downward is the v axis; xy -xy takes the center of the image as the origin, and the x-axis and y-axis are parallel to the u-axis and v-axis respectively. For point P along the track, its coordinates in the camera coordinate system are recorded as (x c ,yc ,z c ), the coordinates of its projection point P' on the image in the image coordinate system and the pixel coordinate system are (x, y) and (u, v) respectively. The conversion relationship between the two is shown in the following formula.

[0077]

[0078] Where, d x d y They represent the width of the column pixels and the height of the row pixels respectively, and u0 and v0 represent the position coordinates of the pixel coordinate system corresponding to the origin of the image coordinate system.

[0079] Based on the similarity relationship, the transformation relationship between P' in the image coordinate system and the camera coordinate system can be calculated, as shown in the following formula.

[0080]

[0081] Where f is the focal length.

[0082] The distances from the optical center origin of the vehicle-mounted camera and point P to the center of the line can be obtained, denoted as L c and L P , we can calculate the x coordinate of P in the camera coordinate system c The coordinate value is L P -L c ,Further using the triangle similarity principle or depth of field measurement method ,the distance from the camera to the target point and the camera coordinate system coordinate ,of the target point can be calculated.

[0083] Figure 3 This is a schematic diagram of target distance recognition disclosed in this embodiment. Figure 3 "O c -X c Y c Z c " is the camera coordinate system; " c " is the optical center origin of the vehicle-mounted camera and also the origin of the camera coordinate system; Z c The X axis is consistent with the main optical axis of the camera. c O c Y c The plane coincides with the lens plane.

[0084] Figure 3 "O uv -uv" is the pixel coordinate system; uv " is the vertex in the upper left corner of the imaging plane and is also the origin of the pixel coordinate system; the origin of the pixel coordinate system is the u axis to the right and the v axis downward.

[0085] Figure 3 "O xy-xy" is the image coordinate system; xy " is the intersection of the camera's principal optical axis and the image, which is the center of the image and the origin of the image coordinate system; the image coordinate system has the x-axis to the right and the y-axis downward.

[0086] Figure 3 Where "P" is the point on the visual label in front of the train, and its coordinates in the camera coordinate system are (x c ,y c ,z c ), "P'" is the position of P in the pixel coordinate system after imaging, and the pixel coordinates are (u, v); according to the installation position of the visual label on the trackside, the x coordinate of P in the camera coordinate system can be obtained. c Coordinate value.

[0087] Furthermore, the train movement authorization is calculated, including:

[0088] The length of the track visible range of the image collected at the current position of the train is recorded as L r ; When there is an obstacle within the visible range, the distance between the train and the obstacle can be obtained and recorded as L o , there is a constraint L o ≤L r At this time, the relative distance L from the current position of the train to the mobile authorization point can be obtained based on the image processing information. MAL =L o -L s or L MAL =L r -L s , L s It is the safety protection distance required by the characteristics of the operation control system. When the train position has been obtained, the authorized end mileage is S MAL =S c +L MAL The mobile authorization end mileage can be missing.

[0089] The train position is not lost or the image collected at the current train position has a visual label with mileage data (visual label mileage is recorded as S vie ) can get the current train position mileage S c For the visual label with mileage data, the camera coordinate system can be combined to calculate the position mileage of the camera origin in the line, so as to obtain the train position mileage data. The distance between the train and the visual label with mileage data is recorded as L vie , S c =S vie -L vie . The train location mileage can be missing.

[0090] The calculation of train ATP protection speed curve is divided into two cases of train position: one is that the train position is known, and the other is that the train position is unknown.

[0091] Figure 4 Schematic diagram of the calculation of the train safety protection speed curve disclosed in this embodiment, Figure 4 "S c " indicates the current mileage of the train, which can be left blank. Figure 4 Here, “Δl” represents the maximum displacement distance of the train within the data processing cycle Δt of the image processing unit. Figure 4 "S MAL ” is the mobile authorization endpoint calculated by the on-board ATP / ATO equipment based on the distance between the train and the obstacle or the visible range of the track. Figure 4 "L o " is the distance between the train and the obstacle. When there is no obstacle in front of the train, it indicates the visible range of the track ahead. Figure 4 "L s " is the safety protection distance required by the operating control system characteristics. Figure 4 "A, B, C, D, E, F, G, H, I, J, K, M" represent the position and speed points respectively. When the train position is not lost, its position is the line mileage, and when the train position is lost, it is the relative train distance. The speed curve ABCM is the speed curve of the train from the current position S c Run to the mobile authorization end point S MAL The emergency braking speed curve DCM is the speed curve of the train from position S c +ΔlRun to the mobile authorization end point S MAL The emergency braking speed curve of the train is GFED. The speed curve GFED is the speed curve of the train from the current position S c Run to position S c +Δl will not exceed the emergency braking speed curve at point D; speed curve HE is the inherent regional speed limit curve constrained by line conditions. Speed ​​curve IJK is the possible running speed curve of the train under the protection of speed curve ABCM.

[0092] The following is combined with Figure 4 Taking the train position as an example, the calculation process of the train ATP protection speed curve is explained, which specifically includes:

[0093] S41: Relative distance L between the train and the end point of the mobile authorization MAL It is known that the train acceleration a under the most unfavorable conditions based on the mobile authorization end point and the current position line parameters in the on-board electronic map is s , the train emergency braking speed curve MCB can be calculated. The train's current position mileage S c The maximum speed at v c , the train braking delay time is recorded as t r , vc The maximum value can be calculated using the following formula.

[0094]

[0095] S42: Combined with v c , the basic train ATP speed protection curve MCBA can be calculated. The train can run with the ATO speed curve under the ATP speed protection curve. After the train runs Δl distance after Δt time (image processing unit data processing cycle, which can be set), the movement authorization is updated. In unfavorable cases, the position mileage of the movement authorization may still be S MAL The train follows the ATO speed curve IJK and arrives at S c +Δl broke through the recalculated ATP speed protection curve, causing the train to emergency brake again.

[0096] S43: According to v c , train and operation control system performance to calculate the maximum possible value of Δl, and then calculate the mileage S c +Δl to mileage S MAL ATP speed protection curve DCM, and calculated v c In a similar way, the train mileage S can be calculated by the following formula c +Δl speed v l Maximum value.

[0097]

[0098] The train acceleration a under the most unfavorable conditions is calculated based on the position speed point D and the current position line parameters in the on-board electronic map. s ', the train emergency braking speed curve DEFG can be calculated. At this time, the train is at the current position mileage S c The maximum speed v c ′ can be calculated using the following formula.

[0099]

[0100] At this point, the train mileage S from the current position is obtained. c Depart from, with location mileage S MAL The ATP speed protection curve GFEDCM of the end point of the movement authorization. The train ATO running speed curve calculated by the speed protection curve can prevent the train from emergency braking when the movement authorization is next updated.

[0101] Due to the constraints of line conditions, some areas have speed limits. Furthermore, the train ATP protection speed curve calculation process also includes step S44: comparing the speed point at the point position on the ATP speed protection curve GFEDCM calculated by S41 to S43 with the speed limit at the corresponding position on the electronic map, and taking the lower speed value at the same position to obtain a new ATP speed protection curve. That is, for any mileage point P at the curve GFEDCM, i =(S i , v i ), Mileage S i The speed limit is v i，lim , if v i，lim <v i , there is P i =(S i , v i，lim ), otherwise P i Remain unchanged. Figure 4 In the curve GFEDCM, G is the position velocity (S c , v c ′), mileage S c The speed limit in the route area is V lim , with V lim <v c ′, so the ATP speed protection curve HEDCM is obtained.

[0102] In some embodiments, when the train position is unknown (the train position is lost and the image captured at the current position of the train does not include a visual label with mileage data), it is impossible to accurately obtain the line speed limit and train acceleration corresponding to the current position of the train in combination with the information in the on-board electronic map. The ATP protection speed curve of the train at the relative position can be calculated according to the preset values ​​(that is, the line speed limit and train acceleration in S41 to S44 above can be considered according to the minimum speed limit and the most unfavorable acceleration of the entire line or the area where the train is located, and can also be preset in advance in the on-board system). The speed curve can be calculated to obtain the speed S at a distance from the current position of the train. j The limit speed v of the position j , the train operation is controlled according to the train ATP protection speed curve. When the visual label with mileage data is obtained during the operation, the train position can be obtained, and the line speed limit value and train acceleration corresponding to the current position of the train can be accurately obtained in combination with the information in the on-board electronic map, and S41~S44 are executed to calculate the train ATP protection speed curve of the relative position.

[0103] In other embodiments, when the position of the train is unknown, the train operation may also be controlled according to preset values ​​(such as a preset speed, etc.).

[0104] Furthermore, the train operation is controlled according to the train protection speed curve, specifically including: based on the train ATP protection speed curve calculated in step S4, the on-board ATP / ATO equipment can control the train speed not to exceed the curve.

[0105] As the train moves forward, the target distance is updated, and the train movement authorization is updated accordingly, so that the train's current position S c Update, repeat the above process until the train runs to the target position and stops, thus completing the train autonomous operation control.

[0106] Based on the same inventive concept, an embodiment of the present disclosure provides an electronic device, including:

[0107] at least one processor; and

[0108] a memory communicatively connected to the at least one processor; wherein,

[0109] The memory stores one or more computer programs that can be executed by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can execute the train operation control method based on image target detection as described above.

[0110] Based on the same inventive concept, an embodiment of the present disclosure provides a storage medium for readable storage, wherein the storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the train operation control method based on image target detection as described above.

[0111] Among them, the processor is a device with data processing capabilities, including but not limited to a central processing unit (CPU), etc.; the memory is a device with data storage capabilities, including but not limited to random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface (read-write interface) is connected between the processor and the memory, and can realize information exchange between the processor and the memory, including but not limited to a data bus (Bus), etc.

[0112] In some embodiments, the processor, memory, and I / O interface are connected to each other and, in turn, to other components of the computing device via a bus.

[0113] In some embodiments, the one or more processors include a field programmable gate array.

[0114] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, including a computer program carried on a machine-readable medium, the computer program containing a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit (CPU), the above-mentioned functions defined in the system of the present disclosure are executed.

[0115] It should be noted that the computer-readable medium shown in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device or device. In the present disclosure, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, in which a computer-readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, which may send, propagate or transmit a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0116] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present disclosure. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of the code, and the aforementioned module, program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0117] It is to be understood that the above embodiments are merely exemplary embodiments used to illustrate the principles of the present disclosure, but the present disclosure is not limited thereto. For those of ordinary skill in the art, various modifications and improvements can be made without departing from the spirit and substance of the present disclosure, and these modifications and improvements are also considered to be within the scope of protection of the present disclosure.

Claims

1. A train operation control system based on image target detection, characterized in that: include: A camera, the camera is used to obtain video images along the track ahead of the train; An image processing unit, the image processing unit is used to extract the target along the track in the image and its feature information, and obtain the distance between the train and the target; The on-board ATP / ATO device is used to calculate the train movement authorization according to the distance between the train and the target, calculate the train protection speed curve according to the train movement authorization, and control the train operation according to the train protection speed curve.

2. A train operation control method based on image target detection, characterized in that: The steps include: S1: Acquire the image ahead of the train; S2: Extract the target and its feature information along the track in the image and obtain the distance between the train and the target; S3: Calculate train movement authorization; S4: Calculate the train protection speed curve according to the train movement authorization; S5: Control train operation according to the train protection speed curve.

3. The train operation control method based on image target detection according to claim 1, characterized in that: Get the distance between the train and the target, including: Establish a camera coordinate system O with the optical center of the vehicle camera as the center point c -X c Y c Z c , camera coordinate system Z c The X axis is consistent with the main optical axis of the camera. c O c Y c The plane is consistent with the lens plane; then establish the pixel coordinate system O uv -uv and image coordinate system O xy -xy, pixel coordinate system O uv -uv takes the upper left corner of the image as the origin, the right is the u axis, and the downward is the v axis; the image coordinate system O xy -xy takes the center of the image as the origin, the x-axis and y-axis are parallel to the u-axis and v-axis respectively. For point P along the track, its coordinates in the camera coordinate system are recorded as (x c ,y c ,z c ), the coordinates of the projection point P' on the image in the image coordinate system and the pixel coordinate system are (x, y) and (u, v), respectively, and the conversion relationship between the two is: Where, d x ,d y Respectively represent the width of the column pixel and the height of the row pixel, u0 and v0 represent the pixel coordinate position corresponding to the origin of the image coordinate system; According to the similarity relationship, the transformation relationship of P' in the image coordinate system and the camera coordinate system is calculated as follows: Where f is the focal length; Get the optical center origin of the vehicle-mounted camera and the distance L from point P to the center of the line c and L P , calculate the x of P in the camera coordinate system c The coordinate value is L P -L c , according to the x of P in the camera coordinate system c The coordinate values ​​calculate the distance from the camera to the target point and the camera coordinate system coordinates of the target point.

4. The train operation control method based on image target detection according to claim 1, characterized in that: Targets include obstacles and visual tags on the trackside; Calculate train movement authorization, including: When there is an obstacle within the visible range, calculate the relative distance L from the current position of the train to the movement authorization point MAL =L o -L s or L MAL =L r -L s , L s is the safety protection distance, L o is the distance between the train and the obstacle, L r is the length of the track visible range of the image collected at the current position of the train, L o ≤L r ; When the train position is not lost or the image collected at the train's current position has a visual label with mileage data, the mileage S of the train's current position is obtained. c , calculate the mobile authorization terminal mileage S MAL =S c +L MAL .

5. The train operation control method based on image target detection according to claim 4 is characterized in that: When the image collected at the current position of the train has a visual label with mileage data, the mileage S of the current position of the train is obtained. c Specifically, it includes: combining the camera coordinate system to calculate the position mileage of the camera origin on the line, and obtaining the train position mileage data S c =S vie -L vie , where S vie is the visual label mileage, L vie is the distance between the train and the visual label with mileage data.

6. The train operation control method based on image target detection according to any one of claims 1 to 5, characterized in that: Calculate the train protection speed curve, including: When the train position is obtained, the relative distance L between the train and the mobile authorization end point is known. MAL When the acceleration a under the most unfavorable conditions is calculated based on the mobile authorization endpoint and the current position line parameters in the vehicle electronic map s , calculate the train emergency braking speed curve MCB, and calculate the train's current position mileage S c The maximum speed v c , v c The calculation formula is: Among them, t r is the train braking delay time; Combined with v c , calculate and obtain the basic train ATP speed protection curve MCBA; According to v c , train and operation control system performance to calculate the maximum possible value of Δl, Δl is the distance generated by the train running at the ATO speed curve under the ATP speed protection curve for Δt, Δt is the image processing cycle, and the mileage S is calculated c +Δl to mileage S MAL The ATP speed protection curve DCM is used to calculate the train speed at mileage S. c +Δl speed v l Maximum value, v l The calculation formula is: According to the position S c +Δl and the acceleration a under the most unfavorable conditions corresponding to the route parameters in the on-board electronic map s ′, calculate the train emergency braking speed curve DEFG, and calculate the train's current position mileage S c The maximum speed v c ′,v c The calculation formula is: At this point, the train mileage S from the current position is obtained. c Depart from, with location mileage S MAL ATP speed protection curve GFEDCM for the mobile authorization endpoint.

7. The train operation control method based on image target detection according to claim 6 is characterized in that: If there is a speed limit in the area, the speed of the point on the calculated ATP speed protection curve GFEDCM is compared with the speed limit at the corresponding position on the electronic map, and the lower speed value at the same position is taken to obtain a new ATP speed protection curve.

8. The train operation control method based on image target detection according to claim 6 or 7, characterized in that: When the train position is missing and the image captured at the current position of the train does not contain a visual label with mileage data, the train protection speed curve is calculated according to the preset value or the train operation is controlled according to the preset value.

9. The train operation control method based on image target detection according to claim 1, characterized in that: Control the train operation according to the train protection speed curve. If the train does not reach the target point, return to step S1. If the train reaches the target point, the control ends. The train operation is controlled according to the train protection speed curve, specifically including: based on the calculated train ATP protection speed curve, the on-board ATP / ATO equipment controls the train speed not to exceed the train ATP protection speed curve.

10. An electronic device, characterized in that: include: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, and the one or more computer programs are executed by the at least one processor so that the at least one processor can execute the train operation control method based on image target detection as described in any one of claims 2 to 9.

Images