A train positioning method and positioning device
By setting coded patterns on the track and using cameras and speed sensors for digital code recognition, the problems of insufficient accuracy and high cost of existing train positioning methods in urban rail transit have been solved, achieving accurate and cost-effective train positioning.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- 青岛佳都微联信号系统有限公司
- Filing Date
- 2023-04-21
- Publication Date
- 2026-06-09
AI Technical Summary
Existing train positioning methods in urban rail transit suffer from problems such as insufficient positioning accuracy, high cost, or inability to be used in underground spaces. In particular, the Doppler velocity measurement positioning method has large errors, the track circuit positioning method has poor accuracy, the wireless beacon positioning method has high cost, and the satellite positioning method cannot be applied.
The system employs multiple coded patterns set on the track, captures coded images with cameras and performs digital code recognition, combines this with speed sensors for positioning, and utilizes the correspondence between coded images and positions to locate the train.
It improves positioning accuracy, reduces positioning costs, and enables precise train positioning in underground spaces, making it suitable for flexible adjustments under different line lengths and conditions.
Smart Images
Figure CN118810865B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of positioning technology, and in particular to a train positioning method and positioning device. Background Technology
[0002] In the field of rail transit control, precise train positioning is of great significance for accurate train stopping and starting.
[0003] Among related technologies, train positioning methods mainly include Doppler velocity measurement positioning, track circuit positioning, wireless beacon positioning, satellite positioning, and transponder positioning. For urban rail transit, Doppler velocity measurement positioning has a large error when the train is running at low speed; track circuit positioning has poor accuracy and does not meet the requirements of line operation; wireless beacon positioning requires laying a large number of electronic tags on the line, which is too costly; underground spaces cannot be used for train positioning via satellite; and the positioning accuracy and construction cost of transponder positioning cannot be simultaneously satisfied. Summary of the Invention
[0004] The exemplary embodiments of this application provide a train positioning method and positioning device to improve positioning accuracy while reducing positioning costs.
[0005] According to a first aspect of an exemplary embodiment, a train positioning method is provided, the method being applied to a positioning device, the train positioning method comprising:
[0006] Multiple coded images are obtained by taking pictures of multiple location markers set on the track during the train's operation;
[0007] For each of the multiple encoded images, perform the following operations to determine the position of the train represented by each encoded image:
[0008] The first coded image is identified to determine the first encoding result of the first coded image; the first position of the first coded image is determined according to the correspondence between the first encoding result and the pre-set encoding result and position; wherein, the first coded image is any one of a plurality of coded images;
[0009] The train is located based on multiple positions corresponding to multiple coded images.
[0010] According to a second aspect of an exemplary embodiment, a positioning device is provided, the positioning device comprising: a transmission unit and a processor;
[0011] The transmission unit is configured to perform:
[0012] Multiple coded images are obtained by taking pictures of multiple location markers set on the track during the train's operation;
[0013] The processor is configured to execute:
[0014] For each of the multiple encoded images, perform the following operations to determine the position of the train represented by each encoded image:
[0015] The first coded image is identified to determine the first encoding result of the first coded image; the first position of the first coded image is determined according to the correspondence between the first encoding result and the pre-set encoding result and position; wherein, the first coded image is any one of a plurality of coded images;
[0016] The train is located based on multiple positions corresponding to multiple coded images.
[0017] According to a third aspect of an exemplary embodiment, a positioning device is provided, the device comprising an image acquisition unit, a processing unit, and a positioning unit:
[0018] The image acquisition unit is used to acquire multiple coded images of multiple location markers set on the track during the train's operation;
[0019] The processing unit is configured to perform the following operations for each of the multiple encoded images to determine the position of the train represented by each encoded image: identify the first encoded image to determine the first encoding result of the first encoded image; determine the first position of the first encoded image according to the correspondence between the first encoding result and a pre-set encoding result and position; wherein the first encoded image is any one of the multiple encoded images;
[0020] The positioning unit is used to locate the train based on multiple positions corresponding to multiple coded images.
[0021] According to a fourth aspect of an exemplary embodiment, a computer storage medium is provided, which stores computer program instructions that, when executed on a computer, cause the computer to perform the train positioning method of the first aspect.
[0022] In this embodiment, the positioning device acquires multiple coded images captured by a train during its journey, showing multiple location markers placed on the track. For each coded image, the following operations are performed to determine the position of the train represented by each coded image: a first coded image is identified to determine a first coding result; a first position of the first coded image is determined based on the correspondence between the first coding result and a pre-set relationship between coding results and positions; and the train is positioned based on the multiple positions corresponding to the multiple coded images. By employing digital coding and automatic recognition, and utilizing the relationship between recognition results and positions, the train is positioned, thereby improving positioning accuracy while reducing positioning costs. Attached Figure Description
[0023] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0024] Figure 1 An exemplary schematic diagram of a train positioning system provided in an embodiment of this application is shown;
[0025] Figure 2 An exemplary schematic diagram of a cross-section of an encoding pattern provided in an embodiment of this application is shown;
[0026] Figure 3 An exemplary schematic diagram of an encoding pattern provided in an embodiment of this application is shown;
[0027] Figure 4 An exemplary diagram illustrates the correspondence between a cross-sectional view and a top view of an encoding pattern provided in an embodiment of this application;
[0028] Figure 5 An exemplary flowchart of a train positioning method provided in an embodiment of this application is shown;
[0029] Figure 6 An exemplary illustration shows a schematic diagram of a first coded image before perspective correction provided in an embodiment of this application;
[0030] Figure 7 An exemplary schematic diagram of a perspective-corrected first coded image provided in an embodiment of this application is shown;
[0031] Figure 8 An exemplary diagram illustrating the variation of a first feature value WT1 provided in an embodiment of this application is shown.
[0032] Figure 9 An exemplary diagram illustrating the variation of a first feature value WT2 provided in an embodiment of this application is shown.
[0033] Figure 10 An exemplary diagram illustrating the variation of a first feature value WT3 provided in an embodiment of this application is shown.
[0034] Figure 11 An exemplary schematic diagram of a train positioning device provided in an embodiment of this application is shown;
[0035] Figure 12 An exemplary schematic diagram of a train positioning device provided in an embodiment of this application is shown. Detailed Implementation
[0036] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.
[0037] In the field of rail transit control, precise train positioning is of great significance for accurate train stopping and starting.
[0038] Among related technologies, train positioning methods mainly include Doppler velocity measurement positioning, track circuit positioning, wireless beacon positioning, satellite positioning, and transponder positioning. For urban rail transit, Doppler velocity measurement positioning has a large error when the train is running at low speed; track circuit positioning has poor accuracy and does not meet the requirements of line operation; wireless beacon positioning requires laying a large number of electronic tags on the line, which is too costly; underground spaces cannot be used for train positioning via satellite; and the positioning accuracy and construction cost of transponder positioning cannot be simultaneously satisfied.
[0039] Therefore, this application provides a train positioning method. In this method, multiple location markers, such as coded patterns, are set on the train track. Each coded pattern consists of multiple coded strips sprayed on the track. One coded strip is sprayed on each track, or n tracks out of N consecutive tracks each have one coded strip, where n is less than N. The length and color of each coded strip are fixed. During train operation, a camera installed at the bottom of the train captures images of the multiple coded patterns, obtaining multiple coded images. Each coded image represents a location; therefore, the train is positioned by recognizing the codes.
[0040] After introducing the design concept of the embodiments of this application, the following is a brief introduction to the application scenarios to which the technical solutions of the embodiments of this application can be applied. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.
[0041] Figure 1 This is a schematic diagram of a train positioning system provided in an embodiment of this application. The positioning system may include an onboard camera, a location marker, a speed sensor, and an image processing unit. After calculating the real-time position of the train, the image processing unit can transmit the real-time position to the vehicle onboard controller (VOBC), which then performs vehicle-to-ground communication. In this embodiment, continuous real-time positioning of the train can be provided starting from when the train leaves the depot.
[0042] refer to Figure 1 The vehicle-mounted camera can include under-vehicle cameras and side-vehicle cameras. The side-vehicle cameras primarily identify parking position images on both sides of the track and track feature information to achieve precise train stopping and track positioning. In this embodiment, the under-vehicle camera is mainly used to capture position markers and locate the train during its journey. Additionally, a speed sensor is used to obtain the train's real-time speed for continuous train positioning. Furthermore, considering that high-speed train operation or camera field of view limitations can easily lead to incomplete position information in a single frame, this application can utilize multiple frames of images to stitch together complete train position information.
[0043] To ensure reliability, an undercarriage camera can be installed at both the front and rear of the train. Additionally, considering that low light conditions during train operation can affect visual recognition, an LED light source should be placed around each camera to ensure sufficient illumination within its field of view. To ensure that the undercarriage camera can capture a complete coded pattern within its field of view, the camera can be a wide-angle camera.
[0044] The coded pattern is composed of coded strips of varying lengths, colors, and digits, sprayed onto the sleepers of the track without the need for additional spraying materials. Typically, coded strips of different lengths and colors can represent different values. Combined with the number of digits in the coded strips, they can store binary, quartic, sigma, octal, decimal, or hexadecimal numbers to store location information. The capacity of the coded pattern is related to the diversity of the coded strips; the more types of coded strips, the larger the capacity of the coded pattern, the longer the track mileage it can accommodate, and the farther the location can be located from the departure point. Since mileage can be used to represent location, the mileage in this embodiment can also be used to describe location.
[0045] For example, the process of setting up the coded patterns can follow the following encoding format: based on the actual mileage of different lines (for example, the total mileage of Qingdao Metro Line 1 is 61 kilometers, or 61,000 meters), a binary, quaternary, octal, decimal, or hexadecimal system can be used to convert the mileage information into coded bars of different colors, lengths, and digits to store the track mileage information. For example, data where m is in base n, after being converted to decimal data, will be greater than 61,000.
[0046] In one implementation, each value represents the position of the coded pattern; in another implementation, each value has a specific correspondence with a position. Therefore, regardless of the implementation method, the coded image obtained from the coded pattern can be recognized to determine the corresponding coded pattern position, thereby locating the train.
[0047] Figure 2 This is a schematic diagram of a cross-section of an encoding pattern provided in an embodiment of this application. The distance between the two sleepers is 58cm. Taking an 8-bit 4-ary encoding format as an example, the length of one segment of the encoding pattern is L0 = 4.64m, d k The distance between the two coded patterns is α. The camera uses a 150° wide-angle lens, so α = 75°. The standard empty hook length is h = 880mm. The calculated visible range is L = 6.57m, which is greater than L0. Therefore, the design requirements are met, and a complete coded pattern can be observed.
[0048] Taking binary encoding as an example, only two white code bars of different lengths are needed to represent 0 / 1 values. If a longer orbital mileage needs to be represented with a limited number of bits, binary encoding is usually insufficient. In this case, other encoding bases can be used, and code bars of other colors (such as yellow) can be added to increase the number of code bar samples. This increases the diversity of sampled feature values after grayscale conversion, allowing for the representation of different values. Grayscale values are calculated from the RGB values of the corresponding positions in the encoded image. When selecting colors, the grayscale value distinguishability can be considered to improve the algorithm's recognition rate. For example, two distinct colors can be used to indicate different code bars.
[0049] Figure 3 This is a schematic diagram of an encoding pattern provided in an embodiment of this application. Figure 4 This diagram illustrates the correspondence between a cross-sectional view and a top view of an encoding pattern provided in an embodiment of this application. Taking one encoding pattern as an example, the beginning and end markers of the position sequence are painted white to identify the encoding segment, but do not store position information. Other coloring methods are for encoding bars that store position information. Figure 3 In the example, each sleeper is painted with a coded strip. In this example, it is an 8-bit 4-ary encoding method, with a white short code representing 0, a white long code representing 1, a yellow short code representing 2, and a yellow long code representing 3.
[0050] Generally, different bit lengths of coding result in different location information capacities. The number of bit lengths should be selected based on the actual track mileage and positioning accuracy requirements. To ensure the effectiveness of continuous train positioning, the minimum number of bit lengths that can cover the total track mileage should be selected. When an 8-bit code in the corresponding base cannot cover the track mileage, consider changing the base without increasing the code bit length. This is to ensure that all code bars of a given coding pattern are captured within the camera's field of view as much as possible. When the mileage is small and all code bits cannot be filled, use "0"s to fill in all empty code bits.
[0051] The spacing d between the two coded patterns k The positioning accuracy can be adjusted according to the specific project requirements. k The smaller the value, the higher the density of the coded pattern and the higher the positioning accuracy; the minimum value can be 0. k The larger the value, the lower the cost, and the longer the track mileage that can be represented by the code. Under the premise of meeting the maximum track coding length, d k It should be minimized as much as possible to improve positioning accuracy.
[0052] Encoding patterns with different bit depths, different bases, and different density can represent different maximum track lengths. Assuming the encoding base in this embodiment is set to j... i The number of bits is w i The coding spacing is d ki The maximum value at this time is ML. i =(j i wi -1)×d ki ;ML i The unit can be set according to the positioning accuracy requirements.
[0053] For shorter tracks, only black and white are used in the coding strip to improve recognition accuracy and ensure positioning precision and reliability. For medium-length tracks, three colors (black, white, and yellow) can be used, employing 6-bit or 7-bit encoding. For longer tracks, the number of coding bits can be increased to increase coding capacity and expand the total track mileage that can be covered. For even longer tracks, the number of coding strip colors can be increased to increase the number of feature values after image grayscale processing, further expanding the total track mileage that can be covered. While meeting positioning accuracy requirements, the coding spacing d can be appropriately increased. k This expands the total length of track that can be covered. The embodiments of this application are applicable under different line conditions and can be configured and parameters adjusted flexibly according to specific application requirements.
[0054] To further illustrate the technical solutions provided in the embodiments of this application, a detailed description is provided below in conjunction with the accompanying drawings and specific implementation methods. Although the embodiments of this application provide method operation steps as shown in the following embodiments or drawings, the method may include more or fewer operation steps based on conventional or non-inventive methods. In steps where there is no logically necessary causal relationship, the execution order of these steps is not limited to the execution order provided in the embodiments of this application.
[0055] The following is combined Figures 1-4 The application scenarios shown are for reference. Figure 5 The flowchart shown illustrates a train positioning method, which explains the technical solution provided in the embodiments of this application.
[0056] S501: The positioning device acquires multiple coded images obtained by taking pictures of multiple coded patterns set on the track during the train's operation.
[0057] S502: For each of the multiple coded images, the positioning device performs the following operations to determine the position of the train represented by each coded image:
[0058] S502-1: The positioning device identifies the first coded image and determines the first encoding result of the first coded image.
[0059] The first coded image is any one of a plurality of coded images.
[0060] S502-2: The positioning device determines the first position of the first coded image based on the correspondence between the first encoding result and the pre-set encoding result and position.
[0061] S503: The positioning device locates the train based on multiple positions corresponding to multiple coded images.
[0062] In this embodiment, the positioning device acquires multiple coded images obtained by capturing multiple coded patterns set on the track during train operation. For each coded image, the following operations are performed to determine the position of the train represented by each coded image: a first coded image is identified to determine a first coded result; a first position of the first coded image is determined based on the correspondence between the first coded result and a pre-set coded result and position; and the train is positioned based on the multiple positions corresponding to the multiple coded images. By employing digital encoding and automatic recognition, and utilizing the relationship between the recognition result and the position, the train is positioned, thereby improving positioning accuracy while reducing positioning costs.
[0063] Regarding S501, during train operation, the camera in the positioning device captures multiple coded patterns set on the track, obtaining multiple coded images. This can be achieved by analyzing the video captured during the capture process to obtain different video frames, with each video frame serving as a coded image.
[0064] according to Figure 2 The location of the camera can be determined, and at any given moment, the camera can capture a complete coded pattern, thus obtaining a coded image. In practical applications, a camera can be installed at both the front and rear of the train to prevent the inability to locate the train if one of the cameras fails.
[0065] In S502-1, the positioning device identifies the first coded image and determines the first encoding result of the first coded image.
[0066] In this system, the first coded image can be any one of multiple coded images, and the first encoding result can be a number represented by the first coded image, which can represent the train's location. The location can be represented by mileage, for example, XX kilometers from the originating station. This recognition process can be implemented using a backpropagation (BP) neural network algorithm.
[0067] For example, the positioning device determines the first encoding result of the first encoded image through steps A1-A5.
[0068] A1: The positioning device performs perspective correction on the first coded image to obtain the first corrected image.
[0069] The first coded image includes a first start coded bar, a first end coded bar, and at least one first positioning coded bar.
[0070] Since the first coded image is captured by a camera installed under the vehicle, the display effect of the first coded image is usually... Figure 6 In other words, the shooting angle may cause visual bias in the first coded image. Therefore, perspective correction is performed on the first coded image to obtain... Figure 7 The first corrected image shown.
[0071] A2: The positioning device determines the number and position of the first sampling lines based on the length of at least one first positioning code bar.
[0072] refer to Figure 7 The first positioning code has 8 bars, meaning the first coded image can represent 8 digits. The number base can be determined according to the actual situation. Figure 7It can be seen that the lengths of the eight first positioning coding bars can be divided into two categories. Therefore, the number of first sampling lines can be determined to be three. In addition, the positions of three first sampling lines are determined based on the lengths of the eight first positioning coding bars to ensure that different first positioning coding bars can be distinguished by the positions of the three first sampling lines and the color values of different first positioning coding bars.
[0073] To reduce the amount of data processing, grayscale processing can be performed on the first coded image. Therefore, grayscale values are sampled at the positions of the three first sampling lines, and the different grayscale values are represented by their respective first feature values. The three sets of grayscale value matrices are converted into feature value matrices, which are then used to identify the first coded image.
[0074] A3: The positioning device determines a first positional relationship based on the position of at least one first sampling line and the length of at least one first positioning code bar.
[0075] The first positional relationship includes the intersection relationship between the first sampling line and the first positioning code bar. For example, the first sampling lines intersecting with the first positioning code bar 2 are W1, W2, and W3; the first sampling line intersecting with the first positioning code bar 3 is W2; the first sampling lines intersecting with the first positioning code bar 4 are W1, W2, and W3; the first sampling lines intersecting with the first positioning code bar 5 are W1, W2, and W3; the first sampling line intersecting with the first positioning code bar 6 is W2; the first sampling line intersecting with the first positioning code bar 7 is W2; the first sampling line intersecting with the first positioning code bar 8 is W2; and the first sampling line intersecting with the first positioning code bar 9 is W2. That is to say, the first positioning code bars intersecting with the first sampling line W1 are 2, 4, and 5; the first positioning code bars intersecting with the first sampling line W2 are 2, 3, 4, 5, 6, 7, and 8; and the first positioning code bars intersecting with the first sampling line W3 are 2, 4, and 5.
[0076] A4: The positioning device determines at least one first feature value corresponding to at least one first sampling line based on the first position relationship and the correspondence between the preset position relationship and the feature value.
[0077] Each first sampling line corresponds to a first feature value. For each of the at least one first sampling lines, the following operations are performed to determine the first feature value corresponding to each first sampling line;
[0078] A4-1: The positioning device determines the first feature value corresponding to the first sampling line based on the color value of at least one first positioning code bar through which the first sampling line passes, and the relationship between the preset color value and the feature value.
[0079] This allows us to obtain the color values of 8, the first positioning code bar, the sleeper, the first start code bar, the first end code bar, and the background color of the first calibration image. In practical applications, the first calibration image can be processed into grayscale, so the color values mentioned here are grayscale values.
[0080] Gray values between 250 and 255 are represented by 0, gray values of the background color of the pattern are represented by 1, gray values between 120 and 130 are represented by 2, and gray values between 0 and 5 are represented by 3.
[0081] The first positioning coding bars intersecting with the first sampling line W1 are 2, 4, and 5. Therefore, the grayscale values of the first sampling line W1 in the 10 first coding bars, including the first start coding bar and the first end coding bar, are 255, 255, 0, 128, 255, 0, 0, 0, 0, and 255, respectively. Thus, the first feature value WT1 of the first sampling line W1 is 0032033330. Figure 8 A variation diagram of the first feature value WT1 provided in an embodiment of this application.
[0082] The first positioning coding bars intersecting with the first sampling line W1 are 2, 3, 4, 5, 6, 7, and 8. Therefore, the grayscale values of the first sampling line W1 in the 10 first coding bars, including the first start coding bar and the first end coding bar, are 255, 255, 128, 128, 255, 255, 255, 255, 255, and 255, respectively. Thus, the first feature value WT2 of the first sampling line W1 is 0022000000. Figure 9 A variation diagram of the first feature value WT2 provided in an embodiment of this application.
[0083] The first positioning coding bars intersecting with the first sampling line W1 are 2, 4, and 5. Therefore, the grayscale values of the first sampling line W1 in the 10 first coding bars, including the first start coding bar and the first end coding bar, are 255, 255, 0, 128, 255, 0, 0, 0, 0, and 255, respectively. Thus, the first feature value WT3 of the first sampling line W1 is 0032033330. Figure 10 A variation diagram of the first feature value WT3 provided in an embodiment of this application.
[0084] The encoding field corresponding to the first positioning encoding bar 1 is 000, the encoding field corresponding to the first positioning encoding bar 2 is 000, the encoding field corresponding to the first positioning encoding bar 3 is 323, the encoding field corresponding to the first positioning encoding bar 4 is 222, the encoding field corresponding to the first positioning encoding bar 5 is 000, the encoding field corresponding to the first positioning encoding bar 6 is 303, the encoding field corresponding to the first positioning encoding bar 7 is 303, the encoding field corresponding to the first positioning encoding bar 8 is 303, the encoding field corresponding to the first positioning encoding bar 9 is 303, and the encoding field corresponding to the first positioning encoding bar 10 is 000.
[0085] A5: The positioning device determines the first encoding result based on at least one first feature value.
[0086] A5-1: The positioning device determines the color, quantity, and positional relationship between the first positioning coding bars included in the first coded image based on at least one first feature value.
[0087] The first eigenvalues WT1, WT2, and WT3 constitute the first feature matrix {0032033330, 0022000000, 0032033330}.
[0088] In addition to the first start code bar and the first end code bar, the first feature value is determined by a total of four code fields: 000, 222, 303, and 323. This means there are also four types of first positioning code bars. The positional relationship between these first positioning code bars corresponds to the order of the first feature values.
[0089] A5-2: The positioning device determines the first coding result based on color, quantity, and positional relationship.
[0090] During the spraying process, the type and quantity of the first coding strip can be set. For example, it can be pre-determined that there are white short codes, white long codes, green short codes, and green long codes. The green short codes and evergreen grayscale values are both displayed as dark gray after processing. It can also be determined that the coding field of the white short code is 303, the coding field of the white long code is 000, the coding field of the green short code is 323, and the coding field of the green long code is 333.
[0091] Therefore, the positioning device can determine that the first encoded image is a white long code, a green short code, a green long code, a white long code, a white short code, a white short code, a white short code, and a white short code. For example, using a pre-set 8-bit 4-ary encoding, with the white short code being 0, the white long code being 1, the green short code being 2, and the green long code being 3, the first encoded result can be determined as 12310000. This can be converted to decimal data as 27904 according to the 4-ary encoding rules.
[0092] Regarding S402-2: The positioning device determines the first position of the first coded image based on the correspondence between the first encoding result and the pre-set encoding result and position.
[0093] In one implementation, the first encoding result, converted to decimal data, represents the mileage, which is also the first position. In another implementation, the first encoding result, converted to decimal data, has a certain correspondence with the mileage, and is then converted to the corresponding mileage based on this correspondence. Using the example above, the first position of the first encoded image is determined to be 27904 meters.
[0094] Regarding S403: The positioning device locates the train based on multiple locations corresponding to multiple coded images.
[0095] The denser the coding pattern, the higher the positioning accuracy, but the higher the positioning cost. Therefore, in order to ensure both positioning accuracy and positioning cost, a speed sensor can be used to obtain at least one intermediate position between the two positions represented by the two coding images to increase positioning accuracy, without the need to spray too many coding patterns.
[0096] For example, the intermediate position can be determined through step B1:
[0097] B1: The positioning device positions the train based on two locations represented by at least two coded images and at least one intermediate location between the two locations.
[0098] This design allows for the acquisition of the positions represented by any two adjacent coded images, as well as several intermediate positions, enabling the positioning of the train.
[0099] For example, the two positions include a first position and a second position, and the intermediate position can be determined through step B1-1:
[0100] B1-1: Based on the first position and the real-time speed of the train when it is between the first and second positions, determine at least one intermediate position of the train associated with the first position; the second position is a position adjacent to the first position.
[0101] Since the position information of position Q can be determined by integrating the velocity curve based on the position information of any position P and the real-time velocity of position Q, at least one intermediate position of the train associated with the first position can be determined based on the first position and the real-time velocity of the train when the train is between the first and second positions. In practical applications, the position information of another position can also be determined based on any position and the real-time velocity of the other position.
[0102] This embodiment of the application achieves continuous train positioning by adding at least one intermediate position between any two locations. Simultaneously, it eliminates the need for numerous coding patterns, offering greater flexibility and scalability, reducing costs, simplifying construction processes, improving the integration of positioning equipment, and facilitating later maintenance. Furthermore, the digitized coding pattern can reduce positioning errors and improve recognition rate, security, and reliability.
[0103] This application proposes a train visual positioning scheme combining digital coding and speed sensors. Accumulated errors may occur when calculating the real-time position of a train using speed curves, affecting real-time positioning accuracy. To address this, ground cameras can be installed at certain intervals along the track to provide point-based positioning for the train. The ground cameras identify the train number information marked on the front of the train, and by querying the camera location information, the current position of the train is obtained. Combined with the calculation results of the train's current speed curve, the real-time position of the train is corrected to eliminate accumulated errors. Furthermore, considering the train degradation issues caused by abnormal train-to-ground communication in the signaling system, the ground cameras can also be used to track the train's position and calculate its speed. The ground cameras serve as a backup redundant system for train-to-ground information transmission, and are deployed throughout the entire operating section. The deployment spacing is flexible and can be adjusted according to train operating speed, positioning accuracy requirements, and construction cost constraints.
[0104] like Figure 11 As shown, based on the same inventive concept, this application provides a positioning device, which includes an image acquisition unit 111, a processing unit 112, and a positioning unit 113:
[0105] Image acquisition unit 111 is used to acquire multiple coded images obtained by taking pictures of multiple position markers set on the track during the train's operation; wherein each position marker is a coded pattern;
[0106] Processing unit 112 is configured to perform the following operations for each of the multiple encoded images to determine the position of the train represented by each encoded image: identify the first encoded image to determine the first encoding result of the first encoded image; determine the first position of the first encoded image according to the correspondence between the first encoding result and a pre-set encoding result and position; wherein the first encoded image is any one of the multiple encoded images;
[0107] The positioning unit 113 is used to locate the train based on multiple positions corresponding to multiple coded images.
[0108] In one possible implementation, the positioning unit 113 is specifically used for:
[0109] The train is located based on two positions represented by at least two coded images, and at least one intermediate position between the two positions.
[0110] In one possible implementation, the two positions include a first position and a second position, and the positioning unit 113 is further configured to:
[0111] Based on the first position and the real-time speed of the train when it is between the first and second positions, at least one intermediate position of the train associated with the first position is determined; the second position is a position adjacent to the first position.
[0112] In one possible implementation, the processing unit 112 is specifically used for:
[0113] A perspective correction is performed on the first coded image to obtain a first corrected image; wherein the first coded image includes a first start coded bar, a first end coded bar, and at least one first positioning coded bar;
[0114] The number and position of the first sampling lines are determined based on the length of at least one first positioning coding bar;
[0115] The first positional relationship is determined based on the position of at least one first sampling line and the length of at least one first positioning code bar;
[0116] Based on the first positional relationship and the correspondence between the preset positional relationship and the feature value, at least one first feature value corresponding to at least one first sampling line is determined; wherein, each first sampling line corresponds to one first feature value;
[0117] The first encoding result is determined based on at least one first feature value.
[0118] In one possible implementation, the processing unit 112 is specifically used for:
[0119] For each of the at least one first sampling lines, perform the following operations to determine the first feature value corresponding to each first sampling line;
[0120] The first feature value corresponding to the first sampling line is determined based on the color value of at least one first positioning coding strip through which the first sampling line passes, and the relationship between the preset color value and the feature value.
[0121] In one possible implementation, the processing unit 112 is specifically used for:
[0122] Based on at least one first feature value, determine the color, number, and positional relationship between the first positioning coding bars included in the first coded image;
[0123] The first encoding result is determined based on color, quantity, and positional relationship.
[0124] In one possible implementation, each location marker consists of multiple coded strips sprayed onto a track; the length and color of each coded strip are fixed.
[0125] Since this device is the same as the device in the method of this application embodiment, and the principle of the device in solving the problem is similar to that of the method, the implementation of the device can be referred to the implementation of the method, and the repeated parts will not be described again.
[0126] like Figure 12 As shown, based on the same inventive concept, this application provides a positioning device, including a transmission unit 121 and a processor 122;
[0127] Transmission unit 121 is configured to perform:
[0128] Multiple coded images are obtained by taking pictures of multiple location markers set on the track during the train's operation; each location marker is a coded pattern.
[0129] Processor 122 is configured to execute:
[0130] For each of the multiple encoded images, perform the following operations to determine the position of the train represented by each encoded image:
[0131] The first coded image is identified to determine the first encoding result of the first coded image; the first position of the first coded image is determined according to the correspondence between the first encoding result and the pre-set encoding result and position; wherein, the first coded image is any one of a plurality of coded images;
[0132] The train is located based on multiple positions corresponding to multiple coded images.
[0133] In one possible implementation, processor 122 is specifically configured to execute:
[0134] The train is located based on two positions represented by at least two coded images, and at least one intermediate position between the two positions.
[0135] In one possible implementation, processor 122 is specifically configured to execute:
[0136] Based on the first position and the real-time speed of the train when it is between the first and second positions, at least one intermediate position of the train associated with the first position is determined; the second position is a position adjacent to the first position.
[0137] In one possible implementation, processor 122 is specifically configured to execute:
[0138] A perspective correction is performed on the first coded image to obtain a first corrected image; wherein the first coded image includes a first start coded bar, a first end coded bar, and at least one first positioning coded bar;
[0139] The number and position of the first sampling lines are determined based on the length of at least one first positioning coding bar;
[0140] The first positional relationship is determined based on the position of at least one first sampling line and the length of at least one first positioning code bar;
[0141] Based on the first positional relationship and the correspondence between the preset positional relationship and the feature value, at least one first feature value corresponding to at least one first sampling line is determined; wherein, each first sampling line corresponds to one first feature value;
[0142] The first encoding result is determined based on at least one first feature value.
[0143] In one possible implementation, processor 122 is specifically configured to execute:
[0144] For each of the at least one first sampling lines, perform the following operations to determine the first feature value corresponding to each first sampling line;
[0145] The first feature value corresponding to the first sampling line is determined based on the color value of at least one first positioning coding strip through which the first sampling line passes, and the relationship between the preset color value and the feature value.
[0146] In one possible implementation, processor 122 is specifically configured to execute:
[0147] Based on at least one first feature value, determine the color, number, and positional relationship between the first positioning coding bars included in the first coded image;
[0148] The first encoding result is determined based on color, quantity, and positional relationship.
[0149] In one possible implementation, each location marker consists of multiple coded strips sprayed onto a track; the length and color of each coded strip are fixed.
[0150] This application also provides a computer storage medium storing computer program instructions, which, when executed on a computer, cause the computer to perform the steps of the above-described train positioning method.
[0151] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.
[0152] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0153] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0154] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0155] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.
Claims
1. A train positioning method, characterized in that, include: Multiple coded images are obtained by taking pictures of multiple location markers set on the track during the train's operation; wherein each location marker is a coded pattern. For each of the multiple encoded images, the following operations are performed to determine the position of the train represented by each encoded image: A perspective correction is performed on the first coded image to obtain a first corrected image; the number and position of the first sampling lines are determined according to the length of at least one first positioning coding bar; a first positional relationship is determined based on the position of at least one first sampling line and the length of the at least one first positioning coding bar; Based on the first positional relationship and the correspondence between the preset positional relationship and feature values, at least one first feature value corresponding to at least one first sampling line is determined; wherein, the first coded image includes a first start coding bar, a first end coding bar, and at least one first positioning coding bar; each first sampling line corresponds to a first feature value; a first coding result is determined based on at least one first feature value; a first position of the first coded image is determined based on the first coding result and the correspondence between the preset coding result and position; the first coded image is any one of the plurality of coded images; The train is located based on multiple positions corresponding to multiple coded images.
2. The method according to claim 1, characterized in that, The step of locating the train based on multiple locations corresponding to multiple coded images includes: The train is located based on two positions represented by at least two coded images, and at least one intermediate position between the two positions.
3. The method according to claim 2, characterized in that, The two positions include a first position and a second position, and the method further includes: Based on the first position and the real-time speed of the train when the train is between the first position and the second position, at least one intermediate position of the train associated with the first position is determined; the second position is a position adjacent to the first position.
4. The method according to claim 1, characterized in that, The step of determining at least one first feature value corresponding to at least one first sampling line based on the first positional relationship and the correspondence between the preset positional relationship and feature values includes: For each of at least one of the first sampling lines, perform the following operation to determine a first feature value corresponding to each of the first sampling lines; The first feature value corresponding to the first sampling line is determined based on the color value of at least one first positioning coding strip through which the first sampling line passes, and the relationship between the preset color value and the feature value.
5. The method according to claim 1, characterized in that, Determining the first encoding result based on at least one of the first feature values includes: Based on at least one of the first feature values, determine the color, number, and positional relationship between the first positioning coding bars included in the first coded image; The first encoding result is determined based on the color, quantity, and positional relationship.
6. The method according to any one of claims 1 to 5, characterized in that, Each of the aforementioned location markers consists of multiple coded strips sprayed onto the track; the length and color of each coded strip are fixed.
7. A positioning device, characterized in that, Includes a transmission unit and a processor; The transmission unit is configured to perform: Multiple coded images are obtained by taking pictures of multiple location markers set on the track during the train's operation; The processor is configured to execute: For each of the multiple encoded images, the following operations are performed to determine the position of the train represented by each encoded image: A perspective correction is performed on the first coded image to obtain a first corrected image; the number and position of the first sampling lines are determined according to the length of at least one first positioning coding bar; a first positional relationship is determined based on the position of at least one first sampling line and the length of the at least one first positioning coding bar; Based on the first positional relationship and the correspondence between the preset positional relationship and feature values, at least one first feature value corresponding to at least one first sampling line is determined; wherein, the first coded image includes a first start coding bar, a first end coding bar, and at least one first positioning coding bar; each first sampling line corresponds to a first feature value; a first coding result is determined based on at least one first feature value; a first position of the first coded image is determined based on the first coding result and the correspondence between the preset coding result and position; the first coded image is any one of the plurality of coded images; The train is located based on multiple positions corresponding to multiple coded images.
8. The positioning device according to claim 7, characterized in that, The processor is configured to execute: The train is located based on two positions represented by at least two coded images, and at least one intermediate position between the two positions.
9. The positioning device according to claim 8, characterized in that, The two positions include a first position and a second position, and the processor is configured to execute: Based on the first position and the real-time speed of the train when the train is between the first position and the second position, at least one intermediate position of the train associated with the first position is determined; the second position is a position adjacent to the first position.