Functionally safe train positioning method, system, electronic device and storage medium

Abstract

The present invention provides a functionally safe train positioning method, system, electronic device and storage medium. The method comprises: obtaining an image picture and radar data of a current train in a travel direction; determining a set of contour curves according to the radar data, determining a standard contour curve set and a standard image picture that match the contour curve set according to the similarity between the curves, and screening out curves that fail to successfully match the contour curve set and the standard contour curve set in terms of curve similarity; determining a first selected area on the image picture according to the contour curve set, and determining a second selected area on the standard image picture according to the standard contour curve set; performing feature matching on the first selected area and the second selected area to obtain a matching result, determining a positioning result according to the matching result and the screened out unsuccessfully matched curves, realizing double matching between curves and images, reducing the amount of calculation in the matching process, and improving positioning accuracy.

Description

Technical Field

[0001] The present invention relates to the field of train operation technology, and in particular to a functionally safe train positioning method, system, electronic equipment and storage medium. Background Art

[0002] With the development of various sensor technologies such as image processing and LiDAR, more and more positioning and navigation technologies are being applied to transportation fields such as drones, robots, and automobiles, which are expanding from military fields such as missiles. The positioning and navigation technologies based on images and LiDAR have high accuracy, strong autonomy, and simple system architecture. Compared with traditional technologies such as GNSS, transponders, axle counters, and speed sensors used in train control systems, they have the advantages of low cost and wide application range. However, the general processing algorithms based on images and LiDAR are complex, computationally intensive, and the output positioning information is unsafe, and may output incorrect positioning results that lead to danger. Summary of the invention

[0003] In view of the problems existing in the prior art, the present invention provides a functionally safe train positioning method, device, system, electronic equipment and storage medium.

[0004] In a first aspect, the present invention provides a functionally safe train positioning method, comprising:

[0005] Obtain the image and radar data of the current train in the direction of travel;

[0006] Determine a contour curve set according to the radar data, perform curve similarity matching on the contour curve set in a preconfigured curve library, determine a standard contour curve set and a standard image picture that match the contour curve set according to the similarity between the curves, and filter out curves that fail to successfully match the contour curve set and the standard contour curve set in terms of curve similarity; wherein the curve library contains a correspondence between the standard image picture and the standard curve set;

[0007] Determining a first selected area on the image screen according to the set of contour curves, and determining a second selected area on the standard image screen according to the set of standard contour curves;

[0008] Perform feature matching on the first selected area and the second selected area to obtain a matching result, and determine a positioning result based on the matching result and the screened out unsuccessful matching curves.

[0009] In one embodiment, determining the first selected area on the image screen according to the set of contour curves includes:

[0010] Based on the position of each curve in the contour curve set on the image screen, a screen area with a preset first pixel width on both sides of each curve is selected on the image screen, and each selected screen area is used as a first selected area.

[0011] In one embodiment, determining the second selected area on the standard image screen according to the standard contour curve set includes:

[0012] Taking the position of each curve in the standard contour curve set on the standard image screen as a reference, selecting a screen area with a preset second pixel width located on both sides of the periphery of each curve on the standard image screen, and each selected screen area is used as a second selected area;

[0013] The first pixel width is consistent with the second pixel width.

[0014] In one embodiment, feature matching is performed on the first selected area and the second selected area to obtain a matching result, and a positioning result is determined according to the matching result and the filtered unmatched curves, including:

[0015] Feature matching is performed on each picture in the first selected area and the corresponding picture in the second selected area. If all matches are successful, there is no obstacle in front of the train. If there is at least one picture that is not matched successfully, and the unmatched picture is completely corresponding to the screened unmatched curve, it is determined that there is an obstacle in the direction of travel of the current train, and the position of the obstacle on the image screen is determined based on the unmatched picture, and the train is positioned.

[0016] In one embodiment, the determining of a standard contour curve set and a standard image frame matching the contour curve set includes:

[0017] If the contour curve set has the largest number of curves successfully matched with a standard contour curve set in a preconfigured curve library in terms of curve similarity, the standard contour curve set is determined to be a curve set matching the contour curve set.

[0018] In a second aspect, the present invention provides a functionally safe train positioning device, comprising:

[0019] The acquisition module is used to obtain the image and radar data of the current train in the travel direction;

[0020] A matching module, for determining a contour curve set according to the radar data, performing curve similarity matching on the contour curve set in a preconfigured curve library, determining a standard contour curve set and a standard image picture that match the contour curve set according to the similarity between the curves, and filtering out curves that fail to successfully match the contour curve set and the standard contour curve set in terms of curve similarity; wherein the curve library contains a correspondence between the standard image picture and the standard curve set;

[0021] A selection module, used to determine a first selected area on the image screen according to the set of contour curves, and to determine a second selected area on the standard image screen according to the set of standard contour curves;

[0022] The positioning module is used to perform feature matching on the first selected area and the second selected area to obtain a matching result, and determine a positioning result based on the matching result and the screened unmatched curves.

[0023] In a third aspect, the present invention provides a functionally safe train positioning system, comprising a first safe computer platform and a second safe computer platform, wherein the first safe computer platform and the second safe computer platform both execute the above-mentioned functionally safe train positioning method and perform positioning judgment based on the positioning results output by each of them.

[0024] In a fourth aspect, the present invention provides an electronic device comprising a memory and a memory storing a computer program, wherein the processor, when executing the program, implements the steps of the functionally safe train positioning method described in the first aspect.

[0025] In a fifth aspect, the present invention provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable the processor to execute the steps of the functionally safe train positioning method described in the first aspect.

[0026] The functionally safe train positioning method, device, electronic device and storage medium provided by the present invention obtain contour curves through radar data, perform similarity matching between the contour curves and standard contour curves in a curve library, obtain standard image pictures corresponding to the standard contour curves and curves for which the contour curves have not successfully matched the standard contour curves by similarity, select partial pictures based on the contour curves on the current image picture and the standard image picture to complete image feature matching, determine the positioning result based on the matching result and the curves that have not successfully matched, realize double matching between curves and between images, reduce the amount of calculation in the matching process, and improve positioning accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0028] Figure 1 It is a schematic diagram of the flow chart of the functionally safe train positioning method provided by the present invention;

[0029] Figure 2 It is a structural schematic diagram of a functionally safe train positioning device provided by the present invention;

[0030] Figure 3 is a schematic diagram of the structure of an electronic device provided by the present invention; DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of 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.

[0032] Combine the following Figure 1-Figure 3 The present invention describes a functionally safe train positioning method, device, system, electronic device and storage medium.

[0033] Figure 1 A flow chart of a functionally safe train positioning method according to the present invention is shown in FIG. Figure 1 , the method comprising:

[0034] 11. Obtain the image and radar data of the current train in the direction of travel;

[0035] 12. Determine a contour curve set according to the radar data, match the contour curve set in a pre-configured curve library for curve similarity, determine a standard contour curve set and a standard image picture that match the contour curve set according to the similarity between the curves, and filter out the curves that the contour curve set and the standard contour curve set do not successfully match in terms of curve similarity; wherein the curve library contains the correspondence between the standard image picture and the standard curve set;

[0036] 13. Determine a first selected area on the image screen according to the set of contour curves, and determine a second selected area on the standard image screen according to the set of standard contour curves;

[0037] 14. Perform feature matching on the first selected area and the second selected area to obtain a matching result, and determine the positioning result based on the matching result and the screened out unsuccessful matching curves.

[0038] Regarding steps 11 to 14, it should be noted that in the present invention, a camera / camera and a laser radar are configured on the train. The camera / camera can collect images in the travel direction in real time while the train is running. The laser radar can collect radar data (i.e., radar point cloud data) in the travel direction in real time while the train is running. The laser radar and the camera / camera adopt a synchronous acquisition method, that is, the laser radar collects radar data in the actual scene of a certain frame of image captured by the camera / camera.

[0039] After the radar data is collected, the distance calculation is performed on the radar data, and points in the radar data that are equidistant from the preset positions on the train are selected to form a set of contour curves. In other words, the radar data collected by the lidar in each collection cycle can form multiple contour curves, and these contour curves are combined together to form a set of contour curves.

[0040] In the present invention, in order to determine whether there is an obstacle in front of the train, it is necessary to compare the data collected in real time with the stored data, and determine whether there is an obstacle in front of the train based on the comparison result. To this end, after obtaining a contour curve set based on radar data, it is necessary to compare the contour curve set with an existing contour curve set. In the present invention, the existing contour curve set is regarded as a standard contour curve set and stored in a preconfigured curve library. Correspondingly, since each standard contour curve set is generated based on point cloud data collected while using a certain image screen, each standard contour curve set corresponds to a standard image screen.

[0041] In the present invention, the contour curve set is matched with each standard contour curve set in the pre-configured curve library for curve similarity, and according to the similarity between the curves, the annotated contour curve set with the closest similarity is determined as the curve set matching the contour curve set. The curve similarity can be calculated by using the Euclidean distance method, the pattern distance method, the shape distance method, etc.

[0042] At the same time, it is also necessary to filter out the curves that have not been successfully matched in the curve similarity between the contour curve set and the standard contour curve set. In this regard, it should be noted that since there may be obstacles at certain positions on the image screen corresponding to the contour curve set or the standard contour curve set, that is, there are obstacles in front of the train, some curves in the contour curve set may not be successfully matched with some curves in the standard contour curve set. These curves that cannot be successfully matched can represent the existence of obstacles here, so it is necessary to filter out the curves that are not successfully matched to achieve the purpose of locating obstacles based on radar data. In addition, if all the curves in the contour curve set and the standard contour curve set can be matched, it means that there are no obstacles in front of the train. At this time, it is impossible to filter out the curves that are not successfully matched.

[0043] In the present invention, in the actual scene corresponding to a certain frame of image, the laser radar can collect corresponding radar data. Therefore, the contour curve set obtained according to the radar data has a corresponding relationship with the image of the frame. To this end, each curve in the contour curve set can be attached to the image, and based on the position of each curve, a preset collection rule (such as a preset pixel width, a preset number of pixels, etc.) is used to select multiple image areas on the image, and each image area is combined to form a first selected area corresponding to the image.

[0044] Similarly, the above selection method is adopted to determine the second selection area on the standard image screen according to the standard contour curve set. It should be noted that since the standard contour curve set corresponds to the contour curve set, there is also a frame of standard image screen corresponding to the standard contour curve set, and the standard image screen and the collected current image screen belong to the same scene.

[0045] At this time, each curve in the standard contour curve set can be attached to the image screen, and based on the position of each curve, a preset acquisition rule (such as preset pixel width, preset number of pixels, etc.) is used to select multiple screen areas on the image screen. The screen areas are combined together to form a second selected area corresponding to the standard image screen.

[0046] In the present invention, since each image area in the first selected area only belongs to a small part of the entire image screen, each image area in the second selected area also only belongs to a small part of the entire image screen. Therefore, the present invention compares the features of a part of the image screen with a part of the standard image screen, which can reduce the processing complexity and high calculation amount in the comparison process.

[0047] After the first selected area and the second selected area are obtained, feature matching is performed on the first selected area and the second selected area to obtain a matching result. The feature matching process can be performed using grayscale matching, line feature (LBD) algorithm, etc. At this time, the determined matching result is a result that can characterize the position of the obstacle based on the image screen.

[0048] Since the picture corresponding to each selected area corresponds to the curve, after obtaining the matching result, the matching result is compared with the above-screened unsuccessful matching curve to see whether the two can completely correspond, and the final positioning result is determined based on the corresponding result.

[0049] In the present invention, further explanation is required. Each picture in the first selected area is feature matched with the corresponding picture in the second selected area. If all the matches are successful, there is no obstacle in front of the train. If there is at least one picture that is not matched successfully, and the unmatched picture is completely corresponding to the screened unmatched curve, it is determined that there is an obstacle in the direction of travel of the current train. That is, the purpose of combining the positioning result based on radar data with the positioning result based on the image picture to determine the location of the obstacle is achieved. By matching the image features of some pictures in the overall image picture, the amount of calculation and complexity in the matching process can be reduced, and the accuracy of positioning can be improved.

[0050] After determining that there is an obstacle in front of the train, it is necessary to determine the position of the obstacle on the image based on the unmatched image or the current complete image, and to locate the position of the train on the track based on the train's positioning system or trackside equipment, so that the control system can effectively control the train and remind the staff to clear the obstacles on the track in time.

[0051] The functionally safe train positioning method provided by the present invention obtains contour curves through radar data, performs similarity matching between the contour curves and standard contour curves in a curve library, obtains standard image pictures corresponding to the standard contour curves and curves for which the contour curves have not successfully matched the standard contour curves by similarity, selects part of the pictures based on the contour curves on the current image picture and the standard image picture to complete image feature matching, determines the positioning result according to the matching result and the curves that have not successfully matched, realizes double matching between curves and between images, reduces the amount of calculation in the matching process, and improves positioning accuracy.

[0052] In the further description of the above method, the processing of determining the first selected area on the image screen according to the contour curve set and determining the second selected area on the standard image screen according to the standard contour curve set is mainly explained, as follows:

[0053] Based on the position of each curve in the contour curve set on the image screen, a screen area with a preset first pixel width on both sides of each curve is selected on the image screen, and each selected screen area is used as the first selected area.

[0054] Taking the position of each curve in the standard contour curve set on the standard image screen as a reference, select a screen area of ​​a preset second pixel width located on both sides of the periphery of each curve on the standard image screen, and the selected screen areas are used as second selected areas;

[0055] The first pixel width is consistent with the second pixel width.

[0056] In this regard, it should be noted that, in the present invention, each curve in the contour curve set is attached to the image screen, and based on the position of each curve in the contour curve set on the image screen, a screen area with a preset first pixel width on both sides of the periphery of each curve is selected on the image screen. That is, each curve corresponds to a screen area, and each screen area does not intersect as much as possible.

[0057] Each curve in the standard contour curve set is attached to the standard image screen, and the position of each curve in the standard contour curve set on the standard image screen is used as a reference to select a screen area of ​​a preset second pixel width on both sides of each curve. That is, each curve corresponds to a screen area, and each screen area is not intersected as much as possible.

[0058] It should be noted that the first pixel width and the second pixel width are consistent, so as to facilitate matching of image features with the same size and dimension.

[0059] In the further description of the above method, the process of determining a standard contour curve set matching a contour curve set is mainly explained, as follows:

[0060] If the contour curve set has the largest number of curves that successfully match a standard contour curve set in the preconfigured curve library in terms of curve similarity, the standard contour curve set is determined to be the curve set that matches the contour curve set.

[0061] In this regard, it should be noted that the contour curve set is matched with each standard contour curve set in the preconfigured curve library for curve similarity. According to the similarity between the curves, when it is determined that the contour curve set has the largest number of curves that successfully match the curve similarity with a certain standard contour curve set in the preconfigured curve library, the standard contour curve set is selected as the curve set that matches the contour curve set.

[0062] When there is an obstacle on a certain impact screen, some curves in the corresponding contour curve set and the standard contour curve set cannot be matched successfully. At this time, the number of curves that can be matched successfully is also the largest. Therefore, a curve set that matches the contour curve set can be determined.

[0063] A further method of the present invention is more intuitive and faster by determining a curve set that matches the contour curve set based on the number of curves.

[0064] The functionally safe train locating device provided by the present invention is described below. The functionally safe train locating device described below and the functionally safe train locating method described above can be referred to each other.

[0065] Figure 2 A structural diagram of a functionally safe train positioning device provided by the present invention is shown. Figure 2 The device includes an acquisition module 21, a matching module 22, a selection module 23 and a positioning module 24, wherein:

[0066] The acquisition module 21 is used to acquire the image and radar data of the current train in the travel direction;

[0067] The matching module 22 is used to determine a set of contour curves according to the radar data, perform curve similarity matching on the set of contour curves in a pre-configured curve library, determine a standard set of contour curves and a standard image picture that match the set of contour curves according to the similarity between the curves, and filter out curves that fail to successfully match the set of contour curves and the set of standard contour curves in terms of curve similarity; wherein the curve library contains a correspondence between the standard image picture and the set of standard curves;

[0068] A selection module 23, used to determine a first selected area on the image screen according to the set of contour curves, and to determine a second selected area on the standard image screen according to the set of standard contour curves;

[0069] The positioning module 24 is used to perform feature matching between the first selected area and the second selected area to obtain a matching result, and determine a positioning result based on the matching result and the screened unmatched curves.

[0070] In a further description of the above device, the selection module is specifically used to:

[0071] Based on the position of each curve in the contour curve set on the image screen, a screen area with a preset first pixel width on both sides of each curve is selected on the image screen, and each selected screen area is used as a first selected area.

[0072] In a further description of the above device, the selection module is specifically used to:

[0073] Taking the position of each curve in the standard contour curve set on the standard image screen as a reference, selecting a screen area with a preset second pixel width located on both sides of the periphery of each curve on the standard image screen, and each selected screen area is used as a second selected area;

[0074] The first pixel width is consistent with the second pixel width.

[0075] In a further description of the above device, the positioning module performs feature matching on the first selected area and the second selected area to obtain a matching result, and determines the positioning result according to the matching result and the screened unmatched curves, specifically for:

[0076] Feature matching is performed on each picture in the first selected area and the corresponding picture in the second selected area. If all matches are successful, there is no obstacle in front of the train. If there is at least one picture that is not matched successfully, and the unmatched picture is completely corresponding to the screened unmatched curve, it is determined that there is an obstacle in the direction of travel of the current train, and the position of the obstacle on the image screen is determined based on the unmatched picture, and the train is positioned.

[0077] In a further description of the above device, the matching module is specifically used to:

[0078] If the contour curve set has the largest number of curves successfully matched with a standard contour curve set in a preconfigured curve library in terms of curve similarity, the standard contour curve set is determined to be a curve set matching the contour curve set.

[0079] Since the principle of the device described in the embodiment of the present invention is the same as that of the method described in the above embodiment, a more detailed explanation will not be repeated here.

[0080] It should be noted that, in the embodiment of the present invention, the relevant functional modules can be implemented by a hardware processor.

[0081] The functionally safe train positioning device provided by the present invention obtains contour curves through radar data, performs similarity matching between the contour curves and standard contour curves in a curve library, obtains standard image pictures corresponding to the standard contour curves and curves for which the contour curves have not successfully matched the standard contour curves by similarity, selects part of the pictures based on the contour curves on the current image picture and the standard image picture to complete image feature matching, determines the positioning result according to the matching result and the curves that have not successfully matched, realizes double matching between curves and images, reduces the amount of calculation in the matching process, and improves positioning accuracy.

[0082] The present invention provides a functionally safe train positioning system, which adopts a two-out-of-two computer platform, which includes a first safe computer platform and a second safe computer platform. The first safe computer platform and the second safe computer platform both execute the functionally safe train positioning method mentioned above. To this end, each safe computer platform can output a positioning result, and then make a final judgment on the positioning based on the two output positioning results to obtain a final result. If the two positioning results match, the final result is adopted. If the two positioning results do not match, the final result is not adopted, and re-positioning monitoring can be performed.

[0083] Figure 3 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 3 As shown, the electronic device may include: a processor 31 , a communication interface 32 , a memory 33 and a communication bus 34 , wherein the processor 31 , the communication interface 32 , and the memory 33 communicate with each other via the communication bus 34 . The processor 31 can call the computer program in the memory 33 to execute the steps of the functionally safe train positioning method, for example, including: obtaining the image screen and radar data of the current train in the travel direction; determining a set of contour curves based on the radar data, matching the contour curves in a preconfigured curve library for curve similarity, determining a standard contour curve set and a standard image screen that match the contour curve set based on the similarity between the curves, and filtering out the curves that the contour curve set and the standard contour curve set do not successfully match in terms of curve similarity; wherein the curve library contains a correspondence between the standard image screen and the standard curve set; determining a first selected area on the image screen based on the contour curve set, and determining a second selected area on the standard image screen based on the standard contour curve set; performing feature matching on the first selected area and the second selected area to obtain a matching result, and determining a positioning result based on the matching result and the filtered out unsuccessful matching curves.

[0084] In addition, the logic instructions in the above-mentioned memory 33 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0085] On the other hand, the present invention also provides a computer program product, which includes a computer program stored on a non-transitory computer-readable storage medium, and the computer program includes program instructions. When the program instructions are executed by a computer, the computer can execute the functionally safe train positioning method provided by the above methods, the method comprising: obtaining an image screen and radar data of the current train in the travel direction; determining a contour curve set according to the radar data, matching the contour curve set in a preconfigured curve library for curve similarity, determining a standard contour curve set and a standard image screen that match the contour curve set according to the similarity between the curves, and filtering out the contour curve set and the standard contour curve set that are not successfully matched in terms of curve similarity; wherein the curve library contains a correspondence between the standard image screen and the standard curve set; determining a first selected area on the image screen according to the contour curve set, and determining a second selected area on the standard image screen according to the standard contour curve set; performing feature matching on the first selected area and the second selected area to obtain a matching result, and determining a positioning result according to the matching result and the filtered unmatched curves.

[0086] On the other hand, an embodiment of the present application further provides a processor-readable storage medium, wherein the processor-readable storage medium stores a computer program, wherein the computer program is used to enable the processor to execute the functionally safe train positioning method provided by the above-mentioned embodiments, for example, including: obtaining an image screen and radar data of the current train in the direction of travel; determining a set of contour curves based on the radar data, matching the contour curves in a preconfigured curve library for curve similarity, determining a standard contour curve set and a standard image screen that match the contour curve set based on the similarity between the curves, and filtering out curves that are not successfully matched between the contour curve set and the standard contour curve set in terms of curve similarity; wherein the curve library contains a correspondence between the standard image screen and the standard curve set; determining a first selected area on the image screen based on the contour curve set, and determining a second selected area on the standard image screen based on the standard contour curve set; performing feature matching between the first selected area and the second selected area to obtain a matching result, and determining a positioning result based on the matching result and the filtered out curves that are not successfully matched.

[0087] The processor-readable storage medium can be any available medium or data storage device that can be accessed by the processor, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NANDFLASH), solid-state drive (SSD)), etc.

[0088] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0089] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0090] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A functionally safe train positioning method, characterized in that: include: Obtain the image and radar data of the current train in the direction of travel; Determine a contour curve set according to the radar data, perform curve similarity matching on the contour curve set in a preconfigured curve library, determine a standard contour curve set and a standard image picture that match the contour curve set according to the similarity between the curves, and filter out curves that fail to successfully match the contour curve set and the standard contour curve set in terms of curve similarity; wherein the curve library contains a correspondence between the standard image picture and the standard curve set; Determining a first selected area on the image screen according to the set of contour curves, and determining a second selected area on the standard image screen according to the set of standard contour curves; Perform feature matching on the first selected area and the second selected area to obtain a matching result, and determine a positioning result based on the matching result and the screened unmatched curves; Performing feature matching on the first selected area and the second selected area to obtain a matching result, and determining a positioning result according to the matching result and the filtered unmatched curves, including: Feature matching is performed on each picture in the first selected area and the corresponding picture in the second selected area. If all matches are successful, there is no obstacle in front of the train. If there is at least one picture that is not matched successfully, and the unmatched picture is completely corresponding to the screened unmatched curve, it is determined that there is an obstacle in the direction of travel of the current train, and the position of the obstacle on the image screen is determined based on the unmatched picture, and the train is positioned.

2. The functionally safe train positioning method according to claim 1, characterized in that: The step of determining a first selected area on the image screen according to the set of contour curves includes: Based on the position of each curve in the contour curve set on the image screen, a screen area with a preset first pixel width on both sides of each curve is selected on the image screen, and each selected screen area is used as a first selected area.

3. The functionally safe train positioning method according to claim 2, characterized in that: The step of determining a second selected area on the standard image screen according to the standard contour curve set includes: Taking the position of each curve in the standard contour curve set on the standard image screen as a reference, selecting a screen area with a preset second pixel width located on both sides of the periphery of each curve on the standard image screen, and each selected screen area is used as a second selected area; The first pixel width is consistent with the second pixel width.

4. The functionally safe train positioning method according to claim 1, characterized in that: The step of determining a standard contour curve set matching the contour curve set comprises: If the contour curve set has the largest number of curves that are successfully matched in terms of curve similarity with a standard contour curve set in a pre-configured curve library, the standard contour curve set is determined to be a curve set that matches the contour curve set.

5. A functionally safe train positioning device, characterized in that: include: The acquisition module is used to obtain the image and radar data of the current train in the travel direction; A matching module, for determining a contour curve set according to the radar data, performing curve similarity matching on the contour curve set in a preconfigured curve library, determining a standard contour curve set and a standard image picture that match the contour curve set according to the similarity between the curves, and filtering out curves that fail to successfully match the contour curve set and the standard contour curve set in terms of curve similarity; wherein the curve library contains a correspondence between the standard image picture and the standard curve set; A selection module, used to determine a first selected area on the image screen according to the set of contour curves, and to determine a second selected area on the standard image screen according to the set of standard contour curves; A positioning module, used for performing feature matching between the first selected area and the second selected area to obtain a matching result, and determining a positioning result according to the matching result and the screened unmatched curves; The positioning module performs feature matching on the first selected area and the second selected area to obtain a matching result, and determines the positioning result according to the matching result and the filtered unmatched curves, specifically for: Feature matching is performed on each picture in the first selected area and the corresponding picture in the second selected area. If all matches are successful, there is no obstacle in front of the train. If there is at least one picture that is not matched successfully, and the unmatched picture is completely corresponding to the screened unmatched curve, it is determined that there is an obstacle in the direction of travel of the current train, and the position of the obstacle on the image screen is determined based on the unmatched picture, and the train is positioned.

6. A functionally safe train positioning system, characterized in that: It comprises a first safety computer platform and a second safety computer platform, wherein the first safety computer platform and the second safety computer platform both execute the functionally safe train positioning method described in any one of claims 1 to 4 above, and perform positioning judgment according to the positioning results output by each.

7. An electronic device comprising a processor and a memory storing a computer program, characterized in that: When the processor executes the computer program, the steps of the functionally safe train positioning method according to any one of claims 1 to 4 are implemented.

8. A processor-readable storage medium, characterized in that: The processor-readable storage medium stores a computer program, and the computer program is used to enable the processor to execute the steps of the functionally safe train positioning method according to any one of claims 1 to 4.

Images