Subway engineering drawing identification method and device

Abstract

The application provides a subway engineering drawing identification method and device, which comprises the following steps: performing regional division on a target subway engineering drawing to obtain a target main line track region and a target kilometer marker region; identifying the target main line track region and the target kilometer marker region to obtain device identification information corresponding to a target device legend and diagram kilometer marker information; converting the diagram kilometer marker information into target kilometer marker information based on a target reference point; and obtaining a target engineering data table based on the device identification information and the target kilometer marker information. The method identifies the legend elements and kilometer marker information in the subway engineering drawing, and generates a target engineering data table representing the linking relationship and internal logic of signal devices and track units according to the relative positions of different devices in the drawing and engineering data, thereby improving the compilation efficiency of the engineering data table and reducing the workload of technical personnel and possible manual errors.

Description

Technical Field

[0001] This invention relates to the field of rail transit technology, and in particular to a method and apparatus for recognizing subway engineering drawings. Background Technology

[0002] In subway and urban rail construction projects, after technicians draw signal equipment drawings in DRW format with engineering data, they also need to mark the kilometer markers of elements such as signal equipment, track units and station facilities in the drawings, compile the link relationships and internal logic of these elements, and output the corresponding engineering data tables for software development and testing.

[0003] Currently, engineering data sheets are usually manually compiled and entered by technicians based on signal equipment drawings and in accordance with engineering data sheet compilation rules.

[0004] Compiling engineering data sheets based on signal equipment drawings is a huge undertaking with repetitive and mechanical tasks. Manual work is inefficient and prone to errors, which can easily affect subsequent software development, testing, and debugging. Summary of the Invention

[0005] This invention provides a method and apparatus for recognizing subway engineering drawings, which solves the problems of low efficiency and high error rate in the manual compilation of engineering data tables in the prior art.

[0006] This invention provides a method for recognizing subway engineering drawings, comprising:

[0007] The target subway engineering map is divided into regions to obtain the target mainline track area and the target kilometer marker area;

[0008] The target mainline track area and the target kilometer marker area are identified to obtain the equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend;

[0009] Convert the illustrated kilometer marker information into target kilometer marker information based on the target reference point;

[0010] Based on the equipment identification information and the target kilometer marker information, a target engineering data table is obtained.

[0011] According to a subway engineering drawing identification method provided by the present invention, the step of dividing the target subway engineering drawing into regions to obtain the target mainline track region and the target kilometer marker region includes:

[0012] Based on the target subway engineering drawings, determine the mainline track boundary line and the kilometer marker boundary line;

[0013] Based on the mainline track boundary line, the target mainline track area is divided on the target subway engineering drawing;

[0014] Based on the kilometer marker boundary line, the target kilometer marker area is delineated on the target subway engineering map.

[0015] According to a subway engineering drawing recognition method provided by the present invention, the step of recognizing the target mainline track area and the target kilometer marker area to obtain equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend includes:

[0016] The target equipment legend in the target mainline track area is determined by image recognition;

[0017] Based on the position of the target equipment legend in the target mainline track area, determine the equipment identification information corresponding to the target equipment legend;

[0018] Based on the location of the target kilometer marker area corresponding to the target equipment legend, the illustrated kilometer marker information corresponding to the target equipment legend is determined.

[0019] According to a subway engineering drawing identification method provided by the present invention, the step of obtaining a target engineering data table based on the equipment identification information and the target kilometer marker information includes:

[0020] Based on the equipment identification information and the location of the target equipment legend in the target mainline track area, the track unit connection relationship and signal equipment setting information are determined;

[0021] Based on the track unit connection relationship, the signal equipment setting information, and the target kilometer marker information, the target engineering data table is obtained.

[0022] According to a subway engineering drawing identification method provided by the present invention, the step of obtaining the target engineering data table based on the track unit connection relationship, the signal equipment setting information, and the target kilometer marker information includes:

[0023] Based on the target kilometer marker information, the connection relationship of the track unit and the setting information of the signal equipment are checked, and the verification is confirmed to be qualified, thus obtaining the target engineering data table.

[0024] According to a subway engineering drawing identification method provided by the present invention, the step of dividing the target subway engineering drawing into regions to obtain the target mainline track region and the target kilometer marker region includes:

[0025] The target subway engineering drawing is input into the first layer of the target recognition model to obtain the target mainline track area and the target kilometer marker area output by the first layer.

[0026] The process of identifying the target mainline track area and the target kilometer marker area to obtain the equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend includes:

[0027] The target mainline track area and the target kilometer marker area are input into the second layer of the target recognition model to obtain the equipment identification information and the illustrated kilometer marker information output by the second layer;

[0028] The step of converting the illustrated kilometer marker information into target kilometer marker information based on the target reference point includes:

[0029] The kilometer marker information shown in the figure is input into the third layer of the target recognition model to obtain the target kilometer marker information output by the third layer;

[0030] The process of obtaining a target project data table based on the equipment identification information and the target kilometer marker information includes:

[0031] The equipment identification information and the target kilometer marker information are input into the fourth layer of the target identification model to obtain the target engineering data table output by the fourth layer;

[0032] The target recognition model is obtained by training a CNN convolutional neural network using a sample training set.

[0033] The present invention also provides a subway engineering drawing recognition device, comprising:

[0034] The first processing module is used to divide the target subway engineering map into regions to obtain the target mainline track area and the target kilometer marker area.

[0035] The second processing module is used to identify the target mainline track area and the target kilometer marker area to obtain the equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend;

[0036] The third processing module is used to convert the illustrated kilometer marker information into target kilometer marker information based on the target reference point;

[0037] The fourth processing module is used to obtain a target engineering data table based on the equipment identification information and the target kilometer marker information.

[0038] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps of any of the above-described subway engineering drawing recognition methods.

[0039] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the subway engineering drawing recognition method described above.

[0040] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the steps of any of the above-described subway engineering drawing recognition methods.

[0041] The subway engineering drawing recognition method and device provided by this invention recognizes the legend elements and kilometer marker information in the subway engineering drawing, and generates a target engineering data table representing the link relationship and internal logic between signal equipment and track units according to the relative positions and engineering data of different equipment in the drawing. This improves the efficiency of engineering data table compilation, reduces the workload of technical personnel and possible human errors, and is beneficial to subsequent software development and testing and debugging work. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0043] Figure 1 This is a flowchart illustrating the subway engineering drawing recognition method provided by the present invention;

[0044] Figure 2 This is one of the example drawings of the subway engineering drawings provided by the present invention;

[0045] Figure 3 This is the second example drawing of the subway engineering drawings provided by the present invention;

[0046] Figure 4 This is the third example drawing of the subway engineering drawings provided by this invention;

[0047] Figure 5 This is a schematic diagram of the structure of the subway engineering drawing recognition device provided by the present invention;

[0048] Figure 6 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0049] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0050] In the description of the embodiments of the present invention, it should be noted that the terms "center," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of the present invention. In addition, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0051] In the description of the embodiments of the present invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "connected" and "linked" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can understand the specific meaning of the above terms in the embodiments of the present invention based on the specific circumstances.

[0052] In embodiments of the present invention, unless otherwise explicitly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0053] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0054] The following is combined Figures 1 to 4 The present invention describes a subway engineering drawing recognition method, wherein the execution subject of the method can be a controller, a cloud, or an edge server.

[0055] like Figure 1 As shown, the subway engineering drawing recognition method of the present invention includes steps 110 to 140.

[0056] Step 110: Divide the target subway engineering map into regions to obtain the target mainline track area and the target kilometer marker area.

[0057] The target metro engineering drawing is the metro engineering drawing to be identified. The target metro engineering drawing includes equipment legends such as signal equipment, track units and station facilities, character labels corresponding to the equipment legends, and kilometer markers.

[0058] It should be noted that during the drawing process of the target metro engineering drawing, the symbols for signal equipment, track units and station facilities are drawn on or near the main track. The character labels corresponding to the symbols are drawn in the area near the symbols. The kilometer markers are drawn at the top and bottom of the target metro engineering drawing, in an area far away from the symbols.

[0059] The kilometer markers at the top of the target subway engineering drawing correspond to the equipment symbols on the upward mainline track, while the kilometer markers at the bottom of the target subway engineering drawing correspond to the equipment symbols on the downward mainline track.

[0060] like Figure 2 As shown, the kilometer markers above the target metro engineering drawing (JZ3204)ZDK42+953.58 to (FB3210)ZDK43+122.21 represent the kilometer markers for the upward mainline track G3202.

[0061] The kilometer markers from YDK42+953.58 (JZ3207) to YDK43+114.99 (FB3219) on the target metro engineering drawing indicate the kilometer markers for the down-line mainline track G3205.

[0062] In this context, ← indicates that the main track is going up, and → indicates that the main track is going down.

[0063] In this step, the target subway engineering map is divided into regions. The area containing equipment legends, such as signal equipment, track units, and station facilities, as well as the character labels corresponding to the equipment legends, is divided into the target mainline track area, and the area containing the kilometer markers is divided into the target kilometer marker area.

[0064] Step 120: Identify the target mainline track area and the target kilometer marker area to obtain the equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend.

[0065] In this step, for the target mainline track area, an image recognition model based on a CNN convolutional neural network structure can be used to identify the target equipment legends, such as signal equipment, track units, and station facilities, and identify the corresponding character identifiers near the target equipment legends to obtain the equipment identification information corresponding to the target equipment legends.

[0066] For example, such as Figure 3 As shown, image recognition is performed on the target's main track area. This target device diagram, according to The target device legend is determined to be a fixed transponder. Based on the keyword FB corresponding to the fixed transponder, the nearby character identifier FB3213 is found and identified. The device identifier information corresponding to the target device legend is FB3213.

[0067] In this embodiment, based on the type of the target equipment legend identified from the target main track area, keywords matching the target equipment legend type are determined, and then the corresponding character identifiers and equipment identifier information are found in the vicinity of the target equipment legend.

[0068] In practice, a sample image library can be established and used as a training set to train an image recognition model based on a CNN convolutional neural network structure, and a character identifier corresponding to each image can be set.

[0069] The sample illustration library can include illustration elements such as signaling equipment, track units, and station facilities. Track units can include illustration elements such as turnouts, stops, axle counters, and logic sections. Signaling equipment can include illustration elements such as transponders and signals. Station facilities can include illustration elements such as platform screen doors and ESB buttons.

[0070] The legend elements included in the sample legend library can be added or removed according to the actual situation of the subway engineering drawings.

[0071] In practice, a sample character library can be established, and the sample image library can be used as a training set to train an image recognition model based on a CNN convolutional neural network structure, thereby recognizing the keywords and corresponding character identifiers of different device images.

[0072] The sample character library can include character elements such as English characters, numeric characters, and Chinese characters in different fonts.

[0073] In this step, for the target kilometer marker area, an image recognition model based on a CNN convolutional neural network structure can also be used to identify the kilometer marker and obtain the graphic kilometer marker information corresponding to the kilometer marker. Based on the positional correspondence between the target equipment legend in the target main track area and the target kilometer marker area, the equipment identification information is bound together with the corresponding graphic kilometer marker information.

[0074] For example, such as Figure 3 As shown, for the fixed transponder FB3213 in the target main track area, the kilometer marker corresponding to the location is found in the target kilometer marker area. The kilometer marker information corresponding to the equipment identification information FB3213 is YDK43+020.47(FB3213).

[0075] Step 130: Convert the illustrated kilometer marker information into target kilometer marker information based on the target reference point.

[0076] In step 120, the correspondence between the target equipment legend, equipment identification information, and illustrated kilometer marker information was unified.

[0077] In this step, the mainline track in the target subway engineering drawing is divided into multiple track sections based on different reference points. Within each track section, the kilometer marker information shown in the drawing is converted into the target kilometer marker information corresponding to each track section based on the target reference point.

[0078] In this embodiment, by converting the illustrated kilometer marker information into target kilometer marker information based on the target reference point, the accuracy of the kilometer marker information is improved, which facilitates subsequent software development, testing, and debugging.

[0079] For example, such as Figure 4 As shown, the main track in the target subway engineering drawing is divided into two track sections, G3106-E and G3106-F, with each track section being 205.00m long.

[0080] Using the ATP partition boundary ZDK41+875.06 as the target reference point, ZDK41+875.06 is converted to CDK0+000.00. The kilometer marker information ZDK42+037.26 corresponding to FB3212 is converted to the target kilometer marker information CDK0+162.20.

[0081] The conversion process is (42+037.26)-(41+875.06)=(0+162.20).

[0082] Step 140: Based on the equipment identification information and the target kilometer marker information, obtain the target project data table.

[0083] In this embodiment, based on the relative position of the target equipment legend in the target subway engineering drawing, as well as the equipment identification information and the corresponding target kilometer marker information of the target equipment legend, the link relationship and internal logic between the signal equipment and the track unit are generated, and the target engineering data table is generated.

[0084] The target project data table includes general equipment configuration information corresponding to the target equipment legend, configuration information for equipment execution actions, and configuration information related to equipment data checks.

[0085] For example, in the target project data table, the configuration information for the fixed transponder FB320 includes the transponder ID, name, coordinates, installation accuracy, version number, and associated signal configuration information.

[0086] The transponder ID, name, coordinates, installation accuracy, and version number are general configuration information for the equipment, while the associated signal is configuration information related to equipment data inspection.

[0087] According to the subway engineering drawing recognition method provided by the present invention, by recognizing the legend elements and kilometer marker information in the subway engineering drawing, and generating a target engineering data table representing the link relationship and internal logic between signal equipment and track units according to the relative positions and engineering data of different equipment in the drawing, the efficiency of compiling the engineering data table is improved, the workload of technical personnel and possible human errors are reduced, and it is beneficial to subsequent software development and testing and debugging work.

[0088] In some embodiments, step 110 includes: determining the mainline track boundary line and the kilometer marker boundary line based on the target metro engineering drawing; dividing the target mainline track area on the target metro engineering drawing based on the mainline track boundary line; and dividing the target kilometer marker area on the target metro engineering drawing based on the kilometer marker boundary line.

[0089] In this embodiment, the location of the main track and the location of the kilometer marker in the target subway engineering drawing are first identified. The main track boundary line is determined within the upper and lower limits of the main track location, and the kilometer marker boundary line is determined within the range of the kilometer marker location.

[0090] like Figure 2 As shown, the upward mainline track G3202 and the downward mainline track G3205 are identified. The first mainline track boundary line 220 is determined above the mainline track G3202, and the second mainline track boundary line 230 is determined below the mainline track G3205.

[0091] Based on the main line track boundary line, the target main line track area is divided on the target subway engineering drawing, that is, the area between the first main line track boundary line 220 and the second main line track boundary line 230 is taken as the target main line track area.

[0092] Among them, the first mainline track boundary line 220 and the second mainline track boundary line 230 include the equipment diagrams of signaling equipment, track units and station facilities of mainline track G3202 and mainline track G3205.

[0093] like Figure 2 As shown, the first kilometer marker boundary line 210 corresponding to the kilometer marker at the top and the second kilometer marker boundary line 240 corresponding to the kilometer marker at the bottom of the target subway engineering drawing are identified.

[0094] Based on the kilometer marker boundary line, the target kilometer marker area is divided on the target subway engineering map, that is, the area above the first kilometer marker boundary line 210 and the area below the second kilometer marker boundary line 240 are taken as the target kilometer marker area.

[0095] Among them, the target kilometer marker area above the first kilometer marker boundary line 210 includes all the kilometer markers at the top of the target subway engineering drawing, corresponding to the equipment of the upward mainline track G3202.

[0096] The target kilometer marker area below the 240-kilometer mark boundary includes all the kilometer markers at the bottom of the target metro engineering drawing, corresponding to the equipment on the down-line main track G3205.

[0097] In practice, a narrow and tall window can be used to capture the target subway engineering drawing for analysis, to determine the location of the main line track, the kilometer marker boundary line, and the upper and lower limits of the possible equipment legends and kilometer markers based on the main line track and kilometer marker boundary line.

[0098] In some embodiments, step 120 includes: determining a target equipment legend in the target mainline track area by image recognition; determining equipment identification information corresponding to the target equipment legend based on the position of the target equipment legend in the target mainline track area; and determining illustrated kilometer marker information corresponding to the target equipment legend based on the position of the target kilometer marker area corresponding to the target equipment legend.

[0099] In this embodiment, an image recognition model based on a CNN convolutional neural network structure can be used to perform image recognition on the target positive track region. After determining a target device legend, the system searches for character identifiers near the target device legend that correspond to the character keywords of the target device legend's type, using the target device legend as the center, to determine the device identifier information corresponding to the target device legend.

[0100] For example, such as Figure 3 As shown, image recognition identifies the out-of-circle 310. After identifying the target device legend, use it as the center to search for the keyword FB corresponding to the fixed transponder in the vicinity, find and identify the nearby character identifier FB3213, and determine that the device identification information corresponding to the target device legend is FB3213.

[0101] In this embodiment, after determining a target device legend, the target device legend is used as a reference point to search for the target kilometer marker area and its corresponding kilometer marker in the vertical direction.

[0102] like Figure 3 As shown, the target equipment legend FB3213 is the kilometer marker selected by the vertical box 320 in the target kilometer marker area.

[0103] It should be noted that after determining the target equipment legend, based on the target equipment legend being located on the upward main line track, the corresponding illustrated kilometer marker information is found in the target kilometer marker area above the target metro engineering drawing; based on the target equipment legend being located on the downward main line track, the corresponding illustrated kilometer marker information is found in the target kilometer marker area below the target metro engineering drawing.

[0104] In some embodiments, step 140 includes: determining the track unit connection relationship and signal equipment setting information based on the equipment identification information and the location of the target equipment legend in the target mainline track area; and obtaining the target engineering data table based on the track unit connection relationship, signal equipment setting information and target kilometer marker information.

[0105] In this embodiment, based on the equipment identification information of the target equipment legend and the position of the target equipment legend in the target main track area, the track unit connection relationship and signal equipment setting information can be determined according to the type and location of the target equipment legend.

[0106] The opening orientation of the turnout can be determined based on its relative position to the mainline track near the turnout. Based on the position of the axle counter, logic section, and stop and the corresponding target kilometer marker information, all track units can be named, and the signal equipment setting information can be determined.

[0107] Based on the relative positions of the track units in the target subway engineering drawing, establish the logical connection relationship between the track units. Based on the relative positions of the signaling equipment in the target subway engineering drawing, set the track unit where the signaling equipment is located and determine the connection relationship between the track units.

[0108] In some embodiments, the track unit connection relationship and signal equipment setting information are verified based on the target kilometer marker information to determine that the verification is qualified, and the target engineering data table is obtained.

[0109] From the identified target equipment legend, logical connection relationships are established based on the relative positions of track units in the target subway engineering drawing, and the distance between track units is calculated based on the corresponding target kilometer marker information.

[0110] Based on the identified target equipment legend, the track unit where the signal equipment is located is set, and the correctness of the signal equipment position is verified according to the target kilometer marker information.

[0111] In actual execution, the offset of the target equipment legend in the track section can be calculated based on the target kilometer marker information, and the position can be judged based on the offset.

[0112] The offset refers to the distance between the target equipment legend and the left end point of the track section, which is obtained by subtracting the absolute value from the target kilometer marker information.

[0113] For example, such as Figure 4 As shown, taking FB3112 as an example, the transponder is located in the G3106-E track section, with a length of 42037.26-41875.06=162.20m. Since 162.20m is less than the section length of 205.00m of the G3106-E track section, the inspection is qualified and the position is correct.

[0114] In this embodiment, if an error occurs in the calculated offset verification, an error record is output as feedback.

[0115] Based on the target kilometer marker information, the rationality of the track unit connection relationship and signal equipment setting information is checked. The target subway engineering drawings are checked according to the consistent design principles. If the verification is qualified, the target engineering data table is obtained. If the verification is unqualified and does not meet the expectations, it is fed back to the warning record.

[0116] In some embodiments, a target recognition model can be trained using a sample training set based on a CNN convolutional neural network. This target recognition model can then be used to identify the target subway engineering drawings and obtain the corresponding target engineering data table.

[0117] In this embodiment, the input to the target recognition model is the target subway engineering drawing, and the output is the target engineering data table.

[0118] The target recognition model includes a first layer, a second layer, a third layer, and a fourth layer.

[0119] The first layer of the target recognition model divides the input target subway engineering map into regions to obtain the target mainline track area and the target kilometer marker area. The second layer identifies the target mainline track area and the target kilometer marker area to obtain the equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend.

[0120] The third layer of the target recognition model converts the illustrated kilometer marker information into target kilometer marker information based on the target reference point. The fourth layer, based on the equipment identification information and the target kilometer marker information, obtains the target engineering data table.

[0121] The subway engineering drawing recognition device provided by the present invention is described below. The subway engineering drawing recognition device described below can be referred to in correspondence with the subway engineering drawing recognition method described above.

[0122] like Figure 5 As shown, the subway engineering drawing recognition device provided by the present invention includes:

[0123] The first processing module 510 is used to divide the target subway engineering map into regions to obtain the target mainline track area and the target kilometer marker area.

[0124] The second processing module 520 is used to identify the target mainline track area and the target kilometer marker area, and obtain the equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend;

[0125] The third processing module 530 is used to convert the illustrated kilometer marker information into target kilometer marker information based on the target reference point;

[0126] The fourth processing module 540 is used to obtain the target engineering data table based on the equipment identification information and the target kilometer marker information.

[0127] According to the subway engineering drawing recognition device provided by the present invention, by recognizing the legend elements and kilometer marker information in the subway engineering drawing, and generating a target engineering data table representing the link relationship and internal logic between signal equipment and track units according to the relative positions and engineering data of different equipment in the drawing, the efficiency of engineering data table compilation is improved, the workload of technical personnel and possible human errors are reduced, and it is beneficial to subsequent software development and testing and debugging work.

[0128] In some embodiments, the first processing module 510 is used to determine the mainline track boundary line and the kilometer marker boundary line based on the target subway engineering drawing;

[0129] Based on the mainline track boundary line, the target mainline track area is divided on the target subway engineering drawing;

[0130] Based on the kilometer marker boundary line, the target kilometer marker area is divided on the target subway engineering map.

[0131] In some embodiments, the second processing module 520 is used to determine the target equipment legend in the target mainline track area through image recognition;

[0132] Based on the location of the target equipment legend in the target mainline track area, determine the equipment identification information corresponding to the target equipment legend;

[0133] Based on the location of the target kilometer marker area corresponding to the target equipment legend, determine the illustrated kilometer marker information corresponding to the target equipment legend.

[0134] In some embodiments, the fourth processing module 540 is used to determine the track unit connection relationship and signal equipment setting information based on the equipment identification information and the position of the target equipment legend in the target mainline track area;

[0135] Based on the track unit connection relationship, signal equipment setting information, and target kilometer marker information, the target engineering data table is obtained.

[0136] In some embodiments, the fourth processing module 540 is used to verify the track unit connection relationship and signal equipment setting information based on the target kilometer marker information, determine that the verification is qualified, and obtain the target engineering data table.

[0137] In some embodiments, the first processing module 510 is further configured to input the target subway engineering drawing into the first layer of the target recognition model to obtain the target mainline track area and the target kilometer marker area output by the first layer;

[0138] The second processing module 520 is also used to input the target mainline track area and the target kilometer marker area into the second layer of the target recognition model to obtain the equipment identification information and graphic kilometer marker information output by the second layer;

[0139] The third processing module 530 is also used to input the illustrated kilometer marker information into the third layer of the target recognition model to obtain the target kilometer marker information output by the third layer;

[0140] The fourth processing module 540 is also used to input the equipment identification information and target kilometer marker information into the fourth layer of the target recognition model to obtain the target engineering data table output by the fourth layer;

[0141] The target recognition model is based on a CNN convolutional neural network, which is trained and learned using a sample training set.

[0142] Figure 6 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 6 As shown, the electronic device may include a processor 610, a communication interface 620, a memory 630, and a communication bus 640. The processor 610, communication interface 620, and memory 630 communicate with each other via the communication bus 640. The processor 610 can call logical instructions in the memory 630 to execute a subway engineering drawing recognition method. This method includes: dividing the target subway engineering drawing into regions to obtain a target mainline track region and a target kilometer marker region; recognizing the target mainline track region and the target kilometer marker region to obtain equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend; converting the illustrated kilometer marker information into target kilometer marker information based on target reference points; and obtaining a target engineering data table based on the equipment identification information and the target kilometer marker information.

[0143] Furthermore, the logical instructions in the aforementioned memory 630 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0144] On the other hand, the present invention also provides a computer program product, which includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the subway engineering drawing recognition method provided by the above methods. The method includes: dividing the target subway engineering drawing into regions to obtain a target mainline track region and a target kilometer marker region; identifying the target mainline track region and the target kilometer marker region to obtain equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend; converting the illustrated kilometer marker information into target kilometer marker information based on the target reference point; and obtaining a target engineering data table based on the equipment identification information and the target kilometer marker information.

[0145] In another aspect, the present invention also provides a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the metro engineering drawing recognition method provided by the above methods. The method includes: dividing the target metro engineering drawing into regions to obtain a target mainline track region and a target kilometer marker region; identifying the target mainline track region and the target kilometer marker region to obtain equipment identification information and illustrated kilometer marker information corresponding to the target equipment legend; converting the illustrated kilometer marker information into target kilometer marker information based on the target reference point; and obtaining a target engineering data table based on the equipment identification information and the target kilometer marker information.

[0146] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0147] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0148] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method of identifying a subway engineering drawing, characterized by, The method comprises the following steps: dividing a target subway engineering map into regions to obtain a target main line track region and a target kilometer marker region, including: based on the target subway engineering map, identifying a main line track and a kilometer marker, determining a main line track boundary within the upper and lower boundaries of the position of the main line track, and determining a kilometer marker boundary within the position of the kilometer marker; based on the main line track boundary, dividing the target main line track region on the target subway engineering map; based on the kilometer marker boundary, dividing the target kilometer marker region on the target subway engineering map; identifying the target main line track region and the target kilometer marker region to obtain device identification information corresponding to a target device legend and diagram kilometer marker information, including: determining the target device legend in the target main line track region through image recognition; taking the target device legend as the center, searching for a character identification corresponding to a character keyword of the type of the target device legend near the target device legend in the target main line track region, and determining the device identification information corresponding to the target device legend; taking the target device legend as a reference point, searching for a position corresponding to the target kilometer marker region, and determining the diagram kilometer marker information corresponding to the target device legend in the vertical direction; converting the diagram kilometer marker information into target kilometer marker information based on a target reference point; based on the device identification information and the target kilometer marker information, obtaining a target engineering data table, including: based on the device identification information and the position of the target device legend in the target main line track region, determining track unit connection relationships and signal device setting information; based on the track unit connection relationships, the signal device setting information, and the target kilometer marker information, obtaining the target engineering data table; based on the track unit connection relationships, the signal device setting information, and the target kilometer marker information, obtaining the target engineering data table, including: based on the target kilometer marker information, verifying the track unit connection relationships and the signal device setting information, and determining that the verification is qualified to obtain the target engineering data table; based on the target kilometer marker information, verifying the track unit connection relationships and the signal device setting information, including: according to the target kilometer marker information, calculating the offset of the target device legend in a track section, and judging the correctness of the signal device setting information according to the offset.

2. The method of claim 1, wherein, The method comprises the following steps: inputting the target subway engineering map into a first layer of a target recognition model to obtain a target main line track region and a target kilometer marker region output by the first layer; The method comprises the following steps: inputting the target main line track region and the target kilometer marker region into a second layer of the target recognition model to obtain the device identification information and the diagram kilometer marker information output by the second layer; The converting the graphic kilometer marker information into target kilometer marker information based on a target reference point comprises: inputting the graphic kilometer marker information into a third layer of the target recognition model to obtain the target kilometer marker information output by the third layer; the target engineering data table is obtained based on the equipment identification information and the target kilometer marker information, comprising: inputting the equipment identification information and the target kilometer marker information into a fourth layer of the target recognition model to obtain the target engineering data table output by the fourth layer; The target recognition model is obtained by training and learning a sample training set based on a CNN convolutional neural network.

3. A subway engineering drawing recognition apparatus characterized by comprising: Comprise: The first processing module is used for dividing the target subway engineering map into regions to obtain a target main line track region and a target kilometer marker region, comprising: identifying a main line track and a kilometer marker based on the target subway engineering map, determining a main line track boundary line within the upper and lower boundaries of the position of the main line track, and determining a kilometer marker boundary line within the position of the kilometer marker; based on the main line track boundary line, dividing the target main line track region on the target subway engineering map; based on the kilometer marker boundary line, dividing the target kilometer marker region on the target subway engineering map; The second processing module is used for identifying the target main line track region and the target kilometer marker region to obtain equipment identification information corresponding to a target equipment legend and graphic kilometer marker information, comprising: determining the target equipment legend in the target main line track region through image recognition; taking the target equipment legend as the center, searching for a character identifier corresponding to a character keyword of the type of the target equipment legend near the target equipment legend in the target main line track region, and determining the equipment identification information corresponding to the target equipment legend; taking the target equipment legend as a reference point, searching for a position corresponding to the target kilometer marker region, and determining the graphic kilometer marker information corresponding to the target equipment legend in the vertical direction; The third processing module is used for converting the graphic kilometer marker information into target kilometer marker information based on a target reference point; The fourth processing module is used for obtaining a target engineering data table based on the equipment identification information and the target kilometer marker information, comprising: determining track unit connection relationships and signal equipment setting information based on the equipment identification information and the position of the target equipment legend in the target main line track region; obtaining the target engineering data table based on the track unit connection relationships, the signal equipment setting information, and the target kilometer marker information; The target engineering data table is obtained based on the track unit connection relationships, the signal equipment setting information, and the target kilometer marker information, comprising: verifying the track unit connection relationships and the signal equipment setting information based on the target kilometer marker information, determining that the verification is qualified, and obtaining the target engineering data table; The verifying the track unit connection relationship and the signal device setting information based on the target kilometer marker information comprises: calculating an offset of the target device legend in a track section according to the target kilometer marker information, and judging the correctness of the signal device setting information according to the offset.

4. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The processor implements the steps of the subway engineering drawing identification method according to any one of claims 1 to 2 when executing the program.

5. A non-transitory computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program implements the steps of the subway engineering drawing identification method according to any one of claims 1 to 2 when executed by the processor.

6. A computer program product comprising a computer program, characterized in that, The computer program implements the steps of the subway engineering drawing identification method according to any one of claims 1 to 2 when executed by the processor. The computer program implements the steps of the subway engineering drawing identification method according to any one of claims 1 to 2 when executed by the processor.

Images