Method, system and electronic device for identifying line feature regions in track geometry detection

Abstract

The present invention belongs to the technical field of rail transit, and specifically relates to a method, system and electronic device for identifying line feature regions in track geometry detection, aiming to solve the problem of insufficient reliability of the monitoring results of track geometry detection line feature information. The present invention includes: determining a track line feature image to be identified; inputting the track line feature image to be identified into a line feature region identification model to obtain a line feature region identification result output by the line feature region identification model; wherein, the line feature region identification model is obtained after being trained based on the sample data of the line feature image and the regional image annotation of the sample data; the line feature region identification model is used to perform multiple feature judgments on the fused data after the space-time synchronization of the track line feature image to be identified and the track geometry detection waveform data to obtain a line feature region identification result. The present invention can achieve high reliability of the monitoring results.

Description

Background Art

[0002] At present, the detection of track line characteristics is mainly achieved by detecting the ALD on the track geometry detection beam carried by the inspection vehicle and collecting and processing the sensor data with the on-vehicle detection equipment. Its technical solution is mainly based on the system structure of "ALD - data acquisition industrial computer - processing system". As shown in the appendix Figure 2 Data is collected through the ALD, encapsulated and stored through the industrial computer and data acquisition card, and the data is processed and aligned through the algorithm in the processing system.

[0003] The principle of the existing technical solution is to display the output result through the signal waveform output after removing the interference signal by the level signal of the ALD. This requires the inspectors to judge through the characteristic signal waveform to determine the line characteristic information at the current position, which has high requirements for the experience of the personnel. Moreover, the waveform characteristics may not be able to truly reflect the line characteristic results, and on-site compounding or comprehensive analysis in combination with other sensors is required for discrimination. It is relatively complex to use, with insufficient reliability and unintuitive results. Summary of the Invention

[0004] In order to solve the above problems in the prior art, that is, the problem of insufficient reliability of the monitoring results of the track geometry detection line characteristic information and the high requirements for the experience of the inspectors, the present invention provides a method for identifying the line characteristic area of track geometry detection, realizing high reliability of the monitoring results.

[0005] One aspect of the present invention proposes a method for identifying the line characteristic area of track geometry detection, including:

[0006] Determine the track line characteristic image to be identified;

[0007] Input the track line characteristic image to be identified into the line characteristic area recognition model to obtain the line characteristic area recognition result output by the line characteristic area recognition model;

[0008] Among them, the line characteristic area recognition model is obtained by training based on the sample data of the line characteristic image and the regional image annotation of the sample data;

[0009] The line characteristic area recognition model is used to perform multiple feature judgments on the fusion data after the space-time synchronization of the track line characteristic image to be identified and the track geometry detection waveform data to obtain the line characteristic area recognition result.

[0010] In some preferred embodiments, the line characteristic area recognition model includes a data acquisition unit, a feature judgment unit, and a regional recognition unit;

[0011] The line feature area recognition model is used to perform multiple feature judgments on the fused data after spatio-temporal synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data, and the line feature area recognition result includes:

[0012] Obtain the fused data after spatio-temporal synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data through the data acquisition unit;

[0013] Input the fused data into the feature judgment unit, and perform multiple feature judgments through the feature judgment unit to screen out the feature areas corresponding to the features of the corresponding type in the to-be-recognized track line feature image;

[0014] Input the feature areas corresponding to the features of the corresponding type in the to-be-recognized track line feature image into the area recognition unit, and output the line feature area recognition result.

[0015] In some preferred embodiments, before obtaining the fused data after spatio-temporal synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data through the data acquisition unit, it includes:

[0016] Collect the to-be-recognized track line feature image through an image sensor, and collect the track geometry detection waveform data through an eddy current gauge;

[0017] Drive the eddy current gauge to start working through the trigger signal sent by the encoder, and return the level signal as a timestamp to achieve the time synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data;

[0018] Make the column data of the to-be-recognized track line feature image, the track geometry detection waveform data, and the spatial position of the real line correspond one by one to achieve the spatial synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data.

[0019] In some preferred embodiments, making the column data of the to-be-recognized track line feature image, the track geometry detection waveform data, and the spatial position of the real line correspond one by one to achieve the spatial synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data includes:

[0020] Based on the number of triggers per revolution of the encoder, the wheel diameter, and the line mileage during data acquisition, obtain the data acquisition position of any frame of the image sensor to establish the spatial position correspondence relationship between the to-be-recognized track line feature image and the real line;

[0021] Offset the collected track geometry detection waveform data according to the frame number based on the corrected offset to obtain the alignment relationship between the middle positions of the track geometry detection waveform data and the track line feature image to be recognized; wherein, the corrected offset is calculated based on the number of triggers per revolution and the wheel diameter of the encoder and the projection distance between the image sensor and the eddy current gauge on the horizontal plane;

[0022] Perform coordinate correction on the position of the track geometry detection waveform data aligned with the center position of the image sensor based on the coordinate correction value to obtain the correspondence between the column data of the track line feature image to be recognized and the track geometry detection waveform data; wherein, the coordinate correction value is calculated based on the true distance of the imaging projection relationship of the image sensor and the data sampling interval.

[0023] In some preferred embodiments, the corrected offset is calculated based on the number of triggers per revolution and the wheel diameter of the encoder and the projection distance between the image sensor and the eddy current gauge on the horizontal plane, and the formula is as follows:

[0024] Q=(L1×n) / (π×d);

[0025] Wherein, Q is the corrected offset, L1 is the projection distance between the image sensor and the eddy current gauge on the horizontal plane, n is the number of triggers per revolution of the encoder, and d is the wheel diameter of the encoder.

[0026] In some preferred embodiments, the coordinate correction value is calculated based on the true distance of the imaging projection relationship of the image sensor and the data sampling interval, and the formula is as follows:

[0027] R=(ΔL×n) / (π×d);

[0028] Wherein, R is the coordinate correction value, ΔL is the true distance of the imaging projection relationship of the image sensor, n is the number of triggers per revolution of the encoder, and d is the wheel diameter of the encoder.

[0029] In some preferred embodiments, inputting the fusion data into the feature judgment unit, and performing multiple feature judgments through the feature judgment unit to screen out the feature regions corresponding to the corresponding type features in the track line feature image to be recognized, including:

[0030] Perform a primary screening of the corresponding type features on the fusion data based on the amplitude feature, amplitude feature, and rising and falling feature of the curve corresponding to the feature region of the preset standard type;

[0031] Performing secondary screening of corresponding type features on the fused data after the first screening based on the width feature corresponding to the feature region in the curve to obtain the feature region of the corresponding type feature in the to-be-recognized track line feature image; wherein, the width feature corresponding to the feature region in the curve is calculated based on the spatial position correspondence between the to-be-recognized track line feature image and the real line and the fixed physical size of the line feature.

[0032] In some preferred embodiments, the eddy current meter is disposed in the middle of the detection beam of the track geometry detection device; the encoder is disposed on the axle of the wheel of the track geometry detection device; the eddy current meter and the image sensor are on the same horizontal plane; the track geometry detection device includes an urban rail transit track geometry detection vehicle.

[0033] On the other hand, the present invention proposes a system for identifying a line feature region of track geometry detection, including:

[0034] An image determination unit, configured to determine a to-be-recognized track line feature image;

[0035] A region recognition unit, configured to input the to-be-recognized track line feature image into a line feature region recognition model to obtain a line feature region recognition result output by the line feature region recognition model;

[0036] Wherein, the line feature region recognition model is obtained after being trained based on sample data of line feature images and region image annotations of the sample data;

[0037] The line feature region recognition model is used to perform multiple feature judgments on the fused data after the space-time synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data to obtain the line feature region recognition result.

[0038] On the third aspect of the present invention, an electronic device is proposed, including:

[0039] At least one processor;

[0040] And a memory communicatively connected to at least one of the processors;

[0041] Wherein, the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned method for identifying a line feature region of track geometry detection.

[0042] The beneficial effects of the present invention:

[0043] The present invention provides an analysis of image data synchronized with a waveform signal, which can not only be compatible with the original data analysis and processing system, but also provide relatively accurate image information, improve the reliability of data, reduce the experience requirements for operators, visually display the line state at the current position, enable track maintenance personnel to accurately and conveniently associate the collected regional feature data with the on-site situation, greatly simplify the process of line feature recognition, reduce the recognition difficulty, and is of great significance for solving the objectively existing problems on site. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Other features, objects, and advantages of the present application will become more apparent by reading the following detailed description of non-limiting embodiments with reference to the accompanying drawings:

[0045] Figure 1 is a flowchart of a method for identifying a line feature area in track geometry detection;

[0046] Figure 2 is a schematic diagram of an existing track line feature detection device;

[0047] Figure 3 is a schematic diagram of an improved track geometry detection device of the present invention;

[0048] Figure 4 is a schematic diagram of the structure of a line feature area recognition model;

[0049] Figure 5 is a structural diagram of a system for identifying a line feature area in track geometry detection;

[0050] Figure 6 is a schematic diagram of the structure of a computer system of a server for implementing the method, system, and electronic device embodiments of the present application;

[0051] Figure 7 is a schematic diagram of an image after an image sensor captures an image, performs grayscale processing, and removes irrelevant areas;

[0052] Figure 8 is a schematic diagram of a feature area identified from an image captured by an image sensor through a depth model;

[0053] Figure 9 is a schematic diagram of converting an image into waveform information by column projection;

[0054] Figure 10 is a schematic diagram of waveform features of ALD data in different sections;

[0055] Figure 11 is a schematic diagram of line features in the main line area identified in actual detection;

[0056] Figure 12It is a schematic diagram of the line features in the turnout area identified in actual detection;

[0057] Figure 13 It is a schematic diagram of the line features in the transponder area identified in actual detection;

[0058] Figure 14 It is a detailed flowchart of the method for identifying the line feature area in geometric detection. Specific implementation manners

[0059] The following further elaborates on the present application in conjunction with the accompanying drawings and embodiments. It can be understood that the specific embodiments described herein are only used to explain the related invention and are not intended to limit the invention. Additionally, it should be noted that for the sake of description, only the parts related to the relevant invention are shown in the drawings.

[0060] It should be noted that, without conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The following will elaborate on the present application in detail with reference to the drawings and embodiments.

[0061] The present invention improves the reliability of the detection results, enhances the credibility of the data and the persuasiveness of the detection results, and reduces the experience requirements for the detection personnel by combining an image sensor and a traditional eddy current sensor for data fusion analysis and processing. Specifically as follows:

[0062] The relevant equipment of the present invention is carried on a train for urban rail geometric detection (i.e., the rail geometric detection equipment), and consists of an ALD, an image sensor, an encoder, a data acquisition industrial control computer, a data analysis industrial control computer, and a system power supply, as Figure 3 shown. The functions of each component are as follows:

[0063] (1) ALD (eddy current gauge sensor, i.e., Figure 3 the eddy current gauge in): Installed in the middle of the detection beam, it measures based on the principle of generating an induced electromagnetic field by eddy currents in the object to be measured. When a current is passed through the excitation coil, an alternating magnetic field is generated, causing the generation of eddy currents in the object to be measured. The eddy currents cause a loss of magnetic flux due to their own damping effect. Subsequently, a change in the level is caused, thereby obtaining the original data of the characteristic information.

[0064] (2) Image sensor (i.e., Figure 3 the vision sensor in): Using a frame-triggered high-speed camera, it takes vertical downward shots, enabling high-speed and high-precision image acquisition.

[0065] (3) Encoder: Set on the axle of the wheels of the rail geometric detection equipment, it is used to convert the angular displacement of the wheels into pulse signals.

[0066] (4) Data acquisition industrial control computer (i.e., Figure 3The real-time acquisition processor): converts the pulse signal provided by the encoder into a trigger signal, sends trigger signals to each sensor, and acquires and stores the data information of each sensor.

[0067] (5) The data analysis industrial control computer (i.e., Figure 3 The data analysis server in): obtains, analyzes, and processes the data information stored by the real-time acquisition processor through the vehicle-mounted local area network.

[0068] (6) System power supply: provides power for each sensor. The data acquisition industrial control computer, the data analysis industrial control computer, and the system power supply are all arranged inside the body structure of the train for urban rail geometric inspection;

[0069] Based on the above devices, the present invention provides a method for identifying line feature regions in track geometry inspection, including:

[0070] Determine the track line feature image to be identified;

[0071] Input the track line feature image to be identified into the line feature region recognition model to obtain the line feature region recognition result output by the line feature region recognition model;

[0072] Among them, the line feature region recognition model is obtained after being trained based on the sample data of the line feature image and the regional image annotation of the sample data;

[0073] The line feature region recognition model is used to perform multiple feature judgments on the fusion data after the space-time synchronization of the track line feature image to be identified and the track geometry detection waveform data to obtain the line feature region recognition result.

[0074] To more clearly illustrate the method for identifying line feature regions in track geometry inspection of the present invention, the following combines Figure 1 , Figure 14 Details of each step in the embodiments of the present invention are described in detail.

[0075] The method for identifying line feature regions in track geometry inspection according to the first embodiment of the present invention, as Figure 1 shown, includes step S101-step S102, and each step is described in detail as follows:

[0076] Step S101, determine the track line feature image to be identified;

[0077] Step S102, input the track line feature image to be identified into the line feature region recognition model to obtain the line feature region recognition result output by the line feature region recognition model;

[0078] Among them, the line feature area recognition model is obtained after training based on the sample data of the line feature image and the area image annotation of the sample data;

[0079] Specifically, there are obvious line feature images in different regions. By analyzing the data set obtained by collecting a large amount of sample data in the corresponding feature intervals, and using deep learning annotation training to recognize the interval images of the sample data, a deep learning model that can initially judge the line features is obtained.

[0080] The line feature area recognition model is used to perform multiple feature judgments on the fusion data after the space-time synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data to obtain the line feature area recognition result.

[0081] The present invention provides an analysis of image data synchronized with waveform signals, which can not only be compatible with the original data analysis and processing system, but also provide relatively accurate image information, improve the reliability of data, and at the same time reduce the experience requirements for operators. It can intuitively display the line state at the current position, enabling track maintenance personnel to accurately and conveniently associate the collected regional feature data with the on-site situation, greatly simplifying the process of line feature recognition, reducing the recognition difficulty, and being of great significance for solving the objectively existing problems on site.

[0082] In the above embodiments, although the steps are described in the above sequential order, those skilled in the art can understand that in order to achieve the effects of this embodiment, different steps do not have to be executed in such an order. They can be executed simultaneously (in parallel) or in a reversed order, and these simple changes are all within the protection scope of the present invention.

[0083] Based on the above embodiments, as Figure 4 shown, the line feature area recognition model includes a data acquisition unit 201, a feature judgment unit 202, and a region recognition unit 203;

[0084] The line feature area recognition model is used to perform multiple feature judgments on the fusion data after the space-time synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data to obtain the line feature area recognition result, including:

[0085] Obtain the fusion data after the space-time synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data through the data acquisition unit 201;

[0086] Input the fusion data into the feature judgment unit 202, and through the feature judgment unit 202, perform multiple feature judgments to screen out the feature regions corresponding to the types of features in the to-be-recognized track line feature image;

[0087] Input the feature region corresponding to the feature of the corresponding type in the to-be-recognized track line feature image into the region recognition unit 203, and output the recognition result of the line feature region.

[0088] Based on the above embodiments, before obtaining the fused data after spatio-temporal synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data by the data acquisition unit, it includes:

[0089] Collect the to-be-recognized track line feature image through an image sensor, and collect the track geometry detection waveform data through an eddy current gauge;

[0090] Drive the eddy current gauge to start working through the trigger signal sent by the encoder, and return the level signal as a timestamp to achieve the time synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data;

[0091] Specifically, when the vehicle is moving, the encoder installed on the axle emits a pulse signal, and the pulse signal is converted into a trigger signal through frequency division processing. When the vision sensor receives the trigger signal, it starts to work, and at the same time returns the level signal as a timestamp to achieve time synchronization.

[0092] Make the column data of the to-be-recognized track line feature image, the track geometry detection waveform data and the spatial position of the real line correspond one by one to achieve the spatial synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data.

[0093] Specifically, establish (1) the spatial position relationship between the camera data and the real line; (2) the corresponding relationship between the middle position of each frame of image and the ALD data; (3) the corresponding relationship between each column data in a frame of image and the ALD data. Based on the above corresponding relationships, any column data of the camera, the ALD data and the spatial position of the real line can be corresponding to achieve spatial synchronization.

[0094] Based on the above embodiments, the making the column data of the to-be-recognized track line feature image, the track geometry detection waveform data and the spatial position of the real line correspond one by one to achieve the spatial synchronization of the to-be-recognized track line feature image and the track geometry detection waveform data includes:

[0095] Based on the number of triggers per revolution of the encoder, the wheel diameter and the line mileage during data acquisition, obtain the data acquisition position of any frame of the image sensor to establish the spatial position corresponding relationship between the to-be-recognized track line feature image and the real line;

[0096] Specifically, according to the encoder principle, if the number of triggers per revolution of the encoder is denoted as n and the wheel diameter is denoted as d, and the line mileage at the start of data collection is denoted as X0, then the data collection position of the m-th frame of the camera is X0 + (m×π×d) / n, thereby establishing the spatial position relationship between the camera data and the actual line.

[0097] Based on the corrected offset, the collected track geometry detection waveform data is offset according to the frame number to achieve the alignment relationship between the middle positions of the track geometry detection waveform data and the track line feature image to be recognized; wherein, the corrected offset is calculated based on the number of triggers per revolution and the wheel diameter of the encoder and the projection distance of the image sensor and the eddy current gauge on the horizontal plane.

[0098] Specifically, the projection distance of the position of the camera lens of the vision sensor and the installation position of the ALD on the horizontal plane is L1. From the number of triggers per revolution (n) and the wheel diameter (d) of the encoder, the number of trigger times for this length can be calculated as (L1×n) / (π×d), that is, the number of frames between the camera shooting position and the ALD measurement position is (L1×n) / (π×d). As known from the above, the ALD collected data is corrected, and the collected ALD data is offset according to the frame number. When the corrected offset Q is (L1×n) / (π×d), the ALD data can be aligned with the middle position of the camera captured image.

[0099] Based on the coordinate correction value, the position of the track geometry detection waveform data aligned with the center position of the image sensor is corrected in coordinates to obtain the correspondence between the column data of the track line feature image to be recognized and the track geometry detection waveform data; wherein, the coordinate correction value is calculated based on the true distance of the imaging projection relationship of the image sensor and the data sampling interval.

[0100] Specifically, denote the position of the ALD data aligned with the center position of the camera image as A0. Since the relative positions of the camera and the rail are determined by the structure of the acquisition device and can be regarded as constants, according to the camera imaging projection relationship, the relationship between the width of the captured image and the width of the corresponding area on the actual line can be obtained. Denote the number of columns between a certain column of data in the image and the middle position as Δw, and the true distance between the two obtained according to the camera imaging projection relationship as ΔL. Given that the sampling interval should be (π×d) / n, the coordinate correction value R between the ALD data corresponding to this column of data and the position at A0 is (ΔL×n) / (π×d). Thus, the correspondence between each column of data in the image and the ALD data can be obtained.

[0101] Based on the above embodiments, inputting the fusion data into the feature judgment unit, and performing multiple feature judgments through the feature judgment unit to screen out the feature regions corresponding to the types of features in the track line feature image to be recognized, including:

[0102] Perform a primary screening of the corresponding type of features on the fusion data based on the amplitude characteristics, amplitude characteristics, and rising and falling characteristics of the characteristic region corresponding curves of the preset standard type;

[0103] Perform a secondary screening of the fusion data after the primary screening based on the width characteristics corresponding to the characteristic region in the curve to obtain the characteristic region of the corresponding type of features in the track line feature image to be recognized; wherein, the width characteristics corresponding to the characteristic region in the curve are calculated based on the spatial position correspondence relationship between the track line feature image to be recognized and the real line and the fixed physical dimensions of the line features.

[0104] Specifically, take a photo, perform grayscale processing, and remove irrelevant areas, such as Figure 7 shown, and take the concerned feature range. After being processed by the deep learning model, the output result of the characteristic region can be recognized, such as Figure 8 shown.

[0105] In addition, perform a vertical grayscale projection on the grayscale image. Move the whole picture to the left by dw and up by dh. Then, for any (h, w) ∈ the pixel range of the picture, the (h, w) pixel point of the new picture should be exactly the same as the (h + dh, w + dw) of the original picture. That is, the h-th row of the new picture should be exactly the same as the (h + dh)-th row of the original picture, and the w-th column of the new picture should be exactly the same as the (w + dw)-th column of the original picture. That is, using this method, a grayscale waveform with the same trend as the original image can be obtained.

[0106] The formulas for row grayscale projection and column grayscale projection are as follows:

[0107] ;

[0108] In the above formula, Gk(i, j) represents the pixel grayscale value of the k-th frame image at (i, j), Gk(i) represents the pixel grayscale value of the i-th row of the image, and Gk(j) represents the pixel grayscale value of the j-th column of the image.

[0109] Therefore, the above image can be projected by columns and converted into waveform information to obtain the projection result, such as Figure 9 shown.

[0110] It can be seen that the grayscale projection waveforms of different characteristic sections are significantly different from those of the main line. Data can be collected for various characteristic regions manually on the line, and this can be used as the standard data for feature recognition to establish a recognition algorithm:

[0111] First, denoise the obtained data and remove isolated points to avoid interference points affecting the results. Subsequently, taking the general main line area as a benchmark, perform max-min normalization on the curve. According to the data of the above standard area, the amplitude characteristics, amplitude characteristics, and rising and falling characteristics of the curve corresponding to this type of area can be determined. As described above, the spatial synchronization process has established the relationship between each column of data in the image and the real physical position. Since the physical size of the line characteristics is fixed, the width characteristics corresponding to the characteristic area in the curve can be calculated. Finally, perform two-step screening according to the above characteristics, and all areas that meet the corresponding characteristics are the corresponding characteristic areas. Traditional determination of characteristic areas mainly relies on the fact that when passing through different sections, the ALD data will have obvious characteristic values, and the line characteristics can be roughly screened according to the waveform characteristics. As Figure 10 shown;

[0112] During actual detection, first, use a deep learning model to judge and screen the interested interval. Subsequently, perform gray projection processing on the image of this area to obtain the gray projection curve of the target area. From the recognition algorithm, the line characteristics can be judged. At the same time, the recognition algorithm can be compatible with the existing ALD waveform and jointly participate in the determination of the characteristic area, so that the line characteristics of this section can be more accurately recognized, such as Figure 11 、 12 、shown in Figure 13.

[0113] The line feature area recognition system for track geometry detection according to the second embodiment of the present invention, as Figure 5 shown, includes:

[0114] An image determination unit 301, configured to determine an image of track line features to be recognized;

[0115] A region recognition unit 302, configured to input the image of the track line features to be recognized into a line feature region recognition model to obtain a line feature region recognition result output by the line feature region recognition model;

[0116] Wherein, the line feature region recognition model is obtained by training based on sample data of line feature images and region image annotations of the sample data;

[0117] The line feature region recognition model is used to perform multiple feature judgments on the fused data after spatio-temporal synchronization of the image of the track line features to be recognized and the track geometry detection waveform data to obtain the line feature region recognition result.

[0118] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process and related descriptions of the above-described system can refer to the corresponding process in the foregoing method embodiment, and will not be repeated here.

[0119] It should be noted that the line feature area recognition system for track geometry detection provided in the above embodiments is only illustrated by dividing the above functional modules. In actual applications, the above functions can be allocated to different functional modules according to needs, that is, the modules or steps in the embodiments of the present invention can be further decomposed or combined. For example, the modules in the above embodiments can be merged into one module, or further split into multiple sub-modules to complete all or part of the functions described above. The names of the modules and steps involved in the embodiments of the present invention are only used to distinguish each module or step, and are not regarded as an improper limitation of the present invention.

[0120] An electronic device according to a third embodiment of the present invention includes:

[0121] At least one processor;

[0122] And a memory communicatively connected to at least one of the processors;

[0123] Wherein, the memory stores instructions executable by the processor, and the instructions are used to be executed by the processor to implement the above-mentioned method for identifying line feature areas of track geometry detection.

[0124] A computer-readable storage medium according to a fourth embodiment of the present invention stores computer instructions, and the computer instructions are used to be executed by the computer to implement the above-mentioned method for identifying line feature areas of track geometry detection.

[0125] Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working processes and related descriptions of the above-described electronic devices and computer-readable storage media can refer to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0126] Those skilled in the art should be able to realize that the modules and method steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, computer software, or a combination of the two. The programs corresponding to the software modules and method steps can be placed in random access memory (RAM), memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium well-known in the technical field. To clearly illustrate the interchangeability of electronic hardware and software, the components and steps of each example have been generally described according to functions in the above description. Whether these functions are executed in the form of electronic hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0127] Refer to the following Figure 6 , which shows a schematic structural diagram of a computer system of a server for implementing the method, system, and device embodiments of the present application. Figure 6 The server shown is merely an example and should not impose any limitations on the functions and usage scope of the embodiments of the present application.

[0128] As Figure 6 shown, the computer system includes a central processing unit (CPU, Central Processing Unit) 601, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM, Read Only Memory) 602 or the program loaded from the storage section 608 into the random access memory (RAM, Random Access Memory) 603. In the RAM 603, various programs and data required for system operation are also stored. The CPU 601, ROM 602, and RAM 603 are connected to each other via a bus 604. The input / output (I / O, Input / Output) interface 605 is also connected to the bus 604.

[0129] The following components are connected to the I / O interface 605: an input section 606 including a keyboard, a mouse, etc.; an output section 607 including, for example, a cathode ray tube (CRT, Cathode Ray Tube), a liquid crystal display (LCD, Liquid Crystal Display), etc., and a speaker, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to the I / O interface 605 as needed. A removable medium 611, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 610 as needed so that a computer program read from it can be installed into the storage section 608 as needed.

[0130] In particular, according to embodiments of the present disclosure, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present disclosure include a computer program product that includes a computer program carried on a computer-readable medium, and the computer program includes program code for performing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network through the communication section 609, and / or installed from the removable medium 611. When the computer program is executed by the central processing unit (CPU) 601, the above-described functions defined in the methods of the present application are performed. It should be noted that the computer-readable medium in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0131] Computer program code for performing the operations of this application can be written in one or more programming languages or combinations thereof. The above-mentioned programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0132] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0133] The terms "first", "second", etc. are used to distinguish similar objects and not to describe or represent a specific order or sequence.

[0134] The term "comprising" or any other similar term is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus / device that comprises a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to those process, method, article, or apparatus / device.

[0135] So far, the technical solution of the present invention has been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present invention.

Claims

1. A method for identifying line feature areas for track geometry detection, characterized in that: include: Determining a track line feature image to be identified; Inputting the track line feature image to be identified into a line feature region identification model to obtain a line feature region identification result output by the line feature region identification model; Wherein, the line feature region recognition model is obtained after training based on sample data of line feature images and regional image annotation of the sample data; The line feature area recognition model is used to perform multiple feature judgments on the fused data of the track line feature image to be identified and the track geometry detection waveform data after time and space synchronization to obtain the line feature area recognition result; Before obtaining the fused data of the track line feature image to be identified and the track geometry detection waveform data after time and space synchronization, it includes: The track line feature image to be identified is collected by an image sensor, and the track geometry detection waveform data is collected by an eddy current meter; The eddy current meter is driven to start working by a trigger signal sent by an encoder, and a level signal is returned as a timestamp to achieve time synchronization between the track line feature image to be identified and the track geometry detection waveform data; The column data of the track line feature image to be identified, the track geometry detection waveform data and the spatial position of the real line are matched one by one to achieve spatial synchronization of the track line feature image to be identified and the track geometry detection waveform data: Based on the number of triggers per revolution of the encoder and the wheel diameter and the line mileage during data collection, the data collection position of any frame of the image sensor is obtained to establish a spatial position correspondence between the characteristic image of the track line to be identified and the real line; The collected track geometry detection waveform data is offset according to the frame number based on the correction offset to obtain the alignment relationship between the track geometry detection waveform data and the middle position of the track line feature image to be identified; wherein the correction offset is calculated based on the number of triggers per circle of the encoder and the wheel diameter and the projection distance between the image sensor and the eddy current meter on the horizontal plane; Based on the coordinate correction value, the position of the track geometry detection waveform data aligned with the center position of the image sensor is corrected to obtain the corresponding relationship between the column data of the track line feature image to be identified and the track geometry detection waveform data; wherein the coordinate correction value is calculated based on the actual distance of the image sensor imaging projection relationship and the data sampling interval.

2. The line feature area recognition method for track geometry detection according to claim 1, characterized in that: The line feature region recognition model includes a data acquisition unit, a feature judgment unit and a region recognition unit; The line feature area recognition model is used to perform multiple feature judgments on the fused data of the track line feature image to be identified and the track geometry detection waveform data after time and space synchronization to obtain the line feature area recognition result, including: Acquire, by the data acquisition unit, fused data of the track line feature image to be identified and the track geometry detection waveform data after time and space synchronization; The fused data is input into the feature judgment unit, and the feature judgment unit performs multiple feature judgments to filter out feature areas of corresponding types of features in the track line feature image to be identified; The feature area of ​​the corresponding type of feature in the track line feature image to be identified is input into the area identification unit, and the line feature area identification result is output.

3. The line feature area recognition method for track geometry detection according to claim 2, characterized in that: The correction offset is calculated based on the number of triggers per revolution of the encoder and the wheel diameter and the projection distance of the image sensor and the eddy current meter on the horizontal plane, and the formula is as follows: Q = (L1 × n) / (π × d); Among them, Q is the correction offset, L1 is the projection distance between the image sensor and the eddy current meter on the horizontal plane, n is the number of triggers per circle of the encoder, and d is the wheel diameter of the encoder.

4. The line feature area recognition method for track geometry detection according to claim 2, characterized in that: The coordinate correction value is calculated based on the actual distance of the image sensor imaging projection relationship and the data sampling interval, and its formula is as follows: R = (ΔL × n) / (π × d); Wherein, R is the coordinate correction value, ΔL is the actual distance of the imaging projection relationship of the image sensor, n is the number of triggers per circle of the encoder, and d is the wheel diameter of the encoder.

5. The line feature area recognition method for track geometry detection according to claim 2, characterized in that: The step of inputting the fused data into the feature judgment unit, and performing multiple feature judgments by the feature judgment unit to screen out feature areas of corresponding types of features in the track line feature image to be identified, includes: Based on the amplitude characteristics, amplitude characteristics, and rise and fall characteristics of the corresponding curves of the characteristic regions of preset standard types, the corresponding type characteristics of the fused data are screened once; Based on the width features corresponding to the feature areas in the curve, the fused data after the primary screening is secondary screened for features of corresponding types, so as to obtain feature areas of corresponding types of features in the feature image of the track line to be identified; wherein the width features corresponding to the feature areas in the curve are calculated based on the spatial position correspondence between the feature image of the track line to be identified and the real line and the fixed physical size of the line features.

6. The line feature area recognition method for track geometry detection according to claim 2, characterized in that: The eddy current meter is arranged in the middle of the detection beam of the track geometry detection device; the encoder is arranged on the axle of the wheel of the track geometry detection device; the eddy current meter and the image sensor are located on the same horizontal plane; The track geometry detection equipment includes an urban transportation track geometry detection vehicle.

7. A line feature area recognition system for track geometry detection, characterized in that: include: An image determination unit, used to determine a track line feature image to be identified; A region recognition unit, used for inputting the track line feature image to be recognized into a line feature region recognition model, and obtaining a line feature region recognition result output by the line feature region recognition model; Wherein, the line feature region recognition model is obtained after training based on sample data of line feature images and regional image annotation of the sample data; The line feature area recognition model is used to perform multiple feature judgments on the fused data of the track line feature image to be identified and the track geometry detection waveform data after time and space synchronization to obtain the line feature area recognition result; Before obtaining the fused data of the track line feature image to be identified and the track geometry detection waveform data after time and space synchronization, it includes: The track line feature image to be identified is collected by an image sensor, and the track geometry detection waveform data is collected by an eddy current meter; The eddy current meter is driven to start working by a trigger signal sent by an encoder, and a level signal is returned as a timestamp to achieve time synchronization between the track line feature image to be identified and the track geometry detection waveform data; The column data of the track line feature image to be identified, the track geometry detection waveform data and the spatial position of the real line are matched one by one to achieve spatial synchronization of the track line feature image to be identified and the track geometry detection waveform data: Based on the number of triggers per revolution of the encoder and the wheel diameter and the line mileage during data collection, the data collection position of any frame of the image sensor is obtained to establish a spatial position correspondence between the characteristic image of the track line to be identified and the real line; The collected track geometry detection waveform data is offset according to the frame number based on the correction offset to obtain the alignment relationship between the track geometry detection waveform data and the middle position of the track line feature image to be identified; wherein the correction offset is calculated based on the number of triggers per circle of the encoder and the wheel diameter and the projection distance between the image sensor and the eddy current meter on the horizontal plane; Based on the coordinate correction value, the position of the track geometry detection waveform data aligned with the center position of the image sensor is corrected to obtain the corresponding relationship between the column data of the track line feature image to be identified and the track geometry detection waveform data; wherein the coordinate correction value is calculated based on the actual distance of the image sensor imaging projection relationship and the data sampling interval.

8. An electronic device, characterized in that: include: at least one processor; and a memory communicatively coupled to at least one of the processors; Wherein, the memory stores instructions that can be executed by the processor, and the instructions are used to be executed by the processor to implement the line feature area identification method for track geometry detection as described in any one of claims 1-6.

Images