A method, device, and storage medium for removing interference from a captured image in a CTC system

Abstract

The present application discloses a method, device and storage medium for removing interference from CTC system captured images, aiming to solve the technical problem of interference such as reflection and shadow existing in existing CTC system captured images. The method includes: obtaining a plurality of CTC system template images of the CTC system, and marking the positions of signal lights to be monitored and background areas therein; inputting a first image obtained by an external imaging device into a preset feature extraction network to determine the first CTC system template image corresponding to the first image; based on the first CTC system template image, performing perspective transformation and chromaticity value adjustment on the first image to obtain a second image; determining the positions and displayed chromaticity values of the signal lights to be monitored in the second image, and adjusting the chromaticity values of the signal lights to be monitored in the first CTC system template image based on the displayed chromaticity values to obtain a second CTC system template image. The present application removes interference such as reflection and shadow existing in the CTC system captured images through the above method.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and particularly to a method, device, and storage medium for removing interference from CTC system captured images. Background Art

[0002] The Centralized Traffic Control (CTC) system is a remote control and telemetry system in which the dispatching center of a railway administration centrally controls signal equipment within a certain dispatching section, directly commands and manages train operations. The display interface of the CTC system is provided with signal lights for displaying relevant information, including signal lights for routes, signal machine status, train number tracking, etc.

[0003] Railway shunting accidents occur frequently, and the main reason is the manual misjudgment of the information on the CTC system display interface by dispatchers. In addition, due to the particularity of the relevant information of the railway system, its system data needs to be strictly confidential and no external interface can be set up externally. Therefore, analyzing the captured images of the CTC system obtained by external imaging devices has become the direction for people to solve this problem.

[0004] However, due to different shooting environments, the captured images of the CTC system obtained by external imaging will change the color information of the CTC system display interface due to interference such as reflection or shadow, thus affecting the recognition of the signal lights included in the CTC system display interface. Therefore, how to remove the interference in the captured images of the CTC system has become an urgent problem to be solved by people. Summary of the Invention

[0005] Embodiments of this application provide a method, device, and storage medium for removing interference from CTC system captured images, so as to solve the technical problem that existing CTC system captured images have interference such as reflection and shadow.

[0006] In a first aspect, embodiments of this application provide a method for removing interference from CTC system captured images, which is characterized in that the method includes: obtaining a plurality of CTC system template images of the CTC system, and marking the positions of the signal lights to be monitored and the background areas in the CTC system template images; inputting a first image obtained by an external imaging device into a preset feature extraction network to determine the first CTC system template image corresponding to the first image; based on the first CTC system template image and a preset image processing network, performing perspective transformation on the first image and adjusting the chromaticity value of the first image to obtain a second image; determining the positions and displayed chromaticity values of the signal lights to be monitored in the second image, and adjusting the chromaticity values of the signal lights to be monitored in the first CTC system template image based on the displayed chromaticity values to obtain a second CTC system template image.

[0007] A method for removing interference from a captured image of a CTC system provided by an embodiment of the present application first processes the obtained CTC system template image so that the signal lights to be detected and the background area in the CTC system template image can be marked. In the case where interference removal is required for the captured image, the CTC system template image corresponding to the captured image is determined according to the feature extraction network. Then, perspective transformation and chromaticity value adjustment are performed on the captured image according to the corresponding CTC system template image so that the captured image can remove interference. Finally, to avoid the influence of the detail differences between captured images on the analysis efficiency of the captured images, based on the marking of the signal lights to be detected in the CTC system template image, the captured image is compared with the CTC system template image to determine the position of the signal lights to be monitored in the captured image. Then, the chromaticity value of the signal lights is extracted, and based on this chromaticity value, the chromaticity value of the corresponding signal lights to be monitored on the CTC system template image is changed so that the obtained image can be the same as the CTC system template image in other details except for the different signal light colors, thereby avoiding interference in the captured image.

[0008] In an implementation manner of the present application, based on the first CTC system template image and a preset image processing network, perspective transformation is performed on the first image, which specifically includes: the image processing network determines the image edge features of the first CTC system template image, and based on the image edge features, determines the image area to be transformed corresponding to the first CTC system template image in the first image; the image area to be transformed is intercepted in the first image, and perspective transformation is performed on the image area to be transformed to obtain a perspective transformation image with the same size as the first CTC system template image and the same feature display position.

[0009] In an implementation manner of the present application, chromaticity value adjustment is performed on the first image to obtain a second image, which specifically includes: the image processing network divides the perspective transformation image into several image fragments, and based on the background area marked in the first CTC system template image, determines the average background chromaticity value of the image fragments corresponding to the background area; determines the difference between the average background chromaticity value and the standard background chromaticity value, and adjusts the chromaticity value of the corresponding image fragments based on the difference; where the standard background chromaticity value is the background chromaticity value corresponding to the background area marked in the first CTC system template image; the several image fragments that have undergone chromaticity value adjustment processing are spliced to obtain a second image.

[0010] In one implementation of the present application, splicing processing is performed on a plurality of image fragments that have undergone chromaticity value adjustment processing, specifically including: determining the chromaticity value of the first edge to be spliced of the first image fragment and determining the chromaticity value of the second edge to be spliced of the second image fragment; wherein, the first edge to be spliced and the second edge to be spliced are the edges of two image fragments to be spliced together; based on the chromaticity value of the first edge to be spliced and a preset weighted value gradient, within a preset fusion size, performing weighted fusion of the chromaticity value on the second edge to be spliced; wherein, the weighted value gradient is a set of weighted values in which the weighted value gradually decreases from the edge to the middle within a preset fusion size; and, based on the chromaticity value of the second edge to be spliced and a preset weighted value gradient, within a preset fusion size, performing weighted fusion of the chromaticity value on the first edge to be spliced; connecting the first edge to be spliced and the second edge to be spliced that have undergone chromaticity value weighted fusion.

[0011] In one implementation of the present application, determining the position and display chromaticity value of the signal lamp to be monitored in the second image, and adjusting the chromaticity value of the signal lamp to be monitored in the first CTC system template map based on the display chromaticity value, specifically including: based on the position of the signal lamp to be monitored marked in the first CTC system template map, comparing the first CTC system template map with the second image to determine the position of the signal lamp to be monitored in the second image, and extracting the display chromaticity value of the signal lamp to be monitored in the second image; adjusting the chromaticity value of the signal lamp to be monitored in the first CTC system template map to the corresponding display chromaticity value.

[0012] In one implementation of the present application, marking the position and background area of the signal lamp to be monitored in the CTC system template map, specifically including: determining the feature element in the CTC system template map that matches the feature model of the signal lamp to be monitored, and determining the feature element as the area of the signal lamp to be monitored; wherein, the feature model of the signal lamp to be monitored includes the chromaticity value distribution law of the signal lamp to be monitored; and, based on the preset background area chromaticity value, determining the background area in the CTC system template map.

[0013] In one implementation of the present application, obtaining a plurality of CTC system template maps of the CTC system, specifically including: obtaining a plurality of CTC system template maps of the CTC system based on a CTC system experimental machine; storing the plurality of CTC system template maps in a preset sample database.

[0014] In one implementation of the present application, before inputting the first image obtained by an external imaging device into a preset feature extraction network, the method further includes: training a preset feature extraction algorithm based on a plurality of sample pictures stored in the sample database to obtain a converged feature extraction model; wherein, the sample pictures are CTC system pictures taken by the external imaging device under different shooting environments.

[0015] Second aspect, the embodiments of the present application further provide an interference removal device for the captured images of the CTC system, characterized in that the device includes: a processor; and a memory storing executable code thereon, which when executed, causes the processor to execute a method according to any one of claims 1-8.

[0016] Third aspect, the embodiments of the present application further provide a non-volatile computer storage medium for interference removal of the captured images of the CTC system, storing computer-executable instructions, characterized in that the computer-executable instructions are set as follows: obtaining a plurality of CTC system template images of the CTC system, and marking the positions and background areas of the signal lights to be monitored in the CTC system template images; inputting the first image obtained by an external imaging device into a preset feature extraction network to determine the first CTC system template image corresponding to the first image; based on the first CTC system template image and a preset image processing network, performing perspective transformation on the first image and adjusting the chromaticity value of the first image to obtain a second image; determining the position and display chromaticity value of the signal lights to be monitored in the second image, and adjusting the chromaticity value of the signal lights to be monitored in the first CTC system template image based on the display chromaticity value to obtain a second CTC system template image. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The schematic embodiments and descriptions thereof of the present application are used to explain the present application and do not constitute an improper limitation to the present application. In the drawings:

[0018] Figure 1 is a flowchart of an interference removal method for the captured images of the CTC system provided by the embodiments of the present application;

[0019] Figure 2 is a CTC system template image provided by the embodiments of the present application;

[0020] Figure 3 is a schematic internal structure diagram of an interference removal device for the captured images of the CTC system provided by the embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To make the objectives, technical solutions, and advantages of the present application clearer, the technical solutions of the present application will be clearly and completely described below in conjunction with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0022] The embodiments of the present application provide a method, device, and storage medium for removing interference from CTC system captured images, aiming to solve the technical problem of interference such as reflection and shadow existing in the existing CTC system captured images.

[0023] The following details the technical solutions proposed in the embodiments of the present application with the help of the accompanying drawings.

[0024] Figure 1 It is a flowchart of a method for removing interference from CTC system captured images provided by the embodiments of the present application. As Figure 1 shown, a method for removing interference from CTC system captured images provided by the embodiments of the present application specifically includes the following steps:

[0025] Step 101: Obtain a number of CTC system template images of the CTC system, and mark the positions of the signal lights to be monitored and the background areas in the CTC system template images.

[0026] It should be noted that the CTC system template images can be obtained based on a CTC system experimental machine. Among them, the CTC system template images can display the train route, signal status, etc., and their display forms are distinguished by the on / off and colors of the signal lights.

[0027] Figure 2 It is a CTC system template image provided by the embodiments of the present application. As Figure 2 shown, it shows the track distribution of the corresponding station in this image, and on the CTC system display interface, the train's corresponding route, status, trigger mode, etc. are represented by the on / off and corresponding colors of the signal lights.

[0028] In an embodiment of the present application, after obtaining a number of CTC system template images of the CTC system based on the CTC system experimental machine, store the number of CTC system template images in a preset sample database.

[0029] In an embodiment of the present application, after storing the CTC system template images in a preset sample database, first perform matching in the CTC system template images based on the feature model of the signal light to be monitored to find feature elements that are the same as the feature model of the signal light to be monitored; among them, the feature model of the signal light to be monitored includes the chromaticity value distribution law of the signal light to be monitored. In the case where it is determined that there are feature elements in the CTC system template images that are the same as the feature model of the signal light to be monitored, determine this feature element in the CTC system template image as the area of the signal light to be monitored, and mark this area of the signal light to be monitored. In addition, determine the continuous area with the chromaticity value of the preset background area chromaticity value in the CTC system template image as the background area in the CTC system template image; among them, the continuous area is an area where the chromaticity values of a certain pixel point and the pixel points in its preset range of neighboring areas are all a certain same chromaticity value.

[0030] It should be noted that the method for confirming the chromaticity value is not limited in the embodiments of the present application, and can be determined based on any existing technical means for confirming the chromaticity value.

[0031] Step 102: Input the first image obtained by the external imaging device into a preset feature extraction network to determine the first CTC system template image corresponding to the first image.

[0032] In an embodiment of the present application, the sample database is not only used to store the CTC system template image, but also used to store sample pictures. The sample pictures are the CTC system pictures obtained by the external imaging device under different shooting environments. After storing the sample pictures in the sample database, based on the sample pictures, a preset feature extraction algorithm is trained to obtain a converged feature extraction network. The converged feature extraction network can accurately determine the CTC system template image corresponding to the input sample picture.

[0033] In an embodiment of the present application, when it is necessary to remove interference from the first image obtained by the external imaging device, the first image obtained by the external imaging device is input into the trained and converged feature extraction network to determine the first CTC system template image corresponding to the first image.

[0034] Step 103: Based on the first CTC system template image and a preset image processing network, perform perspective transformation on the first image and adjust the chromaticity value of the first image to obtain a second image.

[0035] In an embodiment of the present application, after determining the first CTC system template image corresponding to the first image based on the feature extraction network, first perform perspective transformation on the first image through a preset image processing network to make the CTC system information included in the first image the same as that in the first CTC system template image, that is, after performing perspective transformation on the first image, make the obtained perspective transformation image have the same size as the first CTC system template image, and the features in the perspective transformation image are displayed at the same positions as the corresponding features in the first CTC system template image, so that the perspective transformation image and the first CTC system template image are convenient for comparison.

[0036] Specifically, the image processing network first analyzes the first CTC system template image to determine the image edge features and the size of the first CTC system template image. Then, based on the obtained image edge features of the first CTC system template image, feature elements identical to the image edge features are determined in the first image, thereby determining the corresponding image region to be transformed in the first image. After determining the image region to be transformed in the first image, the image region to be transformed is intercepted, and then, the image region to be transformed is subjected to perspective transformation so that the image region to be transformed is transformed into a perspective transformation image identical to the CTC system information included in the first CTC system template image.

[0037] In an embodiment of the present application, after the image processing network obtains the perspective transformation image corresponding to the first image based on the first CTC system template image, the chromaticity value of the perspective transformation image corresponding to the first image is adjusted to obtain a second image free of interference.

[0038] Specifically, based on a preset segmentation rule, the image processing network first performs segmentation processing on the obtained perspective transformation image corresponding to the first image to obtain a plurality of image fragments corresponding to the perspective transformation image; wherein, the segmentation rule may be to equally divide the perspective transformation image based on a preset segmentation size, or to segment the perspective transformation image based on a preset segmentation region, which is not limited in the embodiments of the present application. To avoid segmenting the signal lights to be monitored in the perspective transformation image, therefore, preferably, the perspective transformation image is segmented based on a preset segmentation region, and the embodiments of the present application also take the segmentation of the perspective transformation image based on a preset segmentation region as an example for illustration.

[0039] It should be noted that the preset segmentation region may be pre-annotated in the first CTC system template image. Since the first CTC system template image has the same size and the same feature display position as the perspective transformation image, when the perspective transformation image needs to be segmented, the segmentation region annotated in the first CTC system template image can be directly copied to the perspective transformation image, and then the perspective transformation image is segmented. To avoid uneven distribution of interference in the same image fragment and affect the interference removal effect, therefore, the sizes of the image fragments should be as small as possible. In addition, in the embodiments of the present application, the background part in the image region is used as the chromaticity value reference, so each image fragment should include a part of the background region.

[0040] In one embodiment of the present application, after segmenting the perspective transformation image, first, based on the background region marked in the first CTC system template image, the corresponding background region is determined in each image fragment, and the average background chromaticity value of the corresponding background region is determined. Then, the difference between the average background chromaticity value of each image fragment and the standard background chromaticity value is calculated to obtain the difference value; wherein, the standard background chromaticity value is the chromaticity value of the background region corresponding to the background region marked in the first CTC system template image. After determining the difference between the average background chromaticity value of each image fragment and the standard background chromaticity value, the chromaticity value of the corresponding image fragment is adjusted based on each difference value so that each image fragment can obtain the corresponding chromaticity value after removing interference.

[0041] In one embodiment of the present application, after the chromaticity value adjustment process of each image fragment, the image fragments are stitched together to obtain a second image. Since the chromaticity values between the image fragments are no longer continuous after the chromaticity value adjustment process of each image fragment, when stitching the image fragments, the image fragments cannot be directly stitched simply.

[0042] Specifically, taking two image fragments as an example, they are respectively named the first image fragment and the second image fragment. First, the chromaticity value of the first edge to be stitched of the first image fragment and the chromaticity value of the second edge to be stitched of the second image fragment are determined; wherein, the first edge to be stitched and the second edge to be stitched are the edges of the two image fragments to be stitched together; based on the chromaticity value of the first edge to be stitched and the preset weighted value gradient, within the preset fusion size, the chromaticity value of the second edge to be stitched is weighted and fused; wherein, the weighted value gradient is a set of weighted values in which the weighted value gradually decreases from the edge to the middle within the preset fusion size; and, based on the chromaticity value of the second edge to be stitched and the preset weighted value gradient, within the preset fusion size, the chromaticity value of the first edge to be stitched is weighted and fused; the first edge to be stitched and the second edge to be stitched after chromaticity value weighted fusion are connected. All the edges to be stitched of all the image fragments are traversed so that all the stitching edges can be stitched according to the above method, thereby obtaining the second image.

[0043] Step 104: Determine the position and display chromaticity value of the signal lamp to be monitored in the second image, and adjust the chromaticity value of the signal lamp to be monitored in the first CTC system template image based on the display chromaticity value to obtain a second CTC system template image.

[0044] In one embodiment of the present application, to avoid the detailed differences between captured images from affecting the analysis efficiency of the captured images, after performing perspective transformation and chromaticity value adjustment on the first image based on the first CTC system template image and a preset image processing network to obtain a second image, the position of the signal lamp to be monitored marked in the first CTC system template image is first used to compare the first CTC system template image with the second image to determine the position of the signal lamp to be monitored in the second image. Then, the displayed chromaticity value of the signal lamp to be monitored in the second image is extracted, and the chromaticity value of the signal lamp to be monitored in the first CTC system template image is adjusted to the corresponding displayed chromaticity value to obtain a second CTC system template image that is free of interference and has the same other details as the first CTC system template image except for the signal lamp color, thereby avoiding the interference in the captured images.

[0045] Based on the same inventive concept, an embodiment of the present application also provides a device for removing interference from CTC system captured images, and its internal structure is as Figure 3 shown.

[0046] Figure 3 It is a schematic diagram of the internal structure of a device for removing interference from CTC system captured images provided by an embodiment of the present application. As Figure 3 shown, the device includes: a processor 301; a memory 302, on which executable instructions are stored. When the executable instructions are executed, the processor 301 is caused to execute a method for removing interference from CTC system captured images as described above.

[0047] In one embodiment of the present application, the processor 301 is configured to obtain a plurality of CTC system template images of the CTC system, and mark the positions of the signal lamps to be monitored and the background areas in the CTC system template images; input the first image obtained by an external imaging device into a preset feature extraction network to determine the first CTC system template image corresponding to the first image; perform perspective transformation on the first image and adjust the chromaticity value of the first image based on the first CTC system template image and a preset image processing network to obtain a second image; determine the position and the displayed chromaticity value of the signal lamp to be monitored in the second image, and adjust the chromaticity value of the signal lamp to be monitored in the first CTC system template image based on the displayed chromaticity value to obtain a second CTC system template image.

[0048] Some embodiments of the present application provide a non-volatile computer storage medium corresponding to Figure 1 for removing interference from CTC system captured images, storing computer-executable instructions, and the computer-executable instructions are set to:

[0049] Obtain a plurality of CTC system template images of the CTC system, and mark the positions of the signal lamps to be monitored and the background areas in the CTC system template images;

[0050] Input the first image obtained by an external imaging device into a preset feature extraction network to determine the first CTC system template image corresponding to the first image;

[0051] Based on the first CTC system template image and a preset image processing network, perform perspective transformation on the first image and adjust the chromaticity value of the first image to obtain a second image;

[0052] Determine the position and display chromaticity value of the signal lamp to be monitored in the second image, and adjust the chromaticity value of the signal lamp to be monitored in the first CTC system template image based on the display chromaticity value to obtain a second CTC system template image.

[0053] Each embodiment in this application is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. The key point of each embodiment is to illustrate the differences from other embodiments. In particular, for the embodiments of the Internet of Things devices and media, since they are basically similar to the method embodiments, the description is relatively simple, and for the relevant parts, reference can be made to the partial description of the method embodiments.

[0054] The systems and media provided by the embodiments of this application correspond one-to-one with the methods. Therefore, the systems and media also have beneficial technical effects similar to those of the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be elaborated here.

[0055] Those skilled in the art should understand that the embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0056] This application is described with reference to the flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the embodiments of this application. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as the combination of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to the processors of general-purpose computers, special-purpose computers, embedded processors, or other programmable data processing devices to generate a machine, such that the instructions executed by the processors of the computer or other programmable data processing devices generate means for implementing the functions specified in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0057] These computer program instructions can also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to operate in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including an instruction means that implements the functions specified in one or more of the processes and / or blocks Figure 1 of one or more of the processes and / or blocks Figure 1 specified in one or more of the processes and / or blocks

[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, whereby the instructions executed on the computer or other programmable apparatus provide steps for implementing the functions specified in one or more of the processes and / or blocks Figure 1 of one or more of the processes and / or blocks Figure 1 specified in one or more of the processes and / or blocks

[0059] In a typical configuration, a computing device includes one or more processors (CPUs), an input / output interface, a network interface, and memory.

[0060] The memory may include non-permanent memory in the form of computer-readable media, random access memory (RAM) and / or non-volatile memory such as read-only memory (ROM) or flash memory (flash RAM). Memory is an example of computer-readable media.

[0061] Computer-readable media includes both permanent and non-permanent, removable and non-removable media implemented by any method or technology for storing information. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile discs (DVD) or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include transitory media such as modulated data signals and carrier waves.

[0062] It should also be noted that the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, such that a process, method, commodity or device comprising a series of elements not only includes those elements but also includes other elements not expressly listed, or further includes elements inherent to such process, method, commodity or device. Without further limitation, an element defined by the phrase "comprising an..." does not exclude the presence of additional identical elements in the process, method, commodity or device comprising said element.

[0063] The above description is only for the embodiments of the present application and is not intended to limit the present application. For those skilled in the art, various modifications and changes can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A method for removing interference from the captured images of a CTC system, characterized in that, The method includes: Obtaining a plurality of CTC system template diagrams of the CTC system, and annotating the positions and background regions of the signal lights to be monitored in the CTC system template diagrams; Inputting a first image obtained by an external imaging device into a preset feature extraction network to determine the first CTC system template diagram corresponding to the first image; Based on the first CTC system template diagram and a preset image processing network, performing perspective transformation on the first image and adjusting the chromaticity value of the first image to obtain a second image; Determining the positions and displayed chromaticity values of the signal lights to be monitored in the second image, and adjusting the chromaticity values of the signal lights to be monitored in the first CTC system template diagram based on the displayed chromaticity values to obtain a second CTC system template diagram; Performing perspective transformation on the first image based on the first CTC system template diagram and a preset image processing network, specifically including: The image processing network determines the image edge features of the first CTC system template diagram, and based on the image edge features, determines the image region to be transformed corresponding to the first CTC system template diagram in the first image; Intercepting the image region to be transformed in the first image, and performing perspective transformation on the image region to be transformed to obtain a perspective transformation image with the same size and the same feature display position as the first CTC system template diagram; Adjusting the chromaticity value of the first image to obtain a second image, specifically including: The image processing network divides the perspective transformation image into a plurality of image fragments, and determines the average background chromaticity value of the image fragments corresponding to the background region based on the background region annotated in the first CTC system template diagram; Determining the difference between the average background chromaticity value and the standard background chromaticity value, and adjusting the chromaticity value of the corresponding image fragment based on the difference; wherein, the standard background chromaticity value is the background chromaticity value corresponding to the background region annotated in the first CTC system template diagram; Performing splicing processing on the plurality of image fragments that have undergone chromaticity value adjustment processing to obtain a second image.

2. The interference elimination method for the CTC system captured image according to claim 1, characterized in that, Performing splicing processing on the plurality of image fragments that have undergone chromaticity value adjustment processing, specifically including: Determining the chromaticity value of the first edge to be spliced of the first image fragment and determining the chromaticity value of the second edge to be spliced of the second image fragment; wherein, the first edge to be spliced and the second edge to be spliced are the edges of two image fragments to be spliced together; Based on the chromaticity value of the first edge to be spliced and a preset weighted value gradient, performing weighted fusion of the chromaticity value on the second edge to be spliced within a preset fusion size; wherein, the weighted value gradient is a set of weighted values in which the weighted value gradually decreases from the edge to the middle within a preset fusion size; and, Based on the chromaticity value of the second edge to be spliced and a preset weighted value gradient, performing weighted fusion of the chromaticity value on the first edge to be spliced within a preset fusion size; Connecting the first edge to be spliced and the second edge to be spliced that have undergone chromaticity value weighted fusion.

3. The interference removal method for the CTC system captured image according to claim 1, characterized in that, Determine the position and display chromaticity value of the signal lamp to be monitored in the second image, and adjust the chromaticity value of the signal lamp to be monitored in the first CTC system template map based on the display chromaticity value, which specifically includes: Based on the position of the signal lamp to be monitored marked in the first CTC system template map, compare the first CTC system template map with the second image to determine the position of the signal lamp to be monitored in the second image, and extract the display chromaticity value of the signal lamp to be monitored in the second image; Adjust the chromaticity value of the signal lamp to be monitored in the first CTC system template map to the corresponding display chromaticity value.

4. A method for removing interference from a CTC system captured image according to claim 1, characterized in that, Mark the position and background area of the signal lamp to be monitored in the CTC system template map, which specifically includes: Determine the feature element in the CTC system template map that matches the preset feature model of the signal lamp to be monitored, and determine that the feature element is the area of the signal lamp to be monitored; wherein, the feature model of the signal lamp to be monitored includes the chromaticity value distribution law of the signal lamp to be monitored; and, Based on the preset background area chromaticity value, determine the background area in the CTC system template map.

5. A method for removing interference from a captured image of a CTC system according to claim 1, characterized in that, The obtaining of several CTC system template maps of the CTC system specifically includes: Obtain several CTC system template maps of the CTC system based on the CTC system experimental machine; Store the several CTC system template maps in a preset sample database.

6. The interference removal method for the CTC system captured image according to claim 1, characterized in that Before inputting the first image obtained by the external imaging device into the preset feature extraction network, the method further includes: Train the preset feature extraction algorithm based on several sample pictures stored in the sample database to obtain a converged feature extraction model; wherein, the sample pictures are CTC system pictures obtained by the external imaging device under different shooting environments.

7. An interference removal device for a CTC system captured image, characterized in that, The device includes: A processor; And a memory, on which executable code is stored, and when the executable code is executed, the processor executes a method according to any one of claims 1-6.

8. A non-volatile computer storage medium for removing interference from CTC system captured images, storing computer-executable instructions, characterized in that, The computer executable instructions are set to: Obtain several CTC system template maps of the CTC system, and mark the position and background area of the signal lamp to be monitored in the CTC system template map; Input the first image obtained by the external imaging device into the preset feature extraction network to determine the first CTC system template map corresponding to the first image; Based on the first CTC system template map and the preset image processing network, perform perspective transformation on the first image, and perform chromaticity value adjustment on the first image to obtain a second image; Determine the position and display chromaticity value of the signal lamp to be monitored in the second image, and adjust the chromaticity value of the signal lamp to be monitored in the first CTC system template map based on the display chromaticity value to obtain a second CTC system template map; Based on the first CTC system template map and the preset image processing network, perform perspective transformation on the first image, which specifically includes: The image processing network determines the image edge features of the first CTC system template image, and based on the image edge features, determines the image region to be transformed corresponding to the first CTC system template image in the first image; Crop the image region to be transformed in the first image, and perform a perspective transformation on the image region to be transformed to obtain a perspective transformation image with the same size as the first CTC system template image and the same feature display position; Adjust the chromaticity value of the first image to obtain a second image, specifically including: The image processing network divides the perspective transformation image into several image fragments, and based on the background region marked in the first CTC system template image, determines the average background chromaticity value of the image fragments corresponding to the background region; Determine the difference between the average background chromaticity value and the standard background chromaticity value, and adjust the chromaticity value of the corresponding image fragment based on the difference; wherein, the standard background chromaticity value is the background chromaticity value corresponding to the background region marked in the first CTC system template image; Perform a splicing process on the several image fragments that have undergone chromaticity value adjustment processing to obtain a second image.

Images