A stacked screen information collection method, device and medium

Abstract

The present application discloses a method, device, and medium for collecting information on overlapping screens. The method includes: collecting information displayed on a screen through a camera matrix to obtain several partial images corresponding to the screen; in the case of the information displayed on the screen corresponding to a railway dispatching centralized control system, obtaining a standard image corresponding to the screen, and obtaining the coordinate information of the indicator lights on the screen through the standard image; determining the relative position relationship of each camera in the camera matrix, and selecting a designated indicator light as a reference point within a preset edge area of ​​several partial images; splicing the several partial images according to the relative position relationship and the coordinate information of the reference point to obtain a spliced ​​image, and monitoring the operating status of the railway dispatching centralized control system through the spliced ​​image. The method achieves the acquisition of the display content of the screen to be collected without accessing the system.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method, device and medium for collecting overlapping screen information. Background Art

[0002] In some areas, workers are required to constantly monitor various data displayed on display screens to prevent accidents. This not only consumes workers' energy but can also lead to errors due to carelessness. Therefore, it's necessary to connect to external systems to obtain various data displayed on the display screens, thereby replacing the human workers in monitoring different operations. However, due to high reliability requirements, some systems, such as the railway CTC centralized dispatching control system, do not allow external systems to access the system. Therefore, external systems cannot directly access internal system information, such as screen content. Therefore, they cannot directly obtain the real-time images displayed on the display screens.

[0003] Therefore, there is an urgent need for an information collection method that requires less computation and enables staff to obtain screen display content in real time. Summary of the Invention

[0004] In order to solve the above problems, the present application proposes a stacked screen information collection method, which is applied to a stacked screen information collection device, wherein the stacked screen information collection device is detachably arranged on the outside of the screen, and a camera matrix is ​​provided on the side of the stacked screen information collection device facing the screen; the method includes: collecting information displayed on the screen through the camera matrix to obtain several local images corresponding to the screen; in the information displayed on the screen, when corresponding to a railway dispatching centralized control system, obtaining a standard image corresponding to the screen, and obtaining the coordinate information of the indicator light in the screen through the standard image; determining the relative position relationship of each camera in the camera matrix, and selecting a designated indicator light as a reference point in the preset edge area of ​​the several local images; splicing the several local images according to the relative position relationship and the coordinate information of the reference point to obtain a spliced ​​image, and monitoring the operating status of the railway dispatching centralized control system through the spliced ​​image.

[0005] In one example, before collecting the information displayed on the screen through the camera matrix, the method also includes: collecting abnormal states that have occurred in the history of the railway dispatching centralized control system, and the distribution probability in the standard image corresponding to the screen; determining the display area corresponding to the abnormal state, and determining the camera corresponding to the display area in the camera matrix; according to the distribution probability, setting the collection frequency of the corresponding camera when collecting the information displayed on the screen, and the collection frequency is positively correlated with the distribution probability.

[0006] In one example, after setting the acquisition frequency of the corresponding camera when collecting information displayed on the screen according to the distribution probability, the method also includes: when it is determined that the acquisition frequency is lower than a first preset threshold, judging whether the abnormal state is displayed on the screen by a specified flashing state; if so, determining the flashing cycle of the specified flashing state; determining the minimum acquisition frequency according to the flashing cycle and the preset single-cycle acquisition number; if the set acquisition frequency is lower than the minimum acquisition frequency, adjusting the set acquisition frequency to the minimum acquisition frequency.

[0007] In one example, the display area includes multiple sub-areas, and different sub-areas correspond to different cameras in the camera matrix; according to the distribution probability, the collection frequency of the corresponding camera when collecting information displayed on the screen is set, specifically including: when the distribution probability is lower than a second preset threshold, determining the dependency relationship between the multiple sub-areas in the abnormal state; according to the dependency relationship, setting the collection frequency of the camera corresponding to the first sub-area to 0, and the first sub-area depends on the second sub-area; if it is determined that the abnormal state occurs in the second sub-area, starting the camera corresponding to the first sub-area and setting it to have the same collection frequency as the camera corresponding to the second sub-area.

[0008] In one example, the several local images are stitched together according to the relative position relationship and the coordinate information of the reference point to obtain a stitched image, which specifically includes: determining the initial stitching positions of the several local images according to the relative position relationship of the cameras; determining multiple local images corresponding to the reference point, and adjusting the initial stitching positions of the several local images according to the coordinate information of the reference point to make the corresponding reference points in the several local images overlap to obtain a stitched image.

[0009] In one example, after stitching the several partial images according to the relative position relationship and the coordinate information of the reference point to obtain a stitched image, the method further includes: determining the image completeness of the stitched image by comparing the stitched image with the standard image; determining the position information of the image missing portion in the stitched image according to the image completeness; and adjusting the camera focal length within a preset range near the image missing portion according to the position information corresponding to the image missing portion to obtain a partial image of the image missing portion.

[0010] In one example, after the several local images are stitched together according to the relative position relationship and the coordinate information of the reference point to obtain a stitched image, the method further includes: determining a preset initial judgment model, and training the initial judgment model through the stitched image to obtain a judgment model; determining the abnormal area corresponding to the abnormal state of the indicator light change in the stitched image through the judgment model; and highlighting the abnormal area in the stitched image.

[0011] In one example, the stacked screen acquisition device also includes: a light-shielding shell, which is arranged outside the camera matrix and is used to block external light sources to eliminate the influence of the external light sources on the camera matrix; a display screen, which is arranged on the side of the camera matrix away from the screen and is used to display the spliced ​​image.

[0012] In one example, before the information displayed on the screen is collected through the camera matrix, the method also includes: displaying an equally divided radial radius picture of an equidistant concentric regular figure on the screen, and adjusting the equidistant distance and the radial radius angle of the picture so that each camera in the camera matrix can capture at least one of the complete quadrilaterals; through the quadrilateral, determining the specific position information of the picture captured by the camera on the screen to obtain the stitching parameters of the several local images obtained by the camera matrix.

[0013] The present application also provides a stacked screen information acquisition device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute: collecting the information displayed on the screen through a camera matrix, and obtaining several local images corresponding to the screen; in the information displayed on the screen, when corresponding to a railway dispatching centralized control system, obtaining a standard image corresponding to the screen, and obtaining the coordinate information of the indicator light in the screen through the standard image; determining the relative position relationship of each camera in the camera matrix, and selecting a designated indicator light as a reference point in the preset edge area of ​​the several local images; splicing the several local images according to the relative position relationship and the coordinate information of the reference point to obtain a spliced ​​image, and monitoring the operating status of the railway dispatching centralized control system through the spliced ​​image.

[0014] The present application also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to: collect information displayed on the screen through a camera matrix to obtain several local images corresponding to the screen; in the information displayed on the screen, if it corresponds to a railway dispatching centralized control system, obtain a standard image corresponding to the screen, and obtain the coordinate information of the indicator light on the screen through the standard image; determine the relative position relationship of each camera in the camera matrix, and select a designated indicator light as a reference point within a preset edge area of ​​the several local images; splice the several local images according to the relative position relationship and the coordinate information of the reference point to obtain a spliced ​​image, and monitor the operating status of the railway dispatching centralized control system through the spliced ​​image.

[0015] The stacked screen information acquisition method proposed in this application can obtain partial images of the screen through a camera matrix composed of multiple cameras, and then stitch the partial images together to obtain the display image of the screen. This achieves the acquisition of the display content of the screen to be captured without accessing the system. At the same time, the spliced ​​image can be modified or new information can be superimposed on it before it is displayed on the display screen, thereby assisting staff in supervising the screen. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0017] Figure 1 This is a schematic diagram of a method for collecting overlapping screen information in an embodiment of the present application;

[0018] Figure 2 This is a schematic diagram of an equally spaced concentric circle with equally divided radiation radius in an embodiment of the present application;

[0019] Figure 3 This is a schematic diagram of a stacked screen information collection device in an embodiment of the present application. DETAILED DESCRIPTION

[0020] To make the purpose, technical solutions, and advantages of this application more clear, the technical solutions of this application will be clearly and completely described below in conjunction with the specific embodiments of this application and the corresponding drawings. Obviously, the embodiments described are only part of the embodiments of this application, not all of them. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0021] Figure 1This is a flowchart of a method for collecting overlapping screen information provided in one or more embodiments of this specification. The process can be executed by a computing device in the corresponding field, and some input parameters or intermediate results in the process can be manually adjusted to help improve accuracy.

[0022] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For ease of understanding and description, the following embodiments are described in detail using a server as an example.

[0023] It should be noted that the server can be a single device or a system composed of multiple devices, that is, a distributed server, and this application does not make any specific restrictions on this.

[0024] The following describes in detail the technical solutions provided by various embodiments of the present application in conjunction with the accompanying drawings.

[0025] like Figure 1 As shown, an embodiment of the present application provides a stacked screen information collection method, which is applied to a stacked screen information collection device, wherein the stacked screen information collection device is detachably arranged on the outside of the screen, where the screen refers to the screen on which the display content needs to be collected. The stacked screen information collection device is provided with a camera matrix on the side facing the screen, where the camera matrix includes a certain number of cameras, and the position and number of the cameras are set in advance according to the screen size. The stacked screen information collection method includes:

[0026] S101: Collect information displayed on the screen through the camera matrix to obtain several local images corresponding to the screen.

[0027] To obtain the screen's display content, the screen display information must first be collected through a camera matrix. This means that the screen is photographed by the cameras in the matrix to obtain several partial images of the screen. These partial images will then be stitched together during the subsequent stitching process. It should be noted that after the cameras capture the screen, some raw images of the screen are obtained. These images first undergo various processing steps to obtain several partial images of the screen, which may include processing for image distortion and defocus.

[0028] S102: In the case where the information displayed on the screen corresponds to a railway dispatching centralized control system, a standard image corresponding to the screen is obtained, and coordinate information of indicator lights on the screen is obtained through the standard image.

[0029] After obtaining several partial images of the screen, in order to ensure the accuracy of the image stitching in the subsequent stitching process, it is necessary to find some reference points in each partial image. If the information displayed on the screen corresponds to the railway dispatching centralized control system, that is, when the screen is under the control of the railway dispatching centralized control system, since the railway dispatching centralized control system, the screen display content is mostly a solid color background, and the background accounts for a very high proportion. It also contains a certain number of indicator lights to display the railway dispatching status. When the indicator light's indication state changes, it means that the corresponding railway area of ​​the indicator light has a corresponding problem. This certain number of indicator lights can be used as reference points in the subsequent stitching process. Therefore, it is necessary to obtain the coordinate information of the indicator lights. When obtaining, this can be done through the standard image corresponding to the screen. The standard image here refers to the display image collected by the CTC test software.

[0030] S103: Determine the relative position relationship of each camera in the camera matrix, and select a designated indicator light as a reference point within a preset edge area of ​​the plurality of partial images.

[0031] After obtaining the positional coordinates of each indicator light, since the partial images are captured by several cameras in the camera matrix, the stitching order can be determined by the positional relationship of the cameras in the camera matrix. In other words, the approximate position of the partial images captured by each camera in the stitched image can be directly determined based on the position of each camera in the camera matrix. Knowing the approximate position of the partial images requires selecting appropriate reference points during the stitching process. Therefore, designated indicator lights can be selected as reference points within the preset edge regions of the partial images. Specifically, indicator lights at the edges of each partial image are selected as reference points. It should be noted that since the positions of the cameras are fixed, and the positional information of the indicator lights within the screen is also fixed, reference points only need to be selected once for the fixed stitched image; this set of reference points can be used throughout the subsequent stitching process. Furthermore, since multiple cameras are capturing images of the screen, a single reference point will appear in multiple partial images.

[0032] S104: splicing the plurality of partial images according to the relative position relationship and the coordinate information of the reference point to obtain a spliced ​​image, and monitoring the operating status of the railway dispatching centralized control system through the spliced ​​image.

[0033] Knowing the relative position of the cameras and the coordinates of each reference point allows for stitching of several partial images to create a stitched image. This stitched image allows an external system to monitor the content displayed on the screen on behalf of the operator.

[0034] In one example, when stitching together several partial images based on the relative positional relationship of the cameras and the coordinate information of multiple reference points, the initial stitching positions of the partial images should first be determined based on the relative positional relationship of the cameras. Multiple partial images corresponding to each reference point are then determined, and the initial stitching positions of the partial images are adjusted based on the coordinate information of the reference points to align the corresponding reference points in the partial images to produce a stitched image. Simply stacking the partial images by aligning the reference points eliminates the need to determine the image boundaries for each partial image, thereby saving a significant amount of computational effort.

[0035] In one embodiment, since the importance of the displayed content at different locations on the screen varies in a railway dispatching centralized control system, we hope that the acquisition frequency of the camera corresponding to the more important area will be higher so that the abnormal indication status of the indicator light can be discovered in a timely manner. Therefore, the frequency and location of abnormal states that have occurred in the history of the railway dispatching centralized control system can be collected, and based on the frequency and location of the historical abnormal states, the distribution probability of the expected abnormal state can be determined in each area of ​​the standard image corresponding to the screen; then, the display area corresponding to the abnormal state is determined, and the camera corresponding to the display area in the camera matrix is ​​determined; then, based on the distribution probability, the acquisition frequency of the corresponding camera when collecting the information displayed on the screen is set. Here, the acquisition frequency is positively correlated with the distribution probability, that is, the higher the distribution probability, the more attention the display area needs, and the higher the acquisition frequency of the corresponding camera.

[0036] Furthermore, after setting the acquisition frequency of each camera, since some indicator lights may be in a flashing indication state, it indicates that there is an abnormal state in the area. Therefore, if the acquisition frequency of a camera is too low, it may be impossible to determine the indication state corresponding to the indicator light in the local image corresponding to the camera. Therefore, when it is determined that the acquisition frequency of a camera is lower than the preset threshold, it is determined whether there is an indicator light among the multiple indicator lights corresponding to the camera whose abnormal indication state is a flashing state. If so, the flashing cycle of the indicator light is determined. The flashing cycle here refers to the time from the indicator light ending in the bright state to the next time the indicator light ends. After determining the flashing cycle of the indicator light, the acquisition frequency of the camera is determined based on the preset single-cycle acquisition number. The single-cycle acquisition number here refers to the number of times the camera obtains a local image in one flashing cycle. If the original acquisition frequency of the camera is lower than the re-determined acquisition frequency, the re-determined acquisition frequency is used as the acquisition frequency of the camera.

[0037] In one embodiment, since most of the screen content displayed in a railway dispatching and data collection system is a solid-color background, the indication status of some indicator lights may also depend on the indication status of other indicator lights. Therefore, when monitoring the displayed content on the screen, it is not necessary to monitor the entire screen content. Instead, it is necessary to monitor only the display areas where the indicator lights are most likely to change first, thereby reducing the attention paid to the screen content that depends on these display areas. Therefore, the camera's acquisition frequency when capturing the screen content can be set based on the distribution probability of abnormal states and the dependency relationship. First, the distribution probability of abnormal states in all areas must be determined. If the distribution probability of some areas is below a second preset threshold and there is a dependency relationship between the abnormal state occurrence probability of other sub-areas, the areas where abnormal states occur can be divided into a first area and a second area based on the dependency relationship. The indicator lights in the first sub-area are only likely to be in an abnormal state if the indicator lights in the second sub-area are in an abnormal state. Therefore, the acquisition frequency of the camera corresponding to the first sub-area can be set to 0, that is, the camera corresponding to this area is in a normally closed state. When it is determined that the indicator lights in the second sub-area are in an abnormal state, the camera corresponding to the first sub-area is turned on again, and the acquisition frequency of the camera corresponding to the first sub-area is set to the same as the acquisition frequency of the camera in the second sub-area.

[0038] In one embodiment, after obtaining the stitched image, since there may be a small number of cameras, so that the cameras cannot capture the entire display content on the screen, it is necessary to compare the stitched image with the initially acquired standard image to determine the image integrity of the stitched image. Based on the image integrity, it is determined whether there is an image missing in the stitched image. If there is, the focal length of the camera corresponding to the image missing can be adjusted so that the camera near the image missing can capture the partial image of the image missing.

[0039] In one embodiment, a pre-trained judgment model can be used to determine whether a region within a stitched image exhibits abnormal changes. The training samples can be historical stitched images stored in a database. The judgment model can then be used to determine whether an abnormal region exists within the image to be displayed. Similarly, the presence of an abnormal region can be determined using indicator light change rules input by staff. If an area is determined to be abnormal, it can be highlighted within the stitched image for easier viewing by staff.

[0040] like Figure 2As shown, in one embodiment, since the camera matrix position is fixed, the stitching method for each video frame is exactly the same. Therefore, the parameters that the stitching method relies on can be calibrated once during equipment installation. When the camera matrix is ​​installed, an image of the following equally spaced, concentric regular pattern (using concentric circles as an example) can be displayed on the CTC screen. This image can be displayed directly on the CTC screen using a computer connected to the CTC screen, or it can be projected onto the screen using a projection device. By adjusting the concentric circle radius spacing and the included angle of the radial radius to be sufficiently small, each camera can always capture at least one complete quadrilateral arc. The position of any captured quadrilateral arc, regardless of its size in the image, can be determined within the concentric circle diagram. Any two quadrilateral arcs are either dissimilar in shape or have different orientations. Based on their similarity, the circular ring in which the quadrilateral arc is located can be determined, and based on their orientation, its position within the circular ring can be determined. Based on this characteristic of concentric arcs, we can quickly determine where the camera's image is located in the overall CTC image, and use the vertex coordinates of the captured concentric arcs as the image stitching reference point to quickly calculate the stitching formula parameters of the image obtained by the camera matrix.

[0041] In one embodiment, during operation, there are often other light sources outside the screen to be captured. At this time, other light sources will interfere with the operation of the camera matrix set on the screen, resulting in the possibility of reflections in several partial images obtained. Based on this, a light-shielding shell can be set outside the camera matrix to prevent the camera matrix from being interfered with by external light sources during operation, thereby preventing reflections in partial images. At the same time, due to the presence of the camera matrix and the light-shielding shell, the staff may not be able to see the displayed content on the screen due to the obstruction of the camera matrix. Therefore, a display screen can be set outside the light-shielding shell to display the spliced ​​image, so that the staff can obtain the current displayed content on the screen through the display screen.

[0042] like Figure 3As shown, an embodiment of the present application also provides a signal light status acquisition device within a screen, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: acquire the information displayed on the screen through the camera matrix, and obtain several local images corresponding to the screen; in the information displayed on the screen, when corresponding to a railway dispatching centralized control system, acquire a standard image corresponding to the screen, and acquire the coordinate information of the indicator light within the screen through the standard image; determine the relative position relationship of each camera within the camera matrix, and select a designated indicator light as a reference point within a preset edge area of ​​the several local images; splice the several local images according to the relative position relationship and the coordinate information of the reference point to obtain a spliced ​​image, and monitor the operating status of the railway dispatching centralized control system through the spliced ​​image.

[0043] An embodiment of the present application also provides a non-volatile computer storage medium storing computer-executable instructions, wherein the computer-executable instructions are configured to: collect information displayed on the screen through the camera matrix to obtain several local images corresponding to the screen; in the information displayed on the screen, if it corresponds to a railway dispatching centralized control system, obtain a standard image corresponding to the screen, and obtain the coordinate information of the indicator light on the screen through the standard image; determine the relative position relationship of each camera in the camera matrix, and select a designated indicator light as a reference point within a preset edge area of ​​the several local images; splice the several local images according to the relative position relationship and the coordinate information of the reference point to obtain a spliced ​​image, and monitor the operating status of the railway dispatching centralized control system through the spliced ​​image.

[0044] The various embodiments in this application are described in a progressive manner. Similar portions between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device and medium embodiments are generally similar to the method embodiments, so their descriptions are relatively simple. For relevant portions, refer to the descriptions of the method embodiments.

[0045] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects to their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0046] Those skilled in the art will appreciate that the embodiments of the present application can be provided as methods, systems, or computer program products. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0047] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the steps in the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0048] These computer program instructions may also be stored in a computer readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0049] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0050] In a typical configuration, a computing device includes one or more processors (CPUs), input / output interfaces, network interfaces, and memory.

[0051] Memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0052] Computer-readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. 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 technology, compact disc read-only memory (CD-ROM), digital versatile disc (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 computer-readable media (transit media), such as modulated data signals and carrier waves.

[0053] It should also be noted that the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, commodity, or apparatus that includes a series of elements includes not only those elements but also other elements not explicitly listed, or includes elements inherent to such process, method, commodity, or apparatus. In the absence of further limitations, an element defined by the phrase "comprises a ..." does not exclude the presence of other identical elements in the process, method, commodity, or apparatus that includes the element.

[0054] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A method for collecting overlapping screen information, characterized in that: Applied in a stacked screen information collection device, the stacked screen information collection device is detachably arranged on the outside of the screen, and a camera matrix is ​​arranged on the side of the stacked screen information collection device facing the screen; The method comprises: The information displayed on the screen is collected by the camera matrix to obtain a plurality of local images corresponding to the screen; In the case where the information displayed on the screen corresponds to a railway dispatching centralized control system, a standard image corresponding to the screen is obtained, and coordinate information of indicator lights on the screen is obtained through the standard image; Determining the relative positional relationship of each camera in the camera matrix, and selecting a designated indicator light as a reference point within a preset edge area of ​​the plurality of partial images; splicing the plurality of partial images according to the relative position relationship and the coordinate information of the reference point to obtain a spliced ​​image, and monitoring the operating status of the railway dispatching centralized control system through the spliced ​​image; Before collecting the information displayed on the screen through the camera matrix, the method further includes: Collect the abnormal states that have occurred in the history of the railway dispatching centralized control system and their distribution probability in the standard image corresponding to the screen; Determining a display area corresponding to the abnormal state, and determining a camera corresponding to the display area in the camera matrix; According to the distribution probability, setting a collection frequency of the corresponding camera when collecting information displayed on the screen, wherein the collection frequency is positively correlated with the distribution probability; The display area includes a plurality of sub-areas, and different sub-areas correspond to different cameras in the camera matrix; The setting of the collection frequency of the corresponding camera when collecting information displayed on the screen according to the distribution probability specifically includes: When the distribution probability is lower than a second preset threshold, determining a dependency relationship between the plurality of sub-regions in the abnormal state; According to the dependency relationship, the acquisition frequency of the camera corresponding to the first sub-area is set to 0, and the first sub-area depends on the second sub-area; If it is determined that the abnormal state occurs in the second sub-area, the camera corresponding to the first sub-area is started and set to have the same acquisition frequency as the camera corresponding to the second sub-area.

2. The method according to claim 1, characterized in that After setting the acquisition frequency of the corresponding camera when acquiring information displayed on the screen according to the distribution probability, the method further includes: When it is determined that the acquisition frequency is lower than a first preset threshold, determining whether the abnormal state is displayed on the screen in a manner of displaying the abnormal state in a specified flashing state; If yes, determining the flashing period of the specified flashing state; Determine the minimum acquisition frequency according to the flashing cycle and the preset number of single-cycle acquisitions; If the set acquisition frequency is lower than the minimum acquisition frequency, the set acquisition frequency is adjusted to the minimum acquisition frequency.

3. The method according to claim 1, characterized in that The step of stitching the plurality of partial images according to the relative position relationship and the coordinate information of the reference point to obtain a stitched image specifically includes: Determining initial stitching positions of the plurality of partial images according to the relative positional relationship of the cameras; A plurality of partial images corresponding to the reference points are determined, and the initial stitching positions of the partial images are adjusted according to the coordinate information of the reference points so as to overlap the corresponding reference points in the partial images to obtain a stitched image.

4. The method according to claim 1, wherein After stitching the plurality of partial images together according to the relative positional relationship and the coordinate information of the reference point to obtain a stitched image, the method further includes: Determining the image integrity of the stitched image by comparing the stitched image with the standard image; Determining, based on the image integrity, location information of a missing portion of the image in the stitched image; According to the position information corresponding to the image missing part, the focal length of the camera within a preset range near the image missing part is adjusted to obtain a partial image of the image missing part.

5. The method according to claim 1, wherein After stitching the plurality of partial images together according to the relative positional relationship and the coordinate information of the reference point to obtain a stitched image, the method further includes: Determining a preset initial judgment model, and training the initial judgment model by stitching images to obtain a judgment model; Determining, in the spliced ​​image, the abnormal area corresponding to the abnormal state of the indicator light change by using the judgment model; The abnormal area is highlighted in the stitched image.

6. The method according to claim 1, characterized in that Before collecting the information displayed on the screen through the camera matrix, the method further includes: By displaying equally divided radiation radius images of equidistant concentric regular figures on the screen, and adjusting the equidistant distance and radiation radius angle of the images so that each camera in the camera matrix can capture at least one complete quadrilateral; The specific position information of the image captured by the camera on the screen is determined by the quadrilateral to obtain the splicing parameters of the multiple local images acquired by the camera matrix.

7. A stacked screen information collection device, characterized in that: include: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the method according to any one of claims 1 to 6.

8. A non-volatile computer storage medium storing computer-executable instructions, characterized in that: The computer executable instructions are configured to perform the steps of the method according to any one of claims 1 to 6.

Images