Train positioning method and system, electronic device, storage medium

Abstract

The application discloses a train positioning method and system, an electronic device and a storage medium, and relates to the technical field of video monitoring. The method comprises the following steps: inputting the information of a to-be-tracked train obtained to a train operation model for identification, and determining the operation section of the to-be-tracked train in a preset time period, wherein the train operation model is a model obtained by processing the information of a plurality of sample trains by using a linear regression algorithm of machine learning; calling a target image acquisition device in the operation section to detect the to-be-tracked train; and in the case that the to-be-tracked train is detected, determining the real-time position information of the to-be-tracked train based on the image information of the to-be-tracked train extracted from the target image acquisition device. The real-time operation condition of the to-be-tracked train and the operation environment around the to-be-tracked train are monitored conveniently, and the operation safety of the train is improved.

Description

Technical Field

[0001] This application relates to the field of video surveillance technology, specifically to a train positioning method and system, electronic equipment, and storage medium. Background Technology

[0002] Currently, in the railway transportation industry, the main method for tracking train locations is to use video information corresponding to the train's position pushed by the Dynamic Monitoring System (DMS). This method can simultaneously acquire location data from multiple trains to achieve train positioning.

[0003] However, since the video surveillance system and DMS are located in different local area networks, coordination and interoperability between the two systems and deployment of network equipment are required during use, which increases the complexity of data processing and reduces data security. Summary of the Invention

[0004] Therefore, this application provides a train positioning method and system, electronic device, and storage medium to solve the problem of how to track trains and accurately locate their real-time operating position.

[0005] To achieve the above objectives, the first aspect of this application provides a train positioning method, the method comprising: inputting the acquired information of the train to be tracked into a train operation model for identification, determining the operating section of the train to be tracked within a preset time period, wherein the train operation model is a model obtained by processing information of multiple sample trains using a linear regression algorithm based on machine learning; calling a target image acquisition device within the operating section to detect the train to be tracked; and, if it is determined that the train to be tracked has been detected, determining the real-time location information of the train to be tracked based on the image information of the train to be tracked extracted from the target image acquisition device.

[0006] To achieve the above objectives, a second aspect of this application provides a train positioning system, comprising: a train tracking device, a user terminal, a video monitoring server, and multiple image acquisition devices connected in communication; the train tracking device is configured to execute any of the train positioning methods described in the embodiments of this application; the user terminal is configured to send a positioning request to the train tracking device, the positioning request including information about the train to be tracked, so that the train tracking device can input the acquired information about the train to be tracked into a train operation model for identification, and determine the operating section of the train to be tracked within a preset time period; the video monitoring server is configured to manage the multiple image acquisition devices and acquire image information required by the train tracking device; the image acquisition devices are configured to acquire images of trains within their monitoring range and send the acquired images to the video monitoring server.

[0007] To achieve the above objectives, in a third aspect, this application provides an electronic device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores one or more computer programs executable by the at least one processor, the one or more computer programs being executed by the at least one processor to enable the at least one processor to perform the above-described train positioning method.

[0008] To achieve the above objectives, in a fourth aspect, this application provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor / processor core, implements the above-described train positioning method.

[0009] The train positioning method, system, electronic device, and storage medium in this application identify the train to be tracked by inputting the acquired information into a train operation model. This determines the train's operating range within a preset time period. The train operation model is obtained by processing information from multiple sample trains using a linear regression algorithm based on machine learning. This model clarifies the specific operating range of the train to be tracked, narrowing the monitoring scope. The system then calls upon a target image acquisition device within the operating range to detect the train. This determines whether the target image acquisition device can detect the train. If the train is detected, the system determines the real-time location information of the train based on the image information extracted from the target image acquisition device. This facilitates monitoring the real-time operation of the train and its surrounding environment, improving train operation safety. Attached Figure Description

[0010] The accompanying drawings are provided to further illustrate the embodiments of this disclosure and form part of the specification. They are used together with the embodiments of this disclosure to explain the disclosure and do not constitute a limitation thereof. The above and other features and advantages will become more apparent to those skilled in the art from the detailed description of exemplary embodiments with reference to the accompanying drawings, in which:

[0011] Figure 1 This is a flowchart illustrating a train positioning method provided in an embodiment of this application.

[0012] Figure 2 This is a schematic diagram showing the distribution of image acquisition devices along a train tracking line, as provided in an embodiment of this application.

[0013] Figure 3 This is a flowchart illustrating a training method for a train operation model provided in an embodiment of this application.

[0014] Figure 4This is a schematic diagram illustrating the processing of train schedules and kilometer markers along the train route using a linear regression algorithm based on machine learning, as provided in an embodiment of this application.

[0015] Figure 5 This is a block diagram of a train positioning device provided in an embodiment of this application.

[0016] Figure 6 This is a block diagram of a train positioning system provided in an embodiment of this application.

[0017] Figure 7 This is a block diagram of a train positioning system provided in an embodiment of this application.

[0018] Figure 8 This is a flowchart illustrating the working method of a train positioning system provided in an embodiment of this application.

[0019] Figure 9 This is a block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0020] The specific embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the application. Those skilled in the art can implement this application without requiring some of these specific details. The following description of the embodiments is merely to provide a better understanding of this application by illustrating examples.

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0022] With the development of railway transportation, video surveillance systems are playing an increasingly significant role in transportation command, public security, production operations, and safety monitoring. Among them, integrated video surveillance systems are characterized by wide spatial coverage and 24 / 7 service, providing large-scale network coverage for railway work areas, stations, and railway bureaus / companies. Typically, they primarily utilize video information corresponding to train locations pushed by the DMS (Digital Monitoring System) to achieve real-time train tracking.

[0023] However, since integrated video surveillance systems typically operate within dedicated video networks while DMS operates within dedicated office networks, their use requires coordination, interoperability, and network equipment deployment, increasing data processing complexity and reducing data security. Furthermore, integrated video surveillance systems employ a three-tiered deployment approach (line-level, area-level, and core-level), completely different from DMS systems, making integrated use of the two systems impossible.

[0024] In view of this, this application provides a train positioning method and system, electronic device, and storage medium to solve the problem of accurately locating and tracking trains through an integrated video surveillance system without using a DMS system, thereby ensuring the safety of train operation.

[0025] The first aspect of this application provides a train positioning method. Figure 1 This is a schematic flowchart illustrating a train positioning method provided in an embodiment of this application. This train positioning method can be applied to train positioning devices. Figure 1 As shown, the train positioning method includes, but is not limited to, the following steps.

[0026] Step S101: Input the obtained information of the train to be tracked into the train operation model for identification, and determine the operating section of the train to be tracked within the preset time period.

[0027] The train operation model is a model obtained by processing information from multiple sample trains using a linear regression algorithm based on machine learning.

[0028] For example, the information of the train to be tracked can be obtained by retrieving historical video data from the integrated video system, thus obtaining the image information corresponding to the train to be tracked.

[0029] Step S102: Call the target image acquisition device within the operating section to detect the train to be tracked.

[0030] Among them, the historical image information collected by the target image acquisition device within the operating section is most likely to include the train to be tracked. Therefore, the detection accuracy of the train to be tracked can be improved by calling the historical image data stored in the target image acquisition device within the operating section.

[0031] Step S103: If it is determined that a train to be tracked has been detected, the real-time location information of the train to be tracked is determined based on the image information of the train to be tracked extracted from the target image acquisition device.

[0032] If the train to be tracked is detected from the historical image data stored in the target image acquisition device, the historical image data can be further analyzed to extract the image information of the train to be tracked. This allows for analysis of the image information to determine the real-time location information of the train to be tracked, as well as the surrounding environment information of the train during its operation, thus ensuring the operational safety of the train to be tracked.

[0033] In this embodiment, the acquired information of the train to be tracked is input into the train operation model for identification, thereby determining the operating range of the train to be tracked within a preset time period. The train operation model is a model obtained by processing information from multiple sample trains using a linear regression algorithm based on machine learning, which clarifies the specific operating range of the train to be tracked and narrows the monitoring range. The target image acquisition device within the operating range is invoked to detect the train to be tracked, to determine whether the target image acquisition device can detect the train to be tracked. If the train to be tracked is detected, the real-time location information of the train to be tracked is determined based on the image information of the train to be tracked extracted from the target image acquisition device. This facilitates the monitoring of the real-time operation of the train to be tracked and its surrounding operating environment, thereby improving the safety of train operation.

[0034] Figure 2 This is a schematic diagram illustrating the distribution of image acquisition devices along a train tracking line, as provided in an embodiment of this application. Figure 2 As shown, the train to be tracked departs from station 1, passes through station 2, and travels to station 3. During this journey, the train will pass through image acquisition devices 1, ..., k between station 1 and station 2; and image acquisition devices m, ..., m+p between station 2 and station 3. Here, k, m, and p are all integers greater than or equal to 1.

[0035] The aforementioned multiple image acquisition devices can monitor the train to be tracked, obtain image information of the train during its operation, and thus accurately obtain information about the surrounding environment of the train during its operation. This allows for monitoring whether the train is operating normally and accurately locating the train, thereby improving the safety of train operation.

[0036] In some optional implementations, the information of the sample train includes: information of multiple sample image acquisition devices, wherein the sample image acquisition devices are image acquisition devices between the starting station and the ending station corresponding to the sample train.

[0037] Before inputting the acquired information of the train to be tracked into the train operation model for identification in step S101, and determining the operating section of the train to be tracked within the preset time period, the process also includes:

[0038] Based on the identifier of each sample image acquisition device, determine the kilometer identifier information corresponding to each sample image acquisition device; based on the kilometer identifier information corresponding to each sample image acquisition device, sort the multiple sample image acquisition devices to obtain the device sorting result.

[0039] By extracting information from the identifier of each sample image acquisition device (e.g., the identifier of the sample image acquisition device includes the kilometer number corresponding to the sample image acquisition device), the kilometer identifier information corresponding to each sample image acquisition device can be obtained, which facilitates the location of the sample image acquisition device.

[0040] Furthermore, by sorting multiple sample image acquisition devices based on the kilometer marker information corresponding to each sample image acquisition device, the sequential order of these devices during train operation can be determined. This allows for train positioning based on the sequence numbers of the different sample image acquisition devices in the sorting results, thereby improving positioning accuracy.

[0041] This application provides another possible implementation, wherein the information of the train to be tracked includes the train number information of the train to be tracked, the operating section includes multiple stations to be detected, and image acquisition devices to be confirmed are set up between two adjacent stations to be detected and inside the stations to be detected.

[0042] The step S102, which involves calling the target image acquisition device within the operating range to detect the train to be tracked, can be implemented using the following steps: Based on the current time period and the train number information of the train to be tracked, multiple image acquisition devices to be confirmed are filtered to determine the target image acquisition device; the target image acquisition device is called to detect trains within its monitoring range to obtain detection image information; the detection image information is analyzed to determine whether the detection image information includes the train to be tracked; if it is determined that the detection image information includes the train to be tracked, it is determined that the train to be tracked has been detected.

[0043] By matching the current time period with the train information of the train to be tracked (e.g., the train's departure time at its originating station, the train's arrival time at its destination station, etc.), it is possible to determine whether the train to be tracked is running in the current time period. Then, if it is determined that the train to be tracked is running in the current time period, the target image acquisition device (e.g., camera equipment deployed between the originating station and the destination station of the train to be tracked) that corresponds to the current time period and the train information of the train to be tracked can be selected from multiple image acquisition devices to be confirmed. This allows for the accurate determination of the target image acquisition device that the train to be tracked has passed through, thus narrowing down the positioning range.

[0044] Furthermore, the target image acquisition device is invoked to detect trains within its monitoring range and obtain detection image information; a deep learning target recognition algorithm is used to analyze the detection image information to determine whether the detection image information includes the train to be tracked; and if it is determined that the detection image information includes the train to be tracked, the train to be tracked is detected, thereby improving the positioning accuracy of the train to be tracked.

[0045] In some alternative implementations, the information about the train to be tracked includes: the train's operating speed.

[0046] The step S103, which determines the real-time location information of the train to be tracked based on the image information of the train to be tracked extracted from the target image acquisition device, can be implemented using the following method:

[0047] Image information of the train to be tracked is extracted from the target image acquisition device; the extracted image information is analyzed using a target detection algorithm to determine the position information of the train to be tracked at the time of detection; based on the running speed of the train to be tracked, the current time period information, the time when the train to be tracked was detected and its corresponding position information, the real-time position information of the train to be tracked is determined.

[0048] By using the operating speed of the train to be tracked and the current time period information, the distance traveled by the train can be calculated. Then, the kilometer marker corresponding to the time when the train was detected can be extracted from the location information of the train. Based on the kilometer marker corresponding to the time when the train was detected and the distance traveled by the train, the real-time location information of the train can be calculated (e.g., the kilometer marker to which the train has traveled in the current time period), reducing positioning errors and improving the positioning accuracy of the tracked train.

[0049] In some optional implementations, the information of the sample train includes: the route information corresponding to the sample train;

[0050] Before inputting the acquired information of the train to be tracked into the train operation model for identification in step S101, and determining the operating section of the train to be tracked within the preset time period, the process further includes: processing the training data using a linear regression algorithm based on machine learning to obtain the train operation model.

[0051] Training data is extracted from historical image information stored in multiple sample image acquisition devices in the route information corresponding to the sample trains. The training data is then trained using a linear regression algorithm based on machine learning until the obtained train operation model can identify different trains. This allows the train operation model to be used to identify the trains that users need to track, thereby improving the accuracy of train identification.

[0052] For example, Figure 3 This is a flowchart illustrating a training method for a train operation model provided in an embodiment of this application. Figure 3 As shown, the training method for this train operation model includes, but is not limited to, the following steps.

[0053] Step S301: Based on the route information corresponding to the sample train, extract the historical image information stored in each sample image acquisition device.

[0054] The route information corresponding to the sample train may include train number information, train timetable, kilometer marker information of the route, and kilometer marker information of each station along the route.

[0055] The name of the sample image acquisition device may include kilometer identification information to facilitate the location of each sample image acquisition device.

[0056] Step S302: Obtain the sample time period of the sample image acquisition device as the sample train passes through.

[0057] By using the time information of each train in the train timetable, the sample time period of each sample train passing through the sample image acquisition device can be determined.

[0058] For example, during the operation of train A, the sample image acquisition devices (such as surveillance cameras or photographing devices) that it passes through will record information about train A (such as the time information of train A passing through the sample image acquisition device, the corresponding kilometer marker, etc.), so that the sample time period corresponding to train A can be extracted (such as 10:00~10:15, 11:00~11:15, 12:00~12:15, etc.).

[0059] Step S303: Determine training data based on historical image information stored in multiple sample time periods and multiple sample image acquisition devices, and the device sorting results.

[0060] The equipment sorting result is obtained by ranking the sample image acquisition devices based on the kilometer identifier information included in their names. This sorting reflects the operating sequence of the sample trains and the corresponding order of the sample image acquisition devices.

[0061] Furthermore, based on the device sorting results, it is possible to identify the multiple sample image acquisition devices that the sample train passed through in multiple sample time periods, thereby extracting the historical image information stored in these sample image acquisition devices corresponding to each sample time period, so as to analyze this historical image information and determine the training data.

[0062] Step S304: The training data is processed using a linear regression algorithm based on machine learning to obtain a train operation model.

[0063] In this process, train times and line kilometer markers in the training data can be linearly mapped to obtain information with operational patterns, thereby obtaining a train operation model.

[0064] For example, Figure 4 This diagram illustrates the processing of train schedules and kilometer markers along the train route using a linear regression algorithm derived from machine learning, as provided in an embodiment of this application. Figure 4 As shown, a coordinate system is established with train times as the vertical axis and line kilometer markers as the horizontal axis. By plotting the correspondence between multiple sets of train times and line kilometer markers from the training data within this coordinate system, at least two dashed lines with a linear pattern can be obtained (e.g., ...). Figure 4 (Dash lines 401 and 402 in the text). From Figure 4 The pattern shown indicates that the train operation model exhibits linear changes, with the range of change between dashed lines 401 and 402.

[0065] Through the above processing, the obtained train operation model can reflect which line kilometer marker the sample train will be at at different train times, thereby quickly and accurately locating the sample train and improving positioning accuracy.

[0066] In some optional implementations, training data is determined based on historical image information stored in multiple sample image acquisition devices and device sorting results across multiple sample time periods. This includes: filtering historical image information stored in multiple sample image acquisition devices based on multiple sample time periods to determine sample image information to be processed that matches the multiple sample time periods; sorting multiple sample image information to be processed based on device sorting results and the identifiers of the image acquisition devices corresponding to the sample image information to be processed to obtain image sorting information; and determining training data based on the image sorting information.

[0067] For example, historical image information stored in N sample time periods and M sample image acquisition devices is taken. By extracting images from the historical image information that include the sample time periods, N sample image information to be processed corresponding to the N sample time periods are obtained. Furthermore, the identifiers of the image acquisition devices corresponding to the N sample image information to be processed are sorted. Since the N sample time periods have temporal continuity, the corresponding N sample image information to be processed also have temporal continuity. Therefore, based on this temporal continuity, the image acquisition devices corresponding to the sample image information to be processed are sorted, so that the obtained image sorting information reflects the chronological order of the regions traversed by the sample train. Here, N and M are both integers greater than or equal to 1, and M is greater than N.

[0068] Furthermore, the training data includes multiple training images, which are image information corresponding to the sample train and in chronological order. Therefore, by using a linear regression algorithm based on machine learning to process the above training data, the obtained train operation model can reflect the order in which the train passes through the areas in its chronological order, thus reflecting the operation pattern of the sample train and facilitating subsequent train positioning.

[0069] In some optional implementations, after determining the real-time location information of the train to be tracked based on the image information of the train to be tracked extracted from the target image acquisition device in step S103, the method further includes: feeding back the real-time location information and the image information of the train to be tracked to the user terminal so that the user terminal can monitor the train to be tracked.

[0070] The image information of the train to be tracked includes images with running time information and / or running kilometer markers.

[0071] For example, through automatic video switching and playback technology, the real-time location information of the train to be tracked, as well as image information related to the real-time location information, can be displayed on the user terminal. Furthermore, by switching other camera devices adjacent to the real-time location information of the train to be tracked, the automatic monitoring function of the train to be tracked can be realized, ensuring that the user terminal can observe the operation of the train to be tracked in real time, so as to monitor the real-time operating environment of the train to be tracked and improve the safety of train operation.

[0072] The second aspect of this application provides a train positioning device. Figure 5 This is a block diagram illustrating the components of a train positioning device provided in an embodiment of this application. Figure 5 As shown, the train positioning device 500 includes, but is not limited to, the following modules.

[0073] The identification module 501 is configured to input the acquired information of the train to be tracked into the train operation model for identification, and determine the operating section of the train to be tracked within a preset time period. The train operation model is a model obtained by processing the information of multiple sample trains using a linear regression algorithm of machine learning.

[0074] The detection module 502 is configured to call the target image acquisition device within the operating range to detect the train to be tracked.

[0075] The determination module 503 is configured to determine the real-time location information of the train to be tracked based on the image information of the train to be tracked extracted from the target image acquisition device when it is determined that the train to be tracked has been detected.

[0076] In this embodiment, the identification module inputs the information of the train to be tracked into the train operation model for identification, determining the operating range of the train to be tracked within a preset time period. The train operation model is a model obtained by processing information from multiple sample trains using a linear regression algorithm based on machine learning, clarifying the specific operating range of the train to be tracked and narrowing the monitoring range. The detection module calls the target image acquisition device within the operating range to detect the train to be tracked, to determine whether the target image acquisition device can detect the train to be tracked. If the detection of the train to be tracked is confirmed, the determination module determines the real-time location information of the train to be tracked based on the image information of the train to be tracked extracted from the target image acquisition device. This facilitates the monitoring of the real-time operation of the train to be tracked and its surrounding operating environment, improving the safety of train operation.

[0077] It is worth mentioning that all modules involved in this embodiment are logical modules. In practical applications, a logical unit can be a physical unit, a part of a physical unit, or a combination of multiple physical units. Furthermore, to highlight the innovative aspects of this application, this embodiment does not introduce units that are not closely related to solving the technical problem proposed in this application; however, this does not mean that other units are absent from this embodiment.

[0078] The third aspect of this application provides a train positioning system. Figure 6 This is a block diagram illustrating the components of a train positioning system provided in an embodiment of this application. Figure 6 As shown, the train positioning system includes, but is not limited to, the following devices:

[0079] The system includes a train tracking device 610, a user terminal 620, a video monitoring server 630, and multiple image acquisition devices 640 (e.g., a first image acquisition device 641, a second image acquisition device 642, ..., an Nth image acquisition device 64N), where N represents the number of image acquisition devices and N is an integer greater than or equal to 1.

[0080] The train tracking device 610 is configured to execute any of the train positioning methods in the embodiments of this application.

[0081] User terminal 620 is configured to send a location request to the train tracking device. The location request includes information about the train to be tracked, so that the train tracking device can input the acquired information about the train to be tracked into the train operation model for identification and determine the operating range of the train to be tracked within a preset time period.

[0082] The video surveillance server 630 is configured to manage multiple image acquisition devices and acquire the image information required by the train tracking device;

[0083] Image acquisition device 640 is configured to acquire images of trains within its monitoring range and send the acquired images to a video monitoring server.

[0084] Figure 7 This is a block diagram illustrating the components of a train positioning system provided in an embodiment of this application. Figure 7 As shown, the train positioning system includes a train tracking system 700 and a railway integrated video monitoring system 710. The train tracking system 700 includes, but is not limited to, the following modules: a user interface module 701, an integrated video access module 702, a video detection module 703, and a train data management module 704.

[0085] The railway integrated video surveillance system 710 communicates with the train tracking system 700 through the integrated video access module 702.

[0086] The integrated video access module 702 is used to obtain information about the tracking line cameras (such as the identification of the cameras along the railway line, the name of the cameras, and the location information of the cameras) through the interface between it and the railway integrated video monitoring system 710, and to extract the kilometer identification information (such as the number of kilometers and the location of the kilometers) corresponding to the camera from the camera's name; and to provide a unified video access interface for other modules.

[0087] The video detection module 703 is used to detect video information based on a train target detection algorithm. The video information is obtained from the integrated video access module 702. When a train to be tracked is detected, the information of the train to be tracked is sent to the train data management module 704.

[0088] The train data management module 704 is used to import the train timetable of relevant trains according to user needs, and send train detection tasks to the video detection module 703 according to the train timetable; and determine the train operation model based on the information of multiple sample trains received and the linear regression algorithm based on machine learning; and determine the real-time location information of the train to be tracked based on the image information of the train to be tracked extracted from the target image acquisition device when it is determined that the train to be tracked has been detected.

[0089] The user interface module 701 automatically retrieves the video information of the train to be tracked from the integrated video access module 702 based on user needs and feedback from the train data management module 704, and pushes the video information to other display devices when necessary.

[0090] Figure 8 This is a flowchart illustrating the working method of a train positioning system provided in an embodiment of this application. Figure 8 As shown, the working method of the train positioning system includes, but is not limited to, the following steps.

[0091] Step S801: Obtain information about the train to be tracked selected by the user terminal.

[0092] Among them, the user terminal is the terminal that is expected to track or locate the train to be tracked.

[0093] Step S802: Input the information of the train to be tracked into the train operation model for identification, and determine the operating section of the train to be tracked within the preset time period.

[0094] The train operation model is a model obtained by processing information from multiple sample trains using a linear regression algorithm based on machine learning.

[0095] Step S803: Call the target image acquisition device within the operating section to detect the train to be tracked.

[0096] Step S804: If it is determined that a train to be tracked has been detected, the real-time location information of the train to be tracked is determined based on the image information of the train to be tracked extracted from the target image acquisition device.

[0097] Step S805: The real-time location information of the train to be tracked is fed back to the user terminal so that the user terminal can determine the operating status of the train to be tracked based on the real-time location information of the train to be tracked.

[0098] By determining the real-time location information of the train to be tracked, user terminals can easily monitor and manage the train, thereby improving the safety of train operation.

[0099] In this embodiment, the location and tracking of a train to be tracked can be achieved without using a DMS system, enabling the location of the train to be tracked through a railway integrated video surveillance system. By inputting the acquired information of the train to be tracked into a train operation model for identification, the operating range of the train to be tracked within a preset time period is determined. The train operation model is a model obtained by processing information from multiple sample trains using a linear regression algorithm based on machine learning, thus clarifying the specific operating range of the train to be tracked and narrowing the monitoring range. Target image acquisition devices within the operating range are then invoked to detect the train to be tracked, to determine whether the target image acquisition devices can detect the train. If the train to be tracked is detected, the real-time location information of the train to be tracked is determined based on the image information extracted from the target image acquisition devices. This facilitates the monitoring of the real-time operation of the train to be tracked and its surrounding operating environment, improving the safety of train operation.

[0100] The fourth aspect of this application provides an electronic device and a computer-readable storage medium, both of which can be used to implement any of the train positioning methods in this application. The corresponding technical solutions and descriptions are described in the corresponding section of the method and will not be repeated here.

[0101] Figure 9 This is a block diagram of an electronic device provided in an embodiment of this application. (For example...) Figure 9 As shown, this application embodiment provides an electronic device, which includes: at least one processing module 901; at least one memory 902; and one or more I / O interfaces 903 connected between the processing module 901 and the memory 902; wherein, the memory 902 stores one or more computer programs that can be executed by at least one processing module 901, and the one or more computer programs are executed by at least one processing module 901 to enable at least one processing module 901 to perform the above-described train positioning method.

[0102] This application also provides a computer-readable storage medium storing a computer program thereon, wherein the computer program, when executed by a processor / processor core, implements the above-described train positioning method. The computer-readable storage medium may be volatile or non-volatile.

[0103] This application also provides a computer program product, including computer-readable code, or a non-volatile computer-readable storage medium carrying computer-readable code. When the computer-readable code is run in the processor of an electronic device, the processor in the electronic device executes the above-described train positioning method.

[0104] Those skilled in the art will understand that all or some of the steps, systems, and apparatuses disclosed above, and their functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof. In hardware implementations, the division between functional modules / units mentioned above does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be performed collaboratively by several physical components. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software can be distributed on a computer-readable storage medium, which may include computer storage media (or non-transitory media) and communication media (or transient media).

[0105] As is known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable program instructions, data structures, program modules, or other data). Computer storage media includes, but is not limited to, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), static random access memory (SRAM), flash memory or other memory technologies, portable compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical disc storage, magnetic cartridges, magnetic tape, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and is accessible to a computer. Furthermore, it is known to those skilled in the art that communication media typically contain computer-readable program instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

[0106] The computer-readable program instructions described herein can be downloaded from computer-readable storage media to various computing / processing devices, or downloaded via a network, such as the Internet, local area network, wide area network, and / or wireless network, to an external computer or external storage device. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards them to the computer-readable storage media in the respective computing / processing device.

[0107] The computer program instructions used to perform the operations of this application may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk, C++, etc., and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or may be connected to an external computer (e.g., via the Internet using an Internet service provider). In some embodiments, electronic circuits, such as programmable logic circuits, field-programmable gate arrays (FPGAs), or programmable logic arrays (PLAs), are personalized by utilizing state information from the computer-readable program instructions. These electronic circuits can execute the computer-readable program instructions to implement various aspects of this application.

[0108] The computer program product described herein can be implemented specifically through hardware, software, or a combination thereof. In one alternative embodiment, the computer program product is specifically embodied in a computer storage medium; in another alternative embodiment, the computer program product is specifically embodied in a software product, such as a software development kit (SDK), etc.

[0109] Various aspects of this application are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0110] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when executed by the processor of the computer or other programmable data processing apparatus, they create means for implementing the functions / actions specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, programmable data processing apparatus, and / or other device to operate in a particular manner; thus, the computer-readable medium storing the instructions comprises an article of manufacture that includes instructions for implementing aspects of the functions / actions specified in one or more blocks of the flowchart and / or block diagram.

[0111] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to perform the functions / actions specified in one or more boxes of a flowchart and / or block diagram.

[0112] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of an instruction containing one or more executable instructions for implementing a specified logical function. In some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0113] Example embodiments have been disclosed herein, and while specific terminology has been used, it is for general illustrative purposes only and should not be construed as limiting. In some instances, it will be apparent to those skilled in the art that features, characteristics, and / or elements described in conjunction with particular embodiments may be used alone, or in combination with features, characteristics, and / or elements described in conjunction with other embodiments, unless otherwise expressly indicated. Therefore, those skilled in the art will understand that various changes in form and detail may be made without departing from the scope of this application as set forth by the appended claims.

Claims

1. A train positioning method, characterized in that, The method includes: The acquired information about the train to be tracked is input into the train operation model for identification, and the operating section of the train to be tracked within a preset time period is determined. The train operation model is a model obtained by processing information from multiple sample trains using a linear regression algorithm based on machine learning. The target image acquisition device within the operating range is invoked to detect the train to be tracked; If the train to be tracked is detected, the real-time location information of the train to be tracked is determined based on the image information of the train to be tracked extracted from the target image acquisition device. The information of the sample train includes: the running route information corresponding to the sample train; Before inputting the acquired information of the train to be tracked into the train operation model for identification and determining the operating section of the train to be tracked within a preset time period, the method further includes: Based on the route information corresponding to the sample train, historical image information stored in each sample image acquisition device is extracted; Obtain the sample time period of the sample image acquisition device as the sample train passes through it; Training data is determined based on the historical image information stored in the multiple sample time periods, the multiple sample image acquisition devices, and the device ranking results; the device ranking results are obtained by ranking each sample image acquisition device based on the kilometer identification information included in the name of the sample image acquisition device. The training data is processed using a linear regression algorithm based on machine learning to obtain the train operation model.

2. The method according to claim 1, characterized in that, The information of the train to be tracked includes the train number information of the train to be tracked, and the operating section includes multiple stations to be detected. Image acquisition devices to be confirmed are set up between two adjacent stations to be detected and inside the stations to be detected. The step of calling the target image acquisition device within the operating section to detect the train to be tracked includes: Based on the current time period and the train number information of the train to be tracked, multiple image acquisition devices to be confirmed are filtered to determine the target image acquisition device; The target image acquisition device is invoked to detect trains within its monitoring range and obtain detection image information; The detected image information is analyzed to determine whether the detected image information includes the train to be tracked; If the detected image information includes the train to be tracked, then the train to be tracked has been detected.

3. The method according to claim 1, characterized in that, The information of the train to be tracked includes: the operating speed of the train to be tracked; The step of determining the real-time location information of the train to be tracked based on the image information of the train to be tracked extracted from the target image acquisition device includes: Extract the image information of the train to be tracked from the target image acquisition device; The extracted image information is analyzed using a target detection algorithm to determine the position information of the train to be tracked at the time of detection. Based on the train's operating speed, current time period, the time the train was detected, and its corresponding location information, the real-time location information of the train to be tracked is determined.

4. The method according to claim 1, characterized in that, The information of the sample train includes: information of multiple sample image acquisition devices, wherein the sample image acquisition devices are image acquisition devices between the starting station and the ending station corresponding to the sample train; Before inputting the acquired information of the train to be tracked into the train operation model for identification and determining the operating section of the train to be tracked within a preset time period, the method further includes: Based on the identifier of each of the sample image acquisition devices, determine the kilometer identification information corresponding to each of the sample image acquisition devices; Based on the kilometer identification information corresponding to each of the sample image acquisition devices, the multiple sample image acquisition devices are sorted to obtain the device sorting result.

5. The method according to claim 4, characterized in that, The step of determining training data based on multiple sample time periods, historical image information stored in multiple sample image acquisition devices, and the device sorting results includes: Based on multiple sample time periods, historical image information stored in multiple sample image acquisition devices is filtered to determine sample image information to be processed that matches the multiple sample time periods; Based on the device sorting results and the identifier of the image acquisition device corresponding to the image information of the sample to be processed, the multiple image information of the sample to be processed are sorted to obtain image sorting information; The training data is determined based on the image sorting information; The training data includes multiple training images, which include image information corresponding to the sample train and arranged in chronological order.

6. The method according to any one of claims 1 to 5, characterized in that, After determining the real-time location information of the train to be tracked based on the image information of the train to be tracked extracted from the target image acquisition device, the method further includes: The real-time location information and image information of the train to be tracked are fed back to the user terminal so that the user terminal can monitor the train to be tracked. The image information of the train to be tracked includes images with running time information and / or running kilometer markers.

7. A train positioning system, comprising: The train tracking device, user terminal, video monitoring server, and multiple image acquisition devices are connected via communication. The train tracking device is configured to perform the train positioning method as described in any one of claims 1 to 6; The user terminal is configured to send a location request to the train tracking device. The location request includes information about the train to be tracked, so that the train tracking device can input the acquired information about the train to be tracked into the train operation model for identification and determine the operating range of the train to be tracked within a preset time period. The video surveillance server is configured to manage multiple image acquisition devices and acquire the image information required by the train tracking device. The image acquisition device is configured to acquire images of trains within its monitoring range and send the acquired images to the video monitoring server.

8. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores one or more computer programs that can be executed by the at least one processor, the one or more computer programs being executed by the at least one processor to enable the at least one processor to perform the train positioning method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the train positioning method as described in any one of claims 1-6.

Images