Tramcar driver behavior monitoring system and method, operation host and storage medium

Abstract

The invention discloses a tramcar driver behavior monitoring system and method, an operation host and a storage medium, and relates to the technical field of safe driving. The system comprises an operation host, a gesture monitoring camera and a state monitoring camera, wherein the gesture monitoring camera and the state monitoring camera are connected with the operation host; the gesture monitoring camera is configured to collect gesture data of a driver, the state monitoring camera is configured to collect face data of the driver, and the operation host is configured to analyze the gesture data and the face data and output a behavior monitoring result. By the adoption of the system, the driving behavior of a driver can be guided and improved, driving safety is ensured, and meanwhile the running efficiency of the tramcar is improved.

Description

Technical Field

[0001] The present application relates to the field of safe driving technology, and in particular to a tram driver behavior monitoring system and method, an operating host, and a storage medium. Background Art

[0002] In modern society, with the continuous development of cities, transportation issues are becoming increasingly prominent. As the main means of urban transportation around the world, trams have been widely used due to their safety, speed, comfort and environmental protection. In view of the actual operating requirements of current trams, it is urgent to further improve the driving behavior of crew members and the operating efficiency of trams. Summary of the invention

[0003] In view of the above-mentioned defects or deficiencies in the related art, it is desired to provide a tram driver behavior monitoring system and method, an operating host, and a storage medium that can ensure driving safety and improve operating efficiency.

[0004] In a first aspect, the present application provides a tram driver behavior monitoring system, the tram driver behavior monitoring system comprising an operation host and a gesture monitoring camera and a state monitoring camera connected to the operation host;

[0005] The gesture monitoring camera is configured to collect the driver's gesture data, the state monitoring camera is configured to collect the driver's facial data, and the operating host is configured to analyze the gesture data and the facial data and output the behavior monitoring result.

[0006] Optionally, in some embodiments of the present application, the operating host is specifically used to obtain the aligned color frame image and depth frame image in the gesture data;

[0007] Inputting the color frame image into a pre-trained target detection model to obtain a hand position frame, and using the hand position frame to perform hand segmentation on the depth frame image;

[0008] The average height of all depth frame images corresponding to the hand is counted, and the type of the gesture data is determined according to a comparison result between the average height and a preset threshold range.

[0009] Optionally, in some embodiments of the present application, the manual segmentation method includes at least one of grayscale histogram segmentation and cluster segmentation.

[0010] Optionally, in some embodiments of the present application, the operation host is specifically used to obtain the speed of the tram and send a heartbeat signal to the status monitoring camera;

[0011] If the travel speed reaches a preset threshold speed, the state monitoring camera is controlled to collect the facial data, and when the state monitoring camera detects that the facial data has a doze feature, the doze frame image and alarm information sent by the state monitoring camera are received.

[0012] Optionally, in some embodiments of the present application, the tram driver behavior monitoring system further includes a ground server connected to the operation host, and the ground server is configured to receive the doze frame image and the alarm information uploaded by the operation host.

[0013] Optionally, in some embodiments of the present application, the operating host is specifically used to obtain a face frame image in the face data, and traverse a pre-stored face library to output face information with the highest similarity to the face frame image.

[0014] Optionally, in some embodiments of the present application, the operating host is also specifically used to receive message data sent by the software development kit, and to obtain recognition results from the message data, wherein the recognition results include a version number frame, a face recognition result frame, and a face management result frame.

[0015] In a second aspect, the present application provides a tram driver behavior monitoring method, the tram driver behavior monitoring method is used for the operating host described in any one of the first aspects, the operating host is connected to the gesture monitoring camera and the state monitoring camera respectively, and the method includes:

[0016] Acquire gesture data collected by the gesture monitoring camera and face data collected by the status monitoring camera;

[0017] The gesture data and the face data are analyzed, and a behavior monitoring result is output.

[0018] In a third aspect, the present application provides an operating host, which includes a motherboard and a power plug-in, a communication plug-in, a switch plug-in and an artificial intelligence plug-in connected to the motherboard, and the artificial intelligence plug-in can execute the steps of the tram driver behavior monitoring method described in the second aspect.

[0019] In a fourth aspect, the present application provides a computer-readable storage medium, which stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the tram driver behavior monitoring method described in the second aspect.

[0020] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0021] The embodiment of the present application provides a tram driver behavior monitoring system and method, an operating host, and a storage medium, which uses a gesture monitoring camera to collect the driver's gesture data and a status monitoring camera to collect the driver's facial data, and then objectively analyzes the gesture data and the facial data to obtain behavior monitoring results to guide and improve the driver's driving behavior, thereby ensuring driving safety and improving the operating efficiency of the tram. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A structural block diagram of a tram driver behavior monitoring system provided in an embodiment of the present application;

[0024] Figure 2 A schematic diagram of a vehicle-mounted software connection peripheral interface provided in an embodiment of the present application;

[0025] Figure 3 A schematic diagram of a vehicle-mounted software block diagram connection provided in an embodiment of the present application;

[0026] Figure 4 A schematic diagram of the main data flow transmission of an in-vehicle software provided in an embodiment of the present application;

[0027] Figure 5 A schematic diagram of a flow chart of gesture data analysis provided in an embodiment of the present application;

[0028] Figure 6 A schematic diagram of a process of face data analysis provided in an embodiment of the present application;

[0029] Figure 7 A specific example of a tram driver behavior monitoring system provided in an embodiment of the present application;

[0030] Figure 8 A schematic diagram of another process of face data analysis provided in an embodiment of the present application;

[0031] Fig. 9 A schematic diagram of a message data processing flow provided in an embodiment of the present application;

[0032] Fig.10 A schematic diagram of a flow chart of a tram driver behavior monitoring method provided in an embodiment of the present application;

[0033] Fig.11A front view of a running host provided in an embodiment of the present application;

[0034] Fig.12 A method provided in the embodiment of the present application Fig.11 A top view of the running host;

[0035] Fig.13 A method provided in the embodiment of the present application Fig.11 A diagram of the communication architecture of the running host.

[0036] Reference numerals:

[0037] 10-tram driver behavior monitoring system, 101-operating host, 1011-motherboard, 1012-power plug-in, 1013-communication plug-in, 1014-switch plug-in, 1015-artificial intelligence plug-in, 102-gesture monitoring camera, 103-status monitoring camera, 104-ground server. DETAILED DESCRIPTION

[0038] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0039] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, the present application is further described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0040] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. Figures 1 to 13 The tram driver behavior monitoring system and method, operating host, and storage medium provided in the embodiments of the present application are described in detail.

[0041] Please refer to Figure 1, which is a structural block diagram of a tram driver behavior monitoring system provided in an embodiment of the present application, the tram driver behavior monitoring system 10 comprises an operating host 101 and a gesture monitoring camera 102 and a state monitoring camera 103 connected to the operating host 101. The gesture monitoring camera 102 can collect the driver's gesture data, the state monitoring camera 103 can collect the driver's face data, and the operating host 101 can analyze the gesture data and face data and output the behavior monitoring result. For example, the gesture monitoring camera 102 is installed in front of the driver's seat in the tram cab through a bracket, and is connected to the artificial intelligence plug-in running the host 101 through a cable. It can use a high-resolution depth camera to provide depth data in the range of 58.4° horizontally and 45.5° vertically; the state monitoring camera 103 is installed in front of the driver's seat in the tram cab through a bracket, and is connected to the artificial intelligence plug-in running the host 101 through a cable. It can use a high-resolution infrared camera with a viewing angle range of -30° to 30°, and a distance range from the driver's face of 60cm to 120cm, while the driver's line of sight range is -5° to -30°. For another example, the gesture monitoring camera 102 and the state monitoring camera 103 can also use the same type of camera.

[0042] It should be noted that the software part of the tram driver behavior monitoring system 10 in the embodiment of the present application mainly includes vehicle-mounted software and data center management software, wherein the vehicle-mounted software includes but is not limited to functional software such as AI software, computing software and V2X software, and configuration software such as switching software. Figure 2 As shown in FIG. 1 , it is a schematic diagram of a vehicle-mounted software connection to a peripheral interface provided by an embodiment of the present application, for example, the AI ​​software is connected to the state monitoring camera 103 via Ethernet, connected to the gesture monitoring camera 102 via a USB interface, and the computing software is connected to the vehicle-mounted equipment (VCME) via a multi-function vehicle bus (MVB). And, Figure 3 As shown, it is a schematic diagram of a vehicle-mounted software block diagram connection provided by an embodiment of the present application, for example, the functional software includes but is not limited to a business unit, a recording module, an algorithm module and a communication module. Figure 4 As shown, it is a schematic diagram of the main data flow transmission of an on-board software provided in an embodiment of the present application. The AI ​​unit, the computing unit and the V2X unit exchange data through Ethernet. When the computing unit collects tram operation data and equipment status data, it exchanges data with the on-board equipment through the multi-function vehicle bus.

[0043] For example, Figure 5As shown, when analyzing the driver's gesture data, the operating host 101 of the embodiment of the present application first obtains the aligned color frame image and depth frame image in the gesture data; then the color frame image is input into a pre-trained target detection model to obtain a hand position frame, and the hand position frame is used to perform hand segmentation on the depth frame image. For example, the target detection model can be a YOLOv7 model, which is deployed under the darknet native framework and calls a reserved C++ detection interface. For another example, the hand segmentation method includes but is not limited to at least one of grayscale histogram segmentation and cluster segmentation, and the cluster segmentation can be kmeans cluster segmentation; further, the average height of all depth frame images corresponding to the hand is counted, and according to the average height The type of gesture data is determined based on the comparison result between the hand ratio and the preset threshold range. The type of gesture data includes but is not limited to "hand ratio" and "confirmation", among which "hand ratio" refers to the driver's hand pointing to the signal light in front of the vehicle, and "confirmation" refers to the driver's hand pointing to the instrument in the car. Since gesture is a dynamic process, by capturing hand movement pictures, the hand in each picture has a height. The average height of the hand in each picture is averaged to obtain the average height. For example, if the average height is within the preset threshold range corresponding to the "hand ratio", the type of gesture data is "hand ratio", and if the average height is within the preset threshold range corresponding to the "confirmation", the type of gesture data is "confirmation", thereby judging whether the gesture made by the driver at the specified position is accurate.

[0044] For example Figure 6 As shown, when analyzing the driver's facial data, the operating host 101 of the embodiment of the present application obtains the tram's travel speed through the on-board equipment and sends a heartbeat signal to the status monitoring camera 103. Each tram is equipped with two sets of on-board redundant equipment. If the travel speed reaches the preset threshold speed, the status monitoring camera 103 is controlled to collect facial data, that is, the doze function of the status monitoring camera 103 is turned on and off according to the travel speed, and when the status monitoring camera 103 detects that the facial data has doze features, the doze frame image and alarm information sent by the status monitoring camera 103 are received. For example, the preset threshold speed is 100km / h. Further, as Figure 7 As shown, the tram driver behavior monitoring system 10 also includes a ground server 104 connected to the operating host 101. The ground server 104 can receive the doze frame image and alarm information uploaded by the operating host 101 through a network communication protocol such as TCP, thereby ensuring the driving safety of the tram.

[0045] Another example Figure 8As shown, when analyzing the driver's facial data, the operating host 101 of the embodiment of the present application can obtain the face frame image in the face data, traverse the pre-stored face library, and output the face information with the highest similarity to the face frame image, thereby determining whether the current driver is a scheduled driver. Fig. 9 As shown, the operating host 101 of the embodiment of the present application can also receive message data sent by the Baidu Software Development Kit (SDK) through network communication protocols such as UDP, and obtain recognition results from the message data, and the recognition results include a version number frame, a face recognition result frame and a face management result frame, wherein the version number frame refers to the version number sent by the Baidu Software Development Kit, the face recognition result frame refers to the face information with the highest similarity, and the face management result frame is to count the number of times that face information exceeds the specified score. Only when the number is greater than the preset threshold, it is considered that the correct face is recognized. In other words, driver identity management is implemented using the Baidu Software Development Kit.

[0046] The tram driver behavior monitoring system provided in the embodiment of the present application uses a gesture monitoring camera to collect the driver's gesture data and a status monitoring camera to collect the driver's facial data, and then objectively analyzes the gesture data and the facial data to obtain behavior monitoring results to guide and improve the driver's driving behavior, thereby ensuring driving safety and improving the operating efficiency of the tram.

[0047] Based on the above embodiments, the present application provides a tram driver behavior monitoring method, which is used to Figures 1 to 9 The operating host 101 of the corresponding embodiment, wherein the operating host 101 is connected to the gesture monitoring camera 102 and the state monitoring camera 103 respectively. Fig.10 , which is a flow chart of a tram driver behavior monitoring method provided in an embodiment of the present application, the method specifically comprises the following steps:

[0048] S101, acquiring gesture data collected by a gesture monitoring camera and face data collected by a status monitoring camera.

[0049] S102, analyzing the gesture data and face data, and outputting the behavior monitoring results.

[0050] Exemplarily, when analyzing the gesture data of a driver, the embodiment of the present application first obtains the aligned color frame image and depth frame image in the gesture data; then inputs the color frame image into a pre-trained target detection model to obtain a hand position frame, and uses the hand position frame to perform hand segmentation on the depth frame image. For example, the target detection model may be a YOLOv7 model, and the hand segmentation method includes but is not limited to at least one of grayscale histogram segmentation and cluster segmentation; further, the average height of the hand corresponding to all depth frame images is counted, and the type of gesture data is determined based on the comparison result between the average height and a preset threshold range. The type of gesture data includes but is not limited to "hand ratio" and "confirmation", etc. For example, if the average height is within the preset threshold range corresponding to the "hand ratio", the type of gesture data is "hand ratio", and if the average height is within the preset threshold range corresponding to the "confirmation", the type of gesture data is "confirmation", thereby judging whether the gesture made by the driver at the specified position is accurate.

[0051] For another example, when analyzing the driver's facial data, the embodiment of the present application can obtain the speed of the tram and send a heartbeat signal to the status monitoring camera 103. If the speed reaches the preset threshold speed, the status monitoring camera 103 is controlled to collect facial data, and when the status monitoring camera 103 detects that the facial data has a doze feature, the doze frame image and alarm information sent by the status monitoring camera 103 are received, for example, the preset threshold speed is 100km / h. For another example, the embodiment of the present application can also obtain the face frame image in the face data, traverse the pre-stored face library, and output the face information with the highest similarity to the face frame image, thereby judging whether the current driver is a scheduled driver.

[0052] It should be noted that, for the description of the same contents in this embodiment as those in other embodiments, reference can be made to the description in other embodiments and will not be repeated here.

[0053] The tram driver behavior monitoring method provided in the embodiment of the present application uses a gesture monitoring camera to collect the driver's gesture data and a status monitoring camera to collect the driver's facial data, and then objectively analyzes the gesture data and the facial data to obtain behavior monitoring results to guide and improve the driver's driving behavior, thereby ensuring driving safety and improving the operating efficiency of the tram.

[0054] As another aspect, the present application embodiment provides a running host. Fig.11 and Fig.12 , which are respectively a front view and a top view of a running host provided in an embodiment of the present application. The running host 101 includes a motherboard 1011 and a power plug-in 1012, a communication plug-in 1013, a switching plug-in 1014 and an artificial intelligence plug-in 1015 connected to the motherboard 1011. The artificial intelligence plug-in 1015 can execute Fig.10 The steps of the tram driver behavior monitoring method of the corresponding embodiment.

[0055] It should be noted that the hardware part of the tram driver behavior monitoring system 10 in the embodiment of the present application mainly includes a chassis and plug-ins. A motherboard 1011 is set in the chassis, and the power bus supplies power to each plug-in through the motherboard 1011. The communication within the system uses the motherboard 1011 to connect each plug-in, and the system is connected to the external device using the front line mode. For example, the chassis structure adopts a 2U height, and the outer dimensions are 482.0mm×88.0mm×297.2mm (corresponding to the length, height and depth respectively), and a cooling fan can also be set inside, which can provide air convection and heat dissipation channels for the inside of the chassis.

[0056] For example, combining Fig.13 As shown, ① the motherboard 1011 is installed inside the chassis and fixed to the rear cover of the chassis by screws. The motherboard 1011 connects the internal Ethernet bus of the communication plug-in 1013 to the switching plug-in 1014, and communicates with external devices through the front panel of the switching plug-in 1014. The motherboard 1011 connects the DC24V power output by the power plug-in 1012 to the communication plug-in 1013, the switching plug-in 1014, the artificial intelligence plug-in 1015 and the cooling fan, and provides working power for the communication plug-in 1013, the switching plug-in 1014, the artificial intelligence plug-in 1015 and the cooling fan. In addition, the motherboard 1011 connects the Ethernet bus of the artificial intelligence plug-in 1015 to the switching plug-in 1014, and realizes Ethernet communication with the communication plug-in 1013 and external devices through the switch on the switching plug-in 1014. ②The power plug-in 1012 is inserted into the chassis through the slot of the guide rail, and is connected to the motherboard 1011 through the connector to provide power for the internal plug-ins and the cooling fan. The power plug-in 1012 is fixed to the front panel of the chassis through screws, and is connected to the external DC power supply through the front panel connector. The front panel of the power plug-in 1012 is provided with a power switch to control the power on and off of the whole machine. The power plug-in 1012 is powered by a DC110V power supply, and is provided with a power conversion circuit inside, which realizes the DC110V to DC24V power conversion, and the maximum output current is 6A. ③The communication plug-in 1013 is inserted into the chassis through the slot of the guide rail, and is connected to the motherboard 1011 through the connector. It can provide Ethernet communication connection between the switching plug-in 1014, the artificial intelligence plug-in 1015 and the external device, and provide a multi-function vehicle bus communication connection between the running host 101 and the external device. The communication plug-in 1013 is fixed to the front panel of the chassis through screws, and is connected to the external device through the front panel DB9 connector.

[0057] ④ The switch plug-in 1014 is inserted into the chassis through the slot of the guide rail, connected to the motherboard 1011 through the connector, and expands the Ethernet of the communication plug-in 1013 running in the host 101. The communication plug-in 1013 Ethernet, the artificial intelligence plug-in 1015 Ethernet and the video processing Ethernet are interconnected through the switch chip. The switch plug-in 1014 collects the internal temperature of the host and controls the cooling fan for heat dissipation. The switch plug-in 1014 is fixed to the front panel of the chassis by screws and uses the front panel M12 connector to communicate with external devices through Ethernet. ⑤ The artificial intelligence plug-in 1015 is inserted into the chassis through the slot of the guide rail, connected to the motherboard 1011 through the connector, and uses the motherboard 1011 to communicate with the switch plug-in 1014 through Ethernet. The artificial intelligence plug-in 1015 is fixed to the front panel of the chassis by screws, connected to the external camera through the front panel M12 connector, DB9 connector and USB connector, and can provide DC12V and USB interface DC5V working power for the external camera. ⑥ The cooling fan is connected to the connector of the motherboard 1011 through a cable.

[0058] As another aspect, the present application provides a computer-readable storage medium for storing program code, the program code for executing the aforementioned Fig.10 Implementation of the tram driver behavior monitoring method of the corresponding embodiment.

[0059] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0060] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms. The modules described as separate components may or may not be physically separated, and the components displayed as modules may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0061] In addition, each functional module in each embodiment of the present application may be integrated into a processing unit, or each module may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.

[0062] Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the tram driver behavior monitoring method in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0063] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0064] This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only used to help understand the method and core ideas of this application. At the same time, for those skilled in the art, according to the ideas of this application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting this application.

Claims

1. A tram driver behavior monitoring system, characterized in that: The tram driver behavior monitoring system includes an operation host and a gesture monitoring camera and a status monitoring camera connected to the operation host; The gesture monitoring camera is configured to collect the driver's gesture data, the state monitoring camera is configured to collect the driver's facial data, and the operating host is configured to analyze the gesture data and the facial data and output the behavior monitoring result.

2. The tram driver behavior monitoring system according to claim 1, characterized in that: The operating host is specifically used to obtain the color frame image and the depth frame image in the gesture data that have been aligned; Inputting the color frame image into a pre-trained target detection model to obtain a hand position frame, and using the hand position frame to perform hand segmentation on the depth frame image; The average height of all depth frame images corresponding to the hand is counted, and the type of the gesture data is determined according to a comparison result between the average height and a preset threshold range.

3. The tram driver behavior monitoring system according to claim 2, characterized in that: The hand segmentation method includes at least one of grayscale histogram segmentation and cluster segmentation.

4. The tram driver behavior monitoring system according to claim 1, characterized in that: The operating host is specifically used to obtain the traveling speed of the tram and send a heartbeat signal to the status monitoring camera; If the travel speed reaches a preset threshold speed, the state monitoring camera is controlled to collect the facial data, and when the state monitoring camera detects that the facial data has a doze feature, the doze frame image and alarm information sent by the state monitoring camera are received.

5. The tram driver behavior monitoring system according to claim 4, characterized in that: The tram driver behavior monitoring system further includes a ground server connected to the operation host, and the ground server is configured to receive the doze frame image and the alarm information uploaded by the operation host.

6. The tram driver behavior monitoring system according to any one of claims 1 to 5, characterized in that: The operating host is specifically used to obtain the face frame image in the face data, traverse the pre-stored face library, and output the face information with the highest similarity to the face frame image.

7. The tram driver behavior monitoring system according to claim 6, characterized in that: The operating host is also specifically used to receive message data sent by the software development tool kit, and to strip the message data to obtain recognition results, wherein the recognition results include a version number frame, a face recognition result frame, and a face management result frame.

8. A method for monitoring the behavior of a tram driver, characterized in that: The tram driver behavior monitoring method is used for the operating host according to any one of claims 1 to 7, the operating host is connected to the gesture monitoring camera and the state monitoring camera respectively, and the method comprises: Acquire gesture data collected by the gesture monitoring camera and face data collected by the status monitoring camera; The gesture data and the face data are analyzed, and a behavior monitoring result is output.

9. A running host, characterized in that: The operating host includes a motherboard and a power plug-in, a communication plug-in, a switch plug-in and an artificial intelligence plug-in connected to the motherboard. The artificial intelligence plug-in can execute the steps of the tram driver behavior monitoring method described in claim 8.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the steps of the tram driver behavior monitoring method described in claim 8.

Images