A vehicle anti-rolling monitoring processing method, system and device and storage medium

Abstract

The application discloses a kind of vehicle anti-rolling monitoring processing methods, comprising the following steps: when vehicle stops, the state of driver, the state of passenger, vehicle both sides environment and vehicle speed are monitored in real time;According to each monitoring result, when judging that passenger is in the state of getting off not completed or the distance between the person outside the vehicle and the vehicle is less than the predetermined threshold, and the vehicle speed is greater than zero, it is determined that there is a risk of rolling;When the determination result is that there is a risk of rolling, the risk of rolling is prompted, and the vehicle is controlled to brake urgently.The application also discloses corresponding systems, devices and storage media.

Description

Technical Field

[0001] The present invention relates to the field of intelligent cockpit monitoring of intelligent connected vehicles, and in particular to a monitoring and processing method, system, device and storage medium for vehicle anti-crushing. Background Art

[0002] As vehicles become increasingly integrated into people's lives, vehicle safety is receiving increasing attention. Currently, vehicle safety relies on the driver checking the vehicle chassis and surrounding areas for obstacles before starting. However, in daily vehicle use, vehicle runover accidents often occur due to drivers failing to perform safety checks before starting (especially before restarting after parking, disembarking passengers).

[0003] In some cases, because the driver has a low level of awareness of the progress of people inside the car (such as those in the back seat) getting off the car, when a person inside the car is in the process of getting off the car (has not completed the getting off process) and the driver starts to drive the vehicle, the person's heels may be run over by the vehicle tires; in addition, in cases where people outside the car are close to the vehicle to hand over items / chat, etc., if the distance between the person outside the car and the vehicle is very close, there is a risk of the tires running over the feet of the person outside the car when the driver drives the vehicle. Summary of the Invention

[0004] The technical problem to be solved by the present invention is that the present invention proposes a vehicle anti-crushing monitoring and processing method, system, device and storage medium, which can improve the safety of people inside and outside the vehicle.

[0005] As one aspect of the present invention, a vehicle anti-crushing monitoring and processing method is provided, which comprises at least the following steps:

[0006] When the vehicle stops, the driver's status, passenger status, the environment on both sides of the vehicle, and the vehicle speed are monitored in real time;

[0007] A comprehensive assessment is made based on the monitoring results. If it is determined that a passenger has not yet completed getting off the vehicle or the distance between the person outside the vehicle and the vehicle is less than a predetermined threshold, and the vehicle speed is greater than zero, a crushing risk is determined.

[0008] When the judgment result is that there is a risk of crushing, a crushing risk prompt will be given and the vehicle will be controlled to perform emergency braking.

[0009] Among them, the driver's status, passenger status, vehicle environment and vehicle speed are monitored in real time, including:

[0010] Monitor the driver's status through the driver monitoring system DMS;

[0011] Monitor the status of passengers through the passenger monitoring system OMS;

[0012] monitoring the environment on both sides of the vehicle through the side-view cameras;

[0013] monitoring the current speed of the vehicle in real time through the vehicle speed sensor.

[0014] Further comprising: adjusting the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS on the state of the passengers according to the state of the driver monitored by the driver monitoring system DMS;

[0015] Further comprising: if the driver monitoring system DMS monitors that the driver is seriously distracted or has a serious tired look and does not pay attention to the rear passengers, the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS on the state of the passengers is adjusted to high sensitivity;

[0016] If the driver monitoring system DMS monitors that the driver is distracted or has a tired look, the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS on the state of the passengers is adjusted to medium sensitivity;

[0017] If the driver monitoring system DMS monitors that the driver is not tired and pays attention to the rear passengers, the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS on the state of the passengers is adjusted to low sensitivity.

[0018] Further comprising: the passenger monitoring system OMS is provided with a convolutional neural network trained and learned in advance through a large number of pictures, which is used to identify the complete getting-off action of the passengers, including identifying the trunk key points and limb key points of the rear passengers.

[0019] Further comprising:

[0020] The passenger monitoring system OMS sends the identified rear passenger information to the side-view camera;

[0021] When the side-view camera identifies that the attribute of the person outside the vehicle is consistent with the rear passenger information identified by the passenger monitoring system OMS, the horizontal distance between the rear passengers and the vehicle is monitored;

[0022] When the horizontal distance is greater than the predetermined threshold, the control of prohibiting triggering the crushing risk prompt is performed.

[0023] Further comprising:

[0024] Obtaining the horizontal distance value L from the rear position of the vehicle to the possible crushing point of the rear tire, and calculating the expected crushing time threshold t1 in real time according to the horizontal distance value L and the current vehicle speed V;

[0025] The accumulated time t after the vehicle starts is compared with the estimated crushing time threshold t1. When t<t1, a crushing risk warning is issued; when t≥t1, the electronic body stability system ESP is controlled to perform emergency braking on the vehicle.

[0026] As another aspect of the present invention, a vehicle anti-crushing monitoring and processing system is provided, which at least includes:

[0027] A real-time monitoring unit is used to monitor the driver's status, the passenger's status, the environment on both sides of the vehicle, and the vehicle speed in real time after the vehicle stops;

[0028] The crush risk judgment unit is used to make a comprehensive judgment based on the monitoring results. When it is determined that the passenger is in the state of not getting off the vehicle or the distance between the person outside the vehicle and the vehicle is less than a predetermined threshold, and the vehicle speed is greater than zero, it is determined that there is a crush risk;

[0029] The anti-crushing processing unit is used to issue a crushing hazard warning and control the vehicle to perform emergency braking after monitoring that the passengers have not completed getting off the vehicle or the distance between the outside person and the vehicle is less than a preset threshold, and the vehicle speed is greater than zero.

[0030] Wherein, the real-time monitoring unit is further configured to:

[0031] Monitor the driver's status through the driver monitoring system DMS;

[0032] Monitor the status of passengers through the passenger monitoring system OMS;

[0033] Monitor the environment on both sides of the vehicle through side-view cameras;

[0034] The current speed of the vehicle is obtained through real-time monitoring of the vehicle speed sensor.

[0035] Which further includes:

[0036] An algorithm sensitivity adjustment unit is used to adjust the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS to the passenger's status according to the driver's status monitored by the driver monitoring system DMS;

[0037] If the driver monitoring system (DMS) detects that the driver is seriously distracted or fatigued and not paying attention to the rear seats, the sensitivity level of the passenger monitoring algorithm of the passenger monitoring system (OMS) will be adjusted to high sensitivity.

[0038] If the driver monitoring system (DMS) detects that the driver is distracted or fatigued, the sensitivity level of the algorithm used by the passenger monitoring system (OMS) to monitor the passenger's status is adjusted to medium sensitivity;

[0039] If the driver monitoring system DMS detects that the driver is not tired and is paying attention to the back seat, the algorithm sensitivity level of the passenger monitoring system OMS that monitors the passenger's status is adjusted to low sensitivity.

[0040] Among them, the passenger monitoring system OMS is equipped with a convolutional neural network that has been pre-trained and learned through a large number of pictures, which is used to identify the complete passenger getting off the bus, including: identifying the torso key points and limb key points of the rear passengers.

[0041] Which further includes:

[0042] The associated processing unit is used for the passenger monitoring system (OMS) to send the identified rear passenger information to the side-view camera; when the side-view camera identifies that the attributes of the person outside the vehicle are consistent with the rear passenger information identified by the passenger monitoring system (OMS), the horizontal distance between the rear passenger and the vehicle is monitored; when the horizontal distance is greater than the predetermined threshold, the control prohibits the triggering of the crushing risk prompt.

[0043] Among them, the anti-crushing processing unit is configured to: obtain a pre-calibrated horizontal distance value L from the rear position of the vehicle to the possible crushing point of the rear tire, and calculate the expected crushing time threshold t1 in real time based on the horizontal distance value L and the current vehicle speed V; compare the accumulated time t after the vehicle starts with the expected crushing time threshold t1, and when t<t1, issue a crushing risk prompt; when t≥t1, control the electronic body stability system ESP to perform emergency braking on the vehicle.

[0044] As another aspect of the present invention, an intelligent driving processing device is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the aforementioned method when executing the computer program.

[0045] As another aspect of the present invention, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above method are implemented.

[0046] As another aspect of the present invention, a computer program product is provided, comprising computer instructions, wherein the computer instructions instruct a computer device to execute operations corresponding to the aforementioned method.

[0047] The implementation of the embodiments of the present invention has the following beneficial effects:

[0048] The present invention provides a vehicle crush prevention monitoring and processing method, system, device, and storage medium. The method intelligently detects the exit status of passengers by monitoring the driver's status through a driver monitoring system (DMS) and the passenger's status through an passenger monitoring system (OMS). Side-view cameras are used to identify and determine whether pedestrians are standing to the side of the vehicle, monitoring their posture and proximity to the vehicle. If a passenger is determined to be incompletely exiting the vehicle or the distance from an outsider to the vehicle is less than a predetermined threshold, and the vehicle speed is greater than zero, a crush risk is determined. In such cases, the ESP system can implement emergency braking. This improves vehicle start safety and prevents accidents.

[0049] In addition, in an embodiment of the present invention, the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS to the passenger's status is adjusted according to the driver's status monitored by the driver monitoring system DMS; by differentiating the algorithm recognition sensitivity, the recognition rate of the rear passenger status is improved and the false recognition rate is reduced, and to a certain extent, the need for simultaneous long-term monitoring by the DMS / OMS cameras is avoided, thereby avoiding excessive resource occupation and reducing the cost of use. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, without inventive work, other drawings derived from these drawings still fall within the scope of the present invention.

[0051] Figure 1 A schematic diagram of the main process of an embodiment of a vehicle anti-crushing monitoring and processing method provided by the present invention;

[0052] Figure 2 A more detailed schematic diagram of the method provided by the present invention;

[0053] Figure 3 The present invention provides a schematic structural diagram of an embodiment of a vehicle anti-crushing monitoring and processing system. DETAILED DESCRIPTION

[0054] In order to make the objectives, technical solutions and advantages of the present invention more clear, the present invention will be described in further detail below with reference to the accompanying drawings.

[0055] like Figure 1 FIG. 1 shows a schematic diagram of the main process of an embodiment of a vehicle anti-crushing monitoring and processing method provided by the present invention; and FIG. Figure 2In this embodiment, the method is applied to a vehicle equipped with a driver monitoring system (DMS), an occupant monitoring system (OMS), a side view camera, an electronic vehicle stability system (ESP), and an in-vehicle host (IVI).

[0056] The DMS / OMS system can obtain local information about the occupants (driver and passengers) through sample learning to determine the driver's status. Combined with the door status (open / closed), it can also determine whether the rear passengers have not yet exited the vehicle.

[0057] The side-view camera is used to identify and determine the vertical distance between people outside the vehicle and the side of the vehicle. It can dynamically identify and calculate this vertical distance. Then, based on big data analysis and parameter adjustment of human foot length, a threshold is determined. By comparing the vertical distance measured by the side-view camera with the threshold, it can be determined whether the person outside the vehicle is at risk of being run over.

[0058] The ESP system is used to control the vehicle's emergency braking. When the vehicle speed is greater than 0 and a signal is received that a person's feet may be crushed, emergency braking is performed;

[0059] Vehicle-side host IVI: responsible for intelligent reminder broadcasts, etc.

[0060] Specifically, the vehicle anti-crushing monitoring and processing method provided by the present invention includes at least the following steps:

[0061] Step S10: After the vehicle stops, the driver's status, the passenger's status, the environment on both sides of the vehicle, and the vehicle speed are monitored in real time;

[0062] In a specific example, step S10 includes:

[0063] The driver's status is monitored through the Driver Monitoring System (DMS), which primarily monitors whether the driver is distracted or fatigued, and whether they are paying attention to the posture and movements of the rear seats.

[0064] Passenger status is monitored through the passenger monitoring system (OMS). The OMS is equipped with a convolutional neural network pre-trained with a large number of images to identify the complete passenger exiting action, including identifying key points of the torso and limbs of rear passengers.

[0065] Monitor the environment on both sides of the vehicle through side-view cameras;

[0066] The current speed of the vehicle is obtained through real-time monitoring of the vehicle speed sensor.

[0067] It is understood that the method provided by the present invention further comprises: adjusting the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS to the passenger's state according to the driver's state monitored by the driver monitoring system DMS;

[0068] If the driver monitoring system (DMS) detects that the driver is seriously distracted or fatigued and not paying attention to the rear seat, the OMS's passenger status monitoring algorithm sensitivity level will be adjusted to high sensitivity. For example, in a specific example, at high sensitivity, as long as part of the rear passenger's body (including clothing) is detected in the camera image, it will be determined that the rear passenger has not completed the exit action.

[0069] If the driver monitoring system (DMS) detects that the driver is distracted or fatigued, the OMS's passenger status monitoring algorithm sensitivity level will be adjusted to medium sensitivity. For example, at medium sensitivity, the rear passenger's key body parts must be within the camera image before it is determined that the rear passenger has not completed the exit action.

[0070] If the driver monitoring system DMS detects that the driver is not tired and is paying attention to the rear seat, the algorithm sensitivity level of the passenger monitoring system OMS that monitors the passenger's status will be adjusted to low sensitivity. For example, in a specific example, under low sensitivity, it is necessary to identify the key points of the rear passenger's torso within the camera image, and then it is determined that the rear passenger has not completed the action of getting off the vehicle.

[0071] It is understandable that by differentiating the recognition sensitivity of the algorithm, the recognition rate of the rear passenger status is improved and the false recognition rate is reduced, and to a certain extent, the need for DMS / OMS cameras to monitor for a long time at the same time is avoided, thus avoiding excessive resource occupation.

[0072] Step S11: Perform a comprehensive judgment based on the monitoring results. If it is determined that a passenger is not in the state of getting off the vehicle or the distance between the person outside the vehicle and the vehicle is less than a predetermined threshold, and the vehicle speed is greater than zero, it is determined that there is a risk of crushing.

[0073] Step S12: When the judgment result shows that there is a crushing risk, a crushing risk prompt is issued and the vehicle is controlled to perform emergency braking.

[0074] Which further includes:

[0075] The passenger monitoring system (OMS) sends the identified rear passenger information to the side-view cameras;

[0076] When the side-view camera identifies that the attributes of the person outside the vehicle are consistent with the rear passenger information identified by the OMS, the horizontal distance between the rear passenger and the vehicle is monitored;

[0077] When the horizontal distance is greater than the predetermined threshold, the control prohibits triggering the crushing risk prompt. In this way, the scenario of false triggering can be avoided to a certain extent.

[0078] More specifically, in one example, controlling the vehicle to perform emergency braking further includes:

[0079] Obtain a pre-calibrated horizontal distance value L from the rear seat of the vehicle to the point where the rear tire may run over, and calculate the expected run-over time threshold value t1 in real time based on the horizontal distance value L and the current vehicle speed V. The horizontal distance value L can be calibrated by the relative horizontal position of the rear seat of the vehicle and the tires. The calibration is performed by evaluating and calibrating the location of the footfall points of passengers of different heights who disembark. For example, the area closest to the rear tire can be circled, and the horizontal distance L to the point where the rear tire may run over can be calculated. The expected run-over time threshold value t1 can be calculated using the L and the current vehicle speed V (or the average speed value after departure).

[0080] After the vehicle stops, the vehicle speed V is continuously monitored. If the monitored vehicle speed V>0, the cumulative time t after the vehicle starts is recorded; the cumulative time t after the vehicle starts is compared with the expected crushing time threshold t1. When t<t1, the vehicle IVI is used to issue a crushing risk warning; when t≥t1, the electronic body stability system ESP is controlled to perform emergency braking on the vehicle.

[0081] In a specific example, the car's IVI will make voice announcements and reminders based on different situations, such as: "The occupants of the car have not completely gotten out, please do not drive, please pay attention to safety", "There are pedestrians approaching the car, please confirm that it is safe before driving", etc.

[0082] It is understandable that, in the method provided by the present invention, without adding any hardware to the intelligent connected vehicle, anti-crush monitoring processing in two scenarios can be effectively implemented:

[0083] Scenario 1: The OMS system identifies and determines the posture of the occupants to see if they have not completed their exit. (For example, the OMS system can detect the head, body, and hands of the occupants in the cabin to determine if they have not completed their exit.) If the driver drives the vehicle at this time, the ESP system will perform emergency braking to ensure the safety of the occupants.

[0084] Scenario 2: The side-view camera determines the vertical distance between a person and the side of the vehicle and sets a threshold. When the driver drives the vehicle and the distance is within the threshold, the vehicle will perform emergency braking to ensure the safety of the outsider.

[0085] like Figure 3FIG. 1 is a schematic diagram showing a structure of an embodiment of a vehicle anti-crushing monitoring and processing system provided by the present invention. In this embodiment, the system 1 at least includes:

[0086] The real-time monitoring unit 10 is used to monitor the driver's status, the passenger's status, the environment on both sides of the vehicle and the vehicle speed in real time after the vehicle stops;

[0087] The crush risk judgment unit 11 is used to determine whether the passenger is in the state of getting off the vehicle, or whether there are people outside the vehicle on both sides of the vehicle according to the monitoring results;

[0088] The anti-crushing processing unit 12 is used to issue a crushing danger warning and control the vehicle to perform emergency braking after monitoring that the passenger has not completed getting off the vehicle or the distance between the person outside the vehicle and the vehicle is less than a predetermined threshold and the vehicle speed is greater than zero.

[0089] The algorithm sensitivity adjustment unit 13 is used to adjust the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS to the passenger's status according to the driver's status monitored by the driver monitoring system DMS;

[0090] If the driver monitoring system (DMS) detects that the driver is seriously distracted or fatigued and not paying attention to the rear seats, the sensitivity level of the passenger monitoring algorithm of the passenger monitoring system (OMS) will be adjusted to high sensitivity.

[0091] If the driver monitoring system (DMS) detects that the driver is distracted or fatigued, the sensitivity level of the algorithm used by the passenger monitoring system (OMS) to monitor the passenger's status is adjusted to medium sensitivity;

[0092] If the driver monitoring system DMS detects that the driver is not tired and is paying attention to the back seat, the algorithm sensitivity level of the passenger monitoring system OMS that monitors the passenger's status is adjusted to low sensitivity.

[0093] Among them, the passenger monitoring system OMS is equipped with a convolutional neural network that has been pre-trained and learned through a large number of pictures, which is used to identify the complete passenger getting off the bus, including: identifying the torso key points and limb key points of the rear passengers.

[0094] And further includes: an association processing unit 14, which is used for the passenger monitoring system OMS to send the identified rear passenger information to the side-view camera; when the side-view camera identifies that the attributes of the person outside the vehicle are consistent with the rear passenger information identified by the passenger monitoring system OMS, it monitors the horizontal distance between the rear passenger and the vehicle; when the horizontal distance is greater than the predetermined threshold, the control prohibits triggering the crushing risk prompt.

[0095] In a specific example, the real-time monitoring unit 10 is further configured to:

[0096] Monitor the driver's status through the driver monitoring system DMS;

[0097] Monitor the status of passengers through the passenger monitoring system OMS;

[0098] Monitor the environment on both sides of the vehicle through side-view cameras;

[0099] The current speed of the vehicle is obtained through real-time monitoring of the vehicle speed sensor.

[0100] Among them, the anti-crushing processing unit 12 is configured to: obtain a pre-calibrated horizontal distance value L from the rear position of the vehicle to the possible crushing point of the rear tire, and calculate the expected crushing time threshold t1 in real time based on the horizontal distance value L and the current vehicle speed V; compare the accumulated time t after the vehicle starts with the expected crushing time threshold t1, and when t<t1, issue a crushing risk prompt; when t≥t1, control the electronic body stability system ESP to perform emergency braking on the vehicle.

[0101] For more details, please refer to and combine the above Figures 1 to 2 The description is not repeated here.

[0102] As another aspect of the present invention, there is also provided an intelligent driving processing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the aforementioned Figures 1 to 2 For more details, please refer to and combine the above Figures 1 to 2 The description is not repeated here.

[0103] As another aspect of the present invention, a computer-readable storage medium is provided on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figures 1 to 2 For more details, please refer to and combine the above Figures 1 to 2 The description is not repeated here.

[0104] As another aspect of the present invention, a computer program product is provided, comprising computer instructions, wherein the computer instructions instruct a computer device to execute the above-mentioned Figures 1 to 2 For more details, please refer to and combine the above Figures 1 to 2 The description is not repeated here.

[0105] The implementation of the embodiments of the present invention has the following beneficial effects:

[0106] The present invention provides a vehicle crush prevention monitoring and processing method, system, device, and storage medium. The method intelligently detects the exit status of passengers by monitoring the driver's status through a driver monitoring system (DMS) and the passenger's status through an passenger monitoring system (OMS). Side-view cameras are used to identify and determine whether pedestrians are standing to the side of the vehicle, monitoring their posture and proximity to the vehicle. If a passenger is determined to be incompletely exiting the vehicle or the distance from an outsider to the vehicle is less than a predetermined threshold, and the vehicle speed is greater than zero, a crush risk is determined. In such cases, the ESP system can implement emergency braking. This improves vehicle start safety and prevents accidents.

[0107] In addition, in an embodiment of the present invention, the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS to the passenger's status is adjusted according to the driver's status monitored by the driver monitoring system DMS; by differentiating the algorithm recognition sensitivity, the recognition rate of the rear passenger status is improved and the false recognition rate is reduced, and to a certain extent, the need for simultaneous long-term monitoring by the DMS / OMS cameras is avoided, thereby avoiding excessive resource occupation and reducing the cost of use.

[0108] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0109] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts and / or block diagrams. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0110] The above disclosure is only a preferred embodiment of the present invention and certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A monitoring and processing method for preventing vehicle crushing, characterized in that: At least the following steps are included: When the vehicle stops, the driver's status, the passenger's status, the vehicle's surroundings, and the vehicle speed are monitored in real time; this includes at least: monitoring the driver's status through a driver monitoring system (DMS); and monitoring the passenger's status through an passenger monitoring system (OMS); A comprehensive assessment is made based on the monitoring results. If it is determined that a passenger has not yet completed getting off the vehicle or the distance between the person outside the vehicle and the vehicle is less than a predetermined threshold, and the vehicle speed is greater than zero, a crushing risk is determined. When the judgment result is that there is a crushing risk, a crushing risk warning will be issued and the vehicle will be controlled to perform emergency braking; The method further includes adjusting the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS to the passenger's state according to the driver's state monitored by the driver monitoring system DMS.

2. The method according to claim 1, wherein Real-time monitoring of the driver's status, passenger status, vehicle environment, and vehicle speed further includes: Monitor the environment on both sides of the vehicle through side-view cameras; The current speed of the vehicle is obtained through real-time monitoring of the vehicle speed sensor.

3. The method according to claim 2, wherein According to the driver status monitored by the driver monitoring system DMS, the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS to the passenger status is adjusted, including: If the driver monitoring system (DMS) detects that the driver is seriously distracted or fatigued and is not paying attention to the rear seats, the sensitivity level of the algorithm used by the passenger monitoring system (OMS) to monitor the passenger's status will be adjusted to high sensitivity. If the driver monitoring system (DMS) detects that the driver is distracted or fatigued, the sensitivity level of the algorithm used by the passenger monitoring system (OMS) to monitor the passenger's status is adjusted to medium sensitivity; If the driver monitoring system DMS detects that the driver is not tired and is paying attention to the back seat, the algorithm sensitivity level of the passenger monitoring system OMS that monitors the passenger's status is adjusted to low sensitivity.

4. The method according to claim 3, wherein Further including: The passenger monitoring system (OMS) is equipped with a convolutional neural network that has been pre-trained using a large number of images. It is used to identify the complete passenger's getting off-board action, including identifying the torso key points and limb key points of rear-seat passengers.

5. The method according to claim 3, wherein Further including: The passenger monitoring system (OMS) sends the identified rear passenger information to the side-view cameras; When the side-view camera identifies that the attributes of the person outside the vehicle are consistent with the rear passenger information identified by the OMS, the horizontal distance between the rear passenger and the vehicle is monitored; When the horizontal distance is greater than the predetermined threshold, the control prohibits triggering the crushing risk prompt.

6. The method according to any one of claims 1 to 5, characterized in that The controlling the vehicle to perform emergency braking further includes: Obtain a pre-calibrated horizontal distance value L from the rear seat of the vehicle to the possible crushing point of the rear tire, and calculate the estimated crushing time threshold t1 in real time based on the horizontal distance value L and the current vehicle speed V; The accumulated time t after the vehicle starts is compared with the estimated crushing time threshold t1. When t<t1, a crushing risk warning is issued; when t≥t1, the electronic body stability system ESP is controlled to perform emergency braking on the vehicle.

7. A vehicle anti-crushing monitoring and processing system, characterized in that: At least: A real-time monitoring unit, configured to monitor the driver's status, the passenger's status, the vehicle's surroundings, and the vehicle's speed in real time after the vehicle stops, the real-time monitoring unit being configured to at least: monitor the driver's status via a driver monitoring system (DMS) and monitor the passenger's status via a passenger monitoring system (OMS); The crush risk judgment unit is used to make a comprehensive judgment based on the monitoring results. When it is determined that the passenger is in the state of not completing the disembarkation or the distance between the person outside the vehicle and the vehicle is less than a predetermined threshold, and the vehicle speed is greater than zero, it is determined that there is a crush risk; The anti-crushing processing unit is used to issue a crushing danger warning and control the vehicle to perform emergency braking after detecting that a passenger has not completed getting off the vehicle or the distance between the person outside the vehicle and the vehicle is less than a predetermined threshold and the vehicle speed is greater than zero; Further including: The algorithm sensitivity adjustment unit is used to adjust the sensitivity level of the monitoring algorithm of the passenger monitoring system OMS to the passenger's status according to the driver status monitored by the driver monitoring system DMS.

8. The system according to claim 7, wherein: The real-time monitoring unit is further configured to: Monitor the environment on both sides of the vehicle through side-view cameras; The current speed of the vehicle is obtained through real-time monitoring of the vehicle speed sensor.

9. The system according to claim 8, wherein The algorithm sensitivity adjustment unit adjusts the sensitivity level of the passenger monitoring algorithm of the passenger monitoring system OMS to the passenger status in the following manner: If the driver monitoring system (DMS) detects that the driver is seriously distracted or fatigued and is not paying attention to the rear seats, the sensitivity level of the passenger monitoring algorithm of the passenger monitoring system (OMS) will be adjusted to high sensitivity; If the driver monitoring system (DMS) detects that the driver is distracted or fatigued, the sensitivity level of the algorithm used by the passenger monitoring system (OMS) to monitor the passenger's status is adjusted to medium sensitivity; If the driver monitoring system DMS detects that the driver is not tired and is paying attention to the back seat, the algorithm sensitivity level of the passenger monitoring system OMS that monitors the passenger's status is adjusted to low sensitivity.

10. The system according to any one of claims 7 to 9, characterized in that The anti-crushing processing unit is configured to: obtain a pre-calibrated horizontal distance value L from the rear seat position of the vehicle to a possible crushing point of the rear tire; calculate an estimated crushing time threshold t1 in real time based on the horizontal distance value L and the current vehicle speed V; compare the accumulated time t after the vehicle starts with the estimated crushing time threshold t1; and issue a crushing risk warning when t < t1; When t≥t1, the electronic body stability system ESP is controlled to perform emergency braking on the vehicle.

11. An intelligent driving processing device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

13. A computer program product comprising computer instructions, wherein the computer instructions instruct a computer device to perform operations corresponding to the method according to any one of claims 1 to 6.

Images