Vehicle fall detection method and apparatus

Abstract

A vehicle fall detection method, an apparatus, a vehicle, a system, a computer-readable storage medium, and a computer program product. The method comprises: acquiring first information (201), wherein the first information comprises accelerations of a vehicle in a first direction, a second direction, and a third direction, and / or angular velocities of the vehicle in the first direction, the second direction, and the third direction, and the first direction, the second direction, and the third direction are three coordinate axis directions of a three-dimensional coordinate system, respectively; and on the basis of the first information, determining whether the vehicle has experienced a fall event (202).

Description

A method and apparatus for detecting vehicle falls

[0001] Cross-reference to related applications

[0002] This application claims priority to Chinese Patent Application No. 202411798016.1, filed on December 9, 2024, entitled "A Method and Apparatus for Detecting Vehicle Falls", the entire contents of which are incorporated herein by reference. Technical Field

[0003] This application relates to the field of vehicle networking technology, and in particular to a method and device for vehicle fall detection. Background Technology

[0004] With the rapid development of automotive technology, more and more people are choosing to travel by car, which has made people pay more and more attention to the safety of driving.

[0005] When vehicles fall due to natural environmental factors such as road collapses or bridge breaks, or due to human error, it can cause vehicle damage, injuries, and even large-scale traffic accidents. To reduce the casualties and resource losses caused by vehicle falls, it is necessary to detect whether a vehicle has experienced a fall. Summary of the Invention

[0006] This application provides a vehicle drop detection method and apparatus for determining whether a vehicle has experienced a drop event.

[0007] Firstly, this application provides a vehicle drop detection method, which can be applied to an in-vehicle device, or a module of the in-vehicle device (such as a processor, processing unit, chip, circuit, etc.), or a system corresponding to the in-vehicle device. Based on this, the method includes: acquiring first information, wherein the first information includes the acceleration of the vehicle in a first direction, a second direction, and a third direction, and / or the angular velocity of the vehicle in the first direction, the second direction, and the third direction, where the first direction, the second direction, and the third direction are the three coordinate axes of a three-dimensional coordinate system; and then, determining whether a vehicle drop event has occurred based on the first information.

[0008] In the above method, the first direction can be the x-axis of a three-dimensional coordinate system, the second direction can be the y-axis of a three-dimensional coordinate system, and the third direction can be the z-axis of a three-dimensional coordinate system. In other words, relative to the ground, the first and second directions are horizontal, and the third direction is vertical. This application considers the possible changes in vehicle orientation and rollover during a fall event. Therefore, it performs fall detection based on the vehicle's acceleration (generally not gravitational acceleration) in the first, second, and third directions, and / or the vehicle's angular velocity in the first, second, and third directions, rather than solely relying on the vehicle's velocity change in the third direction. This not only determines whether a fall event has occurred but also ensures the accuracy of the fall detection.

[0009] In one possible implementation, determining whether a vehicle has fallen based on the first information includes: if the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, and the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, then it is determined that a vehicle has fallen.

[0010] Alternatively, based on the first information, determine whether a vehicle has fallen, including: determining the combined acceleration of the vehicle in the first direction, the second direction, and the third direction; if the combined acceleration is greater than or equal to a first threshold, then determine that a vehicle has fallen.

[0011] The above implementation can be applied to scenarios where the first information includes the vehicle's acceleration and angular velocity in the first, second, and third directions, or to scenarios where the first information only includes the vehicle's acceleration in the first, second, and third directions. By performing drop detection on the vehicle using only its acceleration in the first, second, and third directions, drop detection can be performed with a smaller amount of data, reducing computational resource consumption and improving computational efficiency.

[0012] In one possible implementation, determining whether a vehicle has fallen based on the first information includes: if the angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the angular velocity of the vehicle in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction, then it is determined that a vehicle has fallen.

[0013] Alternatively, based on the first information, determine whether a fall event has occurred in the first vehicle, including: determining the angle of the vehicle in the first direction based on the angular velocity of the vehicle in the first direction, determining the angle of the vehicle in the second direction based on the angular velocity of the vehicle in the second direction, and determining the angle of the vehicle in the third direction based on the angular velocity of the vehicle in the third direction; if the angle of the vehicle in the first direction is greater than or equal to the angle threshold corresponding to the first direction, the angle of the vehicle in the second direction is greater than or equal to the angle threshold corresponding to the second direction, and the angle of the vehicle in the third direction is greater than or equal to the angle threshold corresponding to the third direction, then determine that a fall event has occurred in the vehicle.

[0014] The above implementation can be applied to scenarios where the first information includes the vehicle's acceleration and angular velocity in the first, second, and third directions, or to scenarios where the first information only includes the vehicle's angular velocity in the first, second, and third directions. By performing drop detection on the vehicle using only its angular velocities in the first, second, and third directions, drop detection can be performed with a smaller amount of data, reducing computational resource consumption and improving computational efficiency.

[0015] In one possible implementation, determining whether a vehicle has fallen based on the first information includes: if the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, the vehicle's acceleration in a third direction is greater than or equal to the acceleration threshold corresponding to the third direction, the vehicle's angular velocity in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the vehicle's angular velocity in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the vehicle's angular velocity in a third direction is greater than or equal to the angular velocity threshold corresponding to the third direction, then it is determined that a vehicle has fallen.

[0016] Alternatively, based on the first information, determine whether a vehicle has fallen, including: determining the combined acceleration of the vehicle in the first direction, the second direction, and the third direction; if the combined acceleration is greater than or equal to a first threshold, the angular velocity of the vehicle in the first direction is greater than or equal to the corresponding angular velocity threshold, the angular velocity of the vehicle in the second direction is greater than or equal to the corresponding angular velocity threshold, and the angular velocity of the vehicle in the third direction is greater than or equal to the corresponding angular velocity threshold, then determine that a vehicle has fallen.

[0017] Alternatively, based on the first information, determine whether a vehicle has fallen, including: determining the vehicle's angle in the first direction based on the vehicle's angular velocity in the first direction, determining the vehicle's angle in the second direction based on the vehicle's angular velocity in the second direction, and determining the vehicle's angle in the third direction based on the vehicle's angular velocity in the third direction; if the vehicle's angle in the first direction is greater than or equal to the angle threshold corresponding to the first direction, the vehicle's angle in the second direction is greater than or equal to the angle threshold corresponding to the second direction, the vehicle's angle in the third direction is greater than or equal to the angle threshold corresponding to the third direction, the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, and the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, then determine that a vehicle has fallen.

[0018] Alternatively, based on the first information, determine whether a vehicle has fallen, including: determining the resultant acceleration of the vehicle in a first direction, a second direction, and a third direction; determining the vehicle's angle in the first direction based on its angular velocity in the first direction, determining the vehicle's angle in the second direction based on its angular velocity in the second direction, and determining the vehicle's angle in the third direction based on its angular velocity in the third direction; if the resultant acceleration is greater than or equal to a first threshold, the vehicle's angle in the first direction is greater than or equal to the corresponding angle threshold in the first direction, the vehicle's angle in the second direction is greater than or equal to the corresponding angle threshold in the second direction, and the vehicle's angle in the third direction is greater than or equal to the corresponding angle threshold in the third direction, then determine that a vehicle has fallen.

[0019] The above implementation method can be applied to scenarios where the first information includes the vehicle's acceleration and angular velocity in the first, second, and third directions. By using the vehicle's acceleration and angular velocity in the first, second, and third directions, drop detection can be performed, thus ensuring the accuracy of vehicle drop detection.

[0020] In one possible implementation, determining whether a vehicle has fallen based on the first information includes: inputting the first information into a first model to obtain a detection result output by the first model, wherein the detection result output by the first model is used to indicate that a vehicle has fallen, or the detection result output by the first model is used to indicate that a vehicle has not fallen; wherein the training convergence target of the first model is the first information when a vehicle falls.

[0021] In the above implementation, the first model can be a neural network model, a deep learning model, or a deep neural network model. The first information when a vehicle falls may include the acceleration of the vehicle in the first, second, and third directions, and / or the angular velocity of the vehicle in the first, second, and third directions. It can be understood that using the first model to perform vehicle fall detection can improve the efficiency of vehicle fall detection.

[0022] In one possible implementation, the method further includes: when it is determined that a vehicle has fallen, broadcasting first indication information and issuing an alarm, the first indication information indicating that the vehicle has fallen, the first indication information including the location of the vehicle fall.

[0023] In the above implementation, the fall event is transmitted to the outside world through the first indication information. This can alert other vehicles and prevent secondary accidents, thereby reducing casualties and resource losses caused by the fall. The alarm can be used to call for help, ensuring the real-time nature of rescue efforts in response to the fall event.

[0024] Secondly, this application provides a vehicle drop detection method, which can be applied to an in-vehicle device, or a module of the in-vehicle device (such as a processor, processing unit, chip, circuit, etc.), or a system corresponding to the in-vehicle device. Based on this, the method includes: acquiring first information and second information, the first information including the acceleration and angular velocity of the vehicle in a first direction, a second direction, and a third direction, where the first direction, the second direction, and the third direction are the three coordinate axes of a three-dimensional coordinate system; the second information including at least one of the following: the vehicle's tire pressure, the vehicle's suspension height, and environmental information; and then, determining whether a drop event has occurred in the vehicle based on the first information and the second information.

[0025] The above method combines the first and second information to perform drop detection on the vehicle. This not only determines whether a drop event has occurred, but also ensures the accuracy of the vehicle drop detection.

[0026] In one possible implementation, determining whether a fall event has occurred in the first vehicle based on the first information and the second information includes:

[0027] When the first information meets the following detection conditions, the second information is used to determine whether a vehicle has fallen.

[0028] The testing conditions include:

[0029] The vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction;

[0030] The vehicle's acceleration in the second direction is greater than or equal to the corresponding acceleration threshold in the second direction;

[0031] The vehicle's acceleration in the third direction is greater than or equal to the corresponding acceleration threshold in the third direction;

[0032] The vehicle's angular velocity in the first direction is greater than or equal to the corresponding angular velocity threshold in the first direction;

[0033] The vehicle's angular velocity in the second direction is greater than or equal to the corresponding angular velocity threshold in the second direction;

[0034] The vehicle's angular velocity in the third direction is greater than or equal to the corresponding angular velocity threshold in the third direction.

[0035] In one possible implementation, determining whether a vehicle has fallen based on the second information includes: if the vehicle's tire pressure is greater than or equal to a pressure threshold, then determining that a vehicle has fallen.

[0036] Alternatively, based on the second information, determine whether a vehicle has experienced a fall event, including: if the vehicle's suspension height is less than or equal to a height threshold, then determine that a vehicle has experienced a fall event.

[0037] Alternatively, based on the second information, determine whether a vehicle has fallen, including: if the similarity between the environmental information corresponding to the vehicle at the current moment and the environmental information corresponding to the vehicle at the previous moment is less than or equal to a second threshold, then determine that a vehicle has fallen.

[0038] In the above implementation, the tire pressure of the vehicle can be the tire pressure of all wheels of the vehicle, or the tire pressure of some wheels of the vehicle; the suspension height of the vehicle can be the suspension height corresponding to all wheels of the vehicle, or the suspension height corresponding to some wheels of the vehicle; the environmental information corresponding to the vehicle includes, but is not limited to, visual images (such as images collected by image acquisition devices installed on the vehicle, visual data measured by visual sensors), and laser point clouds (such as laser point clouds generated based on millimeter-wave radar, ultrasonic radar, and lidar installed on the vehicle).

[0039] In one possible implementation, determining whether a first vehicle has experienced a fall event based on first information and second information includes: inputting the first information and second information into a second model to obtain a detection result output by the second model, wherein the detection result output by the second model is used to indicate that a fall event has occurred, or the detection result output by the second model is used to indicate that a fall event has not occurred; wherein the training convergence target of the second model is the first information and second information when a fall event occurs.

[0040] In the above implementation, the second model can be a neural network model, a deep learning model, or a deep neural network model. The first information regarding a vehicle fall event may include the vehicle's acceleration in the first, second, and third directions, and / or the vehicle's angular velocity in the first, second, and third directions. The second information regarding a vehicle fall event may include the vehicle's tire pressure at the time of the fall event, and / or the vehicle's suspension height at the time of the fall event, and / or the similarity between the environmental information at the time of the fall event and the environmental information corresponding to the moment preceding the fall event. It can be understood that the second model can be used for vehicle fall detection, thus improving the efficiency of vehicle fall detection.

[0041] In one possible implementation, the method further includes: when it is determined that a vehicle has fallen, broadcasting first indication information and issuing an alarm, the first indication information indicating that the vehicle has fallen, the first indication information including the location of the vehicle fall.

[0042] Thirdly, this application provides an apparatus disposed in a vehicle (i.e., the apparatus is an in-vehicle device), the apparatus including an acquisition module and a processing module; wherein, the acquisition module is used to acquire first information, the first information including the acceleration of the vehicle in a first direction, a second direction and a third direction, and / or the angular velocity of the vehicle in the first direction, the second direction and the third direction, the first direction, the second direction and the third direction being the three coordinate axes of a three-dimensional coordinate system; the processing module is used to determine whether a fall event has occurred in the vehicle based on the first information.

[0043] In one possible implementation, the processing module is specifically used to: determine that a vehicle has fallen if the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, and the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction.

[0044] In one possible implementation, the processing module is specifically used to: determine the resultant acceleration of the vehicle's acceleration in the first direction, the acceleration in the second direction, and the acceleration in the third direction; if the resultant acceleration is greater than or equal to a first threshold, then determine that a vehicle has fallen.

[0045] In one possible implementation, the processing module is specifically used to: determine that a vehicle has fallen if the angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the angular velocity of the vehicle in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction.

[0046] In one possible implementation, the processing module is specifically used to: determine the angle of the vehicle in the first direction based on the angular velocity of the vehicle in the first direction, determine the angle of the vehicle in the second direction based on the angular velocity of the vehicle in the second direction, and determine the angle of the vehicle in the third direction based on the angular velocity of the vehicle in the third direction; if the angle of the vehicle in the first direction is greater than or equal to the angle threshold corresponding to the first direction, the angle of the vehicle in the second direction is greater than or equal to the angle threshold corresponding to the second direction, and the angle of the vehicle in the third direction is greater than or equal to the angle threshold corresponding to the third direction, then it is determined that a vehicle fall event has occurred.

[0047] In one possible implementation, the processing module is specifically configured to: determine that a vehicle fall event has occurred if the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, the vehicle's angular velocity in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the vehicle's angular velocity in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the vehicle's angular velocity in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction.

[0048] In one possible implementation, the processing module is specifically used to: determine the resultant acceleration of the vehicle in the first direction, the second direction, and the third direction; if the resultant acceleration is greater than or equal to a first threshold, the angular velocity of the vehicle in the first direction is greater than or equal to the corresponding angular velocity threshold in the first direction, the angular velocity of the vehicle in the second direction is greater than or equal to the corresponding angular velocity threshold in the second direction, and the angular velocity of the vehicle in the third direction is greater than or equal to the corresponding angular velocity threshold in the third direction, then it is determined that a vehicle fall event has occurred.

[0049] In one possible implementation, the processing module is specifically used to: determine the angle of the vehicle in the first direction based on the angular velocity of the vehicle in the first direction, determine the angle of the vehicle in the second direction based on the angular velocity of the vehicle in the second direction, and determine the angle of the vehicle in the third direction based on the angular velocity of the vehicle in the third direction; if the angle of the vehicle in the first direction is greater than or equal to the angle threshold corresponding to the first direction, the angle of the vehicle in the second direction is greater than or equal to the angle threshold corresponding to the second direction, the angle of the vehicle in the third direction is greater than or equal to the angle threshold corresponding to the third direction, the acceleration of the vehicle in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the acceleration of the vehicle in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, and the acceleration of the vehicle in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, then it is determined that a vehicle fall event has occurred.

[0050] In one possible implementation, the processing module is specifically used to: determine the resultant acceleration of the vehicle in a first direction, a second direction, and a third direction; determine the angle of the vehicle in the first direction based on the angular velocity of the vehicle in the first direction, determine the angle of the vehicle in the second direction based on the angular velocity of the vehicle in the second direction, and determine the angle of the vehicle in the third direction based on the angular velocity of the vehicle in the third direction; if the resultant acceleration is greater than or equal to a first threshold, the angle of the vehicle in the first direction is greater than or equal to the corresponding angle threshold in the first direction, the angle of the vehicle in the second direction is greater than or equal to the corresponding angle threshold in the second direction, and the angle of the vehicle in the third direction is greater than or equal to the corresponding angle threshold in the third direction, then determine that a vehicle fall event has occurred.

[0051] In one possible implementation, the processing module is specifically used to: input the first information into the first model to obtain the detection result output by the first model, wherein the detection result output by the first model is used to indicate that a vehicle has fallen, or the detection result output by the first model is used to indicate that a vehicle has not fallen; wherein the training convergence target of the first model is the first information when a vehicle falls.

[0052] In one possible implementation, the processing module is further configured to: broadcast first indication information and issue an alarm when it is determined that a vehicle has fallen, the first indication information being used to indicate that the vehicle has fallen, and the first indication information including the location of the vehicle fall.

[0053] Fourthly, this application provides an apparatus disposed in a vehicle (i.e., the apparatus is an in-vehicle device), the apparatus comprising an acquisition module and a processing module; wherein, the acquisition module is used to acquire first information and second information, the first information including the acceleration and angular velocity of the vehicle in a first direction, a second direction, and a third direction, the first direction, the second direction, and the third direction being the three coordinate axes of a three-dimensional coordinate system, the second information including at least one of the following: tire pressure of the vehicle, suspension height of the vehicle, and environmental information; the processing module is used to determine whether a fall event has occurred in the vehicle based on the first information and the second information.

[0054] In one possible implementation, the processing module is specifically used to: determine whether a vehicle has fallen based on the second information when the first information satisfies the following detection conditions;

[0055] The testing conditions include:

[0056] The vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction;

[0057] The vehicle's acceleration in the second direction is greater than or equal to the corresponding acceleration threshold in the second direction;

[0058] The vehicle's acceleration in the third direction is greater than or equal to the corresponding acceleration threshold in the third direction;

[0059] The vehicle's angular velocity in the first direction is greater than or equal to the corresponding angular velocity threshold in the first direction;

[0060] The vehicle's angular velocity in the second direction is greater than or equal to the corresponding angular velocity threshold in the second direction;

[0061] The vehicle's angular velocity in the third direction is greater than or equal to the corresponding angular velocity threshold in the third direction.

[0062] In one possible implementation, the processing module is specifically used to: determine that a vehicle has fallen if the vehicle's tire pressure is greater than or equal to a pressure threshold.

[0063] In one possible implementation, the processing module is specifically used to: determine that a vehicle has fallen if the vehicle's suspension height is less than or equal to a height threshold.

[0064] In one possible implementation, the processing module is specifically used to: determine that a vehicle has fallen if the similarity between the environmental information corresponding to the vehicle at the current moment and the environmental information corresponding to the vehicle at the previous moment is less than or equal to a second threshold.

[0065] In one possible implementation, the processing module is specifically used to: input the first information and the second information into the second model to obtain the detection result output by the second model, the detection result output by the second model is used to indicate that a vehicle has fallen, or the detection result output by the second model is used to indicate that a vehicle has not fallen; wherein, the training convergence target of the second model is the first information and the second information when a vehicle falls.

[0066] In one possible implementation, the processing module is further configured to: broadcast first indication information and issue an alarm when it is determined that a vehicle has fallen, the first indication information being used to indicate that the vehicle has fallen, and the first indication information including the location of the vehicle fall.

[0067] Fifthly, this application provides a vehicle including an Inertial Measurement Unit (IMU) and means for performing the methods described in the first or second aspect above. The IMU is used to measure the vehicle's acceleration (including acceleration in a first direction, a second direction, and a third direction) and angular velocity (including angular velocity in the first direction, a second direction, and a third direction). Optionally, the vehicle further includes a Tire Pressure Monitoring System (TPMS) sensor for measuring the vehicle's tire pressure. Optionally, the vehicle further includes a suspension sensor for measuring the vehicle's suspension height. Optionally, the vehicle further includes an image acquisition device and an onboard radar device, the image acquisition device and the onboard radar device being used to generate environmental information corresponding to the vehicle.

[0068] Sixthly, this application provides a system comprising a vehicle and a network device (such as a cloud server) for performing the methods described in the first or second aspect above. The network device is configured to receive first indication information sent by the vehicle and send second indication information to other vehicles. The first indication information indicates that a vehicle has experienced a fall event and includes the location of the fall. The second indication information indicates the vehicle that experienced the fall event and includes the location of the vehicle that experienced the fall event.

[0069] In a seventh aspect, a computer device is provided, including a processor, a memory, a communication interface, and a bus. The processor, memory, and communication interface are connected via the bus and communicate with each other. The memory stores computer execution instructions. When the computer device is in operation, the processor executes the computer execution instructions in the memory to perform the operation steps of the method described in the first or second aspect using the hardware resources of the computer device.

[0070] Eighthly, an apparatus is provided, comprising one or more processors and one or more memories; the one or more memories storing one or more computer programs, the one or more computer programs including instructions that, when executed by the one or more processors, cause the apparatus to perform the operational steps of the method described in the first or second aspect above.

[0071] A ninth aspect provides a chip system comprising at least one chip and a memory, wherein the at least one chip is configured to read and execute a program stored in the memory to implement the operational steps of the method described in the first or second aspect above.

[0072] In a tenth aspect, a non-volatile computer-readable storage medium is provided, the non-volatile computer-readable storage medium including a program that, when the program is run on a device, causes the device to perform the operation steps of the method described in the first or second aspect above.

[0073] Eleventhly, a computer program product is provided, which, when run on a device, causes the device to perform the operational steps of the method described in the first or second aspect above.

[0074] Based on the implementation methods provided in the above aspects, this application can be further combined to provide more implementation methods. Attached Figure Description

[0075] Figure 1 is a structural schematic diagram of a vehicle-mounted device provided in this application;

[0076] Figure 2 is a flowchart illustrating a vehicle drop detection method provided in this application;

[0077] Figure 3 is a schematic diagram of an application scenario provided in this application;

[0078] Figure 4 is a flowchart illustrating a fall avoidance control method provided in this application;

[0079] Figure 5 is a structural schematic diagram of another vehicle-mounted device provided in this application;

[0080] Figure 6 is a flowchart illustrating another vehicle drop detection method provided in this application;

[0081] Figure 7 is a schematic diagram of another application scenario provided in this application;

[0082] Figure 8 is a structural schematic diagram of a device provided in this application;

[0083] Figure 9 is a structural schematic diagram of a device provided in this application. Detailed Implementation

[0084] In recent years, with the development of the automotive industry and the rapid development of automotive technology, more and more people are choosing to travel by car, which has made people pay more and more attention to the safety of driving.

[0085] When vehicles fall due to natural environmental factors such as road collapses or bridge breaks, or due to human error, it can cause vehicle damage, injuries, and even large-scale traffic accidents. To reduce the casualties and resource losses caused by vehicle falls, it is necessary to detect whether a vehicle has experienced a fall.

[0086] In related technologies, considering the change in height of a vehicle in the direction of fall, drop detection is performed based on the rate and manner of this height change. However, some vehicles lack a level sensor (used to measure vehicle height), making drop detection impossible for them.

[0087] Therefore, this application provides a vehicle drop detection method, which aims to determine whether a vehicle drop event has occurred by detecting the vehicle's acceleration in a first, second, and third direction, and / or the vehicle's angular velocity in the same direction. The vehicle's acceleration and angular velocity in these directions can be measured using an inertial measurement unit (IMU) installed on the vehicle. It is understood that most vehicles have an IMU, so the vehicle drop detection method of this application can be applied to most vehicles, improving the universality of vehicle drop detection.

[0088] Figure 1 is a schematic diagram of a vehicle-mounted device provided in this application. The device includes a data center unit and a vehicle information unit (VIU). The data center unit can be a mobile data center (MDC), which includes a data cleaning unit. The data cleaning unit receives first information measured by the IMU (including the vehicle's acceleration in the first, second, and third directions, and / or the vehicle's angular velocity in the first, second, and third directions), and performs data cleaning on this data. Data cleaning includes, but is not limited to, removing invalid data, completing data, interpolation, filtering, and limiting the slope to ensure the accuracy of subsequent vehicle drop detection. The VIU includes a drop detection unit. This drop detection unit determines whether a vehicle drop event has occurred based on the vehicle's acceleration in the first, second, and third directions, and / or the vehicle's angular velocity in the first, second, and third directions after data cleaning.

[0089] Figure 2 is a flowchart illustrating a vehicle drop detection method provided in this application. This process is applied to the vehicle-mounted device shown in Figure 1, or a module of the vehicle-mounted device (such as a processor, processing unit, chip, circuit, etc.), or the corresponding system of the vehicle-mounted device. The vehicle-mounted device can be installed in a vehicle that enables intelligent driving. For example, the vehicle may be equipped with a driving system, such as an Advanced Driving System (ADS). Optionally, the ADS level installed in the vehicle can be at least one of the following: Level 2 (combined driving assistance), Level 3 (conditional automated driving), Level 4 (highly automated driving), or Level 5 (fully automated driving).

[0090] As shown in Figure 2, the method may include the following steps:

[0091] Step 201: Obtain first information, which includes the vehicle's acceleration in the first direction, the second direction, and the third direction, and / or the vehicle's angular velocity in the first direction, the second direction, and the third direction.

[0092] In one possible implementation, the first information is obtained from IMU measurements. An IMU is a device that measures the three-axis attitude angles (or angular rates) and acceleration of a target object. For example, an IMU typically includes three single-axis accelerometers and three single-axis gyroscopes. The accelerometers measure the acceleration signals of the target object along the three independent axes of the carrier coordinate system, and the gyroscopes measure the angular velocity signals of the carrier relative to the navigation coordinate system. Therefore, the IMU can measure the angular velocity and acceleration of a target object (such as a vehicle) in three-dimensional space.

[0093] It is understandable that three-dimensional space can be oriented using a three-dimensional coordinate system, which can be a Cartesian coordinate system. In this process, the first direction, the second direction, and the third direction are the three coordinate axes of the three-dimensional coordinate system; for example, the first direction can be the x-axis direction, the second direction can be the y-axis direction, and the third direction can be the z-axis direction. Alternatively, relative to the ground, the first and second directions are horizontal, and the third direction is vertical.

[0094] For example, a normal driving scenario for a vehicle may include the following scenarios. In different scenarios, the acceleration of the vehicle in the first direction, the second direction, and the third direction, and the angular velocity of the vehicle in the first direction, the second direction, and the third direction may be different.

[0095] Scenario 1: Vehicle traveling horizontally. In this scenario, assume the vehicle's direction of travel is not either the first or second direction. For example, if the angle between the vehicle's direction of travel and the first or second direction is 45°, when the vehicle is traveling at a constant speed, the vehicle's acceleration in the first, second, and third directions is 0. When the vehicle is accelerating, the vehicle's acceleration in the first and second directions is greater than 0, while the acceleration in the third direction is 0. In this scenario, when the vehicle's direction of travel remains unchanged, the vehicle's angular velocity in the first, second, and third directions is 0. When the vehicle's direction of travel changes, the vehicle's angular velocity in the first and second directions is 0, while the angular velocity in the third direction is not 0.

[0096] Scenario 2: Vehicles traveling uphill (e.g., up a slope).

[0097] Scenario 3: Vehicle traveling downhill (as in a downhill slope).

[0098] In both scenarios, assume the vehicle's direction of travel makes an angle of 45° with the first, second, and third directions. When the vehicle is traveling at a constant speed, its acceleration in the first, second, and third directions is zero; when the vehicle is accelerating, its acceleration in the first, second, and third directions is greater than zero. When the vehicle's direction of travel remains unchanged, its angular velocity in the first, second, and third directions is zero; when the vehicle's direction of travel changes, such as when the angle between the vehicle's direction of travel and the third direction changes (e.g., from 45° to 30°), then the vehicle's angular velocity in the first and second directions is zero, but its angular velocity in the third direction is not zero.

[0099] It is understandable that during normal driving, the acceleration, deceleration, and turning of a vehicle result in relatively small or zero angular velocities in the first, second, and third directions. Based on this, considering that a vehicle may rotate or roll over during a fall, resulting in larger accelerations or angular velocities in these directions, a fall detection can be performed based on the vehicle's accelerations and / or angular velocities in these directions. The specific detection method is described in step 202 below.

[0100] Step 202: Based on the first information, determine whether the vehicle has fallen off the road.

[0101] In one possible implementation, before executing step 202, the acquired first information can be cleaned to ensure the accuracy of subsequent vehicle fall detection. Data cleaning includes, but is not limited to, removing invalid data, data completion, interpolation, filtering, and slope limiting; this application does not impose any specific limitations on these methods.

[0102] In this process, the data included in the first piece of information can exist in the following three situations:

[0103] Case 2.1: The first information only includes the vehicle's acceleration in the first, second, and third directions;

[0104] Case 2.2: The first information only includes the angular velocities of the vehicle in the first, second, and third directions;

[0105] In case 2.3, the first information includes both the vehicle's acceleration in the first, second, and third directions, and its angular velocity in the first, second, and third directions.

[0106] Regarding scenario 2.1, it can be determined whether a vehicle has fallen based solely on the vehicle's acceleration in the first, second, and third directions. Regarding scenario 2.2, it can be determined solely on the vehicle's angular velocities in the first, second, and third directions. Regarding scenario 2.3, it can be determined based on the vehicle's acceleration in the first, second, and third directions, or based solely on the vehicle's angular velocities in the first, second, and third directions, or based solely on both the vehicle's acceleration and angular velocities in the first, second, and third directions.

[0107] In either Case 2.1 or Case 2.3, determining whether a vehicle has experienced a fall event based on the vehicle's acceleration in the first, second, and third directions can include the following two methods:

[0108] Method 2.1.1: If the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, and the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, then a vehicle fall event is determined to have occurred. The acceleration thresholds corresponding to the first direction, the second direction, and the third direction can be preset values ​​based on experience, and this application does not impose specific limitations on them.

[0109] Conversely, if the vehicle's acceleration in the first direction is less than the corresponding acceleration threshold, or the vehicle's acceleration in the second direction is less than the corresponding acceleration threshold, or the vehicle's acceleration in the third direction is less than the corresponding acceleration threshold, then it is determined that the vehicle has not experienced a fall event.

[0110] Method 2.1.2 determines the resultant acceleration of the vehicle in the first direction, the second direction, and the third direction. Based on this, if the resultant acceleration is greater than or equal to a first threshold, a vehicle fall event is determined. Here, the resultant acceleration refers to the vector sum of relative acceleration, entrainment acceleration, and Coriolis acceleration experienced by the target object (such as the vehicle in this application) during composite motion. Considering that the resultant acceleration is a well-known technique in the art, it will not be elaborated upon here. For example, the resultant acceleration is the sum of the acceleration in the first direction, the acceleration in the second direction, and the acceleration in the third direction. The first threshold can be a value preset based on experience, and this application does not specifically limit it here.

[0111] Conversely, if the combined acceleration is less than the first threshold, it is determined that the vehicle has not fallen.

[0112] In scenario 2.2 or scenario 2.3, determining whether a vehicle has experienced a fall event based on the vehicle's angular velocities in the first, second, and third directions can include the following two methods:

[0113] Method 2.2.1: If the vehicle's angular velocity in the first direction is greater than or equal to the corresponding angular velocity threshold in the first direction, the vehicle's angular velocity in the second direction is greater than or equal to the corresponding angular velocity threshold in the second direction, and the vehicle's angular velocity in the third direction is greater than or equal to the corresponding angular velocity threshold in the third direction, then a vehicle fall event is determined. The angular velocity thresholds for the first, second, and third directions can be preset values ​​based on experience, and this application does not impose specific limitations on them.

[0114] Conversely, if the vehicle's angular velocity in the first direction is less than the corresponding angular velocity threshold, or the vehicle's angular velocity in the second direction is less than the corresponding angular velocity threshold, or the vehicle's angular velocity in the third direction is less than the corresponding angular velocity threshold, then it is determined that the vehicle has not experienced a fall event.

[0115] Method 2.2.2 determines the vehicle's angle in the first direction based on its angular velocity, the vehicle's angle in the second direction based on its angular velocity, and the vehicle's angle in the third direction based on its angular velocity in a third direction. Based on this, if the vehicle's angle in the first direction is greater than or equal to the corresponding angle threshold, the vehicle's angle in the second direction is greater than or equal to the corresponding angle threshold, and the vehicle's angle in the third direction is greater than or equal to the corresponding angle threshold, then a vehicle fall event is determined. Here, angular velocity refers to the angle of rotation of a target object per unit time. Therefore, based on the angular velocity and the vehicle's angle at the previous moment (the interval between the current moment and the previous moment can be a unit time), the vehicle's angle at the current moment can be determined. Thus, for any direction (first direction, second direction, or third direction), the vehicle's angle in that direction can be determined based on its angular velocity in that direction. The angle thresholds for the first direction, the second direction, and the third direction can be preset values ​​based on experience, and this application does not impose specific limitations on them.

[0116] Conversely, if the vehicle's angle in the first direction is less than the corresponding angle threshold, or the vehicle's angle in the second direction is less than the corresponding angle threshold, or the vehicle's angular velocity in the third direction is less than the corresponding angle threshold, then it is determined that the vehicle has not experienced a fall event.

[0117] Based on the above description, in case 2.3, determining whether a vehicle has experienced a fall event based on the vehicle's acceleration in the first, second, and third directions, and its angular velocities in the first, second, and third directions, can include the following four methods (i.e., combining each of the above methods 2.1.1, 2.1.2 with methods 2.2.1 and 2.2.2 in pairs to obtain these four methods):

[0118] Method 2.3.1: If the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, the vehicle's acceleration in a third direction is greater than or equal to the acceleration threshold corresponding to the third direction, the vehicle's angular velocity in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the vehicle's angular velocity in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the vehicle's angular velocity in a third direction is greater than or equal to the angular velocity threshold corresponding to the third direction, that is, if the acceleration in any direction is greater than or equal to the acceleration threshold corresponding to that direction, and the angular velocity in any direction is greater than or equal to the angular velocity threshold corresponding to that direction, then a vehicle fall event is determined to have occurred.

[0119] Conversely, if the vehicle's acceleration in the first direction is less than the corresponding acceleration threshold, or the vehicle's acceleration in the second direction is less than the corresponding acceleration threshold, or the vehicle's acceleration in a third direction is less than the corresponding acceleration threshold, or the vehicle's angular velocity in the first direction is less than the corresponding angular velocity threshold, or the vehicle's angular velocity in the second direction is less than the corresponding angular velocity threshold, or the vehicle's angular velocity in a third direction is less than the corresponding angular velocity threshold, that is, if the acceleration in any direction is less than the corresponding acceleration threshold, or the angular velocity in any direction is less than the corresponding angular velocity threshold, then it is determined that the vehicle has not experienced a fall event.

[0120] Method 2.3.2: If the combined acceleration is greater than or equal to the first threshold, the angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the angular velocity of the vehicle in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction, then it is determined that a vehicle fall event has occurred.

[0121] Conversely, if the combined acceleration is less than the first threshold, or the angular velocity of the vehicle in the first direction is less than the corresponding angular velocity threshold in the first direction, or the angular velocity of the vehicle in the second direction is less than the corresponding angular velocity threshold in the second direction, or the angular velocity of the vehicle in the third direction is less than the corresponding angular velocity threshold in the third direction, then it is determined that the vehicle has not experienced a fall event.

[0122] Method 2.3.3: If the vehicle's angle in the first direction is greater than or equal to the corresponding angle threshold in the first direction, the vehicle's angle in the second direction is greater than or equal to the corresponding angle threshold in the second direction, and the vehicle's angle in the third direction is greater than or equal to the corresponding angle threshold in the third direction, the vehicle's acceleration in the first direction is greater than or equal to the corresponding acceleration threshold in the first direction, the vehicle's acceleration in the second direction is greater than or equal to the corresponding acceleration threshold in the second direction, and the vehicle's acceleration in the third direction is greater than or equal to the corresponding acceleration threshold in the third direction, then a vehicle fall event is determined to have occurred.

[0123] Conversely, if the vehicle's angle in the first direction is less than the corresponding angle threshold, or the vehicle's angle in the second direction is less than the corresponding angle threshold, or the vehicle's angle in the third direction is less than the corresponding angle threshold, or the vehicle's acceleration in the first direction is less than the corresponding acceleration threshold, or the vehicle's acceleration in the second direction is less than the corresponding acceleration threshold, or the vehicle's acceleration in the third direction is less than the corresponding acceleration threshold, then it is determined that the vehicle has not experienced a fall event.

[0124] Method 2.3.4: If the combined acceleration is greater than or equal to the first threshold, the vehicle's angle in the first direction is greater than or equal to the corresponding angle threshold in the first direction, the vehicle's angle in the second direction is greater than or equal to the corresponding angle threshold in the second direction, and the vehicle's angle in the third direction is greater than or equal to the corresponding angle threshold in the third direction, then it is determined that a vehicle has fallen.

[0125] Conversely, if the combined acceleration is less than the first threshold, or the vehicle's angle in the first direction is less than the corresponding angle threshold, or the vehicle's angle in the second direction is less than the corresponding angle threshold, or the vehicle's angle in the third direction is less than the corresponding angle threshold, then it is determined that the vehicle has not experienced a fall event.

[0126] This application takes into account that when a vehicle falls, it may rotate or roll over, which would result in significant accelerations and angular velocities in the first, second, and third directions. Therefore, the application performs fall detection based on the vehicle's accelerations (generally not gravitational acceleration) in the first, second, and third directions, and / or its angular velocities in the first, second, and third directions, as well as threshold values ​​(including acceleration and angular velocity thresholds) for each direction, rather than solely relying on the vehicle's velocity change in the third direction. This approach not only determines whether a fall has occurred but also ensures the accuracy of the fall detection.

[0127] In one possible implementation, in cases 2.1, 2.2, or 2.3, the first information can be directly input into the first model to obtain the detection result output by the first model. It can be understood that the detection result output by the first model is used to indicate that a vehicle fall event has occurred, or the detection result output by the first model is used to indicate that a vehicle fall event has not occurred.

[0128] The first model can be a neural network model, a deep learning model, or a deep neural network model. For example, the first model can be a self-supervised model trained using training samples, or it can be a Transformer model, or a one-dimensional convolutional network structure. The training convergence objective of this first model is the first information at the time of a vehicle fall event (which may include the acceleration of the vehicle in the first, second, and third directions, and / or the angular velocity of the vehicle in the first, second, and third directions). Using the first model for vehicle fall detection improves the efficiency of vehicle fall detection.

[0129] In one possible implementation, upon determining that a vehicle has fallen, the onboard device broadcasts a first indication message and issues an alarm. The broadcast can be done via the vehicle's audio system or by uploading to the cloud. The first indication message indicates that a vehicle has fallen and includes the location of the fall. The alarm can be understood as a distress call, and the alarm method can be pre-set by the user, such as dialing the police emergency number, ambulance service, or emergency contact number, to ensure real-time rescue in response to the fall.

[0130] Optionally, the initial indication information may also include information about the people inside the vehicle that fell (such as the vehicle owner's information), information about the vehicle that fell (such as the vehicle model and license plate number), the height from which the vehicle fell, and environmental information about the location where the vehicle fell. This provides detailed information for rescue efforts and increases the success rate of the rescue.

[0131] For example, Figure 3 is a schematic diagram of an application scenario provided by this application, including a vehicle (referred to as the first vehicle here to distinguish it from other vehicles) and network equipment (such as a cloud storage unit). The vehicle includes an inertial measurement unit, an on-board device, and a telematics box (T-BOX). The on-board device includes the data center unit and vehicle information unit shown in Figure 1, and also includes a cockpit domain controller (CDC). The data center unit includes a data cleaning unit, the vehicle information unit includes a drop detection unit and an avoidance control unit, and the cockpit domain controller includes a drop event alarm unit and a drop event reminder unit. The inertial measurement unit is used to measure the first information of the first vehicle, the data cleaning unit is used to clean the first information, and the drop detection unit is used to implement the method described in Figure 2. The T-BOX features vehicle-to-X (V2X) wireless communication technology. Based on this, when the drop detection unit determines that a vehicle drop event has occurred, it can send a first indication message to the network device via the T-BOX and a first command to the drop event alarm unit. This first command is used to cause the drop event alarm unit to call for help. Optionally, when a vehicle drop event is determined, the avoidance control unit can perform preset avoidance control operations (such as tightening seat belts, clamping seats, and adjusting suspension stiffness and damping to the minimum). This allows the suspension to absorb the impact force generated during the drop to the maximum extent, securing the occupants in their seats and protecting their personal safety.

[0132] Similarly, when other vehicles (referred to as the second vehicle here to distinguish them from the first vehicle mentioned above) determine that a vehicle has fallen, the second vehicle will also send a first indication message to the network device. Based on this, the first vehicle can obtain the second indication message sent by the network device, which is used to indicate the vehicle that has fallen (such as the second vehicle here). The second indication message includes the location of the vehicle that has fallen. In this way, the first vehicle can know where the fall event is located and can take avoidance measures in advance. Referring to Figure 3, Figure 4 is a flowchart of a fall avoidance control method provided in this application. As shown in Figure 4, this method can be applied to the vehicle information unit. Further, steps 401-404 in this method are applied to the fall detection unit, and steps 405-407 in this method are applied to the avoidance control unit. The method includes the following steps:

[0133] Step 401: Receive second indication information, which is used to indicate the location of the second vehicle where the fall occurred.

[0134] Step 402: Based on the location of the second vehicle, determine whether the first vehicle needs to yield. The first vehicle is the vehicle itself. If yielding is required, proceed to step 403; otherwise, return to step 401.

[0135] In this step, based on the location of the first vehicle, as well as its driving direction, destination address, and route, it can be determined whether the first vehicle passes by the location of the second vehicle. If the first vehicle passes by the location of the second vehicle, it is determined that the first vehicle needs to give way; if the first vehicle does not pass by the location of the second vehicle, it is determined that the first vehicle does not need to give way. The driving direction, destination address, and route of the first vehicle can be obtained from a map application deployed on the terminal device used by the user inside the first vehicle, and this application does not limit its availability.

[0136] Optionally, when it is determined that the first vehicle needs to be avoided, a second instruction (refer to Figure 3) can be sent to the fall event warning unit. This second instruction is used to instruct the avoidance warning unit to remind the user (such as the driver) that a vehicle has fallen ahead and that they need to take timely evasive action. Examples of warning methods include, but are not limited to: text warnings, voice warnings, steering wheel vibration warnings, and beeping warnings.

[0137] Step 403: Determine whether the first vehicle can avoid the second vehicle based on the location of the second vehicle. If it can avoid the second vehicle, proceed to step 404; otherwise, proceed to step 405.

[0138] In this step, the distance between the second vehicle and the first vehicle can be determined based on the location of the second vehicle and the current location of the first vehicle. Then, based on the current speed of the first vehicle and the distance between the second vehicle and the first vehicle, it can be determined whether the first vehicle can stop or avoid the location before reaching the location of the second vehicle. If so, it is determined that the first vehicle can avoid the location; otherwise, it is determined that the first vehicle cannot avoid the location.

[0139] Step 404: Determine whether braking is possible based on the distance between the second vehicle and the first vehicle. If braking is possible, proceed to step 406; otherwise, proceed to step 407.

[0140] In this step, based on the current speed of the first vehicle and the distance between the second vehicle and the first vehicle, it is determined whether the first vehicle can stop before reaching the location of the second vehicle. If so, it is determined that the first vehicle can avoid the collision by braking; otherwise, it is determined that the first vehicle cannot avoid the collision by braking.

[0141] Step 405: Execute the preset avoidance control operation.

[0142] This step includes pre-set avoidance control actions such as tightening seat belts and clamping seats to secure occupants in their seats and protect their safety. It may also include minimizing suspension stiffness and damping to maximize the absorption of impact forces during a fall, further protecting occupants.

[0143] Step 406: Apply brakes to the first vehicle, tighten the seat belts, and clamp the seats.

[0144] In this step, a preset braking torque is applied to the first vehicle, which can cause the first vehicle to brake suddenly (or stop abruptly) and come to a stop before reaching the position of the second vehicle. During this process, the personal safety of the users in the vehicle is protected by tightening the seat belts and clamping the seats.

[0145] Step 407: Brake and steer the first vehicle, tighten the seat belts, and clamp the seats.

[0146] In this step, considering the possibility that the second vehicle may be located in one of the lanes (such as the outer lane) of multiple vehicles, when it is determined that the first vehicle cannot stop before reaching the location of the second vehicle by braking, in addition to braking the first vehicle, the first vehicle is also steered. This allows the first vehicle to travel to another lane (such as the inner lane) before reaching the location of the second vehicle. During this process, the personal safety of the occupants of the vehicle is protected by tightening the seat belts and clamping the seats.

[0147] To further improve the accuracy of vehicle fall detection, Figure 5 is a schematic diagram of another vehicle-mounted device provided in this application. This device includes a data center unit and a vehicle information unit. The data center unit can be a mobile data center (MDC), which includes a data cleaning unit and an identification unit. The data cleaning unit receives the first information measured by the inertial measurement unit and cleans this data. The identification unit receives tire pressure measured by a tire pressure sensor (such as a tire pressure monitoring system (TPMS) sensor), and / or suspension height measured by a suspension sensor, and / or images acquired by an image acquisition device (such as a vision sensor), and / or point clouds generated by vehicle-mounted radar equipment (such as lidar, millimeter-wave radar, or ultrasonic radar), and generates environmental information (i.e., environmental information surrounding the vehicle) based on the images and / or point clouds. The tire pressure can be the tire pressure of all wheels (usually four) of the vehicle, or the tire pressure of some wheels (such as the front wheels). Since the suspension generally corresponds one-to-one with each wheel, the suspension height of the vehicle can be the suspension height corresponding to all wheels, or the suspension height corresponding to some wheels. This application does not specifically limit the tire pressure and suspension height. Optionally, the recognition unit can participate in subsequent drop detection by calculating the average tire pressure of multiple wheels and the average suspension height corresponding to multiple wheels.

[0148] Figure 6 is a flowchart illustrating another vehicle drop detection method provided in this application. This process is applied to the vehicle-mounted device shown in Figure 5, or a module of the vehicle-mounted device (such as a processor, processing unit, chip, circuit, etc.), or the corresponding system of the vehicle-mounted device. The vehicle-mounted device can be installed in a vehicle that enables intelligent driving. For example, the vehicle may be equipped with a driving system, such as an Advanced Driving System (ADS). Optionally, the ADS level installed in the vehicle can be at least one of the following: Level 2 (combined driving assistance), Level 3 (conditional automated driving), Level 4 (highly automated driving), or Level 5 (fully automated driving).

[0149] As shown in Figure 6, the method may include the following steps:

[0150] Step 601: Obtain first information and second information. The first information includes the vehicle's acceleration and angular velocity in the first direction, the second direction, and the third direction. The second information includes at least one of the following: the vehicle's tire pressure, the vehicle's suspension height, and environmental information.

[0151] In this process, the first information can be referred to the description of step 201 above, and will not be repeated here. The tire pressure of the vehicle can be the average tire pressure of multiple wheels of the vehicle (all wheels or some wheels of the vehicle). Similarly, the suspension height of the vehicle can be the average height of multiple suspensions of the vehicle (all suspensions or some suspensions of the vehicle).

[0152] Step 602: Based on the first and second information, determine whether the vehicle has fallen.

[0153] In one possible implementation, before executing step 202, the acquired first information can be cleaned (as shown in Figure 5, the data cleaning unit cleans the first information). Similarly, the second information can also be cleaned (as shown in Figure 5, the recognition unit cleans the second information). This ensures the accuracy of subsequent vehicle fall detection. Data cleaning includes, but is not limited to: invalid data extraction, completion, interpolation, filtering, and slope limiting; these are not limited in this application.

[0154] In one possible implementation, when the first information satisfies the detection conditions, the system can determine whether a vehicle has experienced a fall based on the second information. The detection conditions can be found in step 202 above, specifically in methods 2.1.1 and 2.1.2 for case 2.1, methods 2.2.1 and 2.2.2 for case 2.2, and methods 2.3.1, 2.3.2, 2.3.3, and 2.3.4 for case 2.3. That is, in step 202, if the first information determines that a vehicle has experienced a fall, then the detection conditions in this implementation are met. For example, the detection conditions include the following:

[0155] The vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction;

[0156] The vehicle's acceleration in the second direction is greater than or equal to the corresponding acceleration threshold in the second direction;

[0157] The vehicle's acceleration in the third direction is greater than or equal to the corresponding acceleration threshold in the third direction;

[0158] The vehicle's angular velocity in the first direction is greater than or equal to the corresponding angular velocity threshold in the first direction;

[0159] The vehicle's angular velocity in the second direction is greater than or equal to the corresponding angular velocity threshold in the second direction;

[0160] The vehicle's angular velocity in the third direction is greater than or equal to the corresponding angular velocity threshold in the third direction.

[0161] In this process, the data included in the second information can exist in the following three situations:

[0162] Case 6.1: The second information includes only the vehicle's tire pressure, or only the vehicle's suspension height, or only environmental information.

[0163] In case 6.2, the second information includes the vehicle's tire pressure and suspension height, or the second information includes the vehicle's tire pressure and environmental information, or the second information includes the vehicle's suspension height and environmental information.

[0164] In scenario 6.3, the second piece of information includes the vehicle's tire pressure, the vehicle's suspension height, and environmental information.

[0165] Regarding scenario 6.1, based on the first piece of information satisfying the aforementioned detection conditions, if the vehicle's tire pressure is greater than or equal to a pressure threshold, then a vehicle fall event is determined. Alternatively, if the vehicle's suspension height is less than or equal to a height threshold, then a vehicle fall event is determined. Alternatively, if the similarity between the environmental information corresponding to the vehicle at the current moment and the environmental information corresponding to the vehicle at the previous moment is less than or equal to a second threshold, then a vehicle fall event is determined. The pressure threshold, height threshold, and second threshold can be preset values ​​based on experience, and this application does not impose specific limitations on them. The similarity between the environmental information at the current moment and the environmental information at the previous moment can be calculated using methods such as cosine similarity, Euclidean distance, and Manhattan distance, for example, calculating the similarity between the image at the current moment and the image at the previous moment.

[0166] Regarding scenario 6.2, based on the first piece of information satisfying the aforementioned detection conditions, if the vehicle's tire pressure is greater than or equal to a pressure threshold and the vehicle's suspension height is less than or equal to a height threshold, then a vehicle fall event is determined. Alternatively, if the vehicle's tire pressure is greater than or equal to a pressure threshold and the similarity between the vehicle's current environmental information and the environmental information of the vehicle at the previous moment is less than or equal to a second threshold, then a vehicle fall event is determined. Alternatively, if the vehicle's suspension height is less than or equal to a height threshold and the similarity between the vehicle's current environmental information and the environmental information of the vehicle at the previous moment is less than or equal to a second threshold, then a vehicle fall event is determined.

[0167] Regarding situation 6.3, based on the first information satisfying the above detection conditions, if the vehicle's tire pressure is greater than or equal to the pressure threshold, the vehicle's suspension height is less than or equal to the height threshold, and the similarity between the environmental information corresponding to the vehicle at the current moment and the environmental information corresponding to the vehicle at the previous moment is less than or equal to the second threshold, then it is determined that a vehicle drop event has occurred.

[0168] Conversely, if the vehicle's tire pressure is less than the pressure threshold, and the vehicle has not experienced a fall, then the vehicle is determined not to have fallen, provided the first piece of information meets the aforementioned detection conditions. Alternatively, if the vehicle's suspension height is greater than the height threshold, then the vehicle has not experienced a fall. Alternatively, if the similarity between the environmental information of the vehicle at the current moment and the environmental information of the vehicle at the previous moment is greater than a second threshold, then the vehicle has not experienced a fall.

[0169] This application considers that when a vehicle experiences a fall, and upon landing, the tire pressure increases and the suspension height decreases. Therefore, based on the detection conditions of the first piece of information, further fall detection can be performed on the vehicle by adjusting tire pressure and / or suspension height to ensure the accuracy of vehicle fall detection. Similarly, considering that the environmental information changes significantly between two adjacent moments during a fall, further fall detection can be performed on the vehicle by assessing the similarity between environmental information from two adjacent moments (including the current moment), based on the detection conditions of the first piece of information, to ensure the accuracy of vehicle fall detection.

[0170] Optionally, the second information may also include vehicle airbag information (or collision output signal). For example, based on the detection conditions of the first information, if it is determined that the vehicle airbag is deployed (or the collision output signal indicates that a collision has occurred), then it is determined that a vehicle drop event has occurred. It can be seen that the possible scenarios during a vehicle drop can be used as factors in vehicle drop detection, thereby ensuring the accuracy of vehicle drop detection.

[0171] In one possible implementation, the first and second information can be directly input into the second model to obtain the detection result output by the second model. It can be understood that the detection result output by the second model is used to indicate that a vehicle fall event has occurred, or the detection result output by the second model is used to indicate that a vehicle fall event has not occurred.

[0172] The second model can be a neural network model, a deep learning model, or a deep neural network model. For example, the second model can be a self-supervised model trained using training samples, or it can be a Transformer model, or a one-dimensional convolutional network structure. The training convergence objective of this second model is the first information (which may include the acceleration in the first, second, and third directions, and / or the angular velocity in the first, second, and third directions) and the second information (which may include the tire pressure, suspension height, and / or environmental information at the time of the fall) and the similarity between the environmental information at the time of the fall and the environmental information at the moment preceding the fall. It can be understood that using the second model for vehicle fall detection improves the efficiency of vehicle fall detection.

[0173] In one possible implementation, upon determining that a vehicle has fallen, the on-board device broadcasts a first indication message and issues an alarm. This first indication message can be referred to the description in the method shown in Figure 2 above, and will not be repeated here.

[0174] For example, Figure 7 is a schematic diagram of another application scenario provided by this application, including a vehicle (referred to as the first vehicle here to distinguish it from other vehicles) and network equipment (such as a cloud storage unit). The vehicle includes an inertial measurement unit, tire pressure sensors, suspension sensors, image acquisition devices, vehicle radar equipment, vehicle-mounted devices, and a telematics box (T-BOX). The vehicle-mounted device includes the data center unit and vehicle information unit shown in Figure 5, and also includes a cockpit domain controller (CDC). The data center unit includes a data cleaning unit and an identification unit, the vehicle information unit includes a fall detection unit and an avoidance control unit, and the cockpit domain controller includes a fall event alarm unit and a fall event reminder unit.

[0175] The functions of the inertial measurement unit, tire pressure sensor, suspension sensor, image acquisition device, and vehicle radar equipment are described in Figure 5 above and will not be repeated here. The drop detection unit is used to implement the method described in Figure 6 above. The T-BOX has vehicle-to-X (V2X) wireless communication technology. Based on this, when the drop detection unit determines that a vehicle drop event has occurred, it can send a first indication message to the network device through the T-BOX and send a first command to the drop event alarm unit. This first command is used to cause the drop event alarm unit to call for help. Optionally, when a vehicle drop event is determined, the avoidance control unit can perform preset avoidance control operations (such as tightening the seat belt, clamping the seat, and adjusting the suspension stiffness and damping to the minimum). This allows the suspension to absorb the impact force generated during the drop to the maximum extent, keeping the occupants in their seats and protecting their personal safety.

[0176] Similarly, when other vehicles (referred to as the second vehicle here to distinguish them from the first vehicle mentioned above) determine that a vehicle has fallen, they will also send first indication information to the network device. Based on this, the first vehicle can obtain second indication information sent by the network device, which is used to indicate the vehicle that has fallen (such as the second vehicle here), and includes the location of the vehicle that has fallen. In this way, the first vehicle can know where the fall event is located and can take avoidance measures in advance. Specifically, please refer to the fall avoidance control method described in Figure 4 above, which will not be elaborated here.

[0177] The vehicle drop detection method provided by this application has been described in detail above based on Figures 2 and 6. The apparatus for performing the above method according to this application will be described below with reference to Figure 8.

[0178] Figure 8 is a schematic diagram of the structure of a device provided in this application. This device 800 can be used to implement the above-described vehicle drop detection method, and therefore can also achieve the beneficial effects of the above-described method embodiments.

[0179] As shown in Figure 8, the device 800 includes an acquisition module 810 and a processing module 820. When executing the vehicle fall detection method described in Figure 2, the acquisition module 810 is used to acquire first information, which includes the acceleration of the vehicle in a first direction, a second direction, and a third direction, and / or the angular velocity of the vehicle in the first direction, the second direction, and the third direction, where the first direction, the second direction, and the third direction are the three coordinate axes of a three-dimensional coordinate system. The processing module 820 is used to determine whether a fall event has occurred in the vehicle based on the first information.

[0180] In one possible implementation, the processing module 820 is specifically configured to: determine that a vehicle has fallen if the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, and the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction.

[0181] In one possible implementation, the processing module 820 is specifically used to: determine the combined acceleration of the vehicle in the first direction, the second direction, and the third direction; if the combined acceleration is greater than or equal to a first threshold, then determine that the vehicle has experienced a fall event.

[0182] In one possible implementation, the processing module 820 is specifically configured to: determine that a vehicle has fallen if the angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the angular velocity of the vehicle in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction.

[0183] In one possible implementation, the processing module 820 is specifically configured to: determine the angle of the vehicle in the first direction based on the angular velocity of the vehicle in the first direction; determine the angle of the vehicle in the second direction based on the angular velocity of the vehicle in the second direction; determine the angle of the vehicle in the third direction based on the angular velocity of the vehicle in the third direction; if the angle of the vehicle in the first direction is greater than or equal to an angle threshold corresponding to the first direction, the angle of the vehicle in the second direction is greater than or equal to an angle threshold corresponding to the second direction, and the angle of the vehicle in the third direction is greater than or equal to an angle threshold corresponding to the third direction, then determine that a vehicle fall event has occurred.

[0184] In one possible implementation, the processing module 820 is specifically configured to: determine that a vehicle has experienced a fall if the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, the vehicle's angular velocity in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the vehicle's angular velocity in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the vehicle's angular velocity in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction.

[0185] In one possible implementation, the processing module 820 is specifically configured to: determine the resultant acceleration of the vehicle in the first direction, the second direction, and the third direction; if the resultant acceleration is greater than or equal to a first threshold, the angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the angular velocity of the vehicle in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction, then determine that a fall event has occurred.

[0186] In one possible implementation, the processing module 820 is specifically configured to: determine the angle of the vehicle in the first direction based on the angular velocity of the vehicle in the first direction; determine the angle of the vehicle in the second direction based on the angular velocity of the vehicle in the second direction; determine the angle of the vehicle in the third direction based on the angular velocity of the vehicle in the third direction; if the angle of the vehicle in the first direction is greater than or equal to an angle threshold corresponding to the first direction, the angle of the vehicle in the second direction is greater than or equal to an angle threshold corresponding to the second direction, the angle of the vehicle in the third direction is greater than or equal to an angle threshold corresponding to the third direction, the acceleration of the vehicle in the first direction is greater than or equal to an acceleration threshold corresponding to the first direction, the acceleration of the vehicle in the second direction is greater than or equal to an acceleration threshold corresponding to the second direction, and the acceleration of the vehicle in the third direction is greater than or equal to an acceleration threshold corresponding to the third direction, then determine that a vehicle fall event has occurred.

[0187] In one possible implementation, the processing module 820 is specifically configured to: determine the resultant acceleration of the vehicle in the first direction, the second direction, and the third direction; determine the angle of the vehicle in the first direction based on the angular velocity of the vehicle in the first direction, determine the angle of the vehicle in the second direction based on the angular velocity of the vehicle in the second direction, and determine the angle of the vehicle in the third direction based on the angular velocity of the vehicle in the third direction; if the resultant acceleration is greater than or equal to a first threshold, the angle of the vehicle in the first direction is greater than or equal to the angle threshold corresponding to the first direction, the angle of the vehicle in the second direction is greater than or equal to the angle threshold corresponding to the second direction, and the angle of the vehicle in the third direction is greater than or equal to the angle threshold corresponding to the third direction, then determine that a vehicle fall event has occurred.

[0188] In one possible implementation, the processing module 820 is specifically used to: input the first information into the first model to obtain the detection result output by the first model, wherein the detection result output by the first model is used to indicate that the vehicle has experienced a fall event, or the detection result output by the first model is used to indicate that the vehicle has not experienced a fall event; wherein the training convergence target of the first model is the first information when the vehicle experiences a fall event.

[0189] In one possible implementation, the processing module 820 is further configured to: broadcast first indication information and issue an alarm when it is determined that the vehicle has fallen, wherein the first indication information is used to indicate that the vehicle has fallen and includes the location where the vehicle fell.

[0190] When executing the vehicle fall detection method described in Figure 2, the acquisition module 810 is used to acquire first information and second information. The first information includes the acceleration and angular velocity of the vehicle in a first direction, a second direction, and a third direction, where the first direction, the second direction, and the third direction are the three coordinate axes of a three-dimensional coordinate system. The second information includes at least one of the following: the tire pressure of the vehicle, the suspension height of the vehicle, and environmental information. The processing module 820 is used to determine whether a fall event has occurred in the vehicle based on the first information and the second information.

[0191] In one possible implementation, the processing module 820 is specifically used to: determine whether the vehicle has experienced a fall event based on the second information when the first information satisfies the following detection conditions;

[0192] The detection conditions include:

[0193] The acceleration of the vehicle in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction;

[0194] The acceleration of the vehicle in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction;

[0195] The acceleration of the vehicle in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction;

[0196] The angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction;

[0197] The angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction;

[0198] The vehicle's angular velocity in the third direction is greater than or equal to the corresponding angular velocity threshold in the third direction.

[0199] In one possible implementation, the processing module 820 is specifically used to: determine that the vehicle has fallen if the tire pressure of the vehicle is greater than or equal to a pressure threshold.

[0200] In one possible implementation, the processing module 820 is specifically used to: determine that the vehicle has experienced a fall if the suspension height of the vehicle is less than or equal to a height threshold.

[0201] In one possible implementation, the processing module is specifically used to: determine that the vehicle has fallen if the similarity between the environmental information corresponding to the vehicle at the current moment and the environmental information corresponding to the vehicle at the previous moment is less than or equal to a second threshold.

[0202] In one possible implementation, the processing module 820 is specifically used to: input the first information and the second information into the second model to obtain the detection result output by the second model, wherein the detection result output by the second model is used to indicate that the vehicle has experienced a fall event, or the detection result output by the second model is used to indicate that the vehicle has not experienced a fall event; wherein the training convergence target of the second model is the first information and the second information when the vehicle experiences a fall event.

[0203] In one possible implementation, the processing module 820 is further configured to: broadcast first indication information and issue an alarm when it is determined that the vehicle has fallen, wherein the first indication information is used to indicate that the vehicle has fallen and includes the location where the vehicle fell.

[0204] Both the acquisition module 810 and the processing module 820 can be implemented in software or in hardware. For example, the implementation of the acquisition module 810 will be described below. Similarly, the implementation of the processing module 820 can refer to the implementation of the acquisition module 810.

[0205] As an example of a software functional unit, module 810 may include code running on a computing instance. The computing instance may include at least one of a physical host (computing device), a virtual machine, or a container. Further, the aforementioned computing instance may be one or more. For example, module 810 may include code running on multiple hosts / virtual machines / containers. It should be noted that the multiple hosts / virtual machines / containers used to run the code may be distributed within the same region or in different regions. Further, the multiple hosts / virtual machines / containers used to run the code may be distributed within the same availability zone (AZ) or in different AZs, each AZ including one or more geographically proximate data centers. Typically, a region may include multiple AZs.

[0206] Similarly, multiple hosts / virtual machines / containers used to run this code can be distributed within the same Virtual Private Cloud (VPC) or across multiple VPCs. Typically, a VPC is set up within a region. Communication between two VPCs within the same region, as well as between VPCs in different regions, requires a communication gateway to be set up within each VPC to enable interconnection between VPCs.

[0207] As an example of a hardware functional unit, the acquisition module 810 may include at least one computing device, such as a server. Alternatively, the acquisition module 810 may be implemented using a Central Processing Unit (CPU), an Application-Specific Integrated Circuit (ASIC), or a Programmable Logic Device (PLD). The PLD may be a Complex Programmable Logical Device (CPLD), a Field-Programmable Gate Array (FPGA), a Generic Array Logic (GAL), a Data Processing Unit (DPU), a Neural Network Processing Unit (NPU), a System-on-Chip (SoC), an offload card, an accelerator card, or any combination thereof.

[0208] The multiple computing devices included in the acquisition module 810 can be distributed in the same region or in different regions. Similarly, the multiple computing devices included in the acquisition module 810 can be distributed in the same Availability Zone (AZ) or in different AZs. Likewise, the multiple computing devices included in the acquisition module 810 can be distributed in the same Virtual Private Cloud (VPC) or in multiple VPCs. These multiple computing devices can be any combination of computing devices such as servers, ASICs, PLDs, CPLDs, FPGAs, GALs, DPUs, NPUs, SoCs, offloading cards, and accelerator cards.

[0209] Based on the above embodiments, this application also provides a device that can implement the methods in the above embodiments and has the functions of device 800. Referring to FIG9, the device 900 includes: a transceiver 901, a processor 902, and a memory 903. The transceiver 901, the processor 902, and the memory 903 are interconnected.

[0210] Optionally, the transceiver 901, the processor 902, and the memory 903 are interconnected via a bus 904. The bus 904 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in Figure 9, but this does not indicate that there is only one bus or one type of bus.

[0211] The transceiver 901 is used to receive and send signals to enable communication with other devices.

[0212] The function of the processor 902 can be referred to the description in the above embodiments, and will not be repeated here.

[0213] The processor 902 can be a central processing unit (CPU), a network processor (NP), or a combination of a CPU and an NP, etc. The processor 902 may further include hardware chips. These hardware chips can be application-specific integrated circuits (ASICs), programmable logic controllers (PLDs), or combinations thereof. The PLD can be a CPLD, an FPGA, a gate array (GAL), or any combination thereof. When implementing the above functions, the processor 902 can be implemented in hardware, or it can be implemented by executing corresponding software. The steps of the method disclosed in the above embodiments of this application can be directly reflected as the processor 902 completing the execution, or as the hardware and software modules in the processor 902 combining to complete the execution.

[0214] The memory 903 is used to store program instructions and data. Specifically, the program instructions may include program code, which includes computer operation instructions. The memory 903 may include volatile memory, such as random access memory (RAM); it may also include non-volatile memory, such as at least one disk storage device, hard disk drive (HDD), or solid state drive (SSD). The memory 903 may also be any other medium capable of carrying or storing program code in the form of instructions or data structures and accessible by a computer; this application does not limit this. The processor 902 executes the program instructions stored in the memory 903 to implement the above functions, thereby implementing the method provided in the above embodiments.

[0215] Based on the above embodiments, this application also provides a computer-readable storage medium storing a computer program, which, when executed by a computer, causes the computer to perform the methods provided in the above embodiments.

[0216] Optionally, the aforementioned computer may include, but is not limited to, communication devices such as terminal devices and network devices.

[0217] The storage medium can be any available medium that a computer can access. For example, but not limited to, a computer-readable medium can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.

[0218] Based on the above embodiments, this application also provides a chip for reading a computer program stored in a memory to implement the method provided in the above embodiments. Optionally, the chip may include a processor coupled to the memory for reading the computer program stored in the memory to implement the method provided in the above embodiments. Optionally, the chip may also include components such as a memory, a communication interface, and a power supply module. The memory is used to store the computer program; the communication interface is used to receive and send data; and the power supply module is used to supply power to the processor.

[0219] Based on the above embodiments, this application provides a chip system including a processor for supporting a computer device in implementing the above embodiments. In one possible design, the chip system further includes a memory for storing necessary programs and data of the computer device. This chip system may be composed of chips or may include chips and other discrete components.

[0220] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0221] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to 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 program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0222] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0223] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0224] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for detecting vehicle drop, characterized in that, The method is applied to an in-vehicle device, and the method includes: Obtain first information, which includes the acceleration of the vehicle in a first direction, a second direction, and a third direction, and / or the angular velocity of the vehicle in the first direction, the second direction, and the third direction, where the first direction, the second direction, and the third direction are the three coordinate axes of a three-dimensional coordinate system. Based on the first information, determine whether the vehicle has experienced a fall.

2. The method as described in claim 1, characterized in that, The step of determining whether the vehicle has fallen based on the first information includes: If the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, and the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, then it is determined that the vehicle has experienced a fall event. Alternatively, determining whether the vehicle has fallen based on the first information includes: Determine the combined acceleration of the vehicle in the first direction, the second direction, and the third direction; If the combined acceleration is greater than or equal to the first threshold, then it is determined that the vehicle has fallen.

3. The method as described in claim 1, characterized in that, The step of determining whether the vehicle has fallen based on the first information includes: If the angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the angular velocity of the vehicle in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction, then it is determined that the vehicle has experienced a fall event. Alternatively, determining whether the first vehicle has experienced a fall based on the first information includes: The angle of the vehicle in the first direction is determined based on the angular velocity of the vehicle in the first direction, the angle of the vehicle in the second direction is determined based on the angular velocity of the vehicle in the second direction, and the angle of the vehicle in the third direction is determined based on the angular velocity of the vehicle in the third direction. If the angle of the vehicle in the first direction is greater than or equal to the angle threshold corresponding to the first direction, the angle of the vehicle in the second direction is greater than or equal to the angle threshold corresponding to the second direction, and the angle of the vehicle in the third direction is greater than or equal to the angle threshold corresponding to the third direction, then it is determined that the vehicle has experienced a fall event.

4. The method as described in claim 1, characterized in that, The step of determining whether the vehicle has fallen based on the first information includes: If the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, the vehicle's angular velocity in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the vehicle's angular velocity in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the vehicle's angular velocity in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction, then it is determined that the vehicle has experienced a fall event. Alternatively, determining whether the vehicle has fallen based on the first information includes: Determine the combined acceleration of the vehicle in the first direction, the second direction, and the third direction; If the combined acceleration is greater than or equal to a first threshold, the angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction, the angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction, and the angular velocity of the vehicle in the third direction is greater than or equal to the angular velocity threshold corresponding to the third direction, then it is determined that the vehicle has experienced a fall event. Alternatively, determining whether the vehicle has fallen based on the first information includes: The angle of the vehicle in the first direction is determined based on the angular velocity of the vehicle in the first direction, the angle of the vehicle in the second direction is determined based on the angular velocity of the vehicle in the second direction, and the angle of the vehicle in the third direction is determined based on the angular velocity of the vehicle in the third direction. If the vehicle's angle in the first direction is greater than or equal to the angle threshold corresponding to the first direction, the vehicle's angle in the second direction is greater than or equal to the angle threshold corresponding to the second direction, the vehicle's angle in the third direction is greater than or equal to the angle threshold corresponding to the third direction, the vehicle's acceleration in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction, the vehicle's acceleration in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction, and the vehicle's acceleration in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction, then it is determined that the vehicle has experienced a fall event. Alternatively, determining whether the vehicle has fallen based on the first information includes: Determine the combined acceleration of the vehicle in the first direction, the second direction, and the third direction; The angle of the vehicle in the first direction is determined based on the angular velocity of the vehicle in the first direction, the angle of the vehicle in the second direction is determined based on the angular velocity of the vehicle in the second direction, and the angle of the vehicle in the third direction is determined based on the angular velocity of the vehicle in the third direction. If the combined acceleration is greater than or equal to a first threshold, the angle of the vehicle in the first direction is greater than or equal to the angle threshold corresponding to the first direction, the angle of the vehicle in the second direction is greater than or equal to the angle threshold corresponding to the second direction, and the angle of the vehicle in the third direction is greater than or equal to the angle threshold corresponding to the third direction, then it is determined that the vehicle has experienced a fall event.

5. The method as described in claim 1, characterized in that, The step of determining whether the vehicle has fallen based on the first information includes: The first information is input into the first model to obtain the detection result output by the first model. The detection result output by the first model is used to indicate that the vehicle has fallen, or the detection result output by the first model is used to indicate that the vehicle has not fallen. The training convergence target of the first model is the first information when the vehicle falls off the road.

6. The method according to any one of claims 1-5, characterized in that, The method further includes: Upon determining that the vehicle has fallen, a first indication message is broadcast and an alarm is issued. The first indication message indicates that the vehicle has fallen and includes the location where the vehicle fell.

7. A method for detecting vehicle drop, characterized in that, The method is applied to an in-vehicle device, and the method includes: Acquire first information and second information. The first information includes the acceleration and angular velocity of the vehicle in a first direction, a second direction, and a third direction, where the first direction, the second direction, and the third direction are the three coordinate axes of a three-dimensional coordinate system. The second information includes at least one of the following: the tire pressure of the vehicle, the suspension height of the vehicle, and environmental information. Based on the first information and the second information, determine whether the vehicle has experienced a fall.

8. The method as described in claim 7, characterized in that, The step of determining whether the first vehicle has fallen based on the first information and the second information includes: When the first information is determined to meet the following detection conditions, the vehicle is then determined to have experienced a fall event based on the second information. The detection conditions include: The acceleration of the vehicle in the first direction is greater than or equal to the acceleration threshold corresponding to the first direction; The acceleration of the vehicle in the second direction is greater than or equal to the acceleration threshold corresponding to the second direction; The acceleration of the vehicle in the third direction is greater than or equal to the acceleration threshold corresponding to the third direction; The angular velocity of the vehicle in the first direction is greater than or equal to the angular velocity threshold corresponding to the first direction; The angular velocity of the vehicle in the second direction is greater than or equal to the angular velocity threshold corresponding to the second direction; The vehicle's angular velocity in the third direction is greater than or equal to the corresponding angular velocity threshold in the third direction.

9. The method as described in claim 8, characterized in that, The step of determining whether the vehicle has fallen based on the second information includes: If the tire pressure of the vehicle is greater than or equal to the pressure threshold, then the vehicle is determined to have experienced a fall event. Alternatively, determining whether the vehicle has fallen based on the second information includes: If the suspension height of the vehicle is less than or equal to a height threshold, then it is determined that the vehicle has experienced a fall event. Alternatively, determining whether the vehicle has fallen based on the second information includes: If the similarity between the environmental information of the vehicle at the current moment and the environmental information of the vehicle at the previous moment is less than or equal to a second threshold, then it is determined that the vehicle has experienced a fall event.

10. The method as described in claim 7, characterized in that, The step of determining whether the first vehicle has fallen based on the first information and the second information includes: The first information and the second information are input into the second model to obtain the detection result output by the second model. The detection result output by the second model is used to indicate that the vehicle has fallen, or the detection result output by the second model is used to indicate that the vehicle has not fallen. The training convergence target of the second model is the first and second information when the vehicle falls.

11. The method according to any one of claims 7-10, characterized in that, The method further includes: Upon determining that the vehicle has fallen, a first indication message is broadcast and an alarm is issued. The first indication message indicates that the vehicle has fallen and includes the location where the vehicle fell.

12. An apparatus, characterized in that, The device is disposed in a vehicle, and the device includes: The acquisition module is used to acquire first information, which includes the acceleration of the vehicle in a first direction, a second direction, and a third direction, and / or the angular velocity of the vehicle in the first direction, the second direction, and the third direction, where the first direction, the second direction, and the third direction are the three coordinate axes of a three-dimensional coordinate system. The processing module is used to determine whether the vehicle has fallen based on the first information.

13. An apparatus, characterized in that, The device is disposed in a vehicle, and the device includes: The acquisition module is used to acquire first information and second information. The first information includes the acceleration and angular velocity of the vehicle in a first direction, a second direction, and a third direction, where the first direction, the second direction, and the third direction are the three coordinate axes of a three-dimensional coordinate system. The second information includes at least one of the following: the tire pressure of the vehicle, the suspension height of the vehicle, and environmental information. The processing module is used to determine whether the vehicle has experienced a fall event based on the first information and the second information.

14. An apparatus, characterized in that, include: One or more processors and one or more memories; the one or more memories storing one or more computer programs, the one or more computer programs including instructions that, when executed by the one or more processors, cause the apparatus to perform the method as described in any one of claims 1-11.

15. A vehicle, characterized in that, It includes an inertial measurement unit (IMU) and means for performing the method as described in any one of claims 1-11, wherein the IMU is used to measure the acceleration and angular velocity of the vehicle.

16. A system, characterized in that, include: Vehicles and network devices for performing the method as described in any one of claims 1-11; The network device is used to receive first indication information sent by the vehicle and send second indication information to other vehicles. The first indication information is used to indicate that the vehicle has fallen, and the first indication information includes the location where the vehicle fell. The second indication information is used to indicate the vehicle that fell, and the second indication information includes the location of the vehicle that fell.

17. A non-volatile computer-readable storage medium, characterized in that, The non-volatile computer-readable storage medium includes a program that, when run on the device, causes the device to perform the method as described in any one of claims 1-11.

18. A computer program product, characterized in that, When the computer program product is run on the device, it causes the device to perform the method as described in any one of claims 1-11.

Images