Vehicle multi-direction collision detection method and device

Abstract

The invention relates to a vehicle multi-direction collision detection method and device, and belongs to the technical field of vehicle monitoring, and the vehicle multi-direction collision detection method comprises the steps: obtaining multi-axis acceleration and multi-axis angular velocity of a plurality of sampling points of a target vehicle in a target time period, multiple axes including a first coordinate axis, a second coordinate axis and a third coordinate axis, the first coordinate axis and the second coordinate axis are parallel to the horizontal plane, the positive direction of the first coordinate axis is perpendicular to the vehicle driving direction and points to the left side, the positive direction of the second coordinate axis is parallel to the vehicle driving direction, and the positive direction of the third coordinate axis is perpendicular to the horizontal plane upwards; based on the preprocessed multi-axis acceleration of each sampling point, the collision state and the collision direction of the target vehicle at each sampling point are determined; and determining the turnover state of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration and multi-axis angular velocity of each sampling point. According to the invention, the accuracy of vehicle collision detection is effectively improved.

Description

Technical Field

[0001] This invention relates to the field of vehicle monitoring technology, and in particular to a method and apparatus for multi-directional vehicle collision detection. Background Technology

[0002] With the rapid development of intelligent transportation systems and vehicle-to-everything (V2X) technology, vehicle safety monitoring technology has become an important means of ensuring driving safety. Real-time and accurate detection of collision events and determination of collision direction during vehicle operation are crucial for accident analysis, insurance claims, and emergency rescue.

[0003] Traditional collision detection algorithms are mainly based on a single axial acceleration threshold, which cannot accurately identify complex collision scenarios and has low detection accuracy. Most systems can only detect whether a collision has occurred, but cannot accurately determine the direction of the collision, affecting the accuracy of accident reconstruction. Disturbances such as bumps and braking during normal vehicle driving are easily misjudged as collision events. There is a lack of effective duration verification mechanisms, making it difficult to distinguish between instantaneous disturbances and real collisions. There is no collision state confirmation and cooling mechanism, which can easily lead to frequent jitter problems.

[0004] Therefore, improving the accuracy of vehicle collision detection has become an urgent technical problem to be solved. Summary of the Invention

[0005] In view of this, it is necessary to provide a vehicle multi-directional collision detection method and device to solve the problem of insufficient accuracy of existing vehicle collision detection solutions.

[0006] To address the aforementioned problems, in a first aspect, the present invention provides a vehicle multi-directional collision detection method, comprising: The multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within the target time period are obtained. The multi-axis includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first and second coordinate axes are parallel to the horizontal plane. The positive direction of the first coordinate axis is perpendicular to the vehicle's driving direction and points to the left. The positive direction of the second coordinate axis is parallel to the vehicle's driving direction. The positive direction of the third coordinate axis is perpendicular to the horizontal plane and points upward. Based on the preprocessed multi-axis acceleration of each sampling point, the collision state and collision direction of the target vehicle at each sampling point are determined. Based on the preprocessed multi-axis acceleration and multi-axis angular velocity of each sampling point, the rollover state of the target vehicle at each sampling point is determined.

[0007] In one possible implementation, determining the collision state and collision direction of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration at each sampling point includes: Based on the multi-axis acceleration of each preprocessed sampling point, the collision intensity of each sampling point is determined, and the collision intensity threshold of each sampling point is determined based on the vehicle speed of each sampling point. Based on the collision intensity and collision intensity threshold of each sampling point, the collision state of the target vehicle at each sampling point is determined. If it is determined that the target vehicle collides at the target sampling point, the collision direction of the target vehicle at the target sampling point is determined based on the multi-axis acceleration of the preprocessed target sampling point. The target sampling point is any sampling point within the target time period.

[0008] In one possible implementation, determining the collision intensity of each sampling point based on the preprocessed multi-axis acceleration of each sampling point includes: The collision intensity of each sampling point is determined based on the following formula:

[0009]

[0010]

[0011]

[0012]

[0013]

[0014]

[0015]

[0016]

[0017]

[0018] in, Indicates the intensity of the collision. Indicates the foundation strength. Indicates the rate of change. Indicates the integral intensity. This represents the acceleration of the first coordinate axis after preprocessing. This represents the acceleration of the second coordinate axis after preprocessing. This represents the acceleration of the first coordinate axis after preprocessing. Represents the rate of change of the first coordinate axis. Indicates the rate of change of the second coordinate axis. Indicates the rate of change of the third coordinate axis. Indicates the integral intensity of the first coordinate axis. This represents the integral intensity along the second coordinate axis. Indicates the integral intensity of the third coordinate axis. Indicates the first The acceleration of the first coordinate axis of each sampling point Indicates the first The acceleration of the second coordinate axis at each sampling point Indicates the first The acceleration of the third coordinate axis of each sampling point This is for absolute value operations.

[0019] In one possible implementation, determining the collision intensity threshold for each sampling point based on the vehicle speed at each sampling point includes: The collision intensity threshold for each sampling point is determined based on the following formula:

[0020] in, Indicates the collision intensity threshold. Indicates the basic threshold. Indicates vehicle speed.

[0021] In one possible implementation, determining the collision state of the target vehicle at each sampling point based on the collision intensity and collision intensity threshold at each sampling point includes: If the collision intensity at the target sampling point is greater than the collision intensity threshold at the target sampling point, it is determined that the target vehicle has detected a collision at the target sampling point. If the collision intensity at the target sampling point is less than or equal to the collision intensity threshold at the target sampling point, it is determined that no collision was detected at the target sampling point for the target vehicle.

[0022] In one possible implementation, determining the collision direction of the target vehicle at the target sampling point based on the preprocessed multi-axis acceleration of the target sampling point includes: The direction corresponding to the larger absolute value of the first coordinate axis acceleration and the second coordinate axis acceleration of the target sampling point is determined as the main collision direction of the target vehicle at the target sampling point. If the absolute value of the smaller of the absolute values ​​of the first and second coordinate axis accelerations at the target sampling point is greater than one-fifth of the absolute value of the larger of the two, the direction corresponding to the smaller of the absolute values ​​of the first and second coordinate axis accelerations at the target sampling point is determined as the collision auxiliary direction of the target vehicle at the target sampling point.

[0023] In one possible implementation, determining the rollover state of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration and multi-axis angular velocity of each sampling point includes: Based on the acceleration of the third coordinate axis and the angular velocity of the second coordinate axis of each preprocessed sampling point, the rollover state of the target vehicle at each sampling point is determined.

[0024] In one possible implementation, determining the rollover state of the target vehicle at each sampling point based on the third coordinate axis acceleration and the second coordinate axis angular velocity after preprocessing includes: If the acceleration of the third coordinate axis of the preprocessed target sampling point is greater than the acceleration threshold, and the angular velocity of the second coordinate axis of the preprocessed target sampling point is greater than the angular velocity threshold, it is determined that the target vehicle has been detected to have overturned at the target sampling point, and the target sampling point is any sampling point within the target time period; If the acceleration of the third coordinate axis of the preprocessed target sampling point is less than or equal to the acceleration threshold, or if the angular velocity of the second coordinate axis of the preprocessed target sampling point is less than or equal to the angular velocity threshold, it is determined that the target vehicle has not been detected to have overturned at the target sampling point.

[0025] In one possible implementation, the method further includes: If a collision is detected at all sampling points of the target vehicle within a preset time window, and the collision directions are consistent, then the target vehicle is determined to have collided within the preset time window.

[0026] On the other hand, the present invention also provides a vehicle multi-directional collision detection device, comprising: The acquisition module is used to acquire the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within the target time period. The multi-axis includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first and second coordinate axes are parallel to the horizontal plane. The positive direction of the first coordinate axis is perpendicular to the vehicle's driving direction and points to the left. The positive direction of the second coordinate axis is parallel to the vehicle's driving direction. The positive direction of the third coordinate axis is perpendicular to the horizontal plane and points upward. The first detection module is used to determine the collision state and collision direction of the target vehicle at each sampling point based on the multi-axis acceleration of each preprocessed sampling point. The second detection module is used to determine the rollover state of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration and multi-axis angular velocity of each sampling point.

[0027] Secondly, the present invention also provides a collision detection device, including a memory and a processor, wherein, The memory is used to store programs; The processor, coupled to the memory, is used to execute the program stored in the memory to implement the steps in the vehicle multi-directional collision detection method described in any of the above implementations.

[0028] Thirdly, the present invention also provides a computer-readable storage medium for storing a computer-readable program or instructions, which, when executed by a processor, can implement the steps of the vehicle multi-directional collision detection method described in any of the above implementations.

[0029] The beneficial effects of the present invention are as follows: The vehicle multi-directional collision detection method and apparatus provided by the present invention first acquires the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within a target time period, providing data basis for vehicle collision detection within the target time period. Then, the multi-axis acceleration and multi-axis angular velocity of each sampling point are preprocessed to eliminate noise and improve the signal-to-noise ratio. Finally, the collision state, collision direction and rollover state of the target vehicle at each sampling point are determined by the preprocessed multi-axis acceleration and multi-axis angular velocity, thereby achieving accurate detection of vehicle collisions. The present invention effectively improves the accuracy of vehicle collision detection. Attached Figure Description

[0030] Figure 1 A schematic flowchart of an embodiment of the vehicle multi-directional collision detection method provided by the present invention; Figure 2 A schematic diagram of an embodiment of the collision detection system architecture provided by the present invention; Figure 3 A schematic flowchart of an embodiment of the collision detection process provided by the present invention; Figure 4 A schematic diagram of an embodiment of the collision direction definition provided by the present invention; Figure 5 A schematic diagram of an embodiment of the collision state transition process provided by the present invention; Figure 6 A schematic diagram of an embodiment of the vehicle multi-directional collision detection device provided by the present invention; Figure 7 This is a schematic diagram of an embodiment of the collision detection device provided by the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0032] In the description of the embodiments of the present invention, unless otherwise stated, "multiple" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can represent three situations: A exists alone, A and B exist simultaneously, and B exists alone.

[0033] The terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a technical feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature.

[0034] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0035] This invention provides a method and apparatus for multi-directional collision detection of vehicles, which will be described below.

[0036] Figure 1 This is a schematic flowchart of an embodiment of the vehicle multi-directional collision detection method provided by the present invention, as shown below. Figure 1 As shown, the vehicle multi-directional collision detection method includes: S101. Obtain the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within the target time period. The multi-axis includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first and second coordinate axes are parallel to the horizontal plane. The positive direction of the first coordinate axis is perpendicular to the vehicle's driving direction and points to the left. The positive direction of the second coordinate axis is parallel to the vehicle's driving direction. The positive direction of the third coordinate axis is perpendicular to the horizontal plane and points upward.

[0037] It should be noted that the multi-directional collision detection method for vehicles provided by this invention can be applied to vehicle collision detection scenarios, especially vehicle collision detection scenarios that require determination of the vehicle collision direction.

[0038] When performing multi-directional vehicle collision detection, the collision detection equipment (such as an onboard computer in the vehicle, a desktop computer, or a portable computer at the back end) first acquires the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within a target time period. These multiple axes can include a first coordinate axis (x-axis), a second coordinate axis (y-axis), and a third coordinate axis (z-axis). The first and second coordinate axes are parallel to the horizontal plane. The positive direction of the first coordinate axis is perpendicular to the vehicle's direction of travel and points to the left. The positive direction of the second coordinate axis is parallel to the vehicle's direction of travel, and the positive direction of the third coordinate axis is perpendicular to the horizontal plane and points upwards. By acquiring the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within the target time period, data can be provided for vehicle collision detection within that time period.

[0039] S102. Based on the multi-axis acceleration of each preprocessed sampling point, determine the collision state and collision direction of the target vehicle at each sampling point.

[0040] It should be noted that after obtaining the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within the target time period, preprocessing can be performed on the multi-axis acceleration and multi-axis angular velocity at each sampling point. For example, filtering can be applied to the multi-axis acceleration and multi-axis angular velocity at each sampling point. During filtering, moving average filtering, complementary filtering, and Kalman filtering can be performed sequentially to eliminate noise, improve the signal-to-noise ratio, and thus improve the accuracy of subsequent collision detection. Then, the collision state and collision direction of the target vehicle at each sampling point can be determined using the preprocessed multi-axis acceleration of each sampling point, thereby achieving accurate vehicle collision detection.

[0041] S103. Based on the multi-axis acceleration and multi-axis angular velocity of each preprocessed sampling point, determine the rollover state of the target vehicle at each sampling point.

[0042] It should be noted that, in addition to collision detection, the rollover state of the target vehicle at each sampling point can be determined by the multi-axis acceleration and multi-axis angular velocity of each sampling point after preprocessing, so as to judge the severity of the collision and thus detect the collision state of the target vehicle more accurately.

[0043] In summary, the vehicle multi-directional collision detection method provided by this invention first acquires the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within a target time period, providing data for vehicle collision detection within the target time period. Then, the multi-axis acceleration and multi-axis angular velocity of each sampling point are preprocessed to eliminate noise and improve the signal-to-noise ratio. Finally, the collision state, collision direction, and rollover state of the target vehicle at each sampling point are determined using the preprocessed multi-axis acceleration and multi-axis angular velocity, achieving accurate vehicle collision detection. This invention effectively improves the accuracy of vehicle collision detection.

[0044] In some embodiments of the present invention, determining the collision state and collision direction of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration at each sampling point includes: Based on the multi-axis acceleration of each preprocessed sampling point, the collision intensity of each sampling point is determined, and the collision intensity threshold of each sampling point is determined based on the vehicle speed of each sampling point. Based on the collision intensity and collision intensity threshold of each sampling point, the collision state of the target vehicle at each sampling point is determined. If it is determined that the target vehicle collides at the target sampling point, the collision direction of the target vehicle at the target sampling point is determined based on the multi-axis acceleration of the preprocessed target sampling point. The target sampling point is any sampling point within the target time period.

[0045] It should be noted that when determining the collision state and direction of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration of each sampling point, the collision intensity of each sampling point is first determined based on the preprocessed multi-axis acceleration, and a collision intensity threshold is determined based on the vehicle velocity at each sampling point. Then, the collision state of the target vehicle at each sampling point is determined using the collision intensity and collision intensity threshold. When it is determined that the target vehicle has collided at a certain sampling point, the collision direction of the target vehicle at that sampling point can be determined using the preprocessed multi-axis acceleration of that sampling point, thereby realizing the detection of the collision state and collision direction of the target vehicle.

[0046] In some embodiments of the present invention, determining the collision intensity of each sampling point based on the preprocessed multiaxial acceleration of each sampling point includes: The collision intensity of each sampling point is determined based on the following formula:

[0047]

[0048]

[0049]

[0050]

[0051]

[0052]

[0053]

[0054]

[0055]

[0056] in, Indicates the intensity of the collision. Indicates the foundation strength. Indicates the rate of change. Indicates the integral intensity. This represents the acceleration of the first coordinate axis after preprocessing. This represents the acceleration of the second coordinate axis after preprocessing. This represents the acceleration of the first coordinate axis after preprocessing. Represents the rate of change of the first coordinate axis. Indicates the rate of change of the second coordinate axis. Indicates the rate of change of the third coordinate axis. Indicates the integral intensity of the first coordinate axis. This represents the integral intensity along the second coordinate axis. Indicates the integral intensity of the third coordinate axis. Indicates the first The acceleration of the first coordinate axis of each sampling point Indicates the first The acceleration of the second coordinate axis at each sampling point Indicates the first The acceleration of the third coordinate axis of each sampling point This is for absolute value operations.

[0057] It should be noted that when determining the collision intensity of each sampling point based on the multi-axis acceleration of each sampling point after preprocessing, the collision intensity of each sampling point can be calculated using the above formula.

[0058] In some embodiments of the present invention, determining the collision intensity threshold for each sampling point based on the vehicle speed at each sampling point includes: The collision intensity threshold for each sampling point is determined based on the following formula:

[0059] in, Indicates the collision intensity threshold. Indicates the basic threshold. Indicates vehicle speed.

[0060] It should be noted that when determining the collision intensity threshold for each sampling point based on the vehicle speed at each sampling point, the collision intensity threshold for each sampling point can be calculated using the above formula.

[0061] In some embodiments of the present invention, determining the collision state of the target vehicle at each sampling point based on the collision intensity and collision intensity threshold at each sampling point includes: If the collision intensity at the target sampling point is greater than the collision intensity threshold at the target sampling point, it is determined that the target vehicle has detected a collision at the target sampling point. If the collision intensity at the target sampling point is less than or equal to the collision intensity threshold at the target sampling point, it is determined that no collision was detected at the target sampling point for the target vehicle.

[0062] It should be noted that when determining the collision state of the target vehicle at each sampling point based on the collision intensity and collision intensity threshold, if the collision intensity at the target sampling point is greater than the collision intensity threshold, it can be determined that a collision was detected at the target sampling point. If the collision intensity at the target sampling point is less than or equal to the collision intensity threshold, it can be determined that no collision was detected at the target sampling point.

[0063] In some embodiments of the present invention, determining the collision direction of the target vehicle at the target sampling point based on the preprocessed multi-axis acceleration of the target sampling point includes: The direction corresponding to the larger absolute value of the first coordinate axis acceleration and the second coordinate axis acceleration of the target sampling point is determined as the main collision direction of the target vehicle at the target sampling point. If the absolute value of the smaller of the absolute values ​​of the first and second coordinate axis accelerations at the target sampling point is greater than one-fifth of the absolute value of the larger of the two, the direction corresponding to the smaller of the absolute values ​​of the first and second coordinate axis accelerations at the target sampling point is determined as the collision auxiliary direction of the target vehicle at the target sampling point.

[0064] It should be noted that when determining the collision direction of the target vehicle at the target sampling point based on the preprocessed multi-axis acceleration, the direction corresponding to the larger absolute value of the first and second axis accelerations at the target sampling point can be first determined as the primary collision direction of the target vehicle at the target sampling point. Then, it is determined whether the absolute value of the smaller absolute value of the first and second axis accelerations at the target sampling point is greater than one-fifth of the absolute value of the larger absolute value. If the absolute value of the smaller absolute value of the first and second axis accelerations at the target sampling point is greater than one-fifth of the absolute value of the larger absolute value, then the direction corresponding to the smaller absolute value of the first and second axis accelerations at the target sampling point can be determined as the secondary collision direction of the target vehicle at the target sampling point, thereby achieving the determination of the collision direction.

[0065] In some embodiments of the present invention, determining the rollover state of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration and multi-axis angular velocity of each sampling point includes: Based on the acceleration of the third coordinate axis and the angular velocity of the second coordinate axis of each preprocessed sampling point, the rollover state of the target vehicle at each sampling point is determined.

[0066] It should be noted that when determining the rollover state of the target vehicle at each sampling point based on the multi-axis acceleration and multi-axis angular velocity of each sampling point after preprocessing, the rollover state of the target vehicle at each sampling point can be determined based on the third coordinate axis acceleration and the second coordinate axis angular velocity of each sampling point after preprocessing.

[0067] In some embodiments of the present invention, determining the rollover state of the target vehicle at each sampling point based on the third coordinate axis acceleration and the second coordinate axis angular velocity of each preprocessed sampling point includes: If the acceleration of the third coordinate axis of the preprocessed target sampling point is greater than the acceleration threshold, and the angular velocity of the second coordinate axis of the preprocessed target sampling point is greater than the angular velocity threshold, it is determined that the target vehicle has been detected to have overturned at the target sampling point, and the target sampling point is any sampling point within the target time period; If the acceleration of the third coordinate axis of the preprocessed target sampling point is less than or equal to the acceleration threshold, or if the angular velocity of the second coordinate axis of the preprocessed target sampling point is less than or equal to the angular velocity threshold, it is determined that the target vehicle has not been detected to have overturned at the target sampling point.

[0068] It should be noted that when determining the rollover state of the target vehicle at each sampling point based on the acceleration of the third coordinate axis and the angular velocity of the second coordinate axis after preprocessing, if the acceleration of the third coordinate axis of the preprocessed target sampling point is greater than the acceleration threshold and the angular velocity of the second coordinate axis of the preprocessed target sampling point is greater than the angular velocity threshold, then it can be determined that the target vehicle has been detected to have rolled over at the target sampling point; if the acceleration of the third coordinate axis of the preprocessed target sampling point is less than or equal to the acceleration threshold, or if the angular velocity of the second coordinate axis of the preprocessed target sampling point is less than or equal to the angular velocity threshold, then it can be determined that the target vehicle has not been detected to have rolled over at the target sampling point.

[0069] In some embodiments of the present invention, the method further includes: If a collision is detected at all sampling points of the target vehicle within a preset time window, and the collision directions are consistent, then the target vehicle is determined to have collided within the preset time window.

[0070] It should be noted that, in order to avoid false alarms, this invention also proposes a collision confirmation mechanism, that is, only when the target vehicle is detected to have collided at all sampling points within a preset time window (e.g., 100ms) and the collision directions are consistent, is it determined that the target vehicle has collided within the preset time window, thereby further improving the accuracy of vehicle collision detection.

[0071] Combination Figure 2 As shown, this invention constructs a multi-directional collision detection system using components such as an STM32 main controller, a BMI320 sensor, power management, and a communication interface to achieve collision detection and rollover detection. The system can achieve the following functions: Raw data acquisition: The BMI320 sensor simultaneously acquires triaxial acceleration and triaxial angular velocity.

[0072] Multi-stage filtering: moving average, complementary filtering, Kalman filtering.

[0073] Feature extraction: calculation of basic strength, rate of change, and integral strength.

[0074] Fusion judgment: Weighted fusion of multi-dimensional indicators.

[0075] Intelligent confirmation: a multi-level confirmation mechanism.

[0076] Results output: collision direction, rollover status, and accident severity.

[0077] Combination Figure 3 The collision detection process specifically includes the following steps: 1. Multi-axis data acquisition and preprocessing.

[0078] Triaxial acceleration acquisition: The BMI320 sensor synchronously acquires X, Y, and Z axis acceleration data at a frequency of 166.7Hz. Sampling frequency: 166.7Hz, measurement range: ±2g (corresponding values: -32768 to +32767).

[0079] Data filtering: Multi-level filtering algorithms are used to eliminate noise and interference.

[0080] First-level filtering: moving average filtering, window size N=5, to eliminate high-frequency noise.

[0081] Secondary filtering: complementary filtering, which integrates accelerometer and gyroscope data, with a cutoff frequency of 10Hz.

[0082] Third-stage filtering: Kalman filtering, which further improves the signal-to-noise ratio.

[0083] 2. Enhance threshold calculation.

[0084] Composite strength index: The collision strength index is calculated using a multi-dimensional data fusion algorithm.

[0085] Foundation strength calculation: Let the filtered triaxial acceleration data be as follows: The formula for calculating the foundation strength is:

[0086] Calculation of rate of change: Calculate the rate of change between adjacent sampling points:

[0087]

[0088]

[0089] The formula for calculating the rate of change intensity is:

[0090] Integral strength calculation: Short-time integration (5 data points, corresponding to a 12ms time window):

[0091]

[0092]

[0093] Final intensity index: The final intensity index is calculated using a weighted fusion algorithm.

[0094] The weighting coefficients are: (Basic strength weight) (Rate of change weight) (Integral strength weight).

[0095] Adaptive threshold: The threshold is dynamically adjusted based on the vehicle status.

[0096] Let the basic threshold be The vehicle speed factor is ,in Given the vehicle's current speed, the adaptive threshold calculation formula is:

[0097] 3. Multi-dimensional collision recognition.

[0098] Collision direction determination: based on the dominant axis principle and composite threshold mechanism.

[0099] 1) Collision direction recognition in the XY plane: Dominant axis determination: Compare the absolute values ​​of the X and Y axis accelerations.

[0100] Composite direction detection: When the acceleration of the non-dominant axis exceeds 20% of that of the dominant axis, it is determined to be a composite direction collision.

[0101] Directional encoding: combined Figure 4 It adopts bitwise operation encoding and supports 8 basic directions and 4 composite directions.

[0102] 2) Z-axis rollover detection: Set the rollover acceleration threshold as... Angular velocity threshold is The conditions for determining a rollover are: and .

[0103] When the above conditions are met, it is determined to be a rollover accident, and the collision direction is coded as CRASH_DIRECTION_ROLLOVER.

[0104] 3) Multi-dimensional collision type recognition: Frontal collision: The X / Y directions are dominant, while the Z-axis changes less.

[0105] Side impact: Dominated by a single axis, with dramatic changes.

[0106] Rollover accident: Abnormal Z-axis acceleration, accompanied by changes in angular velocity.

[0107] Composite collision: Multiple axes simultaneously reach the threshold.

[0108] 4. Dedicated algorithm for rollover detection.

[0109] Attitude angle calculation: Calculate vehicle attitude based on accelerometer and gyroscope data.

[0110] Let the filtered triaxial acceleration data be... The three-axis angular velocity data are The formula for calculating the attitude angle is:

[0111] The rollover detection logic adopts a three-level rollover detection mechanism: Level 1 judgment: and .

[0112] Level 2 judgment: and .

[0113] Level 3 Judgment: and .

[0114] When any level of judgment condition is met, the system determines it to be a rollover accident.

[0115] 5. Intelligent status confirmation.

[0116] Enhanced duration verification: Introduce a weighted counting mechanism.

[0117] Combination Figure 5 Let's assume the final strength index is... The first-level threshold is The secondary threshold is ( ), the counter is The weighted counting mechanism is as follows:

[0118]

[0119]

[0120]

[0121]

[0122] Multi-level confirmation mechanism: Let the collision duration be The sampling interval is ,but: Primary Confirmation (Level 1): (Approximately 18ms), when At that time, a primary confirmation is triggered.

[0123] Intermediate Confirmation (Level 2): (Approximately 30ms), when And integral strength At that time, a mid-level confirmation is triggered.

[0124] Advanced Confirmation (Level 3): ,when Advanced confirmation is triggered when the consistency of multi-dimensional indicators meets the conditions.

[0125] The present invention has the following advantages over existing collision detection schemes: Improved detection accuracy: Compared with the traditional single-axis threshold detection method, the multi-axis composite threshold algorithm improves the collision detection accuracy from 75% to over 98%.

[0126] Rollover detection capability: A new Z-axis rollover detection algorithm has been added, achieving a rollover accident recognition accuracy of 95%.

[0127] Accurate orientation recognition: Supports accurate recognition of multiple collision orientations, with an orientation judgment accuracy rate of 94%.

[0128] The false alarm rate has been significantly reduced: through multi-level filtering and weighted confirmation mechanisms, the system's false alarm rate has been reduced from 15% to below 1%.

[0129] Fast response speed: The optimized algorithm achieves a 6ms real-time response, meeting the real-time requirements of the vehicle system.

[0130] Strong environmental adaptability: It can maintain stable and reliable testing performance even under complex working conditions such as bumpy roads and emergency braking.

[0131] Advantages of the integral algorithm: By fusing the basic strength, rate of change, and integral strength in multiple dimensions, the detection sensitivity is improved by 40%.

[0132] The following is an example of collision data processing: Taking a vehicle-mounted driving recorder as an example: Main control chip: STM32L031F6PX. IMU sensor: BMI320, configured with a range of ±2g, sampling frequency of 166.7Hz. Filtering algorithm: complementary filtering, cutoff frequency of 10Hz. Communication interface: UART / RS232, baud rate of 115200.

[0133] Initial parameter settings: Collision threshold: 3g (49152, based on BMI320, 1g = 16384). Duration: 4 data points (24ms). Cooldown: 2000 data points (12 seconds). Composite threshold percentage: 20%.

[0134] Scenario 1: Collision on the left.

[0135] Let the filtered acceleration data be... , .

[0136] Threshold determination: Foundation strength calculation:

[0137] When the base threshold hour: No collision detection is triggered.

[0138] When the threshold is adjusted to hour: This triggers collision detection.

[0139] Direction determination: Dominant axis determination: The X-axis is the dominant axis.

[0140] Direction determination: The collision was determined to be a left-side collision (CRASH_DIRECTION_POSITIVE_X).

[0141] Scenario 2: Left front side compound collision.

[0142] Let the filtered acceleration data be... , .

[0143] Threshold determination: Foundation strength calculation:

[0144] When the base threshold hour: This triggers collision detection.

[0145] Dominant axis determination: The X-axis is the dominant axis.

[0146] Composite threshold detection: .

[0147] Y-axis influence judgment: The Y-axis has a significant impact, and it is determined to be a compound collision.

[0148] Final direction determination: and It was determined to be a left frontal collision.

[0149] Status confirmation instance.

[0150] Time series analysis (assuming a sampling time interval of 1 / 2) ): 1) Collision detection phase: Moment: Collision detected. .

[0151] Moment: Continuous collisions .

[0152] Moment: Continuous collisions .

[0153] Moment: Continuous collisions .

[0154] 2) Status Confirmation Phase: when When a collision is confirmed, the system enters a cooling protection state.

[0155] 3) Cooling protection stage: exist arrive Time (corresponding to 12 seconds): If the collision signal continues, maintain the confirmation state; if the collision signal is interrupted, start the cooling counter; after the cooling counter reaches the preset value, the system resets to the normal monitoring state.

[0156] To better implement the vehicle multi-directional collision detection method in this invention embodiment, based on the vehicle multi-directional collision detection method, correspondingly, as follows: Figure 6 As shown, this embodiment of the invention also provides a vehicle multi-directional collision detection device, the vehicle multi-directional collision detection device 600 including: The acquisition module 601 is used to acquire the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within a target time period. The multi-axis includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first and second coordinate axes are parallel to the horizontal plane. The positive direction of the first coordinate axis is perpendicular to the vehicle's driving direction and points to the left. The positive direction of the second coordinate axis is parallel to the vehicle's driving direction. The positive direction of the third coordinate axis is perpendicular to the horizontal plane and points upward. The first detection module 602 is used to determine the collision state and collision direction of the target vehicle at each sampling point based on the multi-axis acceleration of each preprocessed sampling point. The second detection module 603 is used to determine the rollover state of the target vehicle at each sampling point based on the multi-axis acceleration and multi-axis angular velocity of each sampling point after preprocessing.

[0157] The vehicle multi-directional collision detection device 600 provided in the above embodiments can realize the technical solutions described in the above vehicle multi-directional collision detection method embodiments. The specific implementation principles of each module or unit can be found in the corresponding content in the above vehicle multi-directional collision detection method embodiments, and will not be repeated here.

[0158] like Figure 7 As shown, the present invention also provides a collision detection device 700. The collision detection device 700 includes a processor 701, a memory 702, and a display 703. Figure 7 Only some components of the collision detection device 700 are shown; however, it should be understood that implementation of all shown components is not required, and more or fewer components may be implemented instead.

[0159] In some embodiments, processor 701 may be a central processing unit (CPU), microprocessor, or other data processing chip, used to run program code stored in memory 702 or process data, such as the vehicle multi-directional collision detection method of the present invention.

[0160] In some embodiments, processor 701 may be a single server or a group of servers. The server group may be centralized or distributed. In some embodiments, processor 701 may be local or remote. In some embodiments, processor 701 may be implemented on a cloud platform. In one embodiment, the cloud platform may include a private cloud, public cloud, hybrid cloud, community cloud, distributed cloud, internal cloud, multi-cloud, etc., or any combination thereof.

[0161] In some embodiments, memory 702 may be an internal storage unit of the collision detection device 700, such as a hard disk or memory of the collision detection device 700. In other embodiments, memory 702 may also be an external storage device of the collision detection device 700, such as a pluggable hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., provided on the collision detection device 700.

[0162] Furthermore, the memory 702 may include both internal storage units of the collision detection device 700 and external storage devices. The memory 702 is used to store application software and various types of data installed on the collision detection device 700.

[0163] In some embodiments, display 703 may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, or an organic light-emitting diode (OLED) touchscreen. Display 703 is used to display information from the collision detection device 700 and to display a visual user interface. Components 701-703 of the collision detection device 700 communicate with each other via a system bus.

[0164] In one embodiment, when the processor 701 executes the vehicle multi-directional collision detection program in the memory 702, the following steps can be implemented: The multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within the target time period are obtained. The multi-axis includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first and second coordinate axes are parallel to the horizontal plane. The positive direction of the first coordinate axis is perpendicular to the vehicle's driving direction and points to the left. The positive direction of the second coordinate axis is parallel to the vehicle's driving direction. The positive direction of the third coordinate axis is perpendicular to the horizontal plane and points upward. Based on the preprocessed multi-axis acceleration of each sampling point, the collision state and collision direction of the target vehicle at each sampling point are determined. Based on the preprocessed multi-axis acceleration and multi-axis angular velocity of each sampling point, the rollover state of the target vehicle at each sampling point is determined.

[0165] It should be understood that when the processor 701 executes the vehicle multi-directional collision detection program in the memory 702, in addition to the functions mentioned above, it can also perform other functions, as detailed in the description of the corresponding method embodiments above.

[0166] Furthermore, this embodiment of the invention does not specifically limit the type of collision detection device 700 mentioned. The collision detection device 700 can be a portable electronic device such as a mobile phone, tablet computer, personal digital assistant (PDA), wearable device, or laptop computer. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices running iOS, Android, Microsoft, or other operating systems. The aforementioned portable electronic device can also be other portable electronic devices, such as a laptop computer with a touch-sensitive surface (e.g., a touch panel). It should also be understood that in some other embodiments of the invention, the collision detection device 700 may not be a portable electronic device, but rather a desktop computer with a touch-sensitive surface (e.g., a touch panel).

[0167] Accordingly, this application also provides a computer-readable storage medium for storing a computer-readable program or instruction. When the program or instruction is executed by a processor, it can implement the steps or functions of the vehicle multi-directional collision detection method provided in the above-described method embodiments.

[0168] Those skilled in the art will understand that all or part of the processes of the methods described in the above embodiments can be implemented by a computer program instructing related hardware (such as a processor, controller, etc.), and the computer program can be stored in a computer-readable storage medium. The computer-readable storage medium may be a disk, optical disk, read-only memory, or random access memory, etc.

[0169] The multi-directional collision detection method and device for vehicles provided by the present invention have been described in detail above. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for multi-directional collision detection of vehicles, characterized in that, include: The multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within the target time period are obtained. The multi-axis includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first and second coordinate axes are parallel to the horizontal plane. The positive direction of the first coordinate axis is perpendicular to the vehicle's driving direction and points to the left. The positive direction of the second coordinate axis is parallel to the vehicle's driving direction. The positive direction of the third coordinate axis is perpendicular to the horizontal plane and points upward. Based on the preprocessed multi-axis acceleration of each sampling point, the collision state and collision direction of the target vehicle at each sampling point are determined. Based on the preprocessed multi-axis acceleration and multi-axis angular velocity of each sampling point, the rollover state of the target vehicle at each sampling point is determined.

2. The vehicle multi-directional collision detection method according to claim 1, characterized in that, The determination of the collision state and collision direction of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration at each sampling point includes: Based on the multi-axis acceleration of each preprocessed sampling point, the collision intensity of each sampling point is determined, and the collision intensity threshold of each sampling point is determined based on the vehicle speed of each sampling point. Based on the collision intensity and collision intensity threshold of each sampling point, the collision state of the target vehicle at each sampling point is determined. If it is determined that the target vehicle collides at the target sampling point, the collision direction of the target vehicle at the target sampling point is determined based on the multi-axis acceleration of the preprocessed target sampling point. The target sampling point is any sampling point within the target time period.

3. The vehicle multi-directional collision detection method according to claim 2, characterized in that, The determination of the collision intensity of each sampling point based on the preprocessed multi-axis acceleration of each sampling point includes: The collision intensity of each sampling point is determined based on the following formula: in, Indicates the intensity of the collision. Indicates the foundation strength. Indicates the rate of change. Indicates the integral intensity. This represents the acceleration of the first coordinate axis after preprocessing. This represents the acceleration of the second coordinate axis after preprocessing. This represents the acceleration of the first coordinate axis after preprocessing. Represents the rate of change of the first coordinate axis. Indicates the rate of change of the second coordinate axis. Represents the rate of change of the third coordinate axis. Indicates the integral intensity of the first coordinate axis. Indicates the integral intensity of the second coordinate axis. Indicates the integral intensity of the third coordinate axis. Indicates the first The acceleration of the first coordinate axis of each sampling point Indicates the first The acceleration of the second coordinate axis at each sampling point Indicates the first The acceleration of the third coordinate axis of each sampling point This is for absolute value operations.

4. The vehicle multi-directional collision detection method according to claim 2, characterized in that, The process of determining the collision intensity threshold for each sampling point based on the vehicle speed at each sampling point includes: The collision intensity threshold for each sampling point is determined based on the following formula: in, Indicates the collision intensity threshold. Indicates the basic threshold. Indicates vehicle speed.

5. The vehicle multi-directional collision detection method according to claim 2, characterized in that, The process of determining the collision state of the target vehicle at each sampling point based on the collision intensity and collision intensity threshold at each sampling point includes: If the collision intensity at the target sampling point is greater than the collision intensity threshold at the target sampling point, it is determined that the target vehicle has detected a collision at the target sampling point. If the collision intensity at the target sampling point is less than or equal to the collision intensity threshold at the target sampling point, it is determined that no collision was detected at the target sampling point for the target vehicle.

6. The vehicle multi-directional collision detection method according to claim 2, characterized in that, The determination of the collision direction of the target vehicle at the target sampling point based on the preprocessed multi-axis acceleration of the target sampling point includes: The direction corresponding to the larger absolute value of the first coordinate axis acceleration and the second coordinate axis acceleration of the target sampling point is determined as the main collision direction of the target vehicle at the target sampling point. If the absolute value of the smaller of the absolute values ​​of the first and second coordinate axis accelerations at the target sampling point is greater than one-fifth of the absolute value of the larger of the two, the direction corresponding to the smaller of the absolute values ​​of the first and second coordinate axis accelerations at the target sampling point is determined as the collision auxiliary direction of the target vehicle at the target sampling point.

7. The vehicle multi-directional collision detection method according to claim 1, characterized in that, The determination of the rollover state of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration and multi-axis angular velocity includes: Based on the acceleration of the third coordinate axis and the angular velocity of the second coordinate axis of each preprocessed sampling point, the rollover state of the target vehicle at each sampling point is determined.

8. The vehicle multi-directional collision detection method according to claim 7, characterized in that, The determination of the rollover state of the target vehicle at each sampling point based on the third coordinate axis acceleration and the second coordinate axis angular velocity after preprocessing includes: If the acceleration of the third coordinate axis of the preprocessed target sampling point is greater than the acceleration threshold, and the angular velocity of the second coordinate axis of the preprocessed target sampling point is greater than the angular velocity threshold, it is determined that the target vehicle has been detected to have overturned at the target sampling point, and the target sampling point is any sampling point within the target time period; If the acceleration of the third coordinate axis of the preprocessed target sampling point is less than or equal to the acceleration threshold, or if the angular velocity of the second coordinate axis of the preprocessed target sampling point is less than or equal to the angular velocity threshold, it is determined that the target vehicle has not been detected to have overturned at the target sampling point.

9. The vehicle multi-directional collision detection method according to claim 1, characterized in that, The method further includes: If a collision is detected at all sampling points of the target vehicle within a preset time window, and the collision directions are consistent, then the target vehicle is determined to have collided within the preset time window.

10. A vehicle multi-directional collision detection device, characterized in that, include: The acquisition module is used to acquire the multi-axis acceleration and multi-axis angular velocity of the target vehicle at multiple sampling points within the target time period. The multi-axis includes a first coordinate axis, a second coordinate axis, and a third coordinate axis. The first and second coordinate axes are parallel to the horizontal plane. The positive direction of the first coordinate axis is perpendicular to the vehicle's driving direction and points to the left. The positive direction of the second coordinate axis is parallel to the vehicle's driving direction. The positive direction of the third coordinate axis is perpendicular to the horizontal plane and points upward. The first detection module is used to determine the collision state and collision direction of the target vehicle at each sampling point based on the multi-axis acceleration of each preprocessed sampling point. The second detection module is used to determine the rollover state of the target vehicle at each sampling point based on the preprocessed multi-axis acceleration and multi-axis angular velocity of each sampling point.

Images