Sensor-based vehicle collision detection method, device, equipment and medium

Abstract

The invention relates to a sensor-based vehicle collision detection method, device and equipment and a medium, and the method comprises the steps: setting the sampling frequency of an acceleration sensor; setting a trigger parameter value and recording an initial state value; acquiring three-axis data; judging whether the trigger parameter value is updated or not; performing coordinate system calibration by combining the three-axis data with the mounting angle of the acceleration sensor to obtain calibration data; calculating to obtain variable quantity data; judging whether the number of the variable quantity data reaches a set value or not; variable quantity data are combined to form a data set; judging whether variation data greater than the trigger parameter value exists in the data set or not; respectively calculating to obtain a first resultant force change trend and a second resultant force change trend; judging whether the first resultant force change trend and the second resultant force change trend simultaneously meet a collision triggering condition or not; and affirming that the vehicle has a collision event and reporting. According to the invention, the conditions of wrong judgment and wrong alarm can be avoided, the detection accuracy is improved, and the accuracy is realized without missing alarm.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle collision detection, and in particular to a sensor-based vehicle collision detection method, device, equipment and medium. Background Art

[0002] Leaving first-hand information when a road traffic accident occurs is particularly important for subsequent accident handling, etc. This involves the detection of collision events. Only by timely discovery can evidence collection and warning be carried out in the first place.

[0003] Existing detection technology mainly uses external chip detection to identify collision events. If the external chip identifies a collision, it will inform the device. However, in actual use, the problem of the vehicle being hit but the external chip not recognizing it often occurs, and once a collision occurs, data is not collected in time to issue an alarm, which has a great impact on the subsequent accident handling and identification. In addition, the trigger threshold of the chip is difficult to determine. If it is too low, it is easy to have a false alarm, and if it is too high, it is easy to not report. There are only two situations for the event: yes or no, which makes it difficult to make auxiliary judgments by other means. Summary of the invention

[0004] The purpose of the present invention is to overcome the deficiencies of the prior art and provide a vehicle collision detection method, device, equipment and medium based on a sensor.

[0005] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0006] In a first aspect, this embodiment provides a sensor-based vehicle collision detection method, comprising the following steps:

[0007] Turn on the accelerometer and set the sampling frequency of the accelerometer;

[0008] Set the trigger parameter value and record the starting state value;

[0009] Get the three-axis data collected by the acceleration sensor;

[0010] Determine whether the trigger parameter value has been updated;

[0011] If the trigger parameter value is not updated, the three-axis data is combined with the installation angle of the acceleration sensor to perform coordinate system calibration to obtain calibration data;

[0012] Calculate the variation data according to the calibration data and the initial state value, and store the variation data;

[0013] Determine whether the number of change data reaches the set value;

[0014] If the number of variation data reaches the set value, the variation data reaching the set value are combined to form a data set;

[0015] Determine whether there is any change data in the data set that is greater than the trigger parameter value;

[0016] If there is a change amount data in the data set that is greater than the trigger parameter value, the first resultant force change trend of the first half of the change amount data in the data set and the second resultant force change trend of the second half of the change amount data are calculated respectively;

[0017] Determine whether the first resultant force change trend and the second resultant force change trend simultaneously meet the collision triggering condition;

[0018] If the first resultant force change trend and the second resultant force change trend simultaneously meet the collision triggering conditions, a collision event is deemed to have occurred in the vehicle and is reported.

[0019] A further technical solution is: the initial state value refers to the data collected by the acceleration sensor in the first second, which is accumulated and averaged to obtain the initial state value.

[0020] A further technical solution is as follows: the installation angle of the acceleration sensor refers to the inclination angle between the acceleration sensor and the horizontal plane.

[0021] Its further technical solution is: after the step of judging whether the first combined force change trend and the second combined force change trend simultaneously meet the collision triggering condition, it also includes: if the first combined force change trend and the second combined force change trend do not simultaneously meet the collision triggering condition, then judging whether the first combined force change trend and the second combined force change trend simultaneously meet the suspected collision triggering condition; if the first combined force change trend and the second combined force change trend simultaneously meet the suspected collision triggering condition, then determining that the vehicle has a suspected collision event, and reporting the suspected collision event.

[0022] In a second aspect, the present embodiment provides a sensor-based vehicle collision detection device, comprising: an activation setting unit, a setting recording unit, an acquisition unit, a first judgment unit, a calibration unit, a first calculation unit, a second judgment unit, a formation unit, a third judgment unit, a second calculation unit, a fourth judgment unit, and a first identification reporting unit;

[0023] The start setting unit is used to start the acceleration sensor and set the sampling frequency of the acceleration sensor;

[0024] The setting and recording unit is used to set the trigger parameter value and record the initial state value;

[0025] The acquisition unit is used to acquire the three-axis data collected by the acceleration sensor;

[0026] The first determination unit is used to determine whether the trigger parameter value has been updated;

[0027] The calibration unit is used to calibrate the coordinate system by combining the three-axis data with the installation angle of the acceleration sensor to obtain calibration data if the trigger parameter value is not updated;

[0028] The first calculation unit is used to calculate the variation data according to the calibration data and the initial state value, and store the variation data;

[0029] The second judgment unit is used to judge whether the number of change amount data reaches a set value;

[0030] The forming unit is used for combining the variation data reaching the set value to form a data set if the number of variation data reaches the set value;

[0031] The third judgment unit is used to judge whether there is a change amount data in the data set that is greater than the trigger parameter value;

[0032] The second calculation unit is used to calculate the first resultant force change trend of the first half of the change data and the second resultant force change trend of the second half of the change data in the data set respectively if the change data in the data set is greater than the trigger parameter value;

[0033] The fourth judgment unit is used to judge whether the first resultant force change trend and the second resultant force change trend simultaneously meet the collision triggering condition;

[0034] The first identification and reporting unit is used to identify and report a collision event of the vehicle if the first combined force change trend and the second combined force change trend simultaneously meet the collision triggering conditions.

[0035] A further technical solution is: the initial state value refers to the data collected by the acceleration sensor in the first second, which is accumulated and averaged to obtain the initial state value.

[0036] A further technical solution is as follows: the installation angle of the acceleration sensor refers to the inclination angle between the acceleration sensor and the horizontal plane.

[0037] Its further technical solution is: the device also includes: a fifth judgment unit, which is used to judge whether the first combined force change trend and the second combined force change trend simultaneously meet the triggering suspected collision conditions if the first combined force change trend and the second combined force change trend do not simultaneously meet the triggering collision conditions; if the first combined force change trend and the second combined force change trend simultaneously meet the triggering suspected collision conditions, it is determined that a suspected collision event has occurred in the vehicle, and the suspected collision event is reported.

[0038] In a third aspect, this embodiment provides a computer device, which includes a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the sensor-based vehicle collision detection method as described above is implemented.

[0039] In a fourth aspect, this embodiment provides a storage medium storing a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the sensor-based vehicle collision detection method as described above can be implemented.

[0040] Compared with the prior art, the beneficial effects of the present invention are as follows: by calculating the data collected by the acceleration sensor, it is possible to avoid situations such as erroneous judgments and false alarms caused by quickly passing over speed bumps due to characteristic values ​​similar to those of a collision. It is also possible to modify the detection process and improve detection accuracy in a more intuitive and convenient manner, and to immediately notify the user when a collision alarm is issued, thereby ensuring accuracy without missed reports.

[0041] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0043] Figure 1 A schematic diagram of a flow chart of a sensor-based vehicle collision detection method provided in an embodiment of the present invention;

[0044] Figure 2 A schematic diagram of the installation angle of the acceleration sensor provided by an embodiment of the present invention;

[0045] Figure 3 A schematic diagram of a point set of a collision characteristic value waveform provided by an embodiment of the present invention;

[0046] Figure 4 A schematic block diagram of a sensor-based vehicle collision detection device provided in an embodiment of the present invention;

[0047] Figure 5 A schematic block diagram of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0048] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0049] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0050] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0051] It should be further understood that the term "and / or" used in the present description and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0052] See also Figures 1 to 3 In the specific embodiment shown, the present invention discloses a vehicle collision detection method based on a sensor, comprising the following steps:

[0053] S1, turn on the acceleration sensor and set the sampling frequency of the acceleration sensor;

[0054] Specifically, because the installation location of the equipment (including the acceleration sensor) and the vehicle model installed are uncertain, it is impossible to unify them according to the three-axis coordinate system of the acceleration sensor. Therefore, the horizontal coordinate system is used as the standard, the direction of gravity acceleration is the square of the z-axis, the vehicle's moving direction is the positive direction of the y-axis, and the left side is the positive direction of the x-axis. Figure 2 In actual tests, the y-axes of the two coordinate systems overlap, so only the x-axis and z-axis coordinates need to be converted. According to the positive direction, if the installation angle (the angle between the x-axis of the G-sensor and the x-axis of the horizontal rectangular coordinate system) is β, the x-axis (x s ), y-axis (y s ), z axis (z s ), and the relationship between the calibrated x, y, and z axes is as follows:

[0055] x=(x s *cosβ)-(Z s *sinβ);

[0056] y=y s ;

[0057] z=(x s *sinβ)-(z s *cosβ);

[0058] Among them, x s is the x-axis of the acceleration sensor, y s is the y-axis of the acceleration sensor, z s is the z-axis of the acceleration sensor, and β is the angle between the x-axis of the acceleration sensor and the x-axis of the horizontal rectangular coordinate system due to the installation angle.

[0059] Among them, after the equipment is installed, the inclination angle between the equipment and the horizontal plane is measured and recorded, and the inclination angle is used to calibrate the coordinate system of the acceleration sensor. In addition, the data obtained from multiple tests are analyzed, and the data generated after the collision are statistically plotted into a bar graph. It can be found that each collision will produce a characteristic waveform--a peak, and through statistics and comparison, it is found that the peak shows a decreasing trend in amplitude, and the waveform generated at the moment of collision will have a maximum and minimum value within 120-150ms when the waveform is generated. The peak with the largest amplitude appears. In order to detect the collision characteristics and cover the entire process, the sampling data must collect enough points to express the characteristic value within the duration of the collision, and at least 3 points are required to reflect the characteristics of the peak. Assuming 120ms / 3=40ms, it is obvious that such a sampling frequency only meets the limit value of the characteristics. In actual tests, the sampling points will always skip the peak due to the large time interval, resulting in missed judgment. Theoretically, the higher the sampling frequency, the higher the restoration of the characteristic waveform. However, in actual testing, because the device will also run other services (such as collecting speed information), the normal operation of the service will be affected when the sampling frequency reaches 100Hz. In addition, since the sampling frequency of the accelerometer on the market increases according to the pace, in actual use, only frequencies below 100hz can be used. The maximum sampling frequency of most accelerometers below 100hz is 50hz, so the adopted frequency is set to 50hz.

[0060] Among them, turn on the device, initialize and configure the accelerometer through the hardware interface, and set the sampling frequency of the accelerometer. In order to be compatible with different models of G-sensor chips, unifying the range of the three-axis data can greatly reduce the impact of data collected by different chips on the algorithm calculation results. From the statistical analysis of the collision characteristics data, it can be determined that when a collision actually occurs, the data will change greatly, so there is no need to retain too high precision, and too much data will cause the calculation time to be longer. Therefore, combined with the accuracy required for calculation and the characteristics of the device's storage method, 256LSB / g is used as the range, because 256 just corresponds to the size of the device's char type, which will not cause the data to be too large or lose precision.

[0061] S2, set the trigger parameter value and record the starting state value;

[0062] Specifically, the trigger parameter values ​​include:

[0063] Threshold: One of the conditions that triggers the algorithm calculation. When the change data reaches this value, the calculation will be triggered;

[0064] K 疑 , K 碰 : One of the conditions for judging the event type, the value calculated by the trigger algorithm is greater than K 疑 and less than K 碰 , then a suspected collision event is reported, and the calculated value is greater than K 碰 , then report the collision event;

[0065] T1: When a suspected collision occurs, the current vehicle speed will be detected after waiting for T1 time;

[0066] V: When a suspected collision event occurs, wait for T1 time and then detect the vehicle speed. If the speed is less than V, it will be upgraded to a collision event, otherwise it will not be upgraded.

[0067] Specifically, the initial state value refers to the data collected by the acceleration sensor in the first second, and the average value is accumulated to obtain the initial state value. That is to say, after the device is running, the data collected in the first second is accumulated and averaged, and recorded as the x, y, and z values ​​under the device's reference state, to obtain the initial state value.

[0068] S3, obtaining three-axis data collected by the acceleration sensor;

[0069] Specifically, the acceleration sensor collects three-axis data using existing public technology, which will not be elaborated in detail here.

[0070] S4, determining whether the trigger parameter value has been updated;

[0071] Specifically, the user can set the trigger parameter value as needed. If the user resets the trigger parameter value, the system automatically updates the trigger parameter value, that is, if the trigger parameter value has been updated, the process returns to step S2.

[0072] S5, if the trigger parameter value is not updated, the three-axis data is combined with the installation angle of the acceleration sensor to perform coordinate system calibration to obtain calibration data;

[0073] Specifically, the installation angle of the acceleration sensor refers to the inclination angle between the acceleration sensor and the horizontal plane. In addition, the three-axis data is combined with the installation angle of the device and then adjusted to the value of the horizontal coordinate system to obtain the calibration data.

[0074] S6, calculating the variation data according to the calibration data and the initial state value, and storing the variation data;

[0075] Specifically, by subtracting the initial state value and calculating the change in the resultant force, the data is stored in an array for subsequent algorithm calculations. The change in the resultant force ΔA is calculated using the following formula:

[0076] Δx=p x (x i -x0);

[0077] Δy=p y (y i -y0);

[0078] Δz=p z (z i -z0);

[0079]

[0080] Among them, x i ,y i 、z i are the x, y, and z values ​​passed in each sampling after the coordinate system is calibrated; x0, y0, and z0 are the average values ​​calculated from the 1st second data, which are regarded as the initial state values ​​of the vehicle; p x 、p y 、p z are the weight parameters of the three axes respectively; Δx, Δy, Δz are the changes of the three axes from the initial state values ​​respectively; ΔA is the magnitude of the reaction change.

[0081] Among them, due to the different types of actual vehicles and different installation angles, the weight of each axis in reflecting the severity of the collision is different during a collision. The current algorithm sets the weight of the Z axis to 0 and the weights of the Y and X axes to 1. Because the collision occurs on the horizontal plane, more attention is paid to the horizontal plane. The three weights are introduced to adapt to the situation where the device acceleration sensor does not coincide with the horizontal rectangular coordinate plane. For example, when x s When the Z axis of the horizontal rectangular coordinate system coincides with the Z axis of the horizontal rectangular coordinate system, the p x Set to 0, p y and p z Set to 1 to adapt.

[0082] S7, judging whether the number of the variation data reaches the set value; if the number of the variation data does not reach the set value, returning to step S3.

[0083] S8, if the number of variation data reaches the set value, the variation data reaching the set value are combined to form a data set;

[0084] Specifically, see Figure 3As shown in the figure, a point set that can reflect the characteristic waveform is intercepted from a large amount of data collected when analyzing the collision characteristic value. When a collision occurs, a peak-shaped characteristic quantity as shown in the figure will appear, and then the peak value and the steepness of the peak generated by collisions of different degrees are different. This is used as a characteristic quantity to identify the collision event, that is, to calculate the slope k value. The calculation formula is as follows:

[0085]

[0086] Among them, k is the value showing the trend of the change of the resultant force; x i is the i moment; y i is the change of the resultant force at time i; is the mean value at time n; is the mean value of the resultant force variation under the statistics of time n. This formula is a formula for the derivation of the resultant force variation with respect to time, and the obtained k value reflects the trend of the resultant force variation.

[0087] S9, determining whether there is any change data in the data set that is greater than the trigger parameter value; if there is no change data in the data set that is greater than the trigger parameter value, returning to step S3.

[0088] S10, if there is a change amount data in the data set that is greater than the trigger parameter value, then respectively calculating the first resultant force change trend of the first half of the change amount data in the data set and the second resultant force change trend of the second half of the change amount data;

[0089] Specifically, due to the sampling frequency and collision characteristics, the algorithm calculation can only be performed after collecting x data. x is related to the sampling frequency. Because the data analysis concludes that the collision duration is 120-150ms, the number of points used for calculation must cover this range. Because the sampling frequency is 50hz, at least 8 points are required to ensure that the complete collision duration is covered. When x change data is reached and when a change greater than the threshold is detected, the first x / 2 points and the last x / 2 points at the current moment are passed into the formula In the process, the changing trend k1 of the resultant force reflected by the x / 2 points before the current moment (i.e., the first changing trend of the resultant force) and the changing trend k2 of the resultant force reflected by the x / 2 points after the current moment (i.e., the second changing trend of the resultant force) are calculated.

[0090] S11, determining whether the first resultant force change trend and the second resultant force change trend simultaneously meet a collision triggering condition;

[0091] Specifically, the slope is used to determine whether the condition of the collision characteristic peak is met. Assuming that the slope threshold is set to K, the following conditions are met:

[0092]

[0093] Among them, k1 is the change trend of the resultant force reflected by the first x / 2 points before the current moment; k2 is the change trend of the resultant force reflected by the next x / 2 points after the current moment; K is a quantity for judging whether the change trend meets the collision recognition standard. Among them, the detection standard of dangerous driving behavior mainly refers to the "Data Standard: Specification for Collecting Internet of Vehicles Data of Motor Vehicle Insurance". The determination of a collision is that the acceleration at the moment of collision is greater than 20 m / s 2 , so the theoretical value should be 20÷9.8*256 = 125.44 LSB according to the unit conversion in the algorithm [Parameter introduction in the formula: 20 m / s 2 ; the acceleration of 1 g is 9.8 m / s 2 ; 256 LSB / g]. This variable is set by the user himself. Because the vibration amplitude generated varies greatly according to the installation method and location, it needs to be adjusted according to the actual situation.

[0094] Specifically, after the step of judging whether the first resultant force change trend and the second resultant force change trend simultaneously meet the collision trigger condition, it further includes: S13, if the first resultant force change trend and the second resultant force change trend do not simultaneously meet the collision trigger condition, then judge whether the first resultant force change trend and the second resultant force change trend simultaneously meet the suspected collision trigger condition; S14, if the first resultant force change trend and the second resultant force change trend simultaneously meet the suspected collision trigger condition, then it is determined that the vehicle has a suspected collision event and report the suspected collision event; S15, if the first resultant force change trend and the second resultant force change trend do not simultaneously meet the suspected collision trigger condition, then it is determined that no collision event occurs for the vehicle.

[0095] S12, if the first resultant force change trend and the second resultant force change trend simultaneously meet the collision trigger condition, then it is determined that the vehicle has a collision event and report it.

[0096] Specifically, combined with the characteristic values of the collision, through multiple tests and comparisons, it is found that after different vehicle models collide, the amplitudes transmitted to the device will be different. Therefore, the single-slope threshold (K) cannot solve this problem for this issue. Therefore, it is necessary to make a subdivision treatment of the K value and introduce a double K value (K 疑 , K 碰 ). In this way, the upper and lower limits of the detection can be adjusted separately, so that the collision detection of different vehicle models will not be too sensitive to cause too many false alarms, nor will it cause missed reports due to too high a set threshold.

[0097] Among them, for the event where (K 疑 <k1<K 碰 ) and (-K 碰 <k2<-K 疑 ), it is reported as a suspected collision event, and for the event where (K 碰 <k1) and (k2<-K碰 ) is reported as a collision event. If k1 and k2 do not meet any of the above judgment conditions, it is judged that no collision event has occurred. In addition, at T1 time after the suspected collision event is reported, the vehicle's driving speed is judged in combination with the GPS module. If the speed is less than V, the suspected collision event is upgraded to a collision event, and another collision event is sent based on the original suspected collision event. The user replaces the event by himself; if the speed is greater than V, only a suspected warning prompt will be issued, and there is no need to upgrade the event.

[0098] In the present invention, the detection of collision events no longer relies on the change detection of a single axis by the G-sensor chip, making the judgment detection more sensitive, and introducing the installation angle to calibrate the collected data into a horizontal coordinate system, which is more appropriate to the actual application scenario and improves the accuracy of the judgment of the motion state; in addition, the introduction of the speed dimension allows the detection of collisions to be verified and judged from more dimensions to avoid false alarms. In the existing technical solutions, one is to test through an external acceleration sensor chip, which will cause the user to not know the working principle of the acceleration sensor. When a false alarm or no alarm occurs, it is impossible to analyze whether the set sensitivity is problematic or the hardware itself has a fault. The present invention can determine whether the hardware is damaged or the parameters are not set normally by checking the data of the algorithm, and through the process of executing the calculation, the user can monitor and adjust the actual operating value, which can better adapt to a variety of scenarios. In addition, after introducing the speed dimension, it can avoid the situation where the characteristic value similar to the collision caused by the rapid speed bump leads to wrong judgment and false alarm, and it can also modify the detection process more intuitively and conveniently and improve the detection accuracy, and notify the user immediately when the collision alarm occurs, so as to achieve accurate and no missed alarms. In addition, the introduction of multiple thresholds can also achieve more detailed operations for the scene. For example, when a suspected alarm occurs, the video is recorded, but the user's client is not alerted to avoid anxiety caused by false alarms. However, because there is a recorded video, first-hand evidence is not lost and false alarms are avoided. When a collision alarm occurs, the customer is notified immediately to ensure accuracy and no missed reports.

[0099] See also Figure 4 As shown, the present invention also discloses a sensor-based vehicle collision detection device, comprising: an opening setting unit 10, a setting recording unit 20, an acquisition unit 30, a first judgment unit 40, a calibration unit 50, a first calculation unit 60, a second judgment unit 70, a formation unit 80, a third judgment unit 90, a second calculation unit 100, a fourth judgment unit 110 and a first identification reporting unit 120;

[0100] The start setting unit 10 is used to start the acceleration sensor and set the sampling frequency of the acceleration sensor;

[0101] The setting recording unit 20 is used to set the trigger parameter value and record the initial state value;

[0102] The acquisition unit 30 is used to acquire the three-axis data collected by the acceleration sensor;

[0103] The first determination unit 40 is used to determine whether the trigger parameter value has been updated;

[0104] The calibration unit 50 is used to calibrate the coordinate system by combining the three-axis data with the installation angle of the acceleration sensor to obtain calibration data if the trigger parameter value is not updated;

[0105] The first calculation unit 60 is used to calculate the variation data according to the calibration data and the initial state value, and store the variation data;

[0106] The second judging unit 70 is used to judge whether the number of the variation data reaches a set value;

[0107] The forming unit 80 is used for combining the variation data reaching the set value to form a data set if the number of variation data reaches the set value;

[0108] The third judgment unit 90 is used to judge whether there is a change amount data in the data set that is greater than the trigger parameter value;

[0109] The second calculation unit 100 is used to calculate the first resultant force change trend of the first half of the change data and the second resultant force change trend of the second half of the change data in the data set respectively if the change data in the data set is greater than the trigger parameter value;

[0110] The fourth judgment unit 110 is used to judge whether the first resultant force change trend and the second resultant force change trend simultaneously meet the collision triggering condition;

[0111] The first identification and reporting unit 120 is used to identify and report a collision event of the vehicle if the first combined force change trend and the second combined force change trend simultaneously meet the collision triggering conditions.

[0112] In one embodiment, the initial state value refers to the initial state value obtained by accumulating and averaging the data collected by the acceleration sensor in the first second.

[0113] In one embodiment, the installation angle of the acceleration sensor refers to the inclination angle between the acceleration sensor and the horizontal plane.

[0114] In one embodiment, the device also includes: a fifth judgment unit 130, which is used to judge whether the first resultant force change trend and the second resultant force change trend simultaneously meet the triggering suspected collision condition if the first resultant force change trend and the second resultant force change trend do not simultaneously meet the triggering collision condition.

[0115] In one embodiment, the device further includes: a second identification and reporting unit 140, which is used to identify that a suspected collision event occurs in the vehicle and report the suspected collision event if the first combined force change trend and the second combined force change trend simultaneously meet the triggering suspected collision conditions.

[0116] In one embodiment, the device further includes: a recognition unit 150, which is used to recognize that no collision event occurs to the vehicle if the first resultant force change trend and the second resultant force change trend do not simultaneously satisfy the triggering condition of a suspected collision.

[0117] It should be noted that technicians in the relevant field can clearly understand that the specific implementation process of the above-mentioned sensor-based vehicle collision detection device and each unit can refer to the corresponding description in the aforementioned method embodiment, and for the convenience and brevity of description, it will not be repeated here.

[0118] The above-mentioned sensor-based vehicle collision detection device can be implemented in the form of a computer program, which can be used in Figure 5 Runs on the computer device shown.

[0119] See also Figure 5 , Figure 5 is a schematic block diagram of a computer device provided in an embodiment of the present application; the computer device 500 may be a terminal or a server, wherein the terminal may be an electronic device with communication functions such as a smart phone, a tablet computer, a laptop computer, a desktop computer, a personal digital assistant, and a wearable device. The server may be an independent server or a server cluster composed of multiple servers.

[0120] See also Figure 5 The computer device 500 includes a processor 502 , a memory and a network interface 505 connected via a system bus 501 , wherein the memory may include a non-volatile storage medium 503 and an internal memory 504 .

[0121] The non-volatile storage medium 503 can store an operating system 5031 and a computer program 5032. The computer program 5032 includes program instructions, and when the program instructions are executed, the processor 502 can execute a sensor-based vehicle collision detection method.

[0122] The processor 502 is used to provide computing and control capabilities to support the operation of the entire computer device 500 .

[0123] The internal memory 504 provides an environment for the operation of the computer program 5032 in the non-volatile storage medium 503. When the computer program 5032 is executed by the processor 502, the processor 502 can execute a sensor-based vehicle collision detection method.

[0124] The network interface 505 is used to communicate with other devices over the network. Figure 5 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present application, and does not constitute a limitation on the computer device 500 to which the solution of the present application is applied. The specific computer device 500 may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0125] The processor 502 is used to run the computer program 5032 stored in the memory to implement the following steps:

[0126] Turn on the accelerometer and set the sampling frequency of the accelerometer; set the trigger parameter value and record the initial state value; obtain the three-axis data collected by the accelerometer; determine whether the trigger parameter value has been updated; if the trigger parameter value has not been updated, calibrate the coordinate system of the three-axis data in combination with the installation angle of the accelerometer to obtain the calibration data; calculate the variation data based on the calibration data and the initial state value, and store the variation data; determine whether the number of variation data reaches the set value; if the number of variation data reaches the set value, combine the variation data that reaches the set value to form a data set; determine whether there is variation data in the data set that is greater than the trigger parameter value; if there is variation data in the data set that is greater than the trigger parameter value, calculate the first resultant force change trend of the first half of the variation data in the data set and the second resultant force change trend of the second half of the variation data; determine whether the first resultant force change trend and the second resultant force change trend simultaneously meet the trigger collision condition; if the first resultant force change trend and the second resultant force change trend simultaneously meet the trigger collision condition, determine that the vehicle has a collision event and report it.

[0127] It should be understood that in the embodiment of the present application, the processor 502 may be a central processing unit (CPU), and the processor 502 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0128] It can be understood by those skilled in the art that all or part of the processes in the method for implementing the above embodiment can be completed by instructing the relevant hardware through a computer program. The computer program includes program instructions, and the computer program can be stored in a storage medium, which is a computer-readable storage medium. The program instructions are executed by at least one processor in the computer system to implement the process steps of the embodiment of the above method.

[0129] Therefore, the present invention also provides a storage medium. The storage medium may be a computer-readable storage medium. The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the above-mentioned sensor-based vehicle collision detection method can be implemented. The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the above-mentioned method can be implemented. The program instructions include the following steps:

[0130] Turn on the accelerometer and set the sampling frequency of the accelerometer; set the trigger parameter value and record the initial state value; obtain the three-axis data collected by the accelerometer; determine whether the trigger parameter value has been updated; if the trigger parameter value has not been updated, calibrate the coordinate system of the three-axis data in combination with the installation angle of the accelerometer to obtain the calibration data; calculate the variation data based on the calibration data and the initial state value, and store the variation data; determine whether the number of variation data reaches the set value; if the number of variation data reaches the set value, combine the variation data that reaches the set value to form a data set; determine whether there is variation data in the data set that is greater than the trigger parameter value; if there is variation data in the data set that is greater than the trigger parameter value, calculate the first resultant force change trend of the first half of the variation data in the data set and the second resultant force change trend of the second half of the variation data; determine whether the first resultant force change trend and the second resultant force change trend simultaneously meet the trigger collision condition; if the first resultant force change trend and the second resultant force change trend simultaneously meet the trigger collision condition, determine that the vehicle has a collision event and report it.

[0131] The storage medium may be a USB flash drive, a mobile hard disk, a read-only memory (ROM), a magnetic disk, or an optical disk, etc., which are computer-readable storage media that can store program codes.

[0132] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0133] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of each unit is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or skipped.

[0134] The steps in the method of the embodiment of the present invention can be adjusted in order, combined and deleted according to actual needs. The units in the device of the embodiment of the present invention can be combined, divided and deleted according to actual needs. In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0135] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a storage medium. Based on this understanding, the technical solution of the present invention is essentially or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention.

[0136] The above embodiments are preferred implementation schemes of the present invention. In addition, the present invention may also be implemented in other ways. Any obvious replacement without departing from the concept of the present technical solution is within the protection scope of the present invention.

Claims

1. A vehicle collision detection method based on a sensor, characterized in that: The following steps are involved: Turn on the accelerometer and set the sampling frequency of the accelerometer; Set the trigger parameter value and record the starting state value; Get the three-axis data collected by the acceleration sensor; Determine whether the trigger parameter value has been updated; If the trigger parameter value is not updated, the three-axis data is combined with the installation angle of the acceleration sensor to perform coordinate system calibration to obtain calibration data; Calculate the variation data according to the calibration data and the initial state value, and store the variation data; Determine whether the number of change data reaches the set value; If the number of variation data reaches the set value, the variation data reaching the set value are combined to form a data set; Determine whether there is any change data in the data set that is greater than the trigger parameter value; If there is a change amount data in the data set that is greater than the trigger parameter value, the first resultant force change trend of the first half of the change amount data in the data set and the second resultant force change trend of the second half of the change amount data are calculated respectively; Determine whether the first resultant force change trend and the second resultant force change trend simultaneously meet the collision triggering condition; If the first resultant force change trend and the second resultant force change trend simultaneously meet the collision triggering conditions, a collision event is deemed to have occurred in the vehicle and is reported.

2. The sensor-based vehicle collision detection method according to claim 1, characterized in that: The initial state value refers to the initial state value obtained by accumulating and averaging the data collected by the acceleration sensor in the first second.

3. The sensor-based vehicle collision detection method according to claim 1, characterized in that: The installation angle of the acceleration sensor refers to the inclination angle between the acceleration sensor and the horizontal plane.

4. The sensor-based vehicle collision detection method according to claim 1, characterized in that: After the step of judging whether the first combined force change trend and the second combined force change trend satisfy the collision triggering condition at the same time, the step also includes: if the first combined force change trend and the second combined force change trend do not satisfy the collision triggering condition at the same time, judging whether the first combined force change trend and the second combined force change trend satisfy the suspected collision triggering condition at the same time; if the first combined force change trend and the second combined force change trend satisfy the suspected collision triggering condition at the same time, determining that a suspected collision event occurs in the vehicle, and reporting the suspected collision event.

5. A sensor-based vehicle collision detection device, characterized in that: include: Start the setting unit, the setting recording unit, the obtaining unit, the first judging unit, the calibration unit, the first calculating unit, the second judging unit, the forming unit, the third judging unit, the second calculating unit, the fourth judging unit and the first identification reporting unit; The start setting unit is used to start the acceleration sensor and set the sampling frequency of the acceleration sensor; The setting and recording unit is used to set the trigger parameter value and record the initial state value; The acquisition unit is used to acquire the three-axis data collected by the acceleration sensor; The first determination unit is used to determine whether the trigger parameter value has been updated; The calibration unit is used to calibrate the coordinate system by combining the three-axis data with the installation angle of the acceleration sensor to obtain calibration data if the trigger parameter value is not updated; The first calculation unit is used to calculate the variation data according to the calibration data and the initial state value, and store the variation data; The second judgment unit is used to judge whether the number of change amount data reaches a set value; The forming unit is used for combining the variation data reaching the set value to form a data set if the number of variation data reaches the set value; The third judgment unit is used to judge whether there is a change amount data in the data set that is greater than the trigger parameter value; The second calculation unit is used to calculate the first resultant force change trend of the first half of the change data and the second resultant force change trend of the second half of the change data in the data set respectively if the change data in the data set is greater than the trigger parameter value; The fourth judgment unit is used to judge whether the first resultant force change trend and the second resultant force change trend simultaneously meet the collision triggering condition; The first identification and reporting unit is used to identify and report a collision event of the vehicle if the first combined force change trend and the second combined force change trend simultaneously meet the collision triggering conditions.

6. The sensor-based vehicle collision detection device according to claim 5, characterized in that: The initial state value refers to the initial state value obtained by accumulating and averaging the data collected by the acceleration sensor in the first second.

7. The sensor-based vehicle collision detection device according to claim 5, characterized in that: The installation angle of the acceleration sensor refers to the inclination angle between the acceleration sensor and the horizontal plane.

8. The sensor-based vehicle collision detection device according to claim 5, characterized in that: The device also includes: a fifth judgment unit, which is used to judge whether the first combined force change trend and the second combined force change trend simultaneously meet the triggering suspected collision condition if the first combined force change trend and the second combined force change trend do not simultaneously meet the triggering collision condition; if the first combined force change trend and the second combined force change trend simultaneously meet the triggering suspected collision condition, it is determined that a suspected collision event has occurred in the vehicle, and the suspected collision event is reported.

9. A computer device, characterized in that: The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the sensor-based vehicle collision detection method according to any one of claims 1 to 4 when executing the computer program.

10. A storage medium, characterized in that: The storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the sensor-based vehicle collision detection method according to any one of claims 1 to 4 is implemented.

Images