A collision event determination method, apparatus, device and storage medium
By performing gyroscope signal weighted fitting, filtering, and oversampling on the acceleration signal, the accuracy problem caused by noise aliasing in traditional methods is solved, achieving more efficient and accurate collision event determination.
Patent Information
- Application Number
- CN202310875961.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-07-17
- Publication Date
- 2026-02-17
- Estimated Expiration
- 2043-07-17
AI Technical Summary
Among the existing methods for determining car collision events, the pulse method and the camera method are not accurate enough. The noise aliasing problem of traditional acceleration sensors leads to inaccurate collision event judgment, and the use of high-precision sensors and high-frequency chips is costly.
The original acceleration signal is weighted and filtered using gyroscope signals. Kalman filtering simplification and Shannon oversampling techniques are used to reduce noise and improve signal accuracy.
It improves the accuracy of collision event detection, reduces computational resource consumption, decreases false positives, and lowers costs.
Smart Images
Figure CN116901888B_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of electric control system, and in particular to a collision event determination method, device, equipment and storage medium. BACKGROUND
[0002] At present, the determination of automobile collision events generally adopts pulse method and camera method. The camera method has not been widely used due to the limitation of various use scenarios. The pulse method mainly uses single or double acceleration sensors, but due to the reasons of various collision events and the specificity of the collision pulse transmission path, the basic frequency is often close to or even exceeds the sampling frequency of the vehicle acceleration sensor, so that the pulse exceeding the Nyquist frequency becomes noise aliasing, affecting the determination of the collision event. As a result, the traditional manufacturers have to use one or more higher-precision sensors and higher-frequency main control chips to improve the stability of the filtering algorithm for sampling, but this method is not only expensive but also inaccurate in determining the collision event. SUMMARY
[0003] Therefore, the present application provides a collision event determination method, device, equipment and storage medium to improve the accuracy of determining the collision event.
[0004] In a first aspect, an embodiment of the present application provides a collision event determination method, which comprises:
[0005] For the gyroscope signal and the acceleration raw signal obtained according to each first period, performing: based on the gyroscope signal obtained in the first period, performing weighted fitting processing on the acceleration raw signal obtained in the first period to obtain a first optimized signal; performing filtering processing on the first optimized signal to obtain a second optimized signal; based on the gyroscope signal obtained in the first period, performing weighted fitting processing on the second optimized signal to obtain a target optimized signal;
[0006] Based on the target optimized signal corresponding to each first period, obtaining a target signal corresponding to a second period; wherein the second period includes a preset number of first periods;
[0007] Based on the target signal, determining whether a collision event occurs in the second period.
[0008] In the present application, the original noise of the acceleration sensor is reduced by processing the acceleration original signal by using the gyroscope signal, the sensitive noise of the mechanical vibration in the acceleration original signal is reduced by processing the filtered acceleration original signal by using the gyroscope signal, and the noise introduced due to the gravity and the tilt is reduced by filtering the first optimized signal, so that the purpose signal obtained in the present application is more accurate, thereby ensuring the accuracy of the judgment of the collision event.
[0009] In some possible embodiments, the weighting fitting processing of the acceleration original signal obtained in the first period based on the gyroscope signal obtained in the first period obtains a first optimized signal, including:
[0010] Constructing a first curve based on the gyroscope signal obtained in the first period;
[0011] Constructing a second curve based on the acceleration original signal obtained in the first period;
[0012] The first curve and the second curve are weighted fitting processed according to the first preset weight corresponding to the first curve and the second preset weight corresponding to the second curve, to obtain the first optimized signal.
[0013] In the present application, by setting different weights for the gyroscope signal and the acceleration original signal, the noise introduced due to the gravity and the tilt in the acceleration original signal is reduced.
[0014] In some possible embodiments, the filtering processing of the first optimized signal obtains a second optimized signal, including:
[0015] Simplifying the Kalman filter to obtain a target filter;
[0016] The first optimized signal is filtered by using the target filter to obtain the second optimized signal.
[0017] In the present application, the noise in the acceleration original signal is further reduced by filtering the first optimized signal, thereby ensuring the accuracy of the determined purpose signal.
[0018] In some possible embodiments, the simplifying processing of the Kalman filter to obtain a target filter includes:
[0019] The weight in the Kalman filter is replaced by a preset weight, and the weight in the Kalman filter is a weight updated in real time according to the noise of the acceleration original signal.
[0020] In this application, the Kalman filter is simplified, which reduces the amount of computation and saves computational resources.
[0021] In some possible embodiments, the step of performing weighted fitting processing on the second optimized signal based on the gyroscope signal acquired within the first period to obtain the target optimized signal includes:
[0022] A first curve is constructed based on the gyroscope signals acquired during the first cycle;
[0023] A third curve is constructed based on the first optimized signal;
[0024] The first curve and the third curve are weighted and fitted according to the first preset weight corresponding to the first curve and the third preset weight corresponding to the third curve to obtain the third optimized signal.
[0025] The third optimized signal is sampled and processed to obtain the target optimized signal.
[0026] In this application, noise in the original acceleration signal is reduced by setting different weights.
[0027] In some possible embodiments, the sampling process of the third optimization signal to obtain the target optimization signal includes:
[0028] Based on the timing of each third optimized signal, a first intermediate point is filled between every two third optimized signals using a preset filling method to obtain a set of third optimized signals;
[0029] The target third optimized signal is obtained by performing Shannon oversampling on the third optimized signal set.
[0030] The target third optimization signal is integrated to obtain the target optimization signal.
[0031] In this application, the target optimized signal is determined by using a preset filling method and a Shannon oversampling method, which reduces the overflow of peak values during software sampling and reconstruction of traditional collision accelerometers and improves technical accuracy and reliability.
[0032] In some possible embodiments, obtaining the target signal corresponding to the second period based on the target optimization signal corresponding to each first period includes:
[0033] The target optimization signals are sorted according to the time sequence of each target optimization signal to obtain a target optimization signal sequence;
[0034] In the target optimization signal sequence, a second intermediate signal is filled between every two target optimization signals using a preset filling method to obtain a target optimization signal set;
[0035] The target optimized signal set is subjected to Shannon supersampling to obtain the initial target signal;
[0036] The initial target signal is integrated to obtain the target signal.
[0037] In this application, the target optimized signal is determined by using a preset filling method and a Shannon oversampling method, which reduces the overflow of peak values during software sampling and reconstruction of traditional collision accelerometers and improves technical accuracy and reliability.
[0038] Secondly, embodiments of this application provide a collision event determination device, the device comprising:
[0039] The target optimization signal determination module is used to perform the following operations on the gyroscope signal and the raw acceleration signal acquired in each first cycle: performing weighted fitting processing on the raw acceleration signal acquired in the first cycle based on the gyroscope signal acquired in the first cycle to obtain a first optimized signal; performing filtering processing on the first optimized signal to obtain a second optimized signal; and performing weighted fitting processing on the second optimized signal based on the gyroscope signal acquired in the first cycle to obtain a target optimized signal.
[0040] The target signal determination module is used to obtain the target signal corresponding to the second period based on the target optimization signal corresponding to each first period; wherein, the second period includes a preset number of first periods;
[0041] The collision event determination module is used to determine whether a collision event occurs within the second period based on the target signal.
[0042] In some possible embodiments, when the target optimization signal determination module performs weighted fitting processing on the raw acceleration signal acquired within the first period based on the gyroscope signal acquired within the first period to obtain the first optimized signal, it is specifically used for:
[0043] A first curve is constructed based on the gyroscope signals acquired during the first cycle;
[0044] A second curve is constructed based on the original acceleration signal obtained during the first cycle;
[0045] The first curve and the second curve are weighted and fitted according to the first preset weight corresponding to the first curve and the second preset weight corresponding to the second curve to obtain the first optimized signal.
[0046] In some possible embodiments, when the target optimization signal determination module performs filtering on the first optimization signal to obtain the second optimization signal, it is specifically used for:
[0047] The Kalman filter is simplified to obtain the target filter;
[0048] The first optimized signal is filtered using the target filter to obtain the second optimized signal.
[0049] In some possible embodiments, when the target optimization signal determination module performs a simplification process on the Kalman filter to obtain the target filter, it is specifically used for:
[0050] The weights in the Kalman filter are replaced with preset weights, which are updated in real time based on the noise of the original acceleration signal.
[0051] In some possible embodiments, when the target optimization signal determination module performs weighted fitting processing on the second optimization signal based on the gyroscope signal acquired within the first period to obtain the target optimization signal, it is specifically used for:
[0052] A first curve is constructed based on the gyroscope signals acquired during the first cycle;
[0053] A third curve is constructed based on the first optimized signal;
[0054] The first curve and the third curve are weighted and fitted according to the first preset weight corresponding to the first curve and the third preset weight corresponding to the third curve to obtain the third optimized signal.
[0055] The third optimized signal is sampled and processed to obtain the target optimized signal.
[0056] In some possible embodiments, when the target optimization signal determination module performs sampling processing on the third optimization signal to obtain the target optimization signal, it is specifically used for:
[0057] Based on the timing of each third optimized signal, a first intermediate point is filled between every two third optimized signals using a preset filling method to obtain a set of third optimized signals;
[0058] The target third optimized signal is obtained by performing Shannon oversampling on the third optimized signal set.
[0059] The target third optimization signal is integrated to obtain the target optimization signal.
[0060] In some possible embodiments, when the target signal determination module performs the process of obtaining the target signal corresponding to the second period based on the target optimization signal corresponding to each first period, it is specifically used for:
[0061] The target optimization signals are sorted according to the time sequence of each target optimization signal to obtain a target optimization signal sequence;
[0062] In the target optimization signal sequence, a second intermediate signal is filled between every two target optimization signals using a preset filling method to obtain a target optimization signal set;
[0063] The target optimized signal set is subjected to Shannon supersampling to obtain the initial target signal;
[0064] The initial target signal is integrated to obtain the target signal.
[0065] Thirdly, another embodiment of this application also provides an electronic device, including at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform any of the methods provided in the first aspect embodiment of this application.
[0066] Fourthly, another embodiment of this application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program for causing a computer to perform any of the methods provided in the first aspect of this application.
[0067] Other features and advantages of this application will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the written description, claims, and drawings. Attached Figure Description
[0068] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0069] Figure 1 This is a schematic diagram illustrating an application scenario of a collision event determination method provided in an embodiment of this application.
[0070] Figure 2A flowchart of a collision event determination method provided by an embodiment of the present application is shown in FIG. 1.
[0071] Figure 3 A flowchart of fitting processing of an acceleration original signal in a collision event determination method provided by an embodiment of the present application is shown in FIG. 2.
[0072] Figure 4 A curve diagram of a first curve, a second curve and a first optimized signal in a collision event determination method provided by an embodiment of the present application is shown in FIG. 3.
[0073] Figure 5 A flowchart of weighted fitting processing of a second optimized signal in a collision event determination method provided by an embodiment of the present application is shown in FIG. 4.
[0074] Figure 6 A curve diagram of a first curve, a third curve and a third optimized signal in a collision event determination method provided by an embodiment of the present application is shown in FIG. 5.
[0075] Figure 7 A flowchart of sampling processing of a third optimized signal in a collision event determination method provided by an embodiment of the present application is shown in FIG. 6.
[0076] Figure 8 A curve diagram of a third optimized signal set in a collision event determination method provided by an embodiment of the present application is shown in FIG. 7.
[0077] Figure 9 A flowchart of determining a target signal according to a target optimized signal in a collision event determination method provided by an embodiment of the present application is shown in FIG. 8.
[0078] Figure 10 A device diagram of a collision event determination method provided by an embodiment of the present application is shown in FIG. 9.
[0079] Figure 11 An electronic device diagram of a collision event determination method provided by an embodiment of the present application is shown in FIG. 10. DETAILED DESCRIPTION
[0080] In order to better understand the technical solutions of the present application, the embodiments of the present application are described in detail below with reference to the accompanying drawings.
[0081] It should be clear that the described embodiments are only some of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of protection of the present application.
[0082] The terminology used in the embodiments of this application is for the purpose of describing particular embodiments only and is not intended to be limiting of this application. The singular forms “a,” “the,” and “the” used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.
[0083] It should be understood that the term "and / or" used in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article generally indicates that the preceding and following related objects have an "or" relationship.
[0084] This application provides a collision event determination method, apparatus, device, and storage medium to improve the accuracy of collision event determination. The inventive concept of this application can be summarized as follows: For gyroscope signals and raw acceleration signals acquired in each first cycle, the following steps are performed: Based on the gyroscope signals acquired in the first cycle, the raw acceleration signals acquired in the first cycle are weighted and fitted to obtain a first optimized signal; the first optimized signal is filtered to obtain a second optimized signal; based on the gyroscope signals acquired in the first cycle, the second optimized signal is weighted and fitted to obtain a target optimized signal; a target signal corresponding to the second cycle is obtained based on the target optimized signal corresponding to each first cycle; wherein the second cycle includes a preset number of first cycles; and based on the target signal, it is determined whether a collision event occurs within the second cycle. In this application, by using gyroscope signals to process the raw acceleration signal, the original noise of the acceleration sensor is reduced. By using gyroscope signals to process the filtered raw acceleration signal, the sensitive noise of mechanical vibration in the raw acceleration signal is reduced. By filtering the first optimized signal, the noise introduced by gravity and tilt in the raw acceleration signal is reduced. Therefore, the target signal obtained in this application is more accurate, thereby ensuring the accuracy of the judgment of collision events.
[0085] For ease of understanding, the collision event determination method provided by the embodiments of this application will be described in detail below with reference to the accompanying drawings:
[0086] like Figure 1 The diagram shown illustrates an application scenario of a collision event determination method according to an embodiment of this application. The diagram includes: a microcontroller unit (MCU) 10, a gyroscope 20, and an accelerometer 30; wherein:
[0087] The MCU 10 performs, for the gyroscope signal of the gyroscope 20 and the acceleration raw signal of the acceleration sensor 30 obtained according to each first period: performing weighted fitting processing on the acceleration raw signal obtained in the first period based on the gyroscope signal obtained in the first period to obtain a first optimized signal; performing filtering processing on the first optimized signal to obtain a second optimized signal; performing weighted fitting processing on the second optimized signal based on the gyroscope signal obtained in the first period to obtain a target optimized signal; obtaining a target signal corresponding to a second period based on the target optimized signal corresponding to each first period; and determining whether a collision event occurs in the second period based on the target signal.
[0088] The description in the present application is only detailed for a single MCU 10, gyroscope 20, and acceleration sensor 30, but those skilled in the art should understand that the MCU 10, gyroscope 20, and acceleration sensor 30 shown are intended to represent the operation of the MCU 10, gyroscope 20, and acceleration sensor 30 involved in the technical solution of the present application. There is no limitation on the number, type, or position of the MCU 10, gyroscope 20, and acceleration sensor 30. It should be noted that if additional modules are added to the illustrated environment or individual modules are removed therefrom, the underlying concept of the example embodiments of the present application will not change. In addition, those skilled in the art can understand that the above-mentioned data transmission and reception also needs to be implemented through a network.
[0089] It should be noted that the collision event determination method proposed in the present application is not only applicable to the application scenario shown, but also applicable to any device that has a collision event determination requirement. Figure 1 The collision event determination method provided by the embodiments of the present application can be applied to any device that has a collision event determination requirement.
[0090] As shown in Figure 2 FIG. 1 is a flowchart of a collision event determination method provided by an embodiment of the present application, in which:
[0091] In step 201, for the gyroscope signal obtained according to each first period and the acceleration raw signal, the following is performed: performing weighted fitting processing on the acceleration raw signal obtained in the first period based on the gyroscope signal obtained in the first period to obtain a first optimized signal; performing filtering processing on the first optimized signal to obtain a second optimized signal; and performing weighted fitting processing on the second optimized signal based on the gyroscope signal obtained in the first period to obtain a target optimized signal.
[0092] In step 202, a target signal corresponding to a second period is obtained based on the target optimized signal corresponding to each first period; and the second period includes a preset number of first periods.
[0093] In step 203, whether a collision event occurs in the second period is determined based on the target signal.
[0094] In the present application, the original noise of the acceleration sensor is reduced by processing the acceleration original signal by using the gyroscope signal, the sensitive noise of the mechanical vibration in the acceleration original signal is reduced by processing the filtered acceleration original signal by using the gyroscope signal, and the noise introduced due to the gravity and the tilt is reduced by filtering the first optimized signal, so that the purpose signal obtained in the present application is more accurate, thereby ensuring the accuracy of the determination of the collision event.
[0095] In order to further understand the collision event determination method provided by the embodiments of the present application, the steps in the method will be described in detail below. Figure 2
[0096] In some possible embodiments, in order to save the calculation resources while ensuring the accuracy of the determination of the collision event, the present application sets the first period and the second period, the second period is a long period, each second period includes a plurality of first periods, and whether a collision event will occur is determined once for each second period, so that the real-time calculation is not necessary, and the waste of calculation resources is reduced.
[0097] In some possible embodiments, in order to correct the linear acceleration and reduce the original noise of the acceleration sensor, the acceleration original signal corresponding to the gyroscope signal obtained in each first period is fitted in the present application, and the fitting process can be implemented as the steps shown in Figure 3 , wherein
[0098] In step 301, a first curve is constructed based on the gyroscope signal obtained in the first period.
[0099] In step 302, a second curve is constructed based on the acceleration original signal obtained in the first period.
[0100] In step 303, the first curve and the second curve are weighted and fitted according to the first preset weight corresponding to the first curve and the second preset weight corresponding to the second curve, and a first optimized signal is obtained.
[0101] For example, 7 gyroscope signals a1, a2, a3, a4, a5, a6 and a7 are collected in the first period, and the first curve formed by the 7 gyroscope signals is as shown in Figure 4 , 7 acceleration original signals b1, b2, b3, b4, b5, b6 and b7 are collected in the first period, and the second curve formed by the 7 acceleration original signals is as shown in Figure 4 , the first preset weight corresponding to the first curve is determined as 0.4, the second preset weight corresponding to the second curve is determined as 0.6, and the first optimized signal obtained by fitting the first curve and the second curve is as shown inFigure 4 As shown.
[0102] In the present application, by setting the first preset weight and the second preset weight, the influence of the gravitational acceleration and the inclination angle during the vehicle driving on the acceleration sensor is reduced, and the possibility of false triggering of the collision event is reduced.
[0103] In some possible embodiments, in order to further reduce the noise in the acceleration original signal and ensure the accuracy of the determined target signal, after obtaining the first optimized signal, the first optimized signal needs to be filtered to obtain a second optimized signal, which can be implemented as: simplifying the Kalman filter to obtain a target filter; and filtering the first optimized signal by using the target filter to obtain the second optimized signal.
[0104] In some possible embodiments, when simplifying the Kalman filter, the preset weight can be used to replace the weight in the Kalman filter, and the weight in the Kalman filter is a weight updated in real time according to the noise of the acceleration original signal.
[0105] The main difference between the filtering method adopted in the present application and the Kalman filter is that the weight of the filter adopted in the present application is a preset weight, which is relatively fixed, while in the Kalman filter, the weight is continuously updated according to the noise of the acceleration original signal. The filter provided in the present application can provide a “good controllable” fitting for actual application. The present application combines the vehicle calibration scene list, adjusts the system noise and measurement noise factors measured according to the real vehicle test scene, and has better compatibility for problems encountered in new engineering application scenes, and enhances the operability under the premise that the precision is not much different.
[0106] In some possible embodiments, after obtaining the second optimized signal, the second optimized signal can be subjected to weighted fitting processing, which can be implemented as the steps shown in Figure 5 As shown.
[0107] In step 501, a first curve is constructed based on the gyro signals obtained in the first period.
[0108] In step 502, a third curve is constructed based on the first optimized signal.
[0109] In step 503, the first curve and the third curve are subjected to weighted fitting processing according to the first preset weight corresponding to the first curve and the third preset weight corresponding to the third curve, to obtain a third optimized signal.
[0110] For example, seven gyro signals a1, a2, a3, a4, a5, a6 and a7 are collected in the first period, and a first curve formed by the seven gyro signals is as shown in Figure 6 As shown; and a third curve corresponding to the first optimized signal is as shown inFigure 6 As shown; the first preset weight corresponding to the first curve is determined to be 0.3, and the third preset weight corresponding to the third curve is determined to be 0.7. Then, a weighted fitting is performed on the first curve and the third curve to obtain the curve corresponding to the third optimized signal, as shown. Figure 6 As shown.
[0111] It should be noted that the specific values of the first preset weight, the second preset weight, and the third preset weight are not limited in this application. The above is only an embodiment and is not intended to limit the specific values of the first preset weight, the second preset weight, and the third preset weight. Those skilled in the art can determine the specific values of the first preset weight, the second preset weight, and the third preset weight according to their needs.
[0112] In step 504: the third optimization signal is sampled and processed to obtain the target optimization signal.
[0113] In some possible embodiments, the third optimized signal is sampled, specifically as follows: Figure 7 The steps shown are as follows:
[0114] In step 701: Based on the timing of each third optimized signal, a first intermediate point is filled between every two third optimized signals using a preset filling method to obtain a set of third optimized signals.
[0115] For example: the third optimized signals are c1, c2, c3, c4, c5, c6, and c7; the preset filling method is the mean method. Based on c1 and c2, the first intermediate point corresponding to c1 and c2 is determined as d1; based on c2 and c3, the first intermediate point corresponding to c2 and c3 is determined as d2; based on c3 and c4, the first intermediate point corresponding to c3 and c4 is determined as d3; based on c4 and c5, the first intermediate point corresponding to c4 and c5 is determined as d4; based on c5 and c6, the first intermediate point corresponding to c5 and c6 is determined as d5; based on c6 and c7, the first intermediate point corresponding to c6 and c7 is determined as d6. Therefore, the resulting set of third optimized signals includes: c1, d1, c2, d2, c3, d3, c4, d4, c5, d5, c6, d6, and c7.
[0116] It should be noted that this application does not limit the specific implementation method of the preset filling method. The preset filling method can be the mean method, interpolation method, etc., and those skilled in the art can set the implementation method of the preset filling method according to their needs.
[0117] In step 702: Shannon supersampling is performed on the third optimized signal set to obtain the target third optimized signal.
[0118] For example: the third optimized signal set includes c1, d1, c2, d2, c3, d3, c4, d4, c5, d5, c6, d6, and c7; the curve corresponding to the third optimized signal set is as follows: Figure 8 As shown, Shannon supersampling is performed on the third optimized signal set to obtain the target third optimized signals d1, c2, d2, d3, c4, d4, d5, c6, d6.
[0119] In step 703: The target third optimization signal is integrated to obtain the target optimization signal.
[0120] For example: If the target third optimization signal is d1, c2, d2, d3, c4, d4, d5, c6, d6; then, by integrating d1, c2, d2, d3, c4, d4, d5, c6, d6, the result is e1, and the target optimization signal is e1.
[0121] In some possible embodiments, after determining the target optimization signal corresponding to each first period, in order to further determine the target signal corresponding to the second period, it can be based on... Figure 9 The steps shown are used to determine the target signal based on the target optimization signal, wherein:
[0122] In step 901: The target optimization signals are sorted according to the time sequence of each target optimization signal to obtain the target optimization signal sequence.
[0123] For example, the second cycle includes eight first cycles, namely first cycle 1, first cycle 2, first cycle 3, first cycle 4, first cycle 5, first cycle 6, first cycle 7, and first cycle 8. The target optimization signal 1 corresponds to first cycle 1, the target optimization signal 2 corresponds to first cycle 2, the target optimization signal 3 corresponds to first cycle 3, the target optimization signal 4 corresponds to first cycle 4, the target optimization signal 5 corresponds to first cycle 5, the target optimization signal 6 corresponds to first cycle 6, the target optimization signal 7 corresponds to first cycle 7, and the target optimization signal 8 corresponds to first cycle 8. The target optimization signal sequence obtained by sorting the target optimization signals 1 to 8 is: target optimization signal 1, target optimization signal 2, target optimization signal 3, target optimization signal 4, target optimization signal 5, target optimization signal 6, target optimization signal 7, and target optimization signal 8.
[0124] In step 902: In the target optimization signal sequence, a second intermediate signal is filled between every two target optimization signals using a preset filling method to obtain a target optimization signal set.
[0125] For example: the preset filling method is the mean method. Based on target optimization signal 1 and target optimization signal 2, the second intermediate signal is determined as second intermediate signal 1; based on target optimization signal 2 and target optimization signal 3, the second intermediate signal is determined as second intermediate signal 2; based on target optimization signal 3 and target optimization signal 4, the second intermediate signal is determined as second intermediate signal 3; based on target optimization signal 4 and target optimization signal 5, the second intermediate signal is determined as second intermediate signal 4; based on target optimization signal 5 and target optimization signal 6, the second intermediate signal is determined as second intermediate signal 5; based on target optimization signal 6 and target optimization signal 7, the second intermediate signal is determined as second intermediate signal 6; based on target optimization signal 7 and target optimization signal 8, the second intermediate signal is determined as second intermediate signal 7. The resulting set of target optimization signals includes: target optimization signal 1, second intermediate signal 1, target optimization signal 2, second intermediate signal 2, target optimization signal 3, second intermediate signal 3, target optimization signal 4, second intermediate signal 4, target optimization signal 5, second intermediate signal 5, target optimization signal 6, second intermediate signal 6, target optimization signal 7, second intermediate signal 7, and target optimization signal 8.
[0126] It should be noted that this application does not limit the specific implementation method of the preset filling method. The preset filling method can be the mean method, interpolation method, etc., and those skilled in the art can set the implementation method of the preset filling method according to their needs.
[0127] In step 903: Shannon supersampling is performed on the target optimized signal set to obtain the initial target signal.
[0128] For example: the target optimization signal set includes: target optimization signal 1, second intermediate signal 1, target optimization signal 2, second intermediate signal 2, target optimization signal 3, second intermediate signal 3, target optimization signal 4, second intermediate signal 4, target optimization signal 5, second intermediate signal 5, target optimization signal 6, second intermediate signal 6, target optimization signal 7, second intermediate signal 7, and target optimization signal 8; performing Shannon oversampling on the target optimization signal set yields the initial target signal including: the target optimization signal set includes: second intermediate signal 1, target optimization signal 2, target optimization signal 3, second intermediate signal 3, target optimization signal 4, second intermediate signal 4, second intermediate signal 5, target optimization signal 6, second intermediate signal 6, target optimization signal 7, and target optimization signal 8.
[0129] In step 904: The initial target signal is integrated to obtain the target signal.
[0130] For example, the initial target signal includes: the second intermediate signal 1, the target optimization signal 2, the target optimization signal 3, the second intermediate signal 3, the target optimization signal 4, the second intermediate signal 4, the second intermediate signal 5, the target optimization signal 6, the second intermediate signal 6, the target optimization signal 7, and the target optimization signal 8. The initial target signal is integrated to obtain the target signal.
[0131] In some possible embodiments, after determining the target signal corresponding to the second period, in order to ensure the accuracy of the determination of the collision event, the data collected by the vehicle based on the radar and the vehicle-mounted camera can be fused when determining whether a collision event occurs in the second period according to the target signal. Specifically, the image data collected by the vehicle-mounted camera in the second period and the radar data collected by the radar in the second period are obtained; and whether a collision event occurs in the second period is determined based on the image data, the radar data, and the target signal.
[0132] For example, it is determined that a collision event occurs in the second period according to the image data, according to the radar data, and according to the target signal. If it is determined that no collision event occurs according to the image data, it is determined that a collision event occurs according to the radar data, and it is determined that no collision event occurs according to the target signal, it is determined that no collision event occurs in the second period, and it is also determined that the radar has a false touch event.
[0133] In some possible embodiments, for each vehicle, if the data collected by the vehicle and the record of the collision event are all stored locally, the storage of the vehicle will be burdened. Therefore, after the vehicle determines the target signal or the collision event each time, the target signal and the data corresponding to the collision event can be uploaded to the cloud for storage. A storage device can also be installed locally on the vehicle to store the target signal and the data corresponding to the collision event. It should be noted that the storage device in the embodiments of the present application can be a cache system, a hard disk storage, a memory storage, or the like. The specific storage mode is not limited in the present application, and the skilled in the art can set it according to the needs.
[0134] In some possible embodiments, in order to perform outlier screening on the target signal, the vehicle reports the target signal and the related data collected to the cloud each time the target signal is determined. The cloud constructs a large database of target signals according to the data reported by each vehicle. The large database stores the normal range of the target signal under each working condition. After the large database is constructed, whether the target signal reported by the vehicle is normal can be determined according to the target signal and the large database, and the determination result is sent to the vehicle to enable the user to learn about the related situation of the vehicle in a timely manner.
[0135] Based on the same inventive concept, the application also provides a collision event determination apparatus 1000, as shown in the accompanying drawings, comprising: Figure 10
[0136] a target optimization signal determination module 10001, configured to perform the following operations on the gyroscope signal acquired in each first period and the acceleration raw signal: performing weighted fitting processing on the acceleration raw signal acquired in the first period based on the gyroscope signal acquired in the first period to obtain a first optimization signal; performing filtering processing on the first optimization signal to obtain a second optimization signal; performing weighted fitting processing on the second optimization signal based on the gyroscope signal acquired in the first period to obtain a target optimization signal;
[0137] a target signal determination module 10002, configured to obtain a target signal corresponding to a second period based on the target optimization signal corresponding to each first period; wherein the second period comprises a preset number of first periods.
[0138] a collision event determination module 10003, configured to determine whether a collision event occurs in the second period based on the target signal.
[0139] In some possible embodiments, when the target optimization signal determination module 10001 performs the weighted fitting processing on the acceleration raw signal acquired in the first period based on the gyroscope signal acquired in the first period to obtain the first optimization signal, the target optimization signal determination module 10001 is specifically configured to:
[0140] construct a first curve based on the gyroscope signal acquired in the first period;
[0141] construct a second curve based on the acceleration raw signal acquired in the first period;
[0142] perform weighted fitting processing on the first curve and the second curve according to a first preset weight corresponding to the first curve and a second preset weight corresponding to the second curve to obtain the first optimization signal.
[0143] In some possible embodiments, when the target optimization signal determination module 10001 performs the filtering processing on the first optimization signal to obtain the second optimization signal, the target optimization signal determination module 10001 is specifically configured to:
[0144] simplify Kalman filtering to obtain a target filter;
[0145] perform filtering processing on the first optimization signal by using the target filter to obtain the second optimization signal.
[0146] In some possible embodiments, when the target optimization signal determination module 10001 performs a simplification process on the Kalman filter to obtain the target filter, it is specifically used for:
[0147] The weights in the Kalman filter are replaced with preset weights, which are updated in real time based on the noise of the original acceleration signal.
[0148] In some possible embodiments, when the target optimization signal determination module 10001 performs weighted fitting processing on the second optimization signal based on the gyroscope signal acquired within the first period to obtain the target optimization signal, it is specifically used for:
[0149] A first curve is constructed based on the gyroscope signals acquired during the first cycle;
[0150] A third curve is constructed based on the first optimized signal;
[0151] The first curve and the third curve are weighted and fitted according to the first preset weight corresponding to the first curve and the third preset weight corresponding to the third curve to obtain the third optimized signal.
[0152] The third optimized signal is sampled and processed to obtain the target optimized signal.
[0153] In some possible embodiments, when the target optimization signal determination module 10001 performs sampling processing on the third optimization signal to obtain the target optimization signal, it is specifically used for:
[0154] Based on the timing of each third optimized signal, a first intermediate point is filled between every two third optimized signals using a preset filling method to obtain a set of third optimized signals;
[0155] The target third optimized signal is obtained by performing Shannon oversampling on the third optimized signal set.
[0156] The target third optimization signal is integrated to obtain the target optimization signal.
[0157] In some possible embodiments, when the target signal determination module 10002 performs the task of obtaining the target signal corresponding to the second period based on the target optimization signal corresponding to each first period, it is specifically used for:
[0158] The target optimization signals are sorted according to the time sequence of each target optimization signal to obtain a target optimization signal sequence;
[0159] In the target optimization signal sequence, a second intermediate signal is filled between every two target optimization signals using a preset filling method to obtain a target optimization signal set;
[0160] The target optimized signal set is subjected to Shannon supersampling to obtain the initial target signal;
[0161] The initial target signal is integrated to obtain the target signal.
[0162] Corresponding to the above embodiments, this application also provides an electronic device. Figure 11 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention. The electronic device 1100 may include a processor 1101, a memory 1102, and a communication unit 1103. These components communicate through one or more buses. Those skilled in the art will understand that the structure of the electronic device shown in the figure does not constitute a limitation on the embodiment of the present invention. It may be a bus topology or a star topology, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.
[0163] The communication unit 1103 is used to establish a communication channel, enabling the electronic device to communicate with other devices. It receives user data from other devices or sends user data to other devices.
[0164] The processor 1101 serves as the control center of the electronic device, connecting various parts of the device via various interfaces and lines. It executes software programs and / or modules stored in the memory 1102, and calls data stored in the memory to perform various functions and / or process data. The processor can be composed of integrated circuits (ICs), such as a single packaged IC or multiple packaged ICs with the same or different functions connected together. For example, the processor 1101 may consist only of a central processing unit (CPU). In this embodiment, the CPU may have a single processing core or include multiple processing cores.
[0165] The memory 1102 is used to store the execution instructions of the processor 1101. The memory 1102 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk.
[0166] When the execution instructions in the memory 1102 are executed by the processor 1101, the electronic device 1100 is enabled to perform Figure 7 some or all of the steps in the embodiments shown.
[0167] In a specific implementation, the present application also provides a computer storage medium, wherein the computer storage medium can store a program, and the program can include some or all of the steps in the embodiments of the call method provided by the present application when executed. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), or the like.
[0168] Those skilled in the art can clearly understand that the technology in the embodiments of the present application can be realized by means of software and necessary general hardware platforms. Based on such understanding, the technical solutions in the embodiments of the present application can be embodied in the form of a software product, and the computer software product can be stored in a storage medium, such as a ROM / RAM, a magnetic disc, an optical disc, or the like, and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments of the present application.
[0169] The same or similar parts among the various embodiments in the specification can be referred to each other. In particular, for the device embodiments and the terminal embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.
Claims
1. A collision event determination method characterized by, The method includes: For each first cycle, the following steps are performed: Based on the gyroscope signal acquired in the first cycle, the raw acceleration signal acquired in the first cycle is weighted and fitted to obtain a first optimized signal; the first optimized signal is filtered to obtain a second optimized signal; based on the gyroscope signal acquired in the first cycle, the second optimized signal is weighted and fitted to obtain a target optimized signal. The target signal for the second period is obtained based on the target optimization signal corresponding to each first period; wherein, the second period includes a preset number of first periods; Based on the target signal, determine whether a collision event occurs within the second period.
2. The method of claim 1, wherein, The step of performing weighted fitting processing on the original acceleration signal acquired within the first period based on the gyroscope signal acquired within the first period to obtain the first optimized signal includes: A first curve is constructed based on the gyroscope signals acquired during the first cycle; A second curve is constructed based on the original acceleration signal obtained during the first cycle; The first curve and the second curve are weighted and fitted according to the first preset weight corresponding to the first curve and the second preset weight corresponding to the second curve to obtain the first optimized signal.
3. The method of claim 1, wherein, The step of filtering the first optimized signal to obtain the second optimized signal includes: The Kalman filter is simplified to obtain the target filter; The first optimized signal is filtered using the target filter to obtain the second optimized signal.
4. The method of claim 3, wherein, The simplification process of the Kalman filter to obtain the target filter includes: The weights in the Kalman filter are replaced with preset weights, which are updated in real time based on the noise of the original acceleration signal.
5. The method of claim 1, wherein, The step of performing weighted fitting processing on the second optimized signal based on the gyroscope signal acquired within the first period to obtain the target optimized signal includes: A first curve is constructed based on the gyroscope signals acquired during the first cycle; A third curve is constructed based on the first optimized signal; The first curve and the third curve are weighted and fitted according to the first preset weight corresponding to the first curve and the third preset weight corresponding to the third curve to obtain the third optimized signal. The third optimized signal is sampled and processed to obtain the target optimized signal.
6. The method of claim 5, wherein, The step of sampling and processing the third optimized signal to obtain the target optimized signal includes: Based on the timing of each third optimized signal, a first intermediate point is filled between every two third optimized signals using a preset filling method to obtain a set of third optimized signals; The target third optimized signal is obtained by performing Shannon oversampling on the third optimized signal set. The target third optimization signal is integrated to obtain the target optimization signal.
7. The method of claim 1, wherein, The process of obtaining the target signal for the second period based on the target optimization signal corresponding to each first period includes: The target optimization signals are sorted according to the time sequence of each target optimization signal to obtain a target optimization signal sequence; In the target optimization signal sequence, a second intermediate signal is filled between every two target optimization signals using a preset filling method to obtain a target optimization signal set; The target optimized signal set is subjected to Shannon supersampling to obtain the initial target signal; The initial target signal is integrated to obtain the target signal.
8. A collision event determination apparatus characterized by comprising: The device includes: The target optimization signal determination module is used to perform the following operations on the gyroscope signal and the raw acceleration signal acquired in each first cycle: performing weighted fitting processing on the raw acceleration signal acquired in the first cycle based on the gyroscope signal acquired in the first cycle to obtain a first optimized signal; performing filtering processing on the first optimized signal to obtain a second optimized signal; and performing weighted fitting processing on the second optimized signal based on the gyroscope signal acquired in the first cycle to obtain a target optimized signal. The target signal determination module is used to obtain the target signal corresponding to the second period based on the target optimization signal corresponding to each first period; wherein, the second period includes a preset number of first periods; The collision event determination module is used to determine whether a collision event occurs within the second period based on the target signal.
9. An electronic device, comprising: It includes a memory for storing computer program instructions and a processor for executing the program instructions, wherein when the computer program instructions are executed by the processor, the electronic device is triggered to perform the method of any one of claims 1-7.
10. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein, when the program is executed, it controls the device on which the computer-readable storage medium is located to perform the method according to any one of claims 1-7.
Citation Information
Patent Citations
Customer service method, computing equipment and computer storage medium
CN112153566A
Method for the detection of an impact
CN1620376A