Vehicle collision detection method and device, storage medium and vehicle

Abstract

The invention relates to a vehicle collision detection method and device, a storage medium and a vehicle, and the method comprises the steps: obtaining a plurality of first response data generated by a collision sensor when a target part is subjected to multiple times of collision; acquiring second response data generated by the collision sensor in the vehicle driving process; based on the first response data and the second response data, a classifier corresponding to the collision sensor is constructed, and the classifier is used for determining whether the response data generated by the collision sensor needs to give an alarm or not. According to the technical scheme, the classifier used for carrying out collision detection on the target component is constructed through the response data detected by the collision sensor when the target component is subjected to multiple collisions, the number of the sensors can be reduced, and therefore the cost of collision detection on the vehicle target component can be reduced.

Description

Technical Field

[0001] The present application relates to the field of electronic technology, and in particular to a vehicle collision detection method, device, storage medium and vehicle. Background Art

[0002] The underbody guard is an important protective component of the bottom of the car. It can effectively protect the chassis from being hit by gravel on the road, thereby protecting the key components of the vehicle chassis. In order to ensure the safety of vehicle driving and protect the important components at the bottom of the vehicle, it is necessary to test the underbody guard.

[0003] In the related art, a plurality of sensors are arranged on the bottom guard plate to detect vehicle collision, but more sensors will increase the cost. Summary of the invention

[0004] The embodiments of the present application provide a vehicle collision detection method, device, storage medium and vehicle, which can reduce the cost of collision detection of vehicle target parts to at least partially solve the above-mentioned technical problems.

[0005] In order to achieve the above object, according to a first aspect of the present application, a vehicle collision detection method is provided, wherein a collision sensor is installed on a target component of the vehicle, and the method comprises:

[0006] Acquire a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times;

[0007] Acquiring second response data generated by the collision sensor during the driving of the vehicle;

[0008] Based on the first response data and the second response data, a classifier corresponding to the collision sensor is constructed, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

[0009] Optionally, a collision sensor is installed on the target component.

[0010] Optionally, the target components are struck at different impact positions, and / or the target components are struck at the same impact intensity.

[0011] Optionally, constructing a classifier corresponding to the collision sensor based on the first response data and the second response data includes:

[0012] determining a classification threshold according to the first response data and the second response data;

[0013] The classifier is constructed based on the classification threshold.

[0014] Optionally, the number of the second response data is multiple;

[0015] The determining a classification threshold according to the first response data and the second response data comprises:

[0016] determining minimum response data from the plurality of first response data;

[0017] determining a maximum response data from a plurality of second response data;

[0018] The classification threshold is determined based on the maximum response data and the minimum response data.

[0019] Optionally, constructing a classifier corresponding to the collision sensor based on the first response data and the second response data includes:

[0020] Training a preset classification model according to the first response data and the second response data to obtain a trained classification model;

[0021] Based on the trained classification model, the classifier is obtained.

[0022] Optionally, the first response data and the second response data are both response data detected in the gravity direction.

[0023] Optionally, the first response data is response data detected in a non-gravity direction;

[0024] The step of acquiring the second response data generated by the collision sensor during the driving of the vehicle includes:

[0025] The second response data is obtained by acquiring response data detected by the collision sensor in the non-gravity direction when a target collision occurs during the driving of the vehicle, and the target collision includes a collision with a body of the vehicle.

[0026] Optionally, the method further comprises:

[0027] If the classifier construction fails, then under new collision conditions, re-execute the steps of obtaining a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and the subsequent steps;

[0028] The new impact condition includes: a new impact intensity and / or a new installation position of the collision sensor on the target component.

[0029] Optionally, the target component comprises a bottom guard plate.

[0030] According to a second aspect of the present application, another vehicle collision detection method is provided, wherein a collision sensor is installed on a target component of the vehicle, and the method comprises:

[0031] Acquiring target response data generated by the collision sensor during the driving of the vehicle;

[0032] Based on the classifier corresponding to the collision sensor, the target response data is classified to obtain a classification result, wherein the classifier is constructed based on at least a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and a second response data generated by the collision sensor during the driving of the vehicle;

[0033] According to the classification result, it is determined whether the target response data needs to be alarmed.

[0034] According to a third aspect of the present application, a vehicle collision detection device is provided, comprising:

[0035] A first acquisition unit, used for acquiring a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times;

[0036] A second acquisition unit, used for acquiring second response data generated by the collision sensor during the driving process of the vehicle;

[0037] A construction unit is used to construct a classifier corresponding to the collision sensor based on the first response data and the second response data, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

[0038] According to a fourth aspect of the present application, a computer-readable storage medium is also provided, which stores a computer program executable by a vehicle. When the computer program runs on the vehicle, the vehicle executes the above vehicle collision detection method.

[0039] According to a fifth aspect of the present application, a vehicle is also provided, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the above vehicle collision detection method when executing the program.

[0040] According to a sixth aspect of the present application, a computer program product is also provided, comprising a computer program or instructions, which implement the above vehicle collision detection method when executed by a processor.

[0041] The vehicle collision detection method of the embodiment of the present application obtains multiple first response data generated by the collision sensor when the target part is hit multiple times; obtains the second response data generated by the collision sensor during the vehicle's driving; and constructs a classifier corresponding to the collision sensor based on the first response data and the second response data, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed. The above technical solution constructs a classifier for collision detection of the target part through the response data detected by the collision sensor when the target part is hit multiple times, which can reduce the number of sensors, thereby reducing the cost of collision detection of the target part of the vehicle.

[0042] Other features and advantages of the present application will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application, and those skilled in the art can obtain other drawings based on these drawings without creative work.

[0044] In order to more completely understand the present application and its beneficial effects, the following description will be given in conjunction with the accompanying drawings, wherein the same figure numbers represent the same parts in the following description.

[0045] Figure 1 A schematic flow chart of a vehicle collision detection method provided in an exemplary embodiment of the present disclosure;

[0046] Figure 2 A schematic diagram of an application scenario of a vehicle collision detection method provided in an exemplary embodiment of the present disclosure;

[0047] Figure 3 A schematic diagram of a response data variation curve of a vehicle collision detection method provided in an exemplary embodiment of the present disclosure;

[0048] Figure 4 A schematic flow chart of another vehicle collision detection method provided in an exemplary embodiment of the present disclosure;

[0049] Figure 5 A schematic flow chart of another vehicle collision detection method provided in an exemplary embodiment of the present disclosure;

[0050] Figure 6 It is a structural block diagram of a vehicle collision detection device provided in an exemplary embodiment of the present disclosure;

[0051] Figure 7It is a structural block diagram of another vehicle collision detection device provided in an exemplary embodiment of the present disclosure;

[0052] Figure 8 It is a schematic structural diagram of a vehicle provided in an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0054] Based on the above problems, the embodiments of the present application provide a vehicle collision detection method, device, storage medium and vehicle. Specifically, the vehicle collision detection method of the embodiments of the present application can be performed by a vehicle or a cloud server. Among them, the vehicle can be a fuel vehicle, a plug-in hybrid vehicle or a new energy vehicle, etc., and the present disclosure does not make specific limitations on this. Among them, the cloud server can be an independent physical cloud server, or a cloud server cluster or distributed system composed of multiple physical cloud servers, or a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and basic cloud computing services such as big data and artificial intelligence platforms.

[0055] For example, the vehicle collision detection method provided in the exemplary embodiment of the present disclosure can be applied to a digital signal processor in a vehicle, which can obtain multiple first response data generated by the collision sensor when the target component is hit multiple times; obtain the second response data generated by the collision sensor during the driving of the vehicle; and construct a classifier corresponding to the collision sensor based on the first response data and the second response data, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

[0056] or,

[0057] Acquire target response data generated by the collision sensor during vehicle driving;

[0058] Based on a classifier corresponding to the collision sensor, the target response data is classified to obtain a classification result, wherein the classifier is constructed based on at least a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and a second response data generated by the collision sensor during the driving of the vehicle;

[0059] Based on the classification results, determine whether the target response data needs to be alarmed.

[0060] It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments.

[0061] This application embodiment provides a vehicle collision detection method, see Figure 1 , Figure 1 The following is a flow chart of a vehicle collision detection method provided in an exemplary embodiment of the present disclosure. The specific flow of the vehicle collision detection method may be as follows:

[0062] 101. Acquire a plurality of first response data respectively generated by a collision sensor when a target component is hit multiple times.

[0063] In the embodiment of the present application, a collision sensor is installed on the target component of the vehicle.

[0064] Among them, the collision sensor is a device used to detect the collision or impact of an object, and can measure various physical quantities generated during the collision, such as acceleration, pressure or displacement, etc. In the embodiment of the present application, the collision sensor can be used to detect the physical quantity generated when the vehicle is hit when a collision occurs, and then determine the intensity of the impact on the vehicle. It can be determined whether to issue a collision alarm based on the intensity of the impact on the vehicle to prompt the driving user.

[0065] The collision sensor may include multiple types, such as an acceleration sensor, a collision force sensor, and the like.

[0066] In some embodiments, the collision sensor may be an acceleration sensor.

[0067] In the embodiments of the present application, there is no restriction on the principle and type of the corresponding collision sensor itself. The word "collision" is more of a description of the performance of the sensor: it can meet the high-frequency and high-signal strength measurement under collision conditions. There is no restriction on the measurement principle itself, such as piezoelectric quartz (common collision acceleration sensor), piezoelectric ink (thin film sensor), etc.

[0068] In some embodiments, to save costs, a collision sensor may be installed on the target component.

[0069] In some embodiments, in order to implement collision detection on the bottom of the vehicle, the target component of the vehicle may include an underbody guard plate of the vehicle.

[0070] For example, a collision sensor can be installed on the bottom guard of the vehicle. The selection of the installation position of the collision sensor on the bottom guard needs to consider the collision of all positions of the entire bottom guard. For example, when the vehicle is hit, when the impact reaches the installation position of the collision sensor on the bottom guard, it needs to cause a significant change in the response data generated by the collision sensor.

[0071] The bottom guard plate of the vehicle can be simplified as a rectangular flat plate, and the out-of-plane impact of the bottom obstacle of the vehicle will be transmitted to the surroundings in the form of waves. Collision signals can be collected more or less at multiple positions of the bottom guard plate.

[0072] In some embodiments, when a vehicle is hit, the shock wave generally spreads outward on the bottom guard plate with the impact position as the center. Due to dissipation of materials, the farther away from the impact position, the weaker the collision signal detected by the collision sensor. In order to maximize the strength of the signal received by the collision sensor, the collision sensor can be installed in the middle of the bottom guard plate.

[0073] For example, see Figure 2 , Figure 2 A schematic diagram of an application scenario of a vehicle collision detection method provided in an exemplary embodiment of the present disclosure. Figure 2 The bottom guard plate of the vehicle and the collision sensor arranged at the center of the bottom guard plate are shown. The Z-axis direction is the gravity direction of the vehicle; the X-direction is the front-to-rear direction; and the Y-direction is the direction perpendicular to the front-to-rear direction.

[0074] The first response data may include: when the target component of the vehicle is hit, the acceleration detected by the collision sensor installed on the target component.

[0075] In some embodiments, in order to obtain first response data respectively detected by the collision sensor when different positions of the target component are impacted, when the target component of the vehicle is impacted multiple times, the impact position of each impact on the target component can be controlled to be different.

[0076] For example, multiple impact positions are selected on the target component, which may include: position 1, position 2, position 3, ..., position N, and then the impact positions are impacted in sequence to obtain the first response data N1 generated by the impact sensor when the impact position 1 is hit; obtain the first response data N2 generated by the impact sensor when the impact position 2 is hit; obtain the first response data N3 generated by the impact sensor when the impact position 3 is hit; ...; obtain the first response data Nn generated by the impact sensor when the impact position N is hit. Thus, multiple first response data are obtained: N1, N2, N1, ..., Nn.

[0077] In some embodiments, in order to obtain first response data respectively detected by the collision sensor when different positions of the target component are impacted with the same impact intensity, the impact intensity of each impact on the target component may be controlled to be the same.

[0078] For example, a plurality of impact positions distributed throughout the target component are selected on the target component, and then each impact position is impacted in turn with the same preset impact intensity to obtain a plurality of first response data generated by the collision sensor.

[0079] The preset impact intensity can be determined according to the impact intensity that the target component can withstand. That is, the preset impact intensity can be used to detect whether to trigger a collision alarm for the target component.

[0080] For example, if the condition for triggering a collision alarm for a target component is set as: the impact intensity is greater than 300 J (joules), then the preset impact intensity can be determined to be: 300 J.

[0081] In some embodiments, the preset impact intensity can be set according to regulations, corporate standards, maintenance and other requirements through parameters such as impact energy, impact mass, impact speed, and impact angle.

[0082] 102. Acquire second response data generated by a collision sensor during vehicle driving.

[0083] The vehicle driving process may include other conditions besides the target component being hit.

[0084] Among them, other conditions may include: the vehicle is running normally, other vehicle parts are hit, etc. Among them, other parts are parts of the vehicle other than the target part.

[0085] In some embodiments, the second response data may include: acceleration detected by a collision sensor installed on the target component during the driving of the vehicle.

[0086] In some embodiments, the vehicle driving process may include: the process of the vehicle driving under normal circumstances, such as the vehicle driving under normal road conditions.

[0087] 103. Construct a classifier corresponding to the collision sensor based on the first response data and the second response data.

[0088] The classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

[0089] In some embodiments, in order to determine whether the response data generated by the collision sensor requires an alarm or is triggered by other conditions, the classifier may be a binary classifier, that is, the binary classifier may be used to determine whether the response data generated by the collision sensor requires an alarm.

[0090] Wherein, constructing a classifier corresponding to the collision sensor based on the first response data and the second response data may include: constructing a binary classifier as the classifier corresponding to the collision sensor according to the first response data and the second response data.

[0091] In some embodiments, in order to reduce the complexity of constructing a classifier corresponding to the collision sensor, the step of “constructing a classifier corresponding to the collision sensor based on the first response data and the second response data” may include the following operations:

[0092] determining a classification threshold based on the first response data and the second response data;

[0093] Build a classifier based on the classification threshold.

[0094] The classification threshold refers to a boundary value or standard used to determine the category to which a data point belongs in a binary classification problem. Specifically, the role of the classification threshold is to convert data into discrete category labels (such as 0 or 1). In a binary classifier, by setting the classification threshold, when the data is greater than or equal to this threshold, the data can be classified as a positive class (usually marked as 1); when the data is less than this threshold, we classify the data point as a negative class (usually marked as 0).

[0095] In the embodiment of the present application, the category labels corresponding to the binary classifier may include: bottom guard plate being hit and other conditions. For example, the response data generated by the collision sensor is input into the binary classifier, and the binary classifier determines that the response data belongs to the category of "bottom guard plate being hit" when the response data is greater than or equal to the classification threshold according to the set classification threshold; when the response data is less than the classification threshold, it can be determined that the response data belongs to the category of "other conditions".

[0096] In some embodiments, the step of “determining a classification threshold according to the first response data and the second response data” may include the following operations:

[0097] determining minimum response data from a plurality of first response data;

[0098] determining a maximum response data from a plurality of second response data;

[0099] Based on the maximum response data and the minimum response data, a classification threshold is determined.

[0100] The number of the second response data may be multiple. For example, during the driving process of the vehicle, the response data generated by the collision sensor at different times are acquired to obtain multiple second response data.

[0101] In some embodiments, the response data may include acceleration, and the multiple first response data may include multiple first accelerations, from which the minimum acceleration is selected as the minimum response data; the multiple second response data may include multiple second accelerations, from which the maximum acceleration is selected as the maximum response data.

[0102] Determining the classification threshold based on the maximum response data and the minimum response data may include determining a value range according to the maximum response data and the minimum response data, and then selecting any value from the value range as the classification threshold.

[0103] For example, see Figure 3 , Figure 3 It is a schematic diagram of a response data change curve of a vehicle collision detection method provided in an exemplary embodiment of the present disclosure.

[0104] Figure 3 The curve changes of the first response data (i.e., acceleration) generated by the collision sensor when multiple impact positions of the bottom guard plate are impacted with a preset impact intensity are shown, wherein the multiple impact positions may include: position 1, position 2, position 3, position 4, and position 5, wherein the peak values ​​of the acceleration changes corresponding to position 1 and position 2 are both: >50; the peak value of the acceleration change corresponding to position 3 is: 30; the peak value of the acceleration change corresponding to position 4 is: 25; the peak value of the acceleration change corresponding to position 5 is: 20. Therefore, it can be determined that the minimum response data is: 20.

[0105] For example, the second response data may be acceleration, and the plurality of second response data may include: 1, 2, and 3. Then, the maximum response data may be determined to be: 3 from the plurality of second response data.

[0106] Further, according to the minimum response data: 20, and the maximum response data: 3, a value range is determined, which can be: >3 and <20. Then any value can be selected from this value range as the classification threshold, for example, 18 is selected as the classification threshold, etc. The selection of the specific classification threshold can be determined according to the actual situation and is not limited here.

[0107] Among them, constructing a classifier based on a classification threshold may include: selecting a preset binary classifier, determining a classification standard of the binary classifier according to the classification threshold, and obtaining a constructed classifier.

[0108] In some embodiments, in order to improve the classification accuracy of the classifier, the step of "building a classifier corresponding to the collision sensor based on the first response data and the second response data" may include the following operations:

[0109] Training a preset classification model according to the first response data and the second response data to obtain a trained classification model;

[0110] Based on the trained classification model, a classifier is obtained.

[0111] Among them, the classification model is a machine learning model that can be used to classify instances in a data set into different categories.

[0112] In machine learning, classification models are a type of supervised learning. Classification models build a model that can accurately assign new data instances to their corresponding categories by learning a set of labeled data sets (i.e., target categories).

[0113] In some embodiments, the preset classification model may be a binary classification model. The binary classification model may be used to classify input data into one of two categories.

[0114] The training steps of the preset classification model may include the following:

[0115] Data preparation: Collect and prepare training data sets, including feature vectors and corresponding labels (0 or 1, representing two categories);

[0116] Model selection: Choose an appropriate classification algorithm, such as Logistic Regression, Support Vector Machine (SVM), Decision Tree, Random Forest, K-Nearest Neighbor (K-NN), Neural Networks;

[0117] Model training: The classifier is trained using a training dataset so that it can learn the relationship between features and labels. During the training process, the model adjusts its parameters to minimize the loss function (such as cross entropy loss).

[0118] Model evaluation: Use the validation data set to evaluate the performance of the model. Common evaluation indicators include accuracy, precision, recall, F1 score, etc.

[0119] Model tuning:

[0120] According to the evaluation results, the model parameters can be adjusted, a more complex model can be selected, or feature selection can be performed to improve the performance of the model. Techniques such as cross-validation can also be used to more robustly evaluate and optimize the model.

[0121] In some embodiments, the response data may also include an acceleration signal. Then the step of "training a preset classification model according to the first response data and the second response data to obtain a trained classification model" may include the following operations:

[0122] Acquire a first acceleration signal in the first response data and a second acceleration signal in the second response data;

[0123] Assigning a first label to the first acceleration signal and assigning a second label to the second acceleration signal, wherein the first label may include: the target component is hit, and the second label may include: other conditions;

[0124] The first acceleration signal and the second acceleration signal are used as inputs, the first label and the second label are used as target outputs, and a preset classification algorithm is used to train a preset classification model until the preset classification model converges to obtain a trained classification model.

[0125] In order to improve the classification accuracy of the classification model after training, the first acceleration signal and the second acceleration signal need to be collected by the collision sensor with the same collection frequency; the duration of the first acceleration signal is the same as the duration of the second acceleration signal, for example, 10ms.

[0126] In some embodiments, in order to improve the classification performance of the trained classification model, 30% of the data can be taken from multiple first response data, and 30% of the data can be taken from multiple second response data as a test set to test the trained classification model to obtain the final performance of the classification model.

[0127] Wherein, determining the classifier based on the trained classification model may include: using the trained classification model as the classifier.

[0128] In some embodiments, the first response data and the second response data may be response data in the gravity direction of the vehicle, and the step of “obtaining a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions” may include: when the target component is subjected to multiple collisions, respectively collecting response data in the gravity direction through the collision sensor to obtain a plurality of first response data;

[0129] Then the step of “obtaining second response data generated by the collision sensor during the driving of the vehicle” may include: during the driving of the vehicle, collecting response data in the gravity direction through the collision sensor to obtain the second response data.

[0130] In some embodiments, in order to avoid the influence of the vehicle body collision on the detection of the collision of the target component, the first response data may be the response data in the non-gravity direction of the vehicle. Then the step of "obtaining multiple first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions" may include: when the target component receives multiple collisions, respectively collecting the response data in the non-gravity direction through the collision sensor to obtain multiple first response data.

[0131] The step of “obtaining the second response data generated by the collision sensor during the vehicle driving process” may include the following operations:

[0132] When a target collision occurs during the vehicle's driving, response data detected by the collision sensor in a non-gravity direction is acquired to obtain second response data.

[0133] The target collision situation may include a collision with a body of the vehicle.

[0134] In some embodiments, the non-gravity direction of the vehicle may include: a vehicle head-parking direction, and a direction perpendicular to the vehicle head-to-rear direction. When the vehicle's non-gravity direction is the vehicle head-to-parking direction, the target collision situation may include: a collision with the vehicle head or parking space; when the vehicle's non-gravity direction is a direction perpendicular to the vehicle head-to-rear direction, the target collision situation may include: a collision with the vehicle body side.

[0135] The collision intensity of the target collision situation can be carried out according to the conditions specified by the regulations, for example, a head-on collision with the vehicle at 56 km / h, or a side collision with the vehicle at 35 km / h, etc.

[0136] In an embodiment of the present application, when the response data detected by the collision sensor in the non-gravity direction is used, by obtaining the response data of the collision sensor in a head-on or side collision of the vehicle, it is possible to avoid false alarms of collisions with target components in minor head-on or side collisions of the vehicle; or it is possible to eliminate false alarms of collisions with target components in minor head-on or side collisions by coordinating the signals of the head-on and side collision sensors within the processor.

[0137] In some embodiments, in order to construct a classifier that meets the expected performance index, the method may further include the following steps:

[0138] If the classifier construction fails, then under the new collision condition, the steps of obtaining a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and the subsequent steps are re-executed.

[0139] The failure to construct the classifier may include: failure to obtain a classification threshold based on the first response data and the second response data, or failure to train a trained classification model for classifying collisions and other conditions of the target component based on the first response data and the second response data.

[0140] Among them, the classification threshold cannot be obtained according to the first response data and the second response data, which may include: the minimum response data determined according to the multiple first response data is less than the maximum response data determined according to the multiple second response data, that is, during normal driving of the vehicle, the acceleration detected by the collision sensor is greater than the acceleration detected by the collision sensor when the target component is hit.

[0141] The new impact condition includes: a new impact intensity and / or a new installation position of the collision sensor on the target component.

[0142] For example, when a classification threshold cannot be obtained according to the first response data and the second response data, or a trained classification model for classifying the target component being hit and other conditions cannot be trained according to the first response data and the second response data, a new impact intensity can be used to traverse different positions of the impact target component to obtain multiple new first response data, and a classifier can be constructed according to the new first response data;

[0143] Alternatively, the adjustment position of the collision sensor on the target component may be adjusted, and then different positions of the collision target component may be traversed using a preset collision intensity to obtain a plurality of new first response data, and a classifier may be constructed according to the new first response data.

[0144] In some embodiments, if the classifier construction fails, the classification algorithm may be changed to construct the classifier, etc., until a classifier is constructed that can determine whether the response data generated by the collision sensor is triggered by the collision of the target component.

[0145] The embodiment of the present application discloses a vehicle collision detection method, which includes: obtaining a plurality of first response data respectively generated by the collision sensor when the target part is hit multiple times; obtaining the second response data generated by the collision sensor during the vehicle driving process; based on the first response data and the second response data, constructing a classifier corresponding to the collision sensor, the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed. By constructing a classifier for collision detection of the target part through the response data respectively detected by the collision sensor when the target part is hit multiple times, the number of sensors can be reduced, thereby reducing the cost of collision detection of the target part of the vehicle.

[0146] Based on the above introduction, the vehicle collision detection method of the present application will be further illustrated by giving examples below.

[0147] For example, see Figure 4 , Figure 4 This is a flow chart of another vehicle collision detection method provided in an exemplary embodiment of the present disclosure. Take the vehicle collision detection method applied to the collision detection of the bottom guard plate of the vehicle as an example. The specific process may be as follows:

[0148] First, any position is selected on the bottom guard plate of the vehicle and a collision sensor is arranged at the position;

[0149] Setting a critical bottom impact strength that requires a collision alarm, where the critical bottom impact strength may be an impact strength that the bottom guard plate can withstand (i.e., the preset impact strength mentioned in the above embodiment);

[0150] Through the critical bottom impact strength, traverse each position of the bottom guard plate that is impacted, and respectively obtain the response data detected by the collision sensor (that is, the first response data mentioned in the above embodiment);

[0151] Acquiring response data (that is, the second response data mentioned in the above embodiment) detected by the collision sensor during normal driving of the vehicle;

[0152] Selecting a binary classification algorithm from a plurality of binary classification algorithms, wherein the plurality of binary classification algorithms may include: threshold classification, classification model, etc.;

[0153] A binary classifier for collision detection of the bottom guard plate is constructed by using the selected binary classification algorithm, the first response data and the second response data;

[0154] If the construction fails, the classification algorithm is changed and a binary classifier is rebuilt based on the first response data and the second response data;

[0155] If the classification algorithm still fails to be built after being changed, the installation position of the collision sensor on the bottom guard plate is changed, the critical bottom impact intensity is repeated, each position of the bottom guard plate is traversed, the response data detected by the collision sensor is obtained respectively, and the binary classifier is rebuilt according to the detected data;

[0156] If the construction still fails after changing the installation position of the collision sensor, increase the critical collision intensity, traverse each position of the collision bottom guard plate through the increased critical bottom impact intensity, obtain the response data detected by the collision sensor respectively, and rebuild the binary classifier according to the detected data;

[0157] Until a binary classifier that meets the expected effect is constructed.

[0158] See also Figure 5 , Figure 5This is a flow chart of another vehicle collision detection method provided in an exemplary embodiment of the present disclosure. Taking the vehicle collision detection method as an example, the specific process can be as follows:

[0159] 201. Obtain target response data generated by a collision sensor during vehicle driving.

[0160] A collision sensor may be installed on the target component of the vehicle, and the installation position of the collision sensor on the target component may be determined in the process of constructing the binary classifier according to the above embodiment.

[0161] For example, during the driving of the vehicle, response data detected by a collision sensor disposed on a target component is used as target response data, and the target response data may include acceleration.

[0162] 202. Based on the classifier corresponding to the collision sensor, the target response data is classified to obtain a classification result.

[0163] The classifier is constructed based on at least a plurality of first response data generated by the collision sensor when the target component is hit multiple times, and a second response data generated by the collision sensor during vehicle driving, that is, the classifier is constructed in the above-mentioned embodiment.

[0164] In some embodiments, the classifier corresponding to the collision sensor may be a binary classifier that performs classification based on a classification threshold. Classifying the target response data based on the classifier corresponding to the collision sensor may include:

[0165] The acceleration in the target response data is compared with the classification threshold. If the acceleration in the target response data is greater than or equal to the classification threshold, it can be determined that the target response data is response data that requires an alarm; if the acceleration in the target response data is less than the classification threshold, it can be determined that the target response data is not response data that requires an alarm (for example, it can be response data generated during normal driving of the vehicle), thereby obtaining a classification result.

[0166] 203. According to the classification result, determine whether the target response data needs to be alarmed.

[0167] Among them, if the target response data is response data that requires an alarm, an alarm can be triggered; if the target response data is response data that does not require an alarm, an alarm is not required.

[0168] In some embodiments, when it is determined that the target response data requires an alarm, an alarm reminder can be issued to the driving user so that the driving user can check the collision condition of the vehicle's underbody guard plate and repair it in time; if it is not met, there is no need for an alarm reminder.

[0169] The embodiment of the present application discloses a vehicle collision detection method, which includes: obtaining target response data generated by a collision sensor during vehicle driving; classifying the target response data based on a classifier corresponding to the collision sensor to obtain a classification result, wherein the classifier is constructed based on at least a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times, and a second response data generated by the collision sensor during vehicle driving; and determining whether the target response data needs to be alarmed based on the classification result. In this way, the collision detection cost of the target component of the vehicle can be reduced.

[0170] In order to facilitate better implementation of the vehicle collision detection method provided in the exemplary embodiment of the present disclosure, the embodiment of the present application also provides a vehicle collision detection device based on the above vehicle collision detection method. The meanings of the terms are the same as those in the above vehicle collision detection method, and the specific implementation details can refer to the description in the method embodiment.

[0171] See also Figure 6 , Figure 6 This is a structural block diagram of a vehicle collision detection device provided in an exemplary embodiment of the present disclosure, the device comprising:

[0172] A first acquisition unit 301 is used to acquire a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times;

[0173] A second acquisition unit 302 is used to acquire second response data generated by the collision sensor during the driving process of the vehicle;

[0174] The construction unit 303 is used to construct a classifier corresponding to the collision sensor based on the first response data and the second response data, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

[0175] In some embodiments, the number of the second response data is multiple;

[0176] The construction unit 303 may include:

[0177] A first determining subunit, configured to determine minimum response data from the plurality of first response data;

[0178] A second determining subunit, configured to determine a maximum response data from a plurality of second response data;

[0179] The third determining subunit is configured to determine the classification threshold based on the maximum response data and the minimum response data.

[0180] In some embodiments, the construction unit 303 may include:

[0181] A training subunit, used for training a preset classification model according to the first response data and the second response data to obtain a trained classification model;

[0182] The fourth determination subunit is used to obtain the classifier based on the trained classification model.

[0183] In some embodiments, the first response data is response data detected in a non-gravity direction;

[0184] The second acquisition unit 302 may include:

[0185] The acquisition subunit is used to acquire the response data detected by the collision sensor in the non-gravity direction when a target collision occurs during the driving of the vehicle, and obtain the second response data. The target collision situation includes a collision with the body of the vehicle.

[0186] In some embodiments, the apparatus may further include:

[0187] an execution unit, configured to re-execute, under a new impact condition, the steps of acquiring a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple impacts, and subsequent steps if the classifier construction fails;

[0188] The new impact condition includes: a new impact intensity and / or a new installation position of the collision sensor on the target component.

[0189] The embodiment of the present application discloses a vehicle collision detection device, wherein a first acquisition unit 301 is used to acquire a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times; a second acquisition unit 302 is used to acquire the second response data generated by the collision sensor during the driving process of the vehicle; a construction unit 303 is used to construct a classifier corresponding to the collision sensor based on the first response data, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed. In this way, the cost of collision detection of the target component of the vehicle can be reduced.

[0190] See also Figure 7 , Figure 7 This is a structural block diagram of another vehicle collision detection device provided in an exemplary embodiment of the present disclosure, the device comprising:

[0191] A third acquisition unit 401 is used to acquire target response data generated by the collision sensor during the driving process of the vehicle;

[0192] A classification unit 402 is used to classify the target response data based on a classifier corresponding to the collision sensor to obtain a classification result, wherein the classifier is constructed based on at least a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and a second response data generated by the collision sensor during vehicle driving;

[0193] The determination unit 403 is used to determine whether the target response data needs to be alarmed according to the classification result.

[0194] The embodiment of the present application discloses a vehicle collision detection device, wherein the third acquisition unit 401 acquires the target response data generated by the collision sensor during the driving of the vehicle; the classification unit 402 classifies the target response data based on the classifier corresponding to the collision sensor to obtain a classification result, wherein the classifier is constructed based on at least a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times, and the second response data generated by the collision sensor during the driving of the vehicle; the determination unit 403 determines whether the target response data needs to be alarmed according to the classification result. In this way, the cost of collision detection of the target component of the vehicle can be reduced.

[0195] The embodiment of the present application also provides a computer-readable storage medium, on which a plurality of computer program instructions are stored, and the computer program can be loaded by a processor to execute the steps in any vehicle collision detection method provided in the embodiment of the present application. For example, the computer program can execute the following steps:

[0196] Acquire a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times;

[0197] Acquiring second response data generated by the collision sensor during vehicle driving;

[0198] Based on the first response data and the second response data, a classifier corresponding to the collision sensor is constructed, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

[0199] or,

[0200] Acquire target response data generated by the collision sensor during vehicle driving;

[0201] Based on a classifier corresponding to the collision sensor, the target response data is classified to obtain a classification result, wherein the classifier is constructed based on at least a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and a second response data generated by the collision sensor during the driving of the vehicle;

[0202] Based on the classification results, determine whether the target response data needs to be alarmed.

[0203] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0204] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0205] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0206] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0207] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0208] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0209] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated communication signals and carrier waves.

[0210] In response, the present application embodiment also provides a vehicle. Figure 8 As shown, Figure 8 Schematic diagram of the structure of a vehicle provided in an exemplary embodiment of the present disclosure. The vehicle 600 includes a processor 601 having one or more processing cores, a memory 602 having one or more computer-readable storage media, and a computer program stored in the memory 602 and executable on the processor. The processor 601 is electrically connected to the memory 602. Those skilled in the art will appreciate that Figure 8 The vehicle structure shown in the figure does not constitute a limitation on the vehicle and may include Figure 8 More or fewer components, or combinations of certain components, or different arrangements of components may be shown.

[0211] Processor 601 is the control center of vehicle 600. It uses various interfaces and lines to connect various parts of the entire vehicle 600, executes various functions of vehicle 600 and processes data by running or loading software programs and / or modules stored in memory 602, and calling data stored in memory 602, thereby monitoring vehicle 600 as a whole.

[0212] In the embodiment of the present application, the processor 601 in the vehicle 600 will load instructions corresponding to the processes of one or more application programs into the memory 602 according to the following steps, and the processor 601 will run the application programs stored in the memory 602 to implement various functions:

[0213] Acquire a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times;

[0214] Acquiring second response data generated by the collision sensor during vehicle driving;

[0215] Based on the first response data and the second response data, a classifier corresponding to the collision sensor is constructed, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

[0216] or,

[0217] Acquire target response data generated by the collision sensor during vehicle driving;

[0218] Based on a classifier corresponding to the collision sensor, the target response data is classified to obtain a classification result, wherein the classifier is constructed based on at least a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and a second response data generated by the collision sensor during the driving of the vehicle;

[0219] Based on the classification results, determine whether the target response data needs to be alarmed.

[0220] The embodiment of the present application obtains multiple first response data generated by the collision sensor when the target part is hit multiple times; obtains the second response data generated by the collision sensor during the vehicle's driving; and constructs a classifier corresponding to the collision sensor based on the first response data and the second response data, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed. The above technical solution constructs a classifier for collision detection of the target part through the response data detected by the collision sensor when the target part is hit multiple times, which can reduce the number of sensors, thereby reducing the cost of collision detection of the target part of the vehicle.

[0221] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0222] Optional, such as Figure 8 As shown, the vehicle 600 may further include: a display 603 and an input unit 604. The processor 601 is electrically connected to the display 603 and the input unit 604 respectively. Those skilled in the art will appreciate that Figure 8The vehicle structure shown in the figure does not constitute a limitation on the vehicle, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0223] The display 603 can be used to display a graphical user interface and receive operation instructions generated by the user acting on the graphical user interface. The display 603 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user and various graphical user interfaces of the vehicle, which can be composed of graphics, guidance information, icons, videos and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD, LiquidCrystal Display), an organic light-emitting diode (OLED, Organic Light-Emitting Diode), etc. The touch panel can be used to collect the user's touch operation on or near it (such as the user uses any suitable object or accessory such as a finger, stylus, etc. on the touch panel or near the touch panel), and generate a corresponding operation instruction, and the operation instruction executes the corresponding program. Optionally, the touch panel may include two parts: a touch detection device and a touch controller.

[0224] Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 601, and can receive the command sent by the processor 601 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 601 to determine the type of touch event, and then the processor 601 provides a corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present application, the touch panel and the display panel can be integrated into the display 603 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the display 603 can also be used as a part of the input unit 604 to realize the input function.

[0225] The input unit 604 may be used to receive input numbers, character information or user feature information (such as fingerprint, iris, facial information, etc.), and to generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0226] In some embodiments, the vehicle may further include a radio frequency circuit, which may be used to send and receive radio frequency signals to establish wireless communication with network devices or other vehicles through wireless communication, and to send and receive signals with network devices or other vehicles.

[0227] In some embodiments, the vehicle may further include an audio circuit, which may be used to provide an audio interface between the user and the vehicle battery aging identification device through a speaker and a microphone. The audio circuit may transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit and converted into audio data, and then the audio data is output to the processor 601 for processing, and then sent to, for example, another vehicle battery aging identification device through the radio frequency circuit, or the audio data is output to the memory 602 for further processing. The audio circuit may also include an earplug jack to provide communication between an external headset and the vehicle battery aging identification device.

[0228] although Figure 8 Not shown, the vehicle 600 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be described in detail here.

[0229] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0230] As can be seen from the above, the vehicle provided in this embodiment can obtain multiple first response data generated by the collision sensor when the target component is hit multiple times; obtain second response data generated by the collision sensor during the driving of the vehicle; and construct a classifier corresponding to the collision sensor based on the first response data and the second response data. The classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

[0231] or,

[0232] Acquire target response data generated by the collision sensor during vehicle driving;

[0233] Based on a classifier corresponding to the collision sensor, the target response data is classified to obtain a classification result, wherein the classifier is constructed based on at least a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and a second response data generated by the collision sensor during the driving of the vehicle;

[0234] Based on the classification results, determine whether the target response data needs to be alarmed.

[0235] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0236] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of this application, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0237] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0238] The embodiments, implementation methods and related technical features of the present application can be combined and replaced with each other without conflict.

[0239] The above are only preferred embodiments of the present application and do not constitute any form of limitation to the present application. However, any simple modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present application without departing from the content of the technical solution of the present application are still within the scope of the technical solution of the present application.

Claims

1. A vehicle collision detection method, characterized in that: A collision sensor is installed on the target component of the vehicle, and the method includes: Acquire a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times; Acquiring second response data generated by the collision sensor during the driving of the vehicle; Based on the first response data and the second response data, a classifier corresponding to the collision sensor is constructed, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

2. The method according to claim 1, characterized in that A collision sensor is mounted on the target component.

3. The method according to claim 1, characterized in that During the multiple impacts, the target component is impacted at different impact positions, and / or the target component is impacted at the same impact intensity.

4. The method according to claim 1, characterized in that The step of constructing a classifier corresponding to the collision sensor based on the first response data and the second response data includes: determining a classification threshold according to the first response data and the second response data; The classifier is constructed based on the classification threshold.

5. The method according to claim 4, characterized in that The number of the second response data is multiple; The determining a classification threshold according to the first response data and the second response data comprises: determining minimum response data from the plurality of first response data; determining a maximum response data from a plurality of second response data; The classification threshold is determined based on the maximum response data and the minimum response data.

6. The method according to claim 1, characterized in that The step of constructing a classifier corresponding to the collision sensor based on the first response data and the second response data includes: Training a preset classification model according to the first response data and the second response data to obtain a trained classification model; Based on the trained classification model, the classifier is obtained.

7. The method according to claim 1, characterized in that The first response data and the second response data are both response data detected in the gravity direction.

8. The method according to claim 1, characterized in that The first response data is response data detected in a non-gravity direction; The step of acquiring the second response data generated by the collision sensor during the driving of the vehicle includes: The second response data is obtained by acquiring response data detected by the collision sensor in the non-gravity direction when a target collision occurs during the driving of the vehicle, and the target collision includes a collision with a body of the vehicle.

9. The method according to claim 1, characterized in that: The method further comprises: If the classifier construction fails, then under new collision conditions, re-execute the steps of obtaining a plurality of first response data respectively generated by the collision sensor when the target component is subjected to multiple collisions, and the subsequent steps; The new impact condition includes: a new impact intensity and / or a new installation position of the collision sensor on the target component.

10. The method according to any one of claims 1 to 9, characterized in that: The target component includes a bottom guard plate.

11. A vehicle collision detection method, characterized in that: A collision sensor is installed on the target component of the vehicle, and the method includes: Acquiring target response data generated by the collision sensor during the driving of the vehicle; Based on the classifier corresponding to the collision sensor, the target response data is classified to obtain a classification result, wherein the classifier is obtained based on the method according to any one of claims 1 to 10; According to the classification result, it is determined whether the target response data needs to be alarmed.

12. A vehicle collision detection device, characterized in that: A collision sensor is installed on the target component of the vehicle, including: A first acquisition unit, used for acquiring a plurality of first response data respectively generated by the collision sensor when the target component is hit multiple times; A second acquisition unit, used for acquiring second response data generated by the collision sensor during the driving process of the vehicle; A construction unit is used to construct a classifier corresponding to the collision sensor based on the first response data and the second response data, and the classifier is used to determine whether the response data generated by the collision sensor needs to be alarmed.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program executable by a vehicle, and when the computer program is run on the vehicle, the vehicle is caused to execute the steps of the method according to any one of claims 1 to 11.

14. A vehicle, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method according to any one of claims 1 to 11 are implemented.

15. A computer program product, characterized in that The method comprises a computer program or an instruction, which, when executed by a processor, implements the steps of the method according to any one of claims 1 to 11.

Images