Intelligent anti-collision pad monitoring and alarm method, intelligent anti-collision pad and system

Abstract

This application relates to the technical field of traffic anti-collision devices, and provides an intelligent anti-collision pad monitoring and alarm method, an intelligent anti-collision pad, and a system. The monitoring and alarm method includes: when it is detected based on the detection data collected by the collision detection module that the intelligent anti-collision pad has collided, determining the collision time corresponding to this collision and the collision detection data corresponding to the collision time; determining the collision video data corresponding to this collision from the monitoring data collected by the video monitoring module based on the collision time; combining the collision video data and the collision detection data to determine the collision degree corresponding to this collision; generating a collision alarm message based on the collision degree, and controlling the alarm module to output the collision alarm message. By adopting the above technical solution, the collision degree can be comprehensively determined based on the collision video data and the collision detection data corresponding to the collision process, which can help improve the accuracy of the determined collision degree, and further help improve the accuracy of the anti-collision pad collision alarm.

Description

Technical Field

[0001] This application relates to the technical field of traffic collision avoidance warning devices, and in particular, to an intelligent anti-collision pad monitoring and warning method, an intelligent anti-collision pad, and a system. Background Art

[0002] The anti-collision pads used on roads are an important safety facility. Their main function is to absorb the energy during vehicle collisions, so that the vehicle can stop safely to avoid serious injuries to the occupants.

[0003] In the related art, an intrusion detection and warning system including traffic cones and an alarm terminal is provided, which can output alarm information through the alarm terminal in the case of a collision of the traffic cones.

[0004] However, different from traffic cones, since the anti-collision pad will deform during the collision, the collision degree cannot be accurately judged by traditional methods, which affects the accuracy of the collision alarm information. Summary of the Invention

[0005] In order to help improve the accuracy of the collision alarm information of the anti-collision pad, this application provides an intelligent anti-collision pad monitoring and warning method, a system, and an intelligent anti-collision pad.

[0006] In the first aspect, this application provides an intelligent anti-collision pad monitoring and warning method, adopting the following technical solution:

[0007] An intelligent anti-collision pad monitoring and warning method is used in the controller of an intelligent anti-collision pad. The intelligent anti-collision pad further includes a collision detection module, a video monitoring module, and an alarm module that are signal-connected to the controller. The collision detection module is used to detect the deformation of the anti-collision pad body, and the video monitoring module is used to collect image information of the area where the anti-collision pad body is located. The method includes:

[0008] Monitoring the detection data collected by the collision detection module;

[0009] In the case of detecting that the intelligent anti-collision pad has collided based on the detection data, determining the collision time corresponding to this collision and the collision detection data corresponding to the collision time;

[0010] Determining the collision video data corresponding to this collision from the monitoring data collected by the video monitoring module based on the collision time;

[0011] Combining the collision video data and the collision detection data to determine the collision degree corresponding to this collision;

[0012] Generating a collision alarm information based on the collision degree, and controlling the alarm module to output the collision alarm information.

[0013] By adopting the above technical solution, when it is detected based on the detection data that the intelligent anti-collision pad has collided, the collision degree can be comprehensively determined based on the collision video data and the collision detection data corresponding to the current collision process. This can help improve the accuracy of the determined collision degree, and further help improve the accuracy of the anti-collision pad collision alarm.

[0014] Optionally, the collision video data includes post-collision video data. Determining the collision degree corresponding to the current collision based on the collision video data and the detection data includes:

[0015] Determining the vehicle deformation degree of the target vehicle corresponding to the current collision based on the post-collision video data;

[0016] Determining the deformation degree of the anti-collision pad corresponding to the current collision based on the collision detection data;

[0017] Determining the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad.

[0018] By adopting the above technical solution, during the process of collision degree analysis, the vehicle deformation and the deformation of the anti-collision pad caused by the collision can be fully considered, which can help avoid the problem of inaccurate collision degree determined by using only a single deformation, and further help improve the accuracy of the finally determined collision degree.

[0019] Optionally, the collision video data further includes pre-collision video data. Before determining the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad, it further includes:

[0020] Determining the vehicle parameters of the target vehicle based on the pre-collision video data;

[0021] Determining the prediction confidence corresponding to the vehicle deformation degree based on the vehicle parameters;

[0022] Predicting the deformation degree of the anti-collision pad body based on the prediction confidence and the vehicle deformation degree to obtain a predicted deformation range;

[0023] Determining whether the deformation degree of the anti-collision pad is within the predicted deformation range;

[0024] When the deformation degree of the anti-collision pad is within the predicted deformation range, determining the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad.

[0025] By adopting the above technical solution, before determining the collision degree in combination with the deformation degree of the anti-collision pad, the error of the deformation degree of the anti-collision pad can be verified through the vehicle deformation degree, which can further help ensure the accuracy of the finally determined degree.

[0026] Optionally, after determining whether the degree of collision deformation is within the predicted deformation range, the method further includes:

[0027] When the degree of deformation of the anti-collision pad is not within the predicted deformation range, determining the predicted deformation amount of the anti-collision pad body based on the post-collision video data;

[0028] Determining whether the degree of deformation of the anti-collision pad matches the predicted deformation amount;

[0029] When the degree of deformation of the anti-collision pad matches the predicted deformation amount, determining the degree of collision based on the degree of deformation of the anti-collision pad and the predicted deformation amount.

[0030] By adopting the above technical solution, it is possible to determine the reason why the degree of deformation of the anti-collision pad does not match the degree of deformation of the vehicle through the verification of the degree of deformation of the anti-collision pad, which can help avoid the influence of unreasonable vehicle deformation on the determination of the collision degree, and further help ensure the accuracy of the finally determined collision degree.

[0031] Optionally, after determining whether the degree of deformation of the anti-collision pad matches the predicted deformation amount, the method further includes:

[0032] When the degree of collision deformation does not match the predicted deformation amount, determining whether the predicted deformation amount matches the predicted deformation range;

[0033] When the predicted deformation amount matches the predicted deformation range, determining the degree of collision based on the predicted deformation amount and the degree of vehicle deformation.

[0034] By adopting the above technical solution, it is possible to further determine whether the degree of collision needs to be determined in combination with the degree of vehicle deformation based on the matching relationship between the predicted deformation amount and the predicted deformation range when the degree of collision deformation does not match the predicted deformation amount, which can help accurately judge the reference value of the degree of vehicle deformation in the process of determining the degree of collision, and further help improve the accuracy of the degree of collision while ensuring a high accuracy of the determined degree of collision.

[0035] Optionally, monitoring the detection data collected by the collision detection module includes:

[0036] Monitoring whether the detection data fluctuates;

[0037] When it is monitored that the detection data fluctuates, determining the waveform characteristics corresponding to the detection data;

[0038] Determining whether the intelligent anti-collision pad has collided based on the waveform characteristics.

[0039] By adopting the above technical solution, when it is detected that the detection data fluctuates, it is further possible to determine whether the intelligent collision pad has collided based on the fluctuation of the detection data for verification, which can help reduce the influence of other factors other than collisions on collision detection, and thus can help improve the accuracy of collision detection.

[0040] Optionally, the collision detection module includes a first detection component and a second detection component, and the detection data includes first detection data corresponding to the first detection component and second detection data corresponding to the second detection component. When it is detected that the detection data fluctuates, determining the waveform characteristics of the detection data includes:

[0041] When it is detected that the first detection data and / or the second detection data fluctuates, respectively determine the first waveform characteristic of the first detection data and the second waveform characteristic of the second detection data;

[0042] Determining whether the intelligent anti-collision pad has collided based on the waveform characteristics includes:

[0043] Determine the collision probability based on the first waveform characteristic;

[0044] Determine whether the collision probability is less than the collision probability threshold;

[0045] When the collision probability is less than the collision probability threshold, determine whether there is a risk characteristic in the second waveform characteristic;

[0046] When there is the risk characteristic, perform anomaly verification on the risk characteristic based on the first waveform characteristic;

[0047] When the anomaly verification result indicates that the risk characteristic is abnormal, determine that the intelligent anti-collision pad has not collided.

[0048] By adopting the above technical solution, it is possible to comprehensively determine whether the intelligent anti-collision pad has collided by combining the waveform characteristics corresponding to the detection data collected by different detection components, which can help improve the accuracy of collision detection.

[0049] Optionally, after performing anomaly verification on the risk characteristic based on the first waveform characteristic, it further includes:

[0050] When the anomaly verification result indicates that the risk characteristic is not abnormal, determine the collision characteristic in the first waveform characteristic;

[0051] Perform collision verification on the collision characteristic based on the second waveform characteristic;

[0052] When the collision verification result indicates that a collision feature exists, it is determined that the intelligent anti-collision pad has collided.

[0053] By adopting the above technical solution, when the abnormal verification result indicates that there is no abnormality in the risk feature, the collision feature in the first waveform feature will be further verified for collision based on the second waveform feature, so as to finally determine whether the intelligent anti-collision pad has collided. Thus, it is possible to fully combine the first waveform feature and the second waveform feature to judge whether the intelligent anti-collision pad has collided, which can further help improve the accuracy of collision monitoring.

[0054] In a second aspect, the present application provides an intelligent anti-collision pad, adopting the following technical solution:

[0055] An intelligent anti-collision pad, the intelligent anti-collision pad includes a controller and a collision detection module, a video monitoring module, and an alarm module that are signal-connected to the controller. The collision monitoring module is used to detect the deformation of the anti-collision pad body, and the video monitoring module is used to collect image information of the area where the anti-collision pad body is located;

[0056] The controller is configured to execute any intelligent anti-collision pad monitoring and alarm method provided in the first aspect, and send collision alarm information to the background server.

[0057] In a third aspect, the present application provides an intelligent anti-collision pad alarm system, adopting the following technical solution:

[0058] An intelligent anti-collision pad alarm system, the system includes the intelligent anti-collision pad provided in the second aspect, and a background server that is communicatively connected to the intelligent anti-collision pad;

[0059] The intelligent anti-collision pad is used to generate collision alarm information and send it to the background server;

[0060] The background server is used to process the collision alarm information.

[0061] In summary, the present application includes at least one of the following beneficial technical effects:

[0062] 1. When it is detected based on the detection data that the intelligent anti-collision pad has collided, the collision degree can be comprehensively determined based on the collision video data and collision detection data corresponding to this collision process. This can help improve the accuracy of the determined collision degree, and further help improve the accuracy of the anti-collision pad collision alarm;

[0063] 2. During the process of collision degree analysis, the vehicle deformation and anti-collision pad deformation caused by the collision can be fully considered, which can help avoid the problem of inaccurate collision degree determined by using a single deformation, and further help improve the accuracy of the finally determined collision degree. Brief Description of the Drawings

[0064] Figure 1 is a schematic structural diagram of an intelligent anti-collision pad provided by an embodiment of the present application;

[0065] Figure 2a and Figure 2b is a schematic diagram of a deployment method of an anti-collision pad provided by an embodiment of the present application;

[0066] Figure 3 is a schematic structural diagram of an intelligent anti-collision pad system provided by an embodiment of the present application;

[0067] Figure 4 is a schematic flow diagram of a method for monitoring and alarming an intelligent anti-collision pad provided by an embodiment of the present application;

[0068] Figure 5 is a schematic flow diagram of a method for determining the degree of collision provided by an embodiment of the present application;

[0069] Figure 6 is a schematic flow diagram of a method for verifying the deformation degree of an anti-collision pad provided by an embodiment of the present application;

[0070] Figure 7 is a schematic flow diagram of a method for monitoring detection data provided by an embodiment of the present application;

[0071] Figure 8 is a schematic flow diagram of another method for monitoring and alarming an intelligent anti-collision pad provided by an embodiment of the present application. Detailed Description of the Embodiments

[0072] In order to make the objectives, technical solutions and advantages of the present application clearer, the following further describes the present application in detail with reference to the accompanying Figures 1 to 8 drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0073] An embodiment of the present application discloses an intelligent anti-collision pad. Referring to Figure 1 , the intelligent anti-collision pad 110 includes a controller 111, and a collision detection module 112, a video monitoring module 113, and an alarm module 114 that are signal-connected to the controller 111.

[0074] Among them, the collision detection module 112 is disposed on the anti-collision pad body. The controller 111, the video monitoring module 113, and the alarm component 140 may be disposed on the anti-collision pad body, or may be separately disposed from the anti-collision pad body. In one example, referring to Figure 2a and Figure 2b, the anti-collision pad body is connected to the rear of the transport vehicle and moves to a predetermined position under the drive of the transport vehicle. At this time, the controller 111, the video monitoring module 113, and the alarm component 140 can be arranged on the transport vehicle, which can help avoid the impact on the anti-collision pad body during the collision, and further help ensure that the controller 111, the video monitoring module 113, and the alarm module 114 can work properly during the collision, and then ensure effective collision alarm.

[0075] The collision detection module 112 is used to detect the deformation of the anti-collision pad body. Specifically, the collision detection module 112 includes at least one detection component, and the types and / or installation positions of different detection components are different. In actual implementation, the detection component can be implemented based on sensors that can sense deformation, such as piezoelectric sensors, Hall sensors, linear variable differential transformers (LVDTs), etc.

[0076] The video monitoring module 113 is used to collect image information of the area where the anti-collision pad body is located. Specifically, the video monitoring module 113 includes at least one camera, and the installation positions of different cameras are different. In one example, the video monitoring module 113 includes two wide-angle cameras, which are respectively located on both sides of the anti-collision pad body and are used to collect image information of the anti-collision pad body and its surrounding environment. In another example, the video monitoring module includes cameras in four directions: front, back, left, and right, which are respectively used to collect information in four directions: front, back, left, and right.

[0077] The alarm module 114 is used to output collision alarm information. In one example, the alarm module 114 includes alarm devices, such as alarm lights, horns, display screens, etc. In another example, the alarm module 114 includes a signal transmitting device, such as a network communication module (4G module). At this time, the alarm device 140 can send alarm information to the background server.

[0078] The controller 111 is used to obtain the detection data collected by the collision detection module 112 and the video data collected by the video monitoring module 113, judge the collision and the degree of collision based on the detection data and the video data, and then output collision prompt information through the alarm module 114 to prompt the collision.

[0079] In actual implementation, the intelligent anti-collision pad 110 can also include a positioning module to locate the position where the collision occurs, which can help improve the efficiency of accident rescue.

[0080] The embodiment of the present application also provides an intelligent anti-collision pad alarm system. Refer to Figure 3 , the intelligent anti-collision pad alarm system includes the intelligent anti-collision pad 110 provided in the above embodiment and a background server 120 communicatively connected to the intelligent anti-collision pad;

[0081] The intelligent anti-collision pad 110 is used to generate collision alarm information and send it to the background server 120. In one example, the intelligent anti-collision pad 110 includes a communication module (such as a 4G communication module) that is signal-connected to the controller and is used to establish a communication connection with the background server 120.

[0082] The background server 120 is used to process the collision alarm information sent by the intelligent anti-collision pad 110. Specifically, the background server 120 can automatically push prompts (such as sending prompts via text messages or in-app messages) to relevant departments such as the anti-collision pad manufacturer and the local emergency management department, so as to quickly respond to the collision alarm information. In addition, the background server 120 can also save the content of the collision alarm information for subsequent investigation.

[0083] The embodiment of the present application also discloses an intelligent anti-collision pad monitoring and alarm method, which is used in the controller of the intelligent anti-collision pad provided in the above embodiment. Refer to Figure 4 , the intelligent anti-collision pad monitoring and alarm method includes the following steps:

[0084] Step 201, monitor the detection data collected by the collision detection module.

[0085] Specifically, since the collision monitoring module can collect the deformation of the anti-collision pad body, and after a collision with a vehicle, the anti-collision pad body will deform, resulting in a change in the detection data. Therefore, it is possible to monitor whether the intelligent anti-collision pad has collided by monitoring the value of the detection data and / or the change in the value of the detection data.

[0086] In one example, the collision detection module includes a detection component arranged at the rear of the anti-collision pad body. In the natural state, the detection data collected by the detection component is constant, and when the vehicle hits the detection area where the detection component is located, the detection area will deform, resulting in a change in the detection data corresponding to the detection component.

[0087] Step 202, when it is detected based on the detection data that the intelligent anti-collision pad has collided, determine the collision time corresponding to this collision and the collision detection data corresponding to the collision time.

[0088] Among them, the collision time refers to the time when the collision occurs. Specifically, the collision time can be the start and / or end time of the collision, or it can also be the time period during which the collision lasts.

[0089] The collision detection data refers to the detection data collected during this collision process. Specifically, the collision detection data can be the detection data within a preset time period starting from the collision start time, or it can also be the detection data within a preset time period before the collision end time, or it can also be the detection data during the collision duration.

[0090] In one example, it is determined that the intelligent anti-collision pad has collided when it is monitored that the value of the detection data is greater than a preset threshold.

[0091] In another example, it is determined that the intelligent anti-collision pad has collided when it is monitored that the fluctuation amplitude of the data is greater than a preset amplitude threshold.

[0092] Step 203: Determine the collision video data corresponding to this collision from the monitoring data collected by the video monitoring module based on the collision time.

[0093] In one example, the video monitoring module can continuously collect images. At this time, after determining the collision time, the collision video data corresponding to this collision can be intercepted from the monitoring data based on the collision time.

[0094] In another example, the video monitoring module maintains a low-power mode under normal circumstances and starts recording to collect monitoring data once it receives an activation instruction sent by the controller. Among them, the activation instruction can be generated by the controller when it monitors that the intelligent anti-collision pad has collided based on the detection data, or it can also be generated by the controller when it determines that there is a collision risk, for example: the activation instruction generated by the controller when it determines that a fast vehicle is approaching.

[0095] Step 204: Determine the collision degree corresponding to this collision by combining the collision video data and the collision detection data.

[0096] Among them, the collision degree is used to indicate the damage situation of the intelligent anti-collision pad and the vehicle during the collision. In actual implementation, the collision degree can be represented in a quantifiable way such as a numerical value or a level.

[0097] Specifically, in the research process, it is found that the determination of the collision degree includes multiple influencing factors, such as: collision speed, collision duration, collision intensity, vehicle deformation degree, anti-collision pad deformation degree, etc. For some influencing factors, it is impossible to accurately judge only through the collision detection data. Based on this, in this embodiment, the collision video data and the collision detection data are combined to comprehensively judge the collision degree to accurately judge different influencing factors.

[0098] In one example, determining the collision degree corresponding to this collision by combining the collision video data and the collision detection data includes: determining the collision speed based on the collision video data; determining the collision intensity based on the collision detection data; and determining the collision degree based on the collision speed and the collision intensity.

[0099] In another example, determining the collision degree corresponding to this collision by combining the collision video data and the collision detection data includes: comprehensively determining the collision duration based on the collision video data and the collision detection data; and determining the collision degree in combination with the collision duration.

[0100] In actual implementation, the collision degree can be comprehensively combined with the methods in the above two examples, or the collision degree can also be determined based on other methods.

[0101] Step 205: Generate a collision alarm message based on the collision degree, and control the alarm module to output the collision alarm message.

[0102] Optionally, the collision alarm message includes the collision degree, so that it is convenient to determine the urgency of collision handling based on the alarm message, which can help improve the efficiency of collision handling.

[0103] In one example, the alarm module includes an alarm component. Correspondingly, controlling the alarm module to output the collision alarm message includes: controlling the alarm light to flash, controlling the horn to broadcast an alarm prompt sound, and controlling the display component to display an alarm identifier.

[0104] In another example, the alarm module includes a signal transmitting device. Correspondingly, controlling the alarm module to output the collision alarm message includes: controlling the signal transmitting device to send the collision alarm message to the background server for the background server to process the collision alarm.

[0105] In actual implementation, the collision alarm message can also include the position information of the intelligent anti-collision pad, which can help improve the efficiency of accident rescue.

[0106] The implementation principle of an intelligent anti-collision pad monitoring and alarm method according to an embodiment of the present application is as follows: Monitor the detection data collected by the collision detection module; in the case where it is monitored based on the detection data that the intelligent anti-collision pad has a collision, determine the collision time corresponding to this collision and the collision detection data corresponding to the collision time; determine the collision video data corresponding to this collision from the monitoring data collected by the video monitoring module based on the collision time; combine the collision video data and the collision detection data to determine the collision degree corresponding to this collision; generate a collision alarm message based on the collision degree, and control the alarm module to output the collision alarm message. By adopting the above technical solution, in the case where it is monitored based on the detection data that the intelligent anti-collision pad has a collision, the collision degree can be comprehensively determined based on the collision video data and the collision detection data corresponding to this collision process, which can help improve the accuracy of the determined collision degree, and further help improve the accuracy of the anti-collision pad collision alarm.

[0107] In some embodiments, the collision video data includes post-collision video data. Refer to Figure 5 , the above step 204, combining the collision video data and the collision detection data to determine the collision degree corresponding to this collision specifically includes the following steps:

[0108] Step 301: Determine the vehicle deformation degree of the target vehicle corresponding to this collision based on the post-collision video data.

[0109] Among them, the degree of vehicle deformation is used to indicate the damage condition of the target vehicle during a collision. Specifically, although the anti-collision pad can offset most of the impact generated during the collision, there is still some impact that acts on the target vehicle and may cause the target vehicle to deform. Therefore, it is necessary to consider the degree of vehicle deformation during the collision severity analysis process.

[0110] Optionally, determining the degree of vehicle deformation of the target vehicle corresponding to the current collision based on the post-collision video data includes: extracting the post-collision image from the post-collision video data; intercepting the vehicle image corresponding to the target vehicle from the post-collision image; and determining the degree of vehicle deformation based on the vehicle image. Specifically, feature recognition can be performed on the vehicle image to determine the missing features in the vehicle image, such as: the front bumper, the engine hood, the front windshield, etc., and then the degree of vehicle deformation can be determined based on the missing features in the vehicle image.

[0111] In an example, it can be determined that the vehicle has a minor deformation when the vehicle image indicates that most of the engine hood of the target vehicle is intact; it can be determined that the vehicle has a moderate deformation when the vehicle image indicates that most of the engine hood of the target vehicle is damaged and the front windshield is intact or slightly damaged; it can be determined that the vehicle has a severe deformation when the vehicle image indicates that the engine hood of the target vehicle is missing and the front windshield is also damaged or the front windshield is severely damaged.

[0112] Furthermore, when the deformation level of the vehicle is initially determined, the degree of vehicle deformation can be further scored within the scoring range corresponding to the deformation level based on the scoring method corresponding to the deformation level, and finally a deformation score is obtained. Specifically, the value range of the deformation score can be divided based on the preset damage level to obtain the scoring ranges corresponding to different deformation levels. For example, the value range of the deformation score is 1-10, and the score is positively correlated with the degree of deformation. At this time, the scoring range corresponding to minor deformation is 1-3, the scoring range corresponding to moderate deformation is 4-7, and the scoring range corresponding to severe deformation is 8-10.

[0113] Among them, the scoring methods corresponding to different deformation levels are different. Specifically, the reference features of the scoring methods corresponding to different scoring levels are different. In an example, the reference features corresponding to minor deformation include: the damage condition of the engine hood; the reference features corresponding to moderate deformation include: the damage condition of the engine hood and whether the front windshield is damaged; the reference features corresponding to severe deformation include: the damage condition of the front windshield.

[0114] In actual implementation, the pre-collision images can be further extracted from the post-collision video data. In this way, during the process of judging the deformation degree of the vehicle, the pre-collision images and the post-collision images can be compared and analyzed, which can help improve the accuracy of the finally determined damage degree of the vehicle.

[0115] Step 302: Determine the deformation degree of the bumper corresponding to this collision based on the collision detection data.

[0116] Optionally, determining the deformation degree of the bumper corresponding to this collision based on the collision detection data includes: determining the deformation degree of the bumper based on the peak value of the collision detection data. Specifically, since the bumper is elastic, it generally undergoes large deformation first and then small rebound during the collision. Correspondingly, the collision detection data also fluctuates. The peak position of the collision detection data generally corresponds to the position where the deformation degree of the bumper is the largest. Therefore, based on the peak position, the maximum deformation degree of the bumper body can be determined, which can help ensure the accuracy of the determined deformation degree of the bumper.

[0117] Among them, the correspondence between the peak value and the deformation degree of the bumper is preset. In one example, the value range of the collision detection data is divided according to the deformation level to obtain the numerical intervals corresponding to different deformation levels. At this time, the deformation level can be determined according to the numerical interval to which the peak value belongs. In another example, there is a correspondence between the collision detection data and the deformation score, and this correspondence can be obtained through experiments. Generally speaking, the collision detection data is positively correlated with the deformation score.

[0118] Furthermore, when the collision detection module includes at least two detection components, the collision detection data includes the collision detection data collected by different detection components. At this time, determining the deformation degree of the bumper corresponding to the collision detection data based on the peak value of the collision detection data includes: superimposing the collision detection data collected by different detection components according to a preset superimposing rule to obtain the superimposed detection data; determining the deformation degree of the bumper based on the peak value of the superimposed detection data.

[0119] Among them, the superimposing rule can be set based on the relative positions of the detection components. Specifically, since the deformation detection ranges corresponding to the detection components set at different positions are different, and the deformation detection ranges corresponding to different detection components may overlap, and the deformations at different positions may also affect each other, it is necessary to preset the superimposing rule based on the relative positions of the sensing components to achieve the accurate superimposition of the detection data collected by different detection components.

[0120] In other embodiments, when the collision detection module includes at least two detection components, the peaks corresponding to the collision detection data collected by different detection components can also be determined separately, and the peaks corresponding to the detection data collected by different detection components can be comprehensively analyzed to finally obtain the deformation degree of the anti-collision pad. For example, the collision process can be simulated based on the timing of the peaks corresponding to the detection data collected by different detection components, so that the deformation process of the anti-collision pad can be predicted based on the collision process, and further the deformation degree of the anti-collision pad can be predicted based on the deformation process of the anti-collision pad.

[0121] In actual implementation, factors such as the collision duration indicated by the collision detection data can also be further combined to comprehensively determine the deformation degree of the anti-collision pad to improve the accuracy of the finally determined deformation degree of the anti-collision pad.

[0122] Step 303, determine the collision degree based on the vehicle deformation degree and the anti-collision pad deformation degree.

[0123] In one example, the deformation degree is represented by a deformation level. Correspondingly, determining the collision degree based on the vehicle deformation degree and the anti-collision pad deformation degree includes: determining the more serious one of the vehicle deformation degree and the anti-collision pad deformation degree as the collision degree. For example, the vehicle deformation degree is moderate deformation, and the anti-collision pad deformation degree is severe deformation. At this time, the collision degree is severe collision.

[0124] In another example, the deformation degree is represented by a deformation score. Determining the collision degree based on the vehicle deformation degree and the anti-collision pad deformation degree includes: determining whether the difference between the vehicle deformation degree and the anti-collision pad deformation degree is greater than a preset score difference threshold; if so, determining the larger one of the vehicle deformation degree and the anti-collision pad deformation degree as the collision degree; if not, determining the average value of the vehicle deformation degree and the anti-collision pad deformation degree as the collision degree. For example, the score difference threshold is 3, the vehicle deformation degree is 5, and the anti-collision pad deformation degree is 6. At this time, the collision degree is the average value of the vehicle deformation degree and the anti-collision pad deformation degree, that is, 5.5.

[0125] In the above embodiments, during the determination of the collision degree, the vehicle deformation degree can be first determined based on the video data after the collision, and the deformation degree of the anti-collision pad can be determined based on the collision detection data. Then, the collision degree can be comprehensively analyzed based on the vehicle deformation degree and the anti-collision pad deformation degree. In this way, the vehicle deformation and the anti-collision pad deformation caused by the collision can be fully considered during the analysis of the collision degree, which can help avoid the problem of inaccurate collision degree determined by using a single deformation, and further help improve the accuracy of the finally determined collision degree.

[0126] Meanwhile, since the degree of vehicle deformation is obtained based on the analysis of the post-collision video data without relying on the sensing devices installed on the vehicle, the difficulty and cost of analyzing the degree of vehicle deformation can be reduced, facilitating the practical application of this method.

[0127] Based on the above embodiments, further, the collision video data further includes pre-collision video data. Referring to Figure 6 , before step 303 of determining the collision degree based on the degree of vehicle deformation and the degree of deformation of the anti-collision pad, the following steps are further included:

[0128] Step 401, determining the vehicle parameters of the target vehicle based on the pre-collision video data.

[0129] Among them, the pre-collision video data is collected before the target vehicle is deformed. Specifically, the pre-collision video data can be collected before the target vehicle contacts the anti-collision pad body. For example, it can be the data within 30 seconds before the collision, or the data collected at the moment of contacting the anti-collision pad body.

[0130] In one example, the vehicle parameters include the vehicle model, which can include sedans, SUVs, minivans, trucks, etc. Specifically, since the structures of vehicles of different models may vary, and the structure of the vehicle will affect the deformation after the collision, that is, for the same collision degree, the deformation effects of different types of vehicles may be different. For example, the deformation degree of a sedan may be greater than that of an SUV. Therefore, it is necessary to consider the vehicle model in the process of determining the collision degree based on the degree of vehicle deformation.

[0131] In another example, the vehicle parameters include the vehicle driving speed. Specifically, it is found during the test that the vehicle driving speed will affect the collision process, and may thus lead to different deformations of the vehicle, that is, the factors that may cause the vehicle to deform may be different at different vehicle driving speeds. Therefore, it is necessary to consider the vehicle driving speed in the process of determining the collision degree based on the degree of vehicle deformation.

[0132] In actual implementation, the vehicle parameters can also include parameters related to the actual vehicle such as the length of the vehicle's hood, the width of the vehicle, and whether the vehicle is equipped with a front bumper, etc., which can help accurately judge the actual situation of the vehicle.

[0133] Step 402, determining the prediction confidence corresponding to the degree of vehicle deformation based on the vehicle parameters.

[0134] Among them, the prediction confidence level is used to indicate the correlation degree between the vehicle deformation degree and the collision degree. Specifically, since the corresponding relationship between the vehicle deformation degree and the collision degree may vary dynamically with factors such as vehicle type and vehicle driving speed, in order to help improve the accuracy of the finally predicted collision degree, it is necessary to determine the prediction confidence level based on vehicle parameters and take it into account during the subsequent collision degree prediction process.

[0135] Step 403: Predict the deformation degree of the anti-collision pad body based on the prediction confidence level and the vehicle deformation degree to obtain a predicted deformation range.

[0136] Specifically, different from the vehicle deformation degree, since the structure and material of the anti-collision pad body are predetermined, the corresponding relationship between the anti-collision pad deformation degree and the collision degree is roughly fixed. Based on the prediction confidence level and the vehicle deformation degree, the range of the collision degree can be roughly determined. Therefore, the deformation degree of the anti-collision pad body can be predicted based on the prediction confidence level and the vehicle deformation degree.

[0137] Step 404: Determine whether the deformation degree of the anti-collision pad is within the predicted deformation range.

[0138] Specifically, since the deformation degree of the anti-collision pad is determined based on the collision detection data collected by the collision detection module, during the collision process, the collision module may be displaced and unreasonably deformed due to the force, resulting in errors in the collision detection data, which in turn affects the accuracy of the anti-collision pad deformation degree. Based on this, in this embodiment, the accuracy of the anti-collision pad deformation degree is verified through the predicted deformation range to make a wrong judgment on the anti-collision pad deformation degree.

[0139] Step 405: When the deformation degree of the anti-collision pad is within the predicted deformation range, determine the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad, that is, execute Step 303.

[0140] Specifically, when the deformation degree of the anti-collision pad is within the predicted deformation range, it means that the probability of the anti-collision pad deformation degree being incorrect is relatively low. At this time, determining the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad can help ensure the accuracy of the collision degree.

[0141] Optionally, when the deformation degree of the anti-collision pad is not within the predicted deformation range, it means that the probability of the anti-collision pad deformation degree being incorrect is relatively high. At this time, it can be directly determined not to execute the step of determining the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad, that is, not to execute Step 303, and determine the collision degree based on other methods, such as directly determining the collision degree based on the vehicle deformation degree; or it can also be further verified whether the anti-collision pad deformation degree is incorrect based on other methods.

[0142] In the above technical solution, before determining the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad, the predicted deformation range of the anti-collision pad body can be predicted based on the vehicle deformation degree of the target vehicle and its corresponding prediction confidence, and the collision degree is determined based on the vehicle deformation degree and the deformation degree of the anti-collision pad only when the deformation degree of the anti-collision pad is within the predicted deformation range. In this way, before determining the collision degree in combination with the deformation degree of the anti-collision pad, the vehicle deformation degree can be used to check whether there is an error in the deformation degree of the anti-collision pad, which can help ensure the accuracy of the finally determined degree.

[0143] At the same time, since the prediction confidence corresponding to the vehicle deformation degree is calculated based on vehicle parameters, and the vehicle parameters are determined based on the video data before the collision, without relying on the sensing devices set on the vehicle, the difficulty and cost of verifying the deformation of the anti-collision pad can be reduced, which is convenient for putting this method into practical application.

[0144] Based on the above implementation manner, further, continue to refer to Figure 6 , step 404, after determining whether the deformation degree of the anti-collision pad is within the predicted deformation range, it further includes:

[0145] Step 406, when the deformation degree of the anti-collision pad is not within the predicted deformation range, determine the predicted deformation amount of the anti-collision pad body based on the video data after the collision.

[0146] Among them, the predicted deformation amount refers to the deformation amount of the anti-collision pad body identified based on the video data after the collision. In one example, the predicted deformation amount can be the maximum deformation amount of the anti-collision pad body during the collision. At this time, multiple frames of images need to be intercepted at intervals from the video after the collision for analyzing the deformation amount of the anti-collision pad body to determine the maximum deformation amount. In actual implementation, the predicted deformation amount can also be the deformation amount of the anti-collision pad body after the collision.

[0147] In one example, the predicted deformation amount is represented by the difference between the area of the anti-collision pad body after the collision and the area in the natural state. Among them, the area of the anti-collision pad body after the collision is estimated based on the video data after the collision. In one instance, the area of the anti-collision pad body after the collision is determined based on the number of pixels occupied by the anti-collision pad in the video data after the collision. The corresponding relationship between the pixel amount and the area is set in advance. For example: determine the number of pixels occupied by the anti-collision pad body in the natural state based on the video data collected by the video monitoring module during the non-collision process, and then determine the corresponding relationship between the pixel amount and the area based on the area of the anti-collision pad body and the number of pixels it occupies in the natural state.

[0148] Step 407, determine whether the deformation degree of the anti-collision pad matches the predicted deformation amount.

[0149] Among them, the corresponding relationship between the deformation amount and the deformation degree is set in advance.

[0150] In one example, the deformation degree of the anti-collision pad is represented by a deformation level. Correspondingly, determining whether the deformation degree of the anti-collision pad matches the predicted deformation amount includes: determining whether the predicted deformation amount belongs to the deformation amount range corresponding to the deformation level of the anti-collision pad; if so, determining that the deformation degree of the anti-collision pad matches the predicted deformation amount; if not, determining that the deformation degree of the anti-collision pad does not match the predicted deformation amount.

[0151] In another example, the deformation degree of the anti-collision pad is represented by a deformation score. Correspondingly, determining whether the deformation degree of the anti-collision pad matches the predicted deformation amount includes: determining whether the difference between the deformation score corresponding to the predicted deformation amount and the deformation degree of the anti-collision pad is less than a preset difference threshold; if so, determining that the deformation degree of the anti-collision pad matches the predicted deformation amount; if not, determining that the deformation degree of the anti-collision pad does not match the predicted deformation amount.

[0152] Step 408, when the deformation degree of the anti-collision pad matches the predicted deformation amount, determine the collision degree based on the deformation degree of the anti-collision pad and the predicted deformation amount.

[0153] Specifically, the method of determining the collision degree based on the deformation degree of the anti-collision pad and the expected deformation amount can be analogous to the method of determining the collision degree based on the deformation degree of the vehicle and the deformation degree of the anti-collision pad in step 303 above, which will not be elaborated here.

[0154] In another implementation manner, when the deformation degree of the anti-collision pad matches the predicted deformation amount, a reference time point can be determined based on the collision detection data first, and a reference image corresponding to the reference time point is intercepted from the post-collision image data; determine the reference deformation amount of the anti-collision pad body based on the reference image corresponding to the reference time point, so as to finally determine the collision degree based on the reference deformation amount.

[0155] Among them, the reference time point can be the time point corresponding to the peak value of the collision detection data. When the detection data includes the detection data collected by multiple detection components, the time point corresponding to the detection data with the highest peak value can be determined as the reference time point, or the detection data collected by different detection components can be superimposed, and the time point corresponding to the peak value of the superimposed detection data can be determined as the reference time point.

[0156] In one example, the method of determining the corrected deformation amount of the anti-collision pad body based on the reference image corresponding to the reference time point can be analogous to the method of determining the predicted deformation amount of the anti-collision pad body based on the post-collision video data in step 406 above.

[0157] In another example, the deformation amount is represented by a deformation score. At this time, finally determining the collision degree based on the reference deformation amount includes: determining the corrected deformation amount based on the value corresponding to the reference time point in the collision detection data; determining the collision degree based on the corrected deformation amount and the reference deformation amount.

[0158] Among them, the method of determining the collision degree based on the corrected deformation amount and the reference deformation amount can be analogous to the specific implementation manner of determining the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad in step 303 above, and will not be elaborated here.

[0159] Optionally, in the case where the collision deformation degree does not match the predicted deformation amount, the collision degree can be directly determined based on the predicted deformation amount and the vehicle deformation degree.

[0160] Specifically, since the corresponding relationship between the deformation amount and the deformation degree is preset, the method of determining the collision degree based on the predicted deformation amount and the vehicle deformation degree can be analogous to the specific implementation manner of determining the collision degree based on the vehicle deformation degree and the deformation degree of the anti-collision pad in step 303 above, and will not be elaborated here.

[0161] In the above implementation manner, in the case where the deformation degree of the anti-collision pad is not within the predicted deformation range, the predicted deformation amount of the anti-collision pad body is determined based on the video data after the collision, and in the case where the deformation degree of the anti-collision pad matches the predicted deformation amount, the collision degree is directly determined based on the deformation degree of the anti-collision pad and the predicted deformation amount. In this way, the reason for the mismatch between the deformation degree of the anti-collision pad and the vehicle deformation degree can be determined by verifying the deformation degree of the anti-collision pad, which can help avoid the influence of unreasonable vehicle deformation on the determination of the collision degree, and further help ensure the accuracy of the finally determined collision degree.

[0162] Based on the above implementation manner, further, continue to refer to Figure 6 , step 407, after determining whether the deformation degree of the anti-collision pad matches the predicted deformation amount, the following steps are further included:

[0163] Step 409, in the case where the collision deformation degree does not match the predicted deformation amount, determine whether the predicted deformation amount matches the predicted deformation range.

[0164] Specifically, since the corresponding relationship between the deformation amount and the deformation degree is preset, the method of determining whether the predicted deformation amount matches the predicted deformation range can be analogous to the specific implementation manner of determining whether the deformation degree of the anti-collision pad is within the predicted deformation range in step 404 above, and will not be elaborated here.

[0165] Step 410, in the case where the predicted deformation amount matches the predicted deformation range, determine the collision degree based on the predicted deformation amount and the vehicle deformation degree.

[0166] Optionally, in the case where the predicted deformation amount does not match the predicted deformation range, the collision degree can be directly determined based on the predicted deformation amount.

[0167] In the above embodiments, since it is possible to further determine the collision degree based on the matching relationship between the predicted deformation amount and the predicted deformation range when the collision deformation degree does not match the predicted deformation amount, this can help accurately determine the reference value of the vehicle deformation degree in the process of determining the collision degree, and further help improve the accuracy of the collision degree while ensuring a high accuracy of the determined collision degree.

[0168] In some embodiments, referring to Figure 7 , step 201, monitoring the detection data collected by the collision detection module includes the following steps:

[0169] Step 501, monitoring whether the detection data fluctuates.

[0170] Specifically, when other objects collide with the intelligent anti-collision pad, the anti-collision pad body may deform, and the detection data can reflect the deformation of the anti-collision pad body. Therefore, collision detection can be performed based on whether the detection data fluctuates.

[0171] Step 502, when it is monitored that the detection data fluctuates, determining the waveform characteristics corresponding to the detection data.

[0172] Among them, the waveform characteristics may include factors actually related to the waveform such as the fluctuation amplitude, the peak size, the fluctuation duration, and the difference between the detection data before and after the fluctuation.

[0173] Step 503, determining whether the intelligent anti-collision pad has collided based on the waveform characteristics.

[0174] Specifically, in the actual use process, it is found that in addition to colliding with the vehicle, some special situations (such as: a flying object hitting the anti-collision pad body) may also cause the detection data to fluctuate. In order to improve the accuracy of collision judgment, it is necessary to take appropriate measures to distinguish the fluctuations caused by vehicle collisions from the fluctuations caused by other situations. In this embodiment, considering that the waveform characteristics of fluctuations caused by different situations may be different, in order to more accurately judge whether the intelligent anti-collision pad has collided, the waveform characteristics are used to determine whether the anti-collision pad has collided.

[0175] In an example, determining whether the intelligent anti-collision pad has collided based on the waveform characteristics includes: determining whether the fluctuation amplitude is greater than a preset amplitude threshold; when the fluctuation amplitude is greater than the preset amplitude threshold, further determining whether the fluctuation duration is greater than a preset duration threshold; when the fluctuation duration is greater than the preset fluctuation duration threshold, determining that the intelligent anti-collision pad has collided.

[0176] Further, when the duration of the fluctuation is less than a preset fluctuation duration threshold, further determine whether the difference between the detection data before and after the fluctuation is greater than a preset difference threshold; when the difference between the detection data before and after the fluctuation is greater than the preset difference threshold, it is determined that the intelligent anti-collision pad has collided.

[0177] In the above embodiment, since it is possible to further determine whether the intelligent collision pad has collided based on the fluctuation of the detection data when the detection data fluctuates, this can help reduce the influence of other factors other than the collision on the collision monitoring, and thus can help improve the accuracy of the collision monitoring.

[0178] Based on the above technical solution, further, the collision detection module includes a first detection component and a second detection component. Correspondingly, the detection data includes first detection data corresponding to the first detection component and second detection data corresponding to the second detection component.

[0179] In one example, the first detection component and the second detection component are divided based on the installation direction of the detection component. For example: the first detection component is installed on the front of the anti-collision pad body, that is, the side facing the vehicle driving direction during use; the second detection component is installed on the side of the anti-collision pad body, that is, the side perpendicular to the vehicle driving direction during use. At this time, the first detection component is the main detection component, and the second detection component is used to assist the first detection component to function.

[0180] In actual implementation, the number of the first detection component and the second detection component can be one or multiple. For example: when the number of the first detection components includes two or more, the detection data collected by each first detection component is fused to obtain the first detection data.

[0181] Reference Figure 8 , step 502, when the detection data fluctuates, determine the waveform characteristics of the detection data, including the following steps:

[0182] Step 601, when the first detection data and / or the second detection data fluctuates, respectively determine the first waveform characteristic of the first detection data and the second waveform characteristic of the second detection data.

[0183] Specifically, when any of the first detection data and the second detection data fluctuates, the first waveform characteristic and the second waveform characteristic are respectively determined.

[0184] Correspondingly, step 503, determine whether the intelligent anti-collision pad has collided based on the waveform characteristics, including the following steps:

[0185] Step 602, determine the collision probability based on the first waveform characteristic.

[0186] Optionally, determining the collision probability based on the first waveform feature includes: determining the collision probability based on the difference between the first fluctuation feature and the corresponding preset feature threshold.

[0187] Wherein, the corresponding relationship between the difference and the collision probability is preset. Generally speaking, the collision probability is positively correlated with the difference. For example: if the first fluctuation feature includes the fluctuation amplitude, the larger the difference between the fluctuation amplitude and the fluctuation amplitude threshold, the more serious the deformation of the anti-collision pad body, and the corresponding collision probability is greater.

[0188] Furthermore, when the first waveform feature includes more than two, the collision probabilities corresponding to different first waveform features can be calculated respectively, and the collision probability is comprehensively determined based on the collision probabilities corresponding to each first waveform feature. For example: the collision probabilities corresponding to each first waveform feature can be weighted and summed according to the weights of each first waveform feature to obtain the collision probability. Among them, the weight corresponding to the first waveform feature can be preset based on factors such as the priority of the first waveform feature in the judgment process and the importance of the first wave feature.

[0189] It should be added that when the first waveform feature includes more than two, there may be a situation where some first waveform features are less than the corresponding preset feature thresholds, that is, when the difference between the feature value and the preset feature threshold is negative. At this time, a reference probability (such as: 50%) can be set in the process of calculating the collision probability. For the first waveform feature whose feature value is greater than the corresponding preset feature threshold, the collision probability corresponding to the first waveform feature needs to be determined above the reference probability, that is, the corresponding probability is increased on the basis of the reference value; for the first waveform feature whose feature value is less than the corresponding preset feature threshold, the collision probability corresponding to the first waveform feature needs to be determined below the reference probability, that is, the corresponding probability is reduced on the basis of the reference value, so as to improve the accuracy of anomaly judgment.

[0190] Step 603, determine whether the collision probability is less than the collision probability threshold.

[0191] In one example, the collision probability threshold is 70%.

[0192] Step 604, when the collision probability is less than the collision probability threshold, determine whether there is a risk feature in the second waveform feature.

[0193] Among them, the risk feature refers to the feature in the waveform feature that indicates that there may be no collision.

[0194] Optionally, determining whether there is a risk feature in the second waveform feature includes: determining whether the second fluctuation feature is less than the corresponding preset feature threshold; if so, determine that there is a risk feature; if not, determine that there is no risk feature.

[0195] Further, when there are more than two second waveform features, different second waveform features can be compared with corresponding preset feature thresholds respectively, and the second fluctuation features with feature values less than the corresponding preset feature thresholds are determined as risks. For example, if the waveform feature includes the fluctuation amplitude, it can be determined whether the fluctuation amplitude indicated by the second waveform feature is greater than the preset fluctuation amplitude threshold; if so, it is determined that the abnormal factor includes the fluctuation amplitude.

[0196] Step 605, in the case of the existence of risk features, perform anomaly verification on the risk features based on the first waveform feature.

[0197] In an example, performing anomaly verification on the risk features based on the first waveform feature includes: determining whether the risk feature in the first waveform feature is less than the corresponding feature verification value; if so, generating an anomaly verification result indicating that the risk feature is abnormal; if not, generating an anomaly verification result indicating that the risk feature is not abnormal.

[0198] Among them, the feature verification value is less than the preset feature threshold corresponding to the risk feature. For example, the feature verification value is 60% of the preset feature value.

[0199] The principle of the above anomaly verification of the risk features is: in the case where the risk feature is too small, it indicates that the probability of a collision indicated by the risk feature is relatively low, and at this time, it can be determined that the risk feature is abnormal.

[0200] Optionally, in the case where there are no risk features, it can be directly determined that the intelligent anti-collision pad has collided.

[0201] Step 606, in the case where the verification result indicates that the risk feature is abnormal, determine that the intelligent anti-collision pad has not collided.

[0202] Optionally, in the case where the verification result indicates that the risk feature is not abnormal, it can be directly determined that the intelligent anti-collision pad has collided.

[0203] In the above embodiments, the waveform features corresponding to the detection data collected by different detection components can be combined to comprehensively determine whether the intelligent anti-collision pad has collided, which can help improve the accuracy of collision monitoring.

[0204] At the same time, since in the case where the collision probability is determined to be relatively low based on the first waveform feature, risk features are determined based on the second waveform feature, and the first waveform feature is used to verify the risk features, and only when the verification result indicates that the risk feature is abnormal, it is determined that the intelligent anti-collision pad has not collided, which can reduce the influence of other factors other than collisions on collision monitoring, and thus can help improve the accuracy of collision monitoring.

[0205] In the above-described embodiments, further, with continued reference to Figure 8 , step 604, performing anomaly verification on the risk features based on the first waveform feature, including the following steps:

[0206] Step 607, when the verification result indicates that there is no anomaly in the risk feature, determining the collision feature in the first waveform feature.

[0207] Wherein, the collision feature refers to the feature in the waveform feature indicating that a collision may exist.

[0208] Optionally, determining the collision feature in the first waveform feature includes: determining the first waveform feature in the first waveform feature that is greater than the corresponding preset feature threshold as the collision feature. For example: when the fluctuation amplitude in the first waveform feature is greater than the preset change amplitude threshold, the fluctuation amplitude is the collision feature at this time; when the fluctuation duration is less than the preset fluctuation duration threshold, the fluctuation duration is not the collision feature at this time.

[0209] Step 608, performing collision verification on the collision feature based on the second waveform feature.

[0210] In one example, performing verification on the collision feature based on the second waveform feature includes: determining whether the risk feature in the second waveform feature is greater than the corresponding verification value; if so, generating a collision verification result indicating that there is a collision in the collision feature; if not, generating a verification result indicating that there is no collision in the collision feature.

[0211] Wherein, the feature verification value is less than the preset feature threshold corresponding to the collision feature. For example: the feature verification value is 60% of the preset feature value.

[0212] Step 609, when the collision verification result indicates that there is a collision in the collision feature, determining that the intelligent anti-collision pad has collided.

[0213] Optionally, when the collision verification result indicates that there is no collision in the collision feature, determining that the intelligent collision pad has not collided.

[0214] In the above-described embodiments, since when the anomaly verification result indicates that there is no anomaly in the risk feature, the collision feature in the first waveform feature will be further verified for collision based on the second waveform feature to finally determine whether the intelligent anti-collision pad has collided. In this way, the first waveform feature and the second waveform feature can be fully combined to judge whether the intelligent anti-collision pad has collided, which can further improve the accuracy of collision monitoring.

[0215] It should be understood that although the steps in the flowchart of the accompanying drawings are shown sequentially according to the indication of the arrows, these steps are not necessarily executed sequentially in the order indicated by the arrows. Unless there is a clear indication in this document, there is no strict order restriction for the execution of these steps, and they can be executed in other orders.

[0216] The above are only partial embodiments of the present application. It should be noted that for those of ordinary skill in the art, without departing from the principle of the present application, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present application.

Claims

1. An intelligent anti-collision pad monitoring and alarming method, characterized in that, In a controller for an intelligent anti-collision pad, the intelligent anti-collision pad further includes a collision detection module, a video monitoring module, and an alarm module that are signal-connected to the controller. The collision detection module is used to detect the deformation of the anti-collision pad body, and the video monitoring module is used to collect image information of the area where the anti-collision pad body is located. The method includes: Monitoring the detection data collected by the collision detection module; When it is detected based on the detection data that the intelligent anti-collision pad has collided, determining the collision time corresponding to this collision and the collision detection data corresponding to the collision time; Determining the collision video data corresponding to this collision from the monitoring data collected by the video monitoring module based on the collision time; Combining the collision video data and the collision detection data to determine the collision degree corresponding to this collision; Generating a collision alarm message based on the collision degree and controlling the alarm module to output the collision alarm message; The collision video data includes post-collision video data. Determining the collision degree corresponding to this collision based on the collision video data and the detection data includes: Determining the vehicle deformation degree of the target vehicle corresponding to this collision based on the post-collision video data; Determining the anti-collision pad deformation degree corresponding to this collision based on the collision detection data; Determining the collision degree based on the vehicle deformation degree and the anti-collision pad deformation degree; The collision video data further includes pre-collision video data. Before determining the collision degree based on the vehicle deformation degree and the anti-collision pad deformation degree, it further includes: Determining the vehicle parameters of the target vehicle based on the pre-collision video data; Determining the prediction confidence corresponding to the vehicle deformation degree based on the vehicle parameters; Predicting the deformation degree of the anti-collision pad body based on the prediction confidence and the vehicle deformation degree to obtain a predicted deformation range; Determining whether the anti-collision pad deformation degree is within the predicted deformation range; When the anti-collision pad deformation degree is within the predicted deformation range, determining the collision degree based on the vehicle deformation degree and the anti-collision pad deformation degree.

2. The method according to claim 1, wherein After determining whether the anti-collision pad deformation degree is within the predicted deformation range, it further includes: When the anti-collision pad deformation degree is not within the predicted deformation range, determining the predicted deformation amount of the anti-collision pad body based on the post-collision video data; Determining whether the anti-collision pad deformation degree matches the predicted deformation amount; When the anti-collision pad deformation degree matches the predicted deformation amount, determining the collision degree based on the anti-collision pad deformation degree and the predicted deformation amount.

3. The method according to claim 2, characterized in that, After determining whether the anti-collision pad deformation degree matches the predicted deformation amount, it further includes: When the anti-collision pad deformation degree does not match the predicted deformation amount, determining whether the predicted deformation amount matches the predicted deformation range; When the predicted deformation amount matches the predicted deformation range, determining the collision degree based on the predicted deformation amount and the vehicle deformation degree.

4. The method according to claim 1, wherein The monitoring the detection data collected by the collision detection module includes: Monitor whether the detection data fluctuates; When it is monitored that the detection data fluctuates, determine the waveform characteristics corresponding to the detection data; Based on the waveform characteristics, determine whether the intelligent anti-collision pad has collided.

5. The method according to claim 4, wherein The collision detection module includes a first detection component and a second detection component. The detection data includes first detection data corresponding to the first detection component and second detection data corresponding to the second detection component. When it is monitored that the detection data fluctuates, determining the waveform characteristics of the detection data includes: When it is monitored that the first detection data and / or the second detection data fluctuates, respectively determine the first waveform characteristics of the first detection data and the second waveform characteristics of the second detection data; The determining whether the intelligent anti-collision pad has collided based on the waveform characteristics includes: Determine the collision probability based on the first waveform characteristics; Determine whether the collision probability is less than the collision probability threshold; When the collision probability is less than the collision probability threshold, determine whether there is a risk feature in the second waveform characteristics; When there is the risk feature, perform anomaly verification on the risk feature based on the first waveform characteristics; When the anomaly verification result indicates that the risk feature is abnormal, determine that the intelligent anti-collision pad has not collided.

6. The method according to claim 5, wherein After performing the anomaly verification on the risk feature based on the first waveform characteristics, it further includes: When the anomaly verification result indicates that the risk feature is not abnormal, determine the collision feature in the first waveform characteristics; Perform collision verification on the collision feature based on the second waveform characteristics; When the collision verification result indicates that the collision feature has collided, determine that the intelligent anti-collision pad has collided.

7. An intelligent anti-collision pad, characterized in that, The intelligent anti-collision pad includes a controller, a collision detection module, a video monitoring module, and an alarm module that are signal-connected to the controller. The collision detection module is used to detect the deformation of the anti-collision pad body, and the video monitoring module is used to collect image information of the area where the anti-collision pad body is located; The controller is used to execute the intelligent anti-collision pad monitoring and alarm method according to any one of claims 1 to 6, and output a collision alarm message through the alarm module.

8. An intelligent anti-collision cushion alarm system, characterized in that, The system includes the intelligent anti-collision pad according to claim 7, and a background server that is communicatively connected to the intelligent anti-collision pad; The intelligent anti-collision pad is used to generate a collision alarm message and send it to the background server; The background server is used to process the collision alarm message.

Images