Vehicle event fusion method, device, equipment and readable storage medium

Abstract

The present invention provides a vehicle event fusion method, device, equipment and readable storage medium. The method includes: obtaining a first vehicle event from a first queue and obtaining a second vehicle event from a second queue; obtaining a distance difference based on the occurrence locations of the first vehicle event and the second vehicle event, obtaining a time difference based on the generation moments of the first vehicle event and the second vehicle event, and obtaining a similarity value based on the event types of the first vehicle event and the second vehicle event; calculating a matching degree based on the distance difference, time difference and similarity value; if the matching degree is greater than a preset threshold, performing event fusion on the first vehicle event and the second vehicle event. Through the present invention, the matching degree of two vehicle events is calculated. When the matching degree is greater than the preset threshold, it indicates that the two vehicle events are essentially the same vehicle event, thereby performing event fusion on the two vehicle events, so that the final vehicle event is more complete and more accurate.

Description

Technical Field

[0001] The present invention relates to the field of data fusion technology, and in particular to a vehicle event fusion method, device, equipment and readable storage medium. Background Art

[0002] With the rapid development of the national economy, China's highway network has grown considerably. Due to the high speeds and large number of vehicles on highways, accidents can be serious. Driver error is often the primary cause of accidents, necessitating monitoring and identification of driving behavior to provide timely warnings.

[0003] Currently, driving behavior monitoring and identification is primarily based on sensor-based perception of driving data, which in turn generates corresponding vehicle events. However, different sensor types may generate different content in the generated vehicle events, and the accuracy of the same content may vary. For example, a vehicle event generated by a Type A sensor includes information related to the vehicle's appearance, such as the license plate and vehicle color, while a vehicle event generated by a Type B sensor does not. A Type A sensor may determine a more accurate trajectory than a Type B sensor, but a Type B sensor may determine a more accurate location and time of occurrence than a Type A sensor.

[0004] Therefore, in order to improve the integrity and accuracy of the vehicle events finally generated, a solution for fusing vehicle events generated by different sensing sources is urgently needed. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides a vehicle event fusion method, device, equipment and readable storage medium.

[0006] In a first aspect, the present invention provides a vehicle event fusion method, the vehicle event fusion method comprising:

[0007] Get the first vehicle event from the first queue and get the second vehicle event from the second queue;

[0008] Obtaining a distance difference based on a location of occurrence of the first vehicle event and a location of occurrence of the second vehicle event, obtaining a time difference based on a time instant of generation of the first vehicle event and a time instant of generation of the second vehicle event, and obtaining a similarity value based on an event type of the first vehicle event and an event type of the second vehicle event;

[0009] Calculate the matching degree based on the distance difference, time difference and similarity value;

[0010] If the matching degree is greater than a preset threshold, event fusion is performed on the first vehicle event and the second vehicle event.

[0011] Optionally, the step of calculating the matching degree according to the distance difference, the time difference, and the similarity value includes:

[0012] The distance difference, time difference and similarity value are input into the matching degree calculation formula to obtain the theoretical matching degree. The matching degree calculation formula is:

[0013]

[0014] Wherein, r is the theoretical matching degree, α is the similarity value, t is the time difference, T is the first preset value, m is the distance difference, and M is the second preset value. When t is greater than T or m is greater than M, r is 0.

[0015] A matching degree is obtained based on the theoretical matching degree.

[0016] Optionally, the step of obtaining the matching degree based on the theoretical matching degree includes:

[0017] Obtaining weather types corresponding to the generation times of the first vehicle event and the second vehicle event;

[0018] The theoretical matching degree is corrected based on the characteristic value corresponding to the weather type to obtain a matching degree.

[0019] Optionally, the step of correcting the theoretical matching degree based on the characteristic value corresponding to the weather type to obtain the matching degree includes:

[0020] The characteristic value corresponding to the weather type is multiplied by the theoretical matching degree, and the obtained product is used as the matching degree. The greater the negative impact of the weather type on driving, the lower the corresponding characteristic value.

[0021] Optionally, before the step of obtaining the first vehicle event from the first queue and the step of obtaining the second vehicle event from the second queue, the method further includes:

[0022] Generate a first type of vehicle event according to the first type of perception data of the first sensor, and store the first type of vehicle events into a first queue in chronological order of generation time;

[0023] Generate a second type of vehicle event according to the second type of perception data of the second sensor, and store the second type of vehicle events into a second queue in chronological order of generation time;

[0024] The sensing areas of the first sensor and the second sensor overlap.

[0025] In a second aspect, the present invention further provides a vehicle event fusion device, the vehicle event fusion device comprising:

[0026] an acquisition module, configured to acquire a first vehicle event from the first queue and a second vehicle event from the second queue;

[0027] a calculation module, configured to obtain a distance difference based on a location of occurrence of the first vehicle event and a location of occurrence of the second vehicle event, obtain a time difference based on a time instant of generation of the first vehicle event and a time instant of generation of the second vehicle event, and obtain a similarity value based on an event type of the first vehicle event and an event type of the second vehicle event; and calculate a matching degree based on the distance difference, time difference, and similarity value;

[0028] The fusion module is configured to perform event fusion on the first vehicle event and the second vehicle event if the matching degree is greater than a preset threshold.

[0029] Optionally, the computing module is configured to:

[0030] The distance difference, time difference and similarity value are input into the matching degree calculation formula to obtain the theoretical matching degree. The matching degree calculation formula is:

[0031]

[0032] Where r is the theoretical matching degree, α is the similarity value, t is the time difference, T is the first preset value, m is the distance difference, and M is the second preset value. When t is greater than T or m is greater than M, r is 0.

[0033] A matching degree is obtained based on the theoretical matching degree.

[0034] Optionally, the computing module is configured to:

[0035] Obtaining weather types corresponding to the generation times of the first vehicle event and the second vehicle event;

[0036] The theoretical matching degree is corrected based on the characteristic value corresponding to the weather type to obtain a matching degree.

[0037] In a third aspect, the present invention also provides a vehicle event fusion device, which includes a processor, a memory, and a vehicle event fusion program stored on the memory and executable by the processor, wherein when the vehicle event fusion program is executed by the processor, the steps of the vehicle event fusion method described above are implemented.

[0038] In a fourth aspect, the present invention further provides a readable storage medium, on which a vehicle event fusion program is stored, wherein when the vehicle event fusion program is executed by a processor, the steps of the vehicle event fusion method described above are implemented.

[0039] In the present invention, a first vehicle event is obtained from a first queue, and a second vehicle event is obtained from a second queue; a distance difference is obtained based on the occurrence location of the first vehicle event and the occurrence location of the second vehicle event, a time difference is obtained based on the generation time of the first vehicle event and the generation time of the second vehicle event, and a similarity value is obtained based on the event type of the first vehicle event and the event type of the second vehicle event; a matching degree is calculated based on the distance difference, time difference, and similarity value; if the matching degree is greater than a preset threshold, the first vehicle event and the second vehicle event are subjected to event fusion. Through the present invention, the matching degree of two vehicle events is calculated. When the matching degree is greater than the preset threshold, it indicates that the two vehicle events are essentially the same vehicle event, thereby performing event fusion on the two vehicle events, making the final vehicle event more complete and more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1 This is a flow chart of an embodiment of a vehicle event fusion method according to the present invention;

[0041] Figure 2 This is a flow chart of another embodiment of the vehicle event fusion method of the present invention;

[0042] Figure 3 for Figure 1 Detailed flow chart of step S30;

[0043] Figure 4 for Figure 3 Detailed flow chart of step S302;

[0044] Figure 5 This is a schematic diagram of the functional modules of an embodiment of a vehicle event fusion device of the present invention;

[0045] Figure 6 Schematic diagram of the hardware structure of the vehicle event fusion device involved in the embodiment of the present invention.

[0046] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0048] In a first aspect, an embodiment of the present invention provides a vehicle event fusion method.

[0049] In one embodiment, referring to Figure 1 , Figure 1 FIG. 1 is a flow chart of an embodiment of the vehicle event fusion method of the present invention. Figure 1 As shown, the vehicle event fusion method includes:

[0050] Step S10, obtaining a first vehicle event from the first queue and obtaining a second vehicle event from the second queue;

[0051] In this embodiment, vehicle events generated based on sensor data of different types are stored in the first queue and the second queue, respectively. For example, vehicle events generated based on sensor data from a grating sensor are stored in the first queue, while vehicle events generated based on camera sensor data are stored in the second queue. Based on this, the first vehicle event can be obtained from the first queue, and the second vehicle event can be obtained from the second queue.

[0052] Furthermore, in one embodiment, referring to Figure 2 , Figure 2 FIG. 1 is a flow chart of another embodiment of the vehicle event fusion method of the present invention. Figure 2 As shown, before step S10, the following steps are also included:

[0053] Step S00: Generate a first type of vehicle event based on the first type of perception data of the first sensor, and store the first type of vehicle event in a first queue in chronological order of generation; generate a second type of vehicle event based on the second type of perception data of the second sensor, and store the second type of vehicle event in a second queue in chronological order of generation; wherein the perception areas of the first sensor and the second sensor overlap.

[0054] In this embodiment, taking the first sensor as a grating sensor as an example, trajectory data is determined based on the grating data collected by the grating sensor, a first type of vehicle event is generated based on the trajectory data, and then the first type of vehicle event is stored in the first queue in the order of generation time. Specifically:

[0055] Based on the instantaneous vehicle speed in the trajectory data, if the vehicle speed exceeds the maximum speed limit for n consecutive reporting periods (for example, every 200ms), an overspeed event is generated; if the vehicle speed is below the minimum speed limit for n consecutive reporting periods, an underspeed event is generated. Where n is a preset value.

[0056] Based on the instantaneous vehicle speed and location in the trajectory data, if the vehicle speed is 0 km / h for m consecutive reporting periods and the location does not change, a parking violation event is generated. If the vehicle is parked in the emergency lane, an emergency lane occupation event is generated. Where m is a preset value.

[0057] Based on the vehicle position in the trajectory data, if the vehicle changes lanes continuously for at least two times within a preset time, a continuous lane change event is generated.

[0058] The following distance is calculated based on the vehicle speed and position in the trajectory data. If the following distance is less than the minimum following distance corresponding to the vehicle speed and visibility, a following too close event is generated.

[0059] Similarly, for example, if the second sensor is a license plate recognition camera or multi-line lidar, a second type of vehicle event is generated based on the image data or radar perception data collected by the license plate recognition camera or multi-line lidar. These second type of vehicle events are then stored in the second queue in chronological order. Subsequently, when retrieving vehicle events from the first and second queues, the events can be retrieved in the same order from both queues.

[0060] Step S20, obtaining a distance difference based on the occurrence location of the first vehicle event and the occurrence location of the second vehicle event, obtaining a time difference based on the generation time of the first vehicle event and the generation time of the second vehicle event, and obtaining a similarity value based on the event type of the first vehicle event and the event type of the second vehicle event;

[0061] In this embodiment, the absolute values ​​of the locations are subtracted to obtain the distance difference, and the absolute values ​​of the times of occurrence are subtracted to obtain the time difference. Similarity values ​​corresponding to each event type are preset, ranging from 0 to 1. For example, the similarity value corresponding to low speed and speeding is 0, the similarity value corresponding to low speed and parking is 0.5, and the similarity value of two events of the same type is 1. This is only a schematic illustration of the similarity values ​​corresponding to each event type. The specific similarity values ​​corresponding to each event type can be flexibly set according to actual needs.

[0062] Step S30, calculating the matching degree based on the distance difference, time difference and similarity value;

[0063] In this embodiment, the matching degree is obtained based on the distance difference, time difference and similarity value between the first vehicle event and the second vehicle event, combined with a preset quantization method. The preset quantization method follows the following rules:

[0064] The larger the distance difference, the larger the time difference, and the smaller the similarity value, the smaller the matching degree.

[0065] Furthermore, in one embodiment, referring to Figure 3 , Figure 3 for Figure 1 Detailed flow chart of step S30 in FIG. Figure 3 As shown, step S30 includes:

[0066] Step S301: Input the distance difference, time difference, and similarity value into a matching degree calculation formula to obtain a theoretical matching degree. The matching degree calculation formula is:

[0067]

[0068] Where r is the theoretical matching degree, α is the similarity value, t is the time difference, T is the first preset value, m is the distance difference, and M is the second preset value. When t is greater than T or m is greater than M, r is 0.

[0069] In this embodiment, the distance difference, time difference, and similarity value are input into the matching degree calculation formula to calculate the theoretical matching degree. Furthermore, when the time difference is greater than a first preset value or the distance difference is greater than a second preset value, this indicates that the first vehicle event and the second vehicle event are located at a greater distance or generated at a greater distance, and therefore are unlikely to be the same vehicle event. In this case, the theoretical matching degree between the first and second vehicle events is directly determined to be 0. The first and second preset values ​​are set based on actual needs.

[0070] Step S302: Obtain a matching degree based on the theoretical matching degree.

[0071] In this embodiment, after the theoretical matching degree is obtained based on step S301, the theoretical matching degree may be directly used as the matching degree, or the theoretical matching degree may be further corrected to obtain the matching degree.

[0072] Furthermore, in one embodiment, referring to Figure 4 , Figure 4 for Figure 3 Detailed flow chart of step S302 in FIG. Figure 4 As shown, step S302 includes:

[0073] Step S3021, obtaining the weather type corresponding to the generation time of the first vehicle event and the second vehicle event;

[0074] Step S3022: Correct the theoretical matching degree based on the characteristic value corresponding to the weather type to obtain a matching degree.

[0075] In this embodiment, considering that the weather will affect the accuracy of the perception data collected by the sensor, it is necessary to correct the theoretical matching degree according to the weather type corresponding to the generation time of the first vehicle event and the second vehicle event, specifically, to correct the theoretical matching degree according to the characteristic value corresponding to the weather type.

[0076] Furthermore, in one embodiment, step S3022 includes:

[0077] The characteristic value corresponding to the weather type is multiplied by the theoretical matching degree, and the obtained product is used as the matching degree, wherein the greater the negative impact of the weather type on driving, the lower the corresponding characteristic value.

[0078] In this embodiment, characteristic values ​​corresponding to different weather types are set based on the degree of negative impact they have on driving. For example, a clear day corresponds to a characteristic value of 1, a rainy day corresponds to a characteristic value of 0.6, a snowy day corresponds to a characteristic value of 0.5, and a foggy day corresponds to a characteristic value of 0.3. It should be noted that this is merely a schematic illustration of the characteristic values ​​corresponding to the weather types, and the characteristic values ​​corresponding to the weather types can be flexibly set according to actual needs.

[0079] Step S40: If the matching degree is greater than a preset threshold, event fusion is performed on the first vehicle event and the second vehicle event.

[0080] In this embodiment, the preset threshold is set according to actual needs. If the matching degree is greater than the preset threshold, it means that the first vehicle event and the second vehicle event are the same vehicle event, so the first vehicle event and the second vehicle event can be fused.

[0081] For example, compared with the second vehicle event, the first vehicle event also includes vehicle driving trajectory data, and compared with the first vehicle event, the second vehicle event also includes vehicle appearance data. Therefore, the final vehicle event obtained by event fusion contains more complete data than the first vehicle event and the second vehicle event.

[0082] For another example, the vehicle position of the first vehicle event is more accurate than that of the second vehicle event, and the speed of the second vehicle event is more accurate than that of the first vehicle event. In this way, the vehicle position contained in the final vehicle event obtained by event fusion shall be based on the vehicle position contained in the first vehicle event, and the speed contained shall be based on the speed contained in the second vehicle event, thereby making the data contained in the final vehicle event more accurate.

[0083] In this embodiment, a first vehicle event is obtained from the first queue, and a second vehicle event is obtained from the second queue; a distance difference is obtained based on the occurrence location of the first vehicle event and the occurrence location of the second vehicle event, a time difference is obtained based on the generation time of the first vehicle event and the generation time of the second vehicle event, and a similarity value is obtained based on the event type of the first vehicle event and the event type of the second vehicle event; a matching degree is calculated based on the distance difference, time difference, and similarity value; if the matching degree is greater than a preset threshold, the first vehicle event and the second vehicle event are subjected to event fusion. Through this embodiment, the matching degree of two vehicle events is calculated. When the matching degree is greater than the preset threshold, it indicates that the two vehicle events are essentially the same vehicle event, thereby performing event fusion on the two vehicle events, making the final vehicle event more complete and more accurate.

[0084] In a second aspect, an embodiment of the present invention further provides a vehicle event fusion device.

[0085] In one embodiment, referring to Figure 5 , Figure 5 This is a functional module diagram of an embodiment of the vehicle event fusion device of the present invention. Figure 5 As shown, the vehicle event fusion device includes:

[0086] An acquisition module 10 is configured to acquire a first vehicle event from the first queue and a second vehicle event from the second queue;

[0087] a calculation module 20 configured to obtain a distance difference based on the occurrence location of the first vehicle event and the occurrence location of the second vehicle event, obtain a time difference based on the generation time of the first vehicle event and the generation time of the second vehicle event, and obtain a similarity value based on the event type of the first vehicle event and the event type of the second vehicle event; and calculate a matching degree based on the distance difference, time difference, and similarity value;

[0088] The fusion module 30 is configured to perform event fusion on the first vehicle event and the second vehicle event if the matching degree is greater than a preset threshold.

[0089] Furthermore, in one embodiment, the calculation module is configured to:

[0090] The distance difference, time difference and similarity value are input into the matching degree calculation formula to obtain the theoretical matching degree. The matching degree calculation formula is:

[0091]

[0092] Where r is the theoretical matching degree, α is the similarity value, t is the time difference, T is the first preset value, m is the distance difference, and M is the second preset value. When t is greater than T or m is greater than M, r is 0.

[0093] A matching degree is obtained based on the theoretical matching degree.

[0094] Furthermore, in one embodiment, the calculation module 20 is configured to:

[0095] Obtaining weather types corresponding to the generation times of the first vehicle event and the second vehicle event;

[0096] The theoretical matching degree is corrected based on the characteristic value corresponding to the weather type to obtain a matching degree.

[0097] Furthermore, in one embodiment, the calculation module 20 is configured to:

[0098] The characteristic value corresponding to the weather type is multiplied by the theoretical matching degree, and the obtained product is used as the matching degree, wherein the greater the negative impact of the weather type on driving, the lower the corresponding characteristic value.

[0099] Furthermore, in one embodiment, the vehicle event fusion device further includes a generation module, configured to:

[0100] Generate a first type of vehicle event according to the first type of perception data of the first sensor, and store the first type of vehicle events into a first queue in chronological order of generation time;

[0101] Generate a second type of vehicle event according to the second type of perception data of the second sensor, and store the second type of vehicle events into a second queue in chronological order of generation time;

[0102] The sensing areas of the first sensor and the second sensor overlap.

[0103] Among them, the functional implementation of each module in the above-mentioned vehicle event fusion device corresponds to the various steps in the above-mentioned vehicle event fusion method embodiment, and its functions and implementation processes will not be repeated here one by one.

[0104] In a third aspect, an embodiment of the present invention provides a vehicle event fusion device, which may be a device with data processing capabilities, such as a personal computer (PC), a laptop computer, or a server.

[0105] Reference Figure 6 , Figure 6 Schematic diagram of the hardware structure of the vehicle event fusion device involved in the embodiment of the present invention. In the embodiment of the present invention, the vehicle event fusion device may include a processor 1001 (e.g., a central processing unit (CPU)), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Among them, the communication bus 1002 is used to realize the connection and communication between these components; the user interface 1003 may include a display screen (Display) and an input unit such as a keyboard (Keyboard); the network interface 1004 may optionally include a standard wired interface or a wireless interface (such as a wireless fidelity WIreless-FIdelity, WI-FI interface); the memory 1005 may be a high-speed random access memory (RAM) or a stable memory (non-volatile memory), such as a disk storage. The memory 1005 may also be a storage device independent of the aforementioned processor 1001. It will be understood by those skilled in the art that the hardware structure shown in Figure n does not constitute a limitation of the present invention, and may include more or fewer components than shown, or combine certain components, or arrange components differently.

[0106] Continue to refer to Figure 6 , Figure 6 The memory 1005, which is a computer storage medium, may include an operating system, a network communication module, a user interface module, and a vehicle event fusion program. The processor 1001 may call the vehicle event fusion program stored in the memory 1005 and execute the vehicle event fusion method provided in the embodiment of the present invention.

[0107] In a fourth aspect, an embodiment of the present invention further provides a readable storage medium.

[0108] The readable storage medium of the present invention stores a vehicle event fusion program, wherein when the vehicle event fusion program is executed by a processor, the steps of the vehicle event fusion method described above are implemented.

[0109] Among them, the method implemented when the vehicle event fusion program is executed can refer to the various embodiments of the vehicle event fusion method of the present invention, and will not be repeated here.

[0110] It should be noted that, in this document, the terms "comprises," "includes," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, method, article, or system comprising a series of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or system. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or system comprising the element.

[0111] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0112] Through the description of the above embodiments, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus the necessary general hardware platform, or of course by hardware, but in many cases the former is a better embodiment. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes a number of instructions for enabling a terminal device to execute the methods described in various embodiments of the present invention.

[0113] The above are only preferred embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention description and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A vehicle event fusion method, characterized in that: The vehicle event fusion method includes: Get the first vehicle event from the first queue and get the second vehicle event from the second queue; Obtaining a distance difference based on a location of occurrence of the first vehicle event and a location of occurrence of the second vehicle event, obtaining a time difference based on a time instant of generation of the first vehicle event and a time instant of generation of the second vehicle event, and obtaining a similarity value based on an event type of the first vehicle event and an event type of the second vehicle event; Calculate the matching degree based on the distance difference, time difference and similarity value; If the matching degree is greater than a preset threshold, performing event fusion on the first vehicle event and the second vehicle event; The step of calculating the matching degree according to the distance difference, the time difference and the similarity value comprises: The distance difference, time difference and similarity value are input into the matching degree calculation formula to obtain the theoretical matching degree. The matching degree calculation formula is: Among them, r is the theoretical matching degree, is the similarity value, t is the time difference, T is the first preset value, m is the distance difference, M is the second preset value, wherein, when t is greater than T or m is greater than M, r is 0; Obtaining a matching degree based on the theoretical matching degree; The step of obtaining the matching degree based on the theoretical matching degree includes: Obtaining weather types corresponding to the generation times of the first vehicle event and the second vehicle event; The theoretical matching degree is corrected based on the characteristic value corresponding to the weather type to obtain a matching degree.

2. The vehicle event fusion method according to claim 1, characterized in that: The step of correcting the theoretical matching degree based on the characteristic value corresponding to the weather type to obtain the matching degree includes: The characteristic value corresponding to the weather type is multiplied by the theoretical matching degree, and the obtained product is used as the matching degree, wherein the greater the negative impact of the weather type on driving, the lower the corresponding characteristic value.

3. The vehicle event fusion method according to claim 1 or 2, characterized in that: Before the steps of obtaining the first vehicle event from the first queue and obtaining the second vehicle event from the second queue, the method further includes: Generate a first type of vehicle event according to the first type of perception data of the first sensor, and store the first type of vehicle events into a first queue in chronological order of generation time; Generate a second type of vehicle event according to the second type of perception data of the second sensor, and store the second type of vehicle events into a second queue in chronological order of generation time; The sensing areas of the first sensor and the second sensor overlap.

4. A vehicle event fusion device, characterized in that: The vehicle event fusion device comprises: an acquisition module, configured to acquire a first vehicle event from the first queue and a second vehicle event from the second queue; a calculation module, configured to obtain a distance difference based on a location of occurrence of the first vehicle event and a location of occurrence of the second vehicle event, obtain a time difference based on a time instant of generation of the first vehicle event and a time instant of generation of the second vehicle event, and obtain a similarity value based on an event type of the first vehicle event and an event type of the second vehicle event; and calculate a matching degree based on the distance difference, time difference, and similarity value; a fusion module, configured to perform event fusion on the first vehicle event and the second vehicle event if the matching degree is greater than a preset threshold; The computing module is configured to: The distance difference, time difference and similarity value are input into the matching degree calculation formula to obtain the theoretical matching degree. The matching degree calculation formula is: Among them, r is the theoretical matching degree, is the similarity value, t is the time difference, T is the first preset value, m is the distance difference, M is the second preset value, wherein, when t is greater than T or m is greater than M, r is 0; Obtaining weather types corresponding to the generation times of the first vehicle event and the second vehicle event; The theoretical matching degree is corrected based on the characteristic value corresponding to the weather type to obtain a matching degree.

5. A vehicle event fusion device, characterized in that: The vehicle event fusion device includes a processor, a memory, and a vehicle event fusion program stored in the memory and executable by the processor, wherein when the vehicle event fusion program is executed by the processor, the steps of the vehicle event fusion method as described in any one of claims 1 to 3 are implemented.

6. A readable storage medium, characterized in that: The readable storage medium stores a vehicle event fusion program, wherein when the vehicle event fusion program is executed by a processor, the steps of the vehicle event fusion method according to any one of claims 1 to 3 are implemented.

Images