A method, apparatus, electronic device and storage medium for vehicle information fusion

Abstract

This application discloses a vehicle information fusion method, apparatus, electronic device, and storage medium, relating to the field of image processing technology. It is used to accurately fuse vehicle capture information of the same vehicle from different acquisition directions without relying on the acquisition time sequence of vehicle capture information. The method includes: upon first acquiring first vehicle capture information containing a first license plate number, establishing a first fusion queue using the first license plate number as identifier information, and storing the first vehicle capture information in the first fusion queue; within a target time period after acquiring the first vehicle capture information, if second vehicle capture information is acquired, determining whether the license plate number corresponding to the second vehicle capture information is the same as the first license plate number, obtaining a first determination result; and based on the first determination result, determining whether to fuse the second vehicle capture information and the first fusion queue.

Description

Technical Field

[0001] This application relates to the field of image processing technology, and in particular to a vehicle information fusion method, apparatus, electronic device, and storage medium. Background Technology

[0002] Currently, roads typically have one or more data acquisition devices that collect images of vehicles from different directions. By recognizing the acquired images, vehicle information such as license plate number, vehicle color, and vehicle model can be obtained. This information is then input into electronic devices, which associate the vehicle information collected from different directions for the same vehicle to obtain information such as the vehicle's travel route, vehicle images from different directions, and accurate toll collection vehicle type. This information can be applied in scenarios such as determining vehicle travel routes, training models to recognize different vehicle directions, and vehicle toll collection. The vehicle information fusion process performed by the aforementioned electronic devices is quite labor-intensive.

[0003] Currently, there are methods to associate vehicle capture information of the same vehicle captured from different directions based on the time difference between the acquisition of vehicle images from different acquisition directions. That is, the time difference between the acquisition devices capturing the same vehicle from different acquisition directions is fixed. Based on the time when the first acquisition device in the vehicle's direction of travel acquires the vehicle image and the aforementioned fixed time difference, vehicle images of the same vehicle in other acquisition directions are determined, and then the vehicle capture information of that vehicle in different acquisition directions is associated. However, if the order in which the electronic device receives vehicle capture information from different acquisition directions is different from the order in which the vehicle capture information is acquired, the electronic device may associate vehicle capture information from different vehicles together, causing errors in the vehicle capture information fusion process.

[0004] Therefore, how to accurately integrate vehicle capture information from different collection directions for the same vehicle, without depending on the collection time sequence of the vehicle capture information, is a problem that needs to be solved. Summary of the Invention

[0005] This application provides a vehicle information fusion method, apparatus, electronic device, and storage medium, used to accurately fuse vehicle capture information of the same vehicle from different capture directions without relying on the time sequence of vehicle capture information acquisition. To achieve the above technical objective, this application adopts the following technical solution:

[0006] In a first aspect, embodiments of this application provide a vehicle information fusion method applied to an electronic device. The method includes: upon first acquisition of first vehicle capture information containing a first license plate number, establishing a first fusion queue using the first license plate number as identifier information, and storing the first vehicle capture information in the first fusion queue; within a target time period after acquiring the first vehicle capture information, if second vehicle capture information is acquired, determining whether the license plate number to be compared corresponding to the second vehicle capture information is the same as the first license plate number, and obtaining a first determination result; and determining whether to fuse the second vehicle capture information and the first fusion queue based on the first determination result. The technical solution provided in this application brings at least the following beneficial effects: When the first vehicle capture information containing the first license plate number is acquired for the first time, a first fusion queue is established using the first license plate number as the identifier. By judging whether the license plate number to be compared corresponding to the second vehicle capture information is the same as the first license plate number, it can be determined whether the second vehicle capture information and the first fusion queue can be fused based on the judgment result. Even if the acquisition order of the vehicle capture information is different from the order in which the electronic device receives the vehicle capture information, the vehicle capture information of the same vehicle in different acquisition directions can be accurately fused, avoiding the error of fusion of vehicle capture information of different vehicles, and the vehicle capture information fusion result is more accurate. At the same time, by fusing the second vehicle capture information and the first fusion queue within a target time after the first vehicle capture information is acquired, the end of the target time indicates that the vehicle capture information represented by the first license plate number may have been captured. The setting of the target time can avoid the electronic device waiting for vehicle capture information for a long time, reducing the time required for the electronic device to enter the fusion of vehicle capture information.

[0007] In one possible implementation, the second vehicle capture information includes a second vehicle image and a second license plate number, wherein the second license plate number is the license plate number identified from the second vehicle image; the license plate number to be compared corresponding to the second vehicle capture information is the second license plate number and the third license plate number, wherein the third license plate number is the license plate number obtained by secondary recognition of the second vehicle image when there is no queue of identification information that is the same as the second license plate number.

[0008] In one possible implementation, based on the first judgment result, determining whether to fuse the second vehicle capture information and the first fusion queue includes: fusion of the second vehicle capture information and the first fusion queue when the first judgment result indicates that the first license plate number is the same as the second license plate number, or fusion of the second vehicle capture information and the first fusion queue when the first judgment result indicates that the first license plate number is different from the second license plate number and the first license plate number is the same as the third license plate number.

[0009] In one possible implementation, the second vehicle capture information further includes a second acquisition direction, which is the acquisition direction of the second vehicle image in the second vehicle capture information; fusing the second vehicle capture information and the first queue to be fused includes: fusing the second vehicle capture information and the first queue to be fused according to the acquisition direction in each vehicle capture information in the first queue to be fused, and the second acquisition direction.

[0010] In one possible implementation, the second vehicle capture information and the first fusion queue are fused according to the acquisition direction and the second acquisition direction in the capture information of each vehicle in the first fusion queue, including: if there is no vehicle capture information in the first fusion queue with the same acquisition direction as the second acquisition direction, the second vehicle capture information is stored in the first fusion queue.

[0011] In one possible implementation, the second vehicle capture information and the first fusion queue are fused based on the acquisition direction and the second acquisition direction in the capture information of each vehicle in the first fusion queue. The fusion also includes: if there is a third vehicle capture information in the first fusion queue with the same acquisition direction as the second acquisition direction, the fourth license plate number in the third vehicle capture information is compared with the first license plate number to obtain a comparison result; and the second vehicle capture information and the first fusion queue are fused based on the comparison result.

[0012] In one possible implementation, the second vehicle capture information and the first queue to be fused are fused according to the comparison result, including: if the comparison result indicates that the fourth license plate number is different from the first license plate number, then the second vehicle capture information is used to replace the third vehicle capture information.

[0013] In one possible implementation, the second vehicle capture information and the first queue to be fused are fused according to the comparison result. The fusion process also includes: if the comparison result indicates that the fourth license plate number is the same as the first license plate number, and the credibility of the license plate number to be compared corresponding to the second vehicle capture information is greater than the credibility of the fourth license plate number, then the third vehicle capture information is replaced with the second vehicle capture information.

[0014] In one possible implementation, based on the first judgment result, determining whether to fuse the second vehicle capture information and the first fusion queue includes: if there is no fusion queue whose identifier information is the same as the license plate number to be compared, then within the target duration of receiving the second vehicle capture information, searching for a fusion queue whose identifier information differs from the license plate number to be compared by N bits, where N is a positive integer; if the identifier information of the second fusion queue differs from the license plate number to be compared by N bits, then based on the credibility of the license plate number to be compared and the credibility of each target license plate number, determining the comprehensive credibility of each target license plate number, where the target license plate number is the identifier information of the second fusion queue and the credibility of the target license plate number is the credibility of the license plate number in the vehicle capture information with the earliest collection time in the second fusion queue; judging whether the comprehensive credibility of each target license plate number meets the preset credibility condition to obtain the second judgment result; and based on the second judgment result, determining whether to fuse the second vehicle capture information and the second fusion queue.

[0015] In one possible implementation, searching for the existence of a fusion queue where the identification information differs from the license plate number to be compared by N bits includes: searching for the existence of a fusion queue where the identification information differs from the license plate number to be compared by i bits, where i is a positive integer; if no fusion queue exists where the identification information differs from the license plate number to be compared by i bits, searching for the existence of a fusion queue where the identification information differs from the license plate number to be compared by i+1 bits; wherein, in the first search, i is 1.

[0016] In one possible implementation, the overall credibility of each target license plate number is determined based on the credibility of the license plate number to be compared and the credibility of each target license plate number. This includes: obtaining the credibility of a second or third license plate number that differs from the target license plate number by N positions; and determining the overall credibility of each target license plate number based on the credibility of each target license plate number and the credibility of the second or third license plate number that differs from the target license plate number by N positions.

[0017] In one possible implementation, determining whether to fuse the second vehicle capture information and the second fusion queue based on the second judgment result includes: if the second judgment result indicates that the comprehensive credibility meeting the preset credibility condition is one, then determining whether there is vehicle capture information in the third fusion queue in the second acquisition direction, obtaining a third judgment result, where the second acquisition direction is the acquisition direction of the second vehicle image in the second vehicle capture information, and the third fusion queue is the second fusion queue corresponding to the target license plate number that meets the preset credibility condition; if the third judgment result indicates that there is no vehicle capture information in the second acquisition direction in the third fusion queue, then the second vehicle capture information is stored in the third fusion queue; if the third judgment result indicates that there is vehicle capture information in the second acquisition direction in the third fusion queue, then determining whether the fifth license plate number in the vehicle capture information in the second acquisition direction in the third fusion queue is the same as the target license plate number, obtaining a fourth judgment result; and fusing the second vehicle capture information and the third fusion queue based on the fourth judgment result.

[0018] In one possible implementation, based on the fourth judgment result, the second vehicle capture information and the third fusion queue are fused, including: if the fourth judgment result indicates that the fifth license plate number in the vehicle capture information in the second acquisition direction in the third fusion queue is different from the target license plate number, the number of identical characters between the fifth license plate number and the target license plate number is determined as a first value, and the number of identical characters between the license plate number to be compared that differs from the target license plate number by N positions is determined as a second value; if the second value is greater than the first value, or the second value is equal to the first value, and the confidence of the license plate number to be compared that differs from the target license plate number by N positions is greater than the confidence of the fifth license plate number, the second vehicle capture information replaces the vehicle capture information in the second acquisition direction in the third fusion queue.

[0019] In one possible implementation, determining whether to fuse the second vehicle capture information and the second fusion queue based on the second judgment result further includes: if the second judgment result indicates that multiple comprehensive credibility values ​​meet preset credibility conditions, determining the fourth fusion queue containing the vehicle capture information with the highest similarity to the second vehicle capture information from the second fusion queue corresponding to the target license plate number of the multiple comprehensive credibility values ​​that meet the preset credibility conditions; and fusing the second vehicle capture information and the fourth fusion queue according to the second acquisition direction.

[0020] In one possible implementation, the method further includes: if the first license plate number has no characters and the second license plate number has no characters, and the similarity between the first vehicle capture information and the second vehicle capture information is within a preset similarity range, then the second vehicle capture information and the first queue to be fused are fused.

[0021] Secondly, this application provides a vehicle information fusion device, comprising:

[0022] The acquisition module is used to acquire the first vehicle capture information containing the first license plate number;

[0023] The processing module is used to establish a first queue to be fused with the first license plate number as the identifier when the first vehicle capture information containing the first license plate number is obtained for the first time, and to store the first vehicle capture information in the first queue to be fused; the processing module is also used to determine whether the license plate number to be compared corresponding to the second vehicle capture information is the same as the first license plate number if the second vehicle capture information is obtained within a target time period after the first vehicle capture information is obtained, and to obtain a first judgment result;

[0024] The processing module is also used to determine, based on the first judgment result, whether to fuse the second vehicle capture information and the first queue to be fused.

[0025] In one possible implementation, the second vehicle capture information includes a second vehicle image and a second license plate number, wherein the second license plate number is the license plate number identified from the second vehicle image; the license plate number to be compared corresponding to the second vehicle capture information is the second license plate number and the third license plate number, wherein the third license plate number is the license plate number obtained by secondary recognition of the second vehicle image when there is no queue of identification information that is the same as the second license plate number.

[0026] In one possible implementation, the processing module is specifically used to fuse the second vehicle capture information and the first fusion queue when the first judgment result indicates that the first license plate number is the same as the second license plate number, or when the first judgment result indicates that the first license plate number is different from the second license plate number and the first license plate number is the same as the third license plate number.

[0027] In one possible implementation, the second vehicle capture information further includes a second acquisition direction, which is the acquisition direction of the second vehicle image in the second vehicle capture information; the processing module is specifically used to fuse the second vehicle capture information and the first fusion queue according to the acquisition direction in each vehicle capture information in the first fusion queue and the second acquisition direction.

[0028] In one possible implementation, the processing module is specifically used to: if there is no vehicle capture information in the first queue to be fused with the same acquisition direction as the second acquisition direction, store the second vehicle capture information in the first queue to be fused. In another possible implementation, the processing module is specifically used to: if there is third vehicle capture information in the first queue to be fused with the same acquisition direction as the second acquisition direction, compare the fourth license plate number in the third vehicle capture information with the first license plate number to obtain a comparison result; and based on the comparison result, fuse the second vehicle capture information and the first queue to be fused. In yet another possible implementation, the processing module is specifically used to: if the comparison result indicates that the fourth license plate number is different from the first license plate number, replace the third vehicle capture information with the second vehicle capture information.

[0029] In one possible implementation, the processing module is specifically used to replace the third vehicle capture information with the second vehicle capture information if the comparison result indicates that the fourth license plate number is the same as the first license plate number, and the credibility of the license plate number to be compared corresponding to the second vehicle capture information is greater than the credibility of the fourth license plate number.

[0030] In one possible implementation, the processing module is specifically used to: if there is no queue of vehicles to be fused with the same identification information as the license plate number to be compared, then within the target time period after receiving the second vehicle capture information, search for a queue of vehicles to be fused where the identification information differs from the license plate number to be compared by N bits, where N is a positive integer; if a queue of vehicles to be fused with the same identification information as the license plate number to be compared by N bits is found, then determine the comprehensive credibility of each target license plate number based on the credibility of the license plate number to be compared and the credibility of each target license plate number, where the target license plate number is the identification information of the second queue of vehicles to be fused, and the credibility of the target license plate number is the credibility of the license plate number in the earliest captured vehicle capture information in the second queue of vehicles to be fused; determine whether the comprehensive credibility of each target license plate number meets the preset credibility condition to obtain a second judgment result; and determine whether to fuse the second vehicle capture information and the second queue of vehicles to be fused based on the second judgment result. In one possible implementation, the processing module is specifically used to: search for whether there exists a queue of vehicles whose identification information differs from the license plate number to be compared by i bits, where i is a positive integer; if there is no queue of vehicles whose identification information differs from the license plate number to be compared by i bits, search for whether there exists a queue of vehicles whose identification information differs from the license plate number to be compared by i+1 bits; where i is 1 in the first search.

[0031] In one possible implementation, the processing module is specifically used to: obtain the credibility of a second or third license plate number that differs from the target license plate number by N bits; and determine the comprehensive credibility of each target license plate number based on the credibility of each target license plate number and the credibility of the second or third license plate number that differs from the target license plate number by N bits. In another possible implementation, the processing module is specifically used to: if the second judgment result indicates that there is only one comprehensive credibility that meets the preset credibility condition, then determine whether there is vehicle capture information in the third fusion queue with the second acquisition direction, and obtain the third judgment result. The second acquisition direction is the acquisition direction of the second vehicle image in the second vehicle capture information, and the third fusion queue is the second fusion queue corresponding to the target license plate number with the comprehensive credibility that meets the preset credibility condition.

[0032] In one possible implementation, if the third judgment result is that there is no vehicle capture information in the second acquisition direction in the third queue to be fused, then the second vehicle capture information is stored in the third queue to be fused; if the third judgment result is that there is vehicle capture information in the second acquisition direction in the third queue to be fused, then it is determined whether the fifth license plate number in the vehicle capture information in the second acquisition direction in the third queue to be fused is the same as the target license plate number, and a fourth judgment result is obtained; according to the fourth judgment result, the second vehicle capture information and the third queue to be fused are fused.

[0033] In one possible implementation, the processing module is specifically used to: if the fourth judgment result indicates that the fifth license plate number in the vehicle capture information in the second acquisition direction in the third fusion queue is different from the target license plate number, determine the number of identical characters between the fifth license plate number and the target license plate number as a first value, and the number of identical characters between the license plate number to be compared that differs from the target license plate number by N positions as a second value; if the second value is greater than the first value, or the second value is equal to the first value, and the credibility of the license plate number to be compared that differs from the target license plate number by N positions is greater than the credibility of the fifth license plate number, replace the vehicle capture information in the second acquisition direction in the third fusion queue with the second vehicle capture information.

[0034] In one possible implementation, the processing module is specifically used to: if the second judgment result indicates that multiple comprehensive credibility levels all meet preset credibility conditions, determine the fourth fusion queue containing the vehicle capture information with the highest similarity to the second vehicle capture information from the second fusion queue corresponding to the target license plate numbers corresponding to the multiple comprehensive credibility levels that meet the preset credibility conditions; and fuse the second vehicle capture information and the fourth fusion queue according to the second acquisition direction. In another possible implementation, the processing module is further used to: if the first license plate number has no characters and the second license plate number has no characters, and the similarity between the first vehicle capture information and the second vehicle capture information is within a preset similarity range, fuse the second vehicle capture information and the first fusion queue.

[0035] Thirdly, this application provides an electronic device, including: one or more processors; one or more memories; wherein the one or more memories are used to store computer program code, the computer program code including computer instructions, and when the one or more processors execute the computer instructions, the electronic device executes any of the vehicle information fusion methods provided in the first aspect above.

[0036] Fourthly, this application provides a computer-readable storage medium storing computer-executable instructions, which, when executed on a computer, cause the computer to perform any of the vehicle information fusion methods provided in the first aspect above.

[0037] Fifthly, this application provides a computer program product including computer instructions that, when executed on an electronic device, cause the electronic device to perform the vehicle information fusion method as described in the first aspect and any possible design thereof.

[0038] For a detailed description of the second to fifth aspects and their various implementations in this application, please refer to the detailed description in the first aspect and its various implementations; and for a detailed analysis of the beneficial effects of the second to fifth aspects and their various implementations in the first aspect and its various implementations, please refer to the beneficial effect analysis in the first aspect and its various implementations, which will not be repeated here.

[0039] These or other aspects of this application will become more readily apparent in the following description. Attached Figure Description

[0040] Figure 1 This is a schematic diagram of the structure of a vehicle information fusion system to which a vehicle information fusion method is applicable, as provided in an embodiment of this application.

[0041] Figure 2 This is a schematic diagram of the hardware composition of a computing device provided in an embodiment of this application;

[0042] Figure 3 A flowchart illustrating a vehicle information fusion method provided in this application embodiment;

[0043] Figure 4 A logical illustration of a vehicle information fusion method provided in this application embodiment. Figure 1 ;

[0044] Figure 5 A logical illustration of a vehicle information fusion method provided in this application embodiment. Figure 2 ;

[0045] Figure 6 This is a schematic diagram of the structure of a vehicle information fusion device provided in an embodiment of this application;

[0046] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0047] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0048] It should be noted that, in the embodiments of this application, the terms "exemplary" or "for example" are used to indicate examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner. The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0049] To facilitate understanding, we will first provide a brief introduction and explanation of some terms or basic concepts of technology involved in the embodiments of this application.

[0050] Vehicle information fusion is the process of associating images of the same vehicle taken from different acquisition directions with the vehicle information extracted from these images.

[0051] The above is an introduction to some of the concepts involved in the embodiments of this application, which will not be repeated below.

[0052] Currently, roads typically have one or more data acquisition devices that collect images of vehicles from different directions. By recognizing the acquired images, vehicle information such as license plate number, vehicle color, and vehicle model can be obtained. This information is then input into electronic devices, which associate the vehicle information collected from different directions for the same vehicle to obtain information such as the vehicle's travel route, vehicle images from different directions, and accurate toll collection vehicle type. This information can be applied in scenarios such as determining vehicle travel routes, training models to recognize different vehicle directions, and vehicle toll collection. The vehicle information fusion process performed by the aforementioned electronic devices is quite labor-intensive.

[0053] Currently, there are methods to associate vehicle capture information of the same vehicle captured from different directions based on the time difference between the acquisition of vehicle images from different acquisition directions. That is, the time difference between the acquisition devices capturing the same vehicle from different acquisition directions is fixed. Based on the time when the first acquisition device in the vehicle's direction of travel acquires the vehicle image and the aforementioned fixed time difference, vehicle images of the same vehicle in other acquisition directions are determined, and then the vehicle capture information of that vehicle in different acquisition directions is associated. However, if the order in which the electronic device receives vehicle capture information from different acquisition directions is different from the order in which the vehicle capture information is acquired, the electronic device may associate vehicle capture information from different vehicles together, causing errors in the vehicle capture information fusion process.

[0054] Therefore, how to accurately integrate vehicle capture information from different collection directions for the same vehicle, without depending on the collection time sequence of the vehicle capture information, is a problem that needs to be solved.

[0055] To address this issue, this application provides a vehicle information fusion method. Upon first acquisition of vehicle capture information containing a first license plate number, a first fusion queue is established using the first license plate number as an identifier. The first vehicle capture information is stored in this queue. It is then determined whether the license plate number of a second capture message received within a target time period after acquiring the first vehicle capture information is the same as the first license plate number. Based on the determination result, it is decided whether to fuse the second vehicle capture information and the first fusion queue. In this way, the license plate number alone can determine whether to fuse different vehicle capture information. Even if the acquisition order of the vehicle capture information differs from the order in which the electronic device receives the vehicle capture information, it can accurately fuse vehicle capture information of the same vehicle from different acquisition directions, avoiding errors such as merging vehicle capture information from different vehicles together. This results in more accurate vehicle information fusion results.

[0056] Please refer to Figure 1This illustrates the vehicle information fusion system to which the vehicle information fusion method provided in this application is applicable. For example... Figure 1 As shown, the vehicle information fusion system 1 includes: multiple acquisition devices 10 and electronic devices 20.

[0057] In this system, multiple data acquisition devices 10 and electronic devices 20 establish communication connections directly or indirectly. It should be understood that the connection method can be a wireless connection, such as a Bluetooth connection or a wireless fidelity (Wi-Fi) connection; or, the connection method can be a wired connection, such as a fiber optic connection, etc., and there is no limitation on this.

[0058] In some embodiments, the acquisition device 10 and the electronic device 20 perform time correction via Network Time Protocol (NTP) to avoid time differences between them. In some embodiments, the acquisition device 10 is used to capture information of vehicles traveling on the road, such as images of the vehicle during its journey and video files of the vehicle passing through the acquisition range of the acquisition device 10. Multiple acquisition devices located at the same location may include multiple acquisition directions with the same acquisition direction. For example, at location A, there may be three acquisition devices capturing images of the vehicle from the front, two acquisition devices capturing images of the vehicle from the left, two acquisition devices capturing images of the vehicle from the right, and two acquisition devices capturing images of the vehicle from behind.

[0059] In some embodiments, the acquisition device 10 has a built-in speed measuring device, and the vehicle capture information acquired by the acquisition device 10 includes the vehicle speed.

[0060] In some embodiments, the acquisition device 10 includes a capture device for acquiring vehicle images, and the vehicle capture information acquired by the acquisition device 10 includes the vehicle images acquired by the capture device.

[0061] In some embodiments, the acquisition device 10 may include a processing unit for identifying information such as the vehicle's license plate number, license plate color, lane number, vehicle type, number of axles, vehicle toll type, and vehicle brand from the vehicle image. In this case, the vehicle capture information acquired by the acquisition device 10 includes information such as the vehicle's license plate number, license plate color, lane number, vehicle type, number of axles, vehicle toll type, and vehicle brand identified by the processing unit from the vehicle image.

[0062] In some embodiments, the acquisition device 10 transmits the acquired vehicle capture information to the electronic device 20. Alternatively, the acquisition device 10 transmits the acquired vehicle image and vehicle speed to the electronic device 20, which then identifies the vehicle image to obtain information such as the vehicle's license plate number, license plate color, lane number, vehicle type, number of axles, vehicle toll type, and vehicle brand.

[0063] In some embodiments, the electronic device 20 is used to fuse vehicle capture information where the license plate number represents the same vehicle based on the license plate number in the vehicle capture information.

[0064] In some embodiments, the electronic device 20 may include a processor. The processor is used to implement the fusion process of vehicle capture information. The processor may be a central processing unit (CPU), a network processor (NP), a digital signal processor (DSP), a microprocessor, a microcontroller, a programmable logic device (PLD), or any combination thereof. The processor may also be other devices with processing functions, such as circuits, devices, or software modules; this application embodiment does not impose any limitations on this.

[0065] In some embodiments, the electronic device 20 may further include a memory for storing vehicle capture information from the acquisition device 10 and / or video files captured when a vehicle passes by the acquisition device 10. The processor can then retrieve vehicle capture information, related video files, etc., from the memory and fuse the vehicle capture information of the same vehicle. Optionally, the electronic device 20 is composed of a vehicle information recognition device and a vehicle information fusion device. The vehicle information recognition device identifies the vehicle images or related video files acquired by the acquisition device 10 to obtain vehicle capture information, and the vehicle capture information fusion device fuses the vehicle capture information representing the same vehicle sent by the vehicle information recognition device.

[0066] Optionally, the electronic device 20 may also include a display device, or the electronic device 20 may be connected to a display device for displaying the fusion results of the vehicle capture information to the user.

[0067] In some embodiments, the data acquisition device 10 can be a camera, video camera, video recorder, or other device that can be mounted on a road to capture images of vehicles traveling on the road. This application embodiment does not limit the specific type of the data acquisition device 10. The hardware structure of the aforementioned electronic device includes... Figure 2 The components included in the computing device shown. The following are examples... Figure 2 Taking the computing device shown as an example, the hardware structure of electronic devices is introduced.

[0068] like Figure 2 As shown, the computing device may include a processor 301, a memory 302, a communication interface 303, and a bus 304. The processor 301, the memory 302, and the communication interface 303 can be connected via the bus 304.

[0069] Processor 301 is the control center of the computing device and can be a single processor or a collective term for multiple processing elements. For example, processor 301 can be a general-purpose central processing unit (CPU) or other general-purpose processors. The general-purpose processor can be a microprocessor or any conventional processor. As one embodiment, processor 301 may include one or more CPUs, for example... Figure 2 CPU 0 and CPU 1 are shown in the diagram.

[0070] The memory 302 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), disk storage medium or other magnetic storage device, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but is not limited thereto.

[0071] In one possible implementation, the memory 302 can exist independently of the processor 301. The memory 302 can be connected to the processor 301 via the bus 304 and is used to store instructions or program code. When the processor 301 calls and executes the instructions or program code stored in the memory 302, it can implement the model deployment method provided in this application embodiment. In another possible implementation, the memory 302 can also be integrated with the processor 301. The communication interface 303 is used for the computing device to connect with other devices through a communication network, which can be Ethernet, radio access network (RAN), wireless local area network (WLAN), etc. The communication interface 303 can include a receiving unit for receiving data and a sending unit for sending data. The bus 304 can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2 The symbol is represented by only one thick line, but this does not indicate that there is only one bus or one type of bus. It should be noted that... Figure 2 The structure shown does not constitute a limitation on the computing device, except Figure 2 In addition to the components shown, the computing device may include more or fewer components than illustrated, or combine certain components, or have different component arrangements. Embodiments of this application will now be described in detail with reference to the accompanying drawings.

[0072] The vehicle information fusion method provided in this application embodiment can be executed by the aforementioned electronic device 20. For example... Figure 3As shown, this application embodiment provides a vehicle information fusion method, which includes the following steps: S101, when first vehicle capture information containing a first license plate number is obtained for the first time, a first fusion queue is established using the first license plate number as the identifier, and the first vehicle capture information is stored in the first fusion queue. In some embodiments, the first vehicle capture information includes a first vehicle image. When the electronic device receives the first vehicle capture information containing the first license plate number, if there is no fusion queue in the fusion queue stored by the electronic device with the first license plate number as the identifier, the first vehicle image is re-identified to obtain a re-identified license plate number. If there is also no fusion queue in the fusion queue stored by the electronic device with the re-identified license plate number as the identifier, and there is also no fusion queue where the identifier meets a preset similarity condition with the first license plate number and / or the re-identified license plate number, the electronic device determines that the first vehicle capture information is obtained for the first time. The preset similarity condition may be that the number of identical characters in the two license plate numbers is greater than a preset number.

[0073] In some embodiments, the acquisition directions of vehicle capture information from a single acquisition location in the queue to be merged are all different. For example, as shown in Table 1, for a certain acquisition location, the electronic device stores multiple queues to be merged corresponding to that acquisition location. Taking queue 1 to be merged as an example, the identification information of queue 1 to be merged is license plate number 1, and queue 1 to be merged includes three vehicle capture information entries with different acquisition directions.

[0074] Table 1. Schematic diagram of the fusion queue corresponding to the Nth collection location.

[0075]

[0076] In this way, by establishing a queue to be fused, vehicle capture information of the same vehicle at the same collection location is stored together, making it convenient for users to view vehicle capture information and to organize the capture information of the same vehicle. In some embodiments, extracting lane number, vehicle type, vehicle toll type, etc. from the first vehicle image capture information can be achieved by deep learning neural network algorithms, etc. The embodiments of this application do not specifically limit the method of extracting vehicle capture information from vehicle images.

[0077] In some embodiments, the acquisition device records video files of a vehicle driving within the acquisition device's shooting range. After identifying the video files recorded by the acquisition device, the frame with the highest clarity, located at a preset position within the acquisition device's shooting range, is taken as the vehicle image acquired by the acquisition device.

[0078] In some embodiments, the acquisition device captures images of vehicles traveling within its shooting range at a preset frequency. After identifying the captured vehicle images, the image of the vehicle whose position is closest to a preset position within the shooting range of the acquisition device, and with the highest clarity, is taken as the vehicle image acquired by the acquisition device. S102: Within a target time period after acquiring the first vehicle capture information, if second vehicle capture information is acquired, it is determined whether the license plate number to be compared corresponding to the second vehicle capture information is the same as the first license plate number, and a first judgment result is obtained. In some embodiments, when the first vehicle capture information includes vehicle speed and the vehicle speed is positive, the electronic device determines the target time period based on the location of the first and last captured vehicles at the same acquisition location in the vehicle's direction of travel, as well as the vehicle speed; when the first vehicle capture information includes vehicle speed and the vehicle speed is zero, or when the first vehicle capture information does not include vehicle speed, the electronic device determines the preset time period as the target time period. It should be understood that the shooting range of the data acquisition device is constant. Therefore, the electronic system can determine the location of the vehicle captured by the data acquisition device based on the shooting range of the data acquisition device, that is, determine the location of the earliest captured vehicle and the location of the last captured vehicle.

[0079] For example, at a certain data collection location, data collection device A is the first device to capture a vehicle, and data collection device B is the last device to capture a vehicle. Assuming that based on the shooting range of data collection devices A and B, the distance between the location of the first vehicle captured and the location of the last vehicle captured at that data collection location is 100m, if the electronic device receives the first vehicle capture information for the first time and determines from the first vehicle capture information that the vehicle passed through the data collection location at a speed of 72km / h, then the time for the vehicle to pass through the data collection location is 5s, which is the target duration of 5s. Therefore, the electronic device starts timing 5s from receiving the first vehicle capture information, and considers that any vehicle capture information received after 5s is not the capture information of that vehicle. In other words, the vehicle capture information fusion operation for that vehicle at that data collection location will not continue after 5s.

[0080] In this way, by determining the target duration and completing the vehicle capture information fusion operation within the target duration, the electronic equipment can avoid waiting for the vehicle capture information for a long time, thus reducing the time required for vehicle fusion.

[0081] In some embodiments, the second vehicle capture information includes a second vehicle image and a second license plate number, where the second license plate number is the license plate number identified from the second vehicle image. The license plate numbers to be compared corresponding to the second vehicle capture information are the second license plate number and a third license plate number. The third license plate number is the license plate number obtained by secondary recognition of the second vehicle image when there is no fusion queue with the same identification information as the second license plate number. By performing secondary recognition on the second vehicle image, errors in vehicle capture information fusion caused by inaccurate second license plate numbers identified in the first step can be avoided. Furthermore, combining the second and third license plate numbers in subsequent processes to fuse the vehicle capture information yields a more accurate fusion result.

[0082] In this way, by performing secondary recognition on the second vehicle image, the accuracy of license plate number recognition can be improved. Then, by combining the second and third license plate numbers to fuse the vehicle capture information, a more accurate vehicle capture information fusion result can be obtained.

[0083] S103. Based on the first judgment result, determine whether to merge the second vehicle capture information and the first queue to be merged. The first judgment result includes: the first license plate number is the same as the second license plate number; the first license plate number is different from the second license plate number but the first license plate number is the same as the third license plate number; or the first license plate number is different from both the second and third license plate numbers.

[0084] In some embodiments, when the first judgment result indicates that the first license plate number is the same as the second license plate number, or when the first judgment result indicates that the first license plate number is different from the second license plate number, but the first license plate number is the same as the third license plate number, the electronic device fuses the second vehicle capture information and the first queue to be fused.

[0085] In some embodiments, the second vehicle capture information further includes a second acquisition direction, which is the acquisition direction of the second vehicle image in the second vehicle capture information. The electronic device fuses the second vehicle capture information and the first fusion queue, specifically by fusing the second vehicle capture information and the first fusion queue according to the acquisition direction in each vehicle capture information in the first fusion queue and the second acquisition direction.

[0086] Specifically, during the process of fusing the second vehicle capture information and the first fusion queue based on the acquisition direction of each vehicle capture information in the first fusion queue and the second acquisition direction, if there is no vehicle capture information in the first fusion queue with the same acquisition direction as the second acquisition direction, the electronic device stores the second vehicle capture information in the first fusion queue.

[0087] If there is a third vehicle capture information in the first queue to be fused with the same acquisition direction as the second acquisition direction, the electronic device compares the fourth license plate number in the third vehicle capture information with the first license plate number to obtain the comparison result. Then, the electronic device merges the second vehicle capture information and the first queue to be fused based on the comparison result.

[0088] If the comparison result indicates that the fourth license plate number is the same as the first license plate number, and the credibility of the license plate number to be compared corresponding to the second vehicle capture information is greater than the credibility of the fourth license plate number, then the second vehicle capture information will replace the third vehicle capture information.

[0089] For example, the second vehicle capture information contains a frontal image of the vehicle. Assuming the first fusion queue does not store vehicle capture information containing a frontal image, the electronic device directly stores the second vehicle capture information in the first fusion queue. Assuming the first fusion queue stores third vehicle capture information containing a frontal image, the electronic device determines the fourth license plate number in the third vehicle capture information. If the fourth license plate number is the same as the identifier in the first fusion queue, and the license plate number corresponding to the second vehicle capture information is also the same as the identifier in the first fusion queue, then the license plate number alone cannot determine which vehicle capture information is more reliable. Therefore, the electronic device compares the reliability of the license plate number corresponding to the second vehicle capture information with the reliability of the fourth license plate number. When their reliability is equal, it indicates that the reliability of the two vehicle capture information is equal. The electronic device can then replace the third vehicle capture information with the second vehicle capture information, or it can choose not to replace it. If the reliability of the license plate number corresponding to the second vehicle capture information is less than that of the fourth license plate number, it indicates that the third vehicle capture information is more reliable, and the electronic device retains the third vehicle capture information. If the reliability of the license plate number corresponding to the second vehicle capture information is greater than that of the fourth license plate number, it indicates that the second vehicle capture information is more reliable, and the electronic device replaces the third vehicle capture information with the second vehicle capture information.

[0090] In this way, the vehicle capture information stored in the queue to be fused established by the electronic device is the most reliable vehicle capture information in that acquisition direction, and the final fused vehicle capture information fusion result is also more reliable.

[0091] In some embodiments, step S103 can be specifically implemented as follows: If there is no queue to be fused with the same identification information as the license plate number to be compared, the electronic device searches for a queue to be fused within the target time period after receiving the second vehicle capture information if the identification information differs from the license plate number to be compared by N bits; if the identification information of the second queue to be fused differs from the license plate number to be compared by N bits, the electronic device determines the comprehensive credibility of each target license plate number based on the credibility of the license plate number to be compared and the credibility of each target license plate number; the electronic device judges whether the comprehensive credibility of each target license plate number meets the preset credibility condition to obtain a second judgment result; then, the electronic device determines whether to fuse the second vehicle capture information and the second queue to be fused based on the second judgment result. Wherein, N is a positive integer, the target license plate number is the identification information of the second queue to be fused, and the credibility of the target license plate number is the credibility of the license plate number in the earliest captured vehicle capture information in the second queue to be fused.

[0092] In some embodiments, the electronic device searches for the existence of a fusion queue where the identification information differs from the license plate number to be compared by N bits. Specifically, the electronic device searches for the existence of a fusion queue where the identification information differs from the license plate number to be compared by i bits, where i is a positive integer. If no fusion queue exists where the identification information differs from the license plate number to be compared by i bits, the electronic device searches for the existence of a fusion queue where the identification information differs from the license plate number to be compared by i+1 bits. In the first search, i is 1.

[0093] For example, if the license plate numbers to be compared are Ab1233 and Ab1234, the electronic device searches for queues in the previously established fusion queues that differ from Ab1233 and / or Ab1234 by only one character. For instance, if the electronic device finds a queue with the identifier Ac1234, which differs from Ab1234 by only one character, the electronic device will not continue searching for queues whose identifiers differ from the license plate numbers by two characters. If the electronic device does not find a queue whose identifiers differ from Ab1233 and / or Ab1234 by one character, it will continue searching for queues whose identifiers differ from Ab1233 and / or Ab1234 by two characters.

[0094] Generally, license plate numbers are only 7 digits long. If the number of characters between two license plate numbers differs by more than two, it is unlikely that the two license plate numbers are the same. Therefore, the two license plate numbers are not considered to represent the same vehicle. Thus, if the electronic device does not find a fusion queue where the identification information differs from the license plate number to be compared by two characters, it will not continue to search for a fusion queue where the identification information differs from the license plate number to be compared by three characters.

[0095] In this way, when there is no license plate number exactly the same as the license plate number to be compared, it may be due to a misidentification of the license plate number to be compared. In this case, the license plate number that differs from the license plate number to be compared by N characters is searched from the identification information of the pre-stored fusion queue. That is, the fusion queue that may represent the same vehicle as the license plate number to be compared is found. This can avoid the situation where the vehicle capture information representing the same vehicle as the second vehicle capture information cannot be found due to the misidentification of the license plate number to be compared. The accuracy of the vehicle fusion result is also higher.

[0096] In some embodiments, the electronic device determines the overall credibility of each target license plate number based on the credibility of the license plate number to be compared and the credibility of each target license plate number. Specifically, the electronic device obtains the credibility of a second or third license plate number that differs from the target license plate number by N positions; and then determines the overall credibility of each target license plate number based on the credibility of each target license plate number and the credibility of the second or third license plate number that differs from the target license plate number by N positions.

[0097] The credibility of a license plate number is used to characterize the probability that the license plate number is genuine. In practical applications, the credibility of a license plate number can be a score, such as a clarity score; the higher the clarity, the more credible the identified license plate number.

[0098] For example, the license plate numbers to be compared corresponding to the second vehicle capture information are license plate number 1 and license plate number 2. The electronic device finds the identification information of the queue to be merged 1 as license plate number 3, which differs from license plate number 1 by only one character. The identification information of the queue to be merged 2 is license plate number 4, which also differs from license plate number 1 by only one character. The identification information of the queue to be merged 3 is license plate number 5, which differs from license plate number 2 by only one character. Then, by multiplying the credibility of license plate number 1 by the credibility of license plate number 3, we can obtain the comprehensive credibility of license plate number 3. By multiplying the credibility of license plate number 1 by the credibility of license plate number 4, we can obtain the comprehensive credibility of license plate number 4. By multiplying the credibility of license plate number 2 by the credibility of license plate number 5, we can obtain the comprehensive credibility of license plate number 5. In this way, based on the credibility of each of the two license plate numbers, a comprehensive credibility is obtained, which can accurately represent the probability that the two license plate numbers represent the same vehicle. The calculation process is also relatively simple, saving the time required for the vehicle capture information fusion process. In some embodiments, the electronic device determines whether to fuse the second vehicle capture information and the second fusion queue based on the second judgment result. Specifically, if the second judgment result indicates that the comprehensive credibility meeting the preset credibility condition is one, the electronic device determines whether there is vehicle capture information in the third fusion queue in the second acquisition direction, and obtains a third judgment result. The second acquisition direction is the acquisition direction of the second vehicle image in the second vehicle capture information, and the third fusion queue is the second fusion queue corresponding to the target license plate number that meets the preset credibility condition. If the third judgment result indicates that there is no vehicle capture information in the second acquisition direction in the third fusion queue, the second vehicle capture information is stored in the third fusion queue. If the third judgment result indicates that there is vehicle capture information in the second acquisition direction in the third fusion queue, the device determines whether the fifth license plate number in the vehicle capture information in the second acquisition direction in the third fusion queue is the same as the target license plate number, and obtains a fourth judgment result. Based on the fourth judgment result, the second vehicle capture information and the third fusion queue are fused.

[0099] Specifically, when the overall credibility is within a preset credibility threshold range, the overall credibility satisfies the preset credibility condition. Since the license plate number to be compared and the target license plate number are different, the higher the credibility of the two license plate numbers, the higher the overall credibility between them, and the lower the probability of misidentification. In other words, the lower the probability that the two license plate numbers represent the same vehicle. Conversely, a lower overall credibility indicates that at least one of the license plate numbers has a low credibility, and the credibility of both license plate numbers representing the same vehicle is also low. Therefore, by setting a preset credibility threshold range, excessively high or low overall credibility values ​​are deleted, retaining only those with relatively high credibility. The retained overall credibility values ​​correspond to a relatively high probability that the two license plate numbers represent the same vehicle.

[0100] For example, based on the above example, if the overall credibility of license plate number 3, license plate number 4, and license plate number 5 is such that only the overall credibility of license plate number 4 falls within the preset credibility threshold range, then the queue to be fused corresponding to license plate number 4 becomes the third queue to be fused. The electronic device then fuses the second vehicle capture information with the third queue to be fused. In this way, by using the credibility of each license plate number to be compared and the credibility of each target license plate number, the overall credibility of each target license plate number is determined. This allows for the selection of overall credibility that meets the conditions within the preset credibility threshold range. Furthermore, based on the selected overall credibility, the second queue to be fused can be determined more accurately, resulting in a more accurate fusion result for the vehicle capture information.

[0101] In some embodiments, the electronic device fuses the second vehicle capture information and the third fusion queue according to the fourth judgment result. Specifically, if the fourth judgment result indicates that the fifth license plate number in the vehicle capture information in the second acquisition direction in the third fusion queue is different from the target license plate number, the number of identical characters between the fifth license plate number and the target license plate number is determined as a first value, and the number of identical characters between the license plate number to be compared that differs from the target license plate number by N positions is determined as a second value; if the second value is greater than the first value, or the second value is equal to the first value, and the confidence of the license plate number to be compared that differs from the target license plate number by N positions is greater than the confidence of the fifth license plate number, the second vehicle capture information replaces the vehicle capture information in the second acquisition direction in the third fusion queue.

[0102] For example, the identifier information of the third queue to be fused is license plate number 1, and the license plate number to be compared with license plate number 1 that meets the preset confidence level is license plate number 2. If there is no vehicle capture information in the third queue to be fused with the same acquisition direction as the second vehicle capture information, the electronic device directly stores the second vehicle capture information in the third queue to be fused. If there is vehicle capture information A in the third queue to be fused with the same acquisition direction as the second vehicle capture information, and vehicle capture information A includes license plate number 3, the electronic device determines the number of identical characters 'a' in license plate number 1 and license plate number 2, and the number of identical characters 'b' in license plate number 1 and license plate number 3. If a < b, the electronic device still retains vehicle capture information A. If a = b, the electronic device further compares the credibility of license plate number 2 with that of license plate number 3. When the credibility of license plate number 2 is greater than that of license plate number 3, the electronic device replaces vehicle capture information A with the second vehicle capture information. When the credibility of license plate number 2 is less than that of license plate number 3, the electronic device retains vehicle capture information A. When the credibility of license plate number 2 is equal to that of license plate number 3, the electronic device can either retain vehicle capture information A or replace it with the second vehicle capture information. If a > b, the electronic device replaces vehicle capture information A with the second vehicle capture information.

[0103] In this way, the more identical characters two license plate numbers have, the greater the likelihood that the two license plate numbers represent the same vehicle. By comparing the number of identical characters between the fifth license plate number and the target license plate number, and the number of identical characters between the license plate number to be compared (which differs from the target license plate number by N positions) and the target license plate number, vehicle capture information with a large number of identical characters to the identifier information in the third fusion queue can be retained. The last vehicle capture information stored in the third fusion queue is also more likely to represent the same vehicle, resulting in a more accurate final vehicle capture information fusion result. In some embodiments, the electronic device determines whether to fuse the second vehicle capture information and the second fusion queue based on the second judgment result. This can also be implemented as follows: if the second judgment result indicates that multiple comprehensive credibility levels meet the preset credibility conditions, the fourth fusion queue containing the vehicle capture information with the highest similarity to the second vehicle capture information is determined from the second fusion queue corresponding to the target license plate number that meets the preset credibility conditions; the second vehicle capture information and the fourth fusion queue are then fused according to the second acquisition direction.

[0104] For example, there are no queues to be merged whose identification information differs from the license plate number to be compared by 1 digit. However, there are 3 queues to be merged whose identification information differs from the second license plate number by 2 digits, and 3 queues to be merged whose identification information differs from the third license plate number by 2 digits. The comprehensive credibility of these 5 target license plate numbers is calculated. If all 5 comprehensive credibility values ​​meet the preset credibility conditions, the vehicle capture information first received in the queues to be merged with the second vehicle capture information is compared with the second vehicle capture information. The queue to be merged corresponding to the vehicle capture information with the highest similarity to the second vehicle capture information is the queue to be merged with the second vehicle capture information.

[0105] In this way, after determining multiple comprehensive credibility levels that meet the preset credibility similarity conditions, the fourth fusion queue is determined more accurately by comparing the similarity between the first vehicle capture information received in the fusion queue corresponding to these comprehensive credibility levels and the second vehicle capture information. Finally, the fusion result of the vehicle capture information is also more accurate. Figure 3 The technical solution described above offers at least the following advantages: Upon first acquisition of vehicle capture information containing the first license plate number, a first fusion queue is established using the first license plate number as an identifier. The first vehicle capture information is stored in this queue. It is then determined whether the license plate number of the second capture information received within a target time period after acquiring the first vehicle capture information is the same as the first license plate number. Based on the determination result, it is decided whether to fuse the second vehicle capture information and the first fusion queue. In this way, the license plate number alone can determine whether to fuse capture information from different vehicles. Even if the order in which vehicle capture information is collected differs from the order in which the electronic device receives the information, it can accurately fuse capture information from the same vehicle in different acquisition directions, avoiding errors such as merging capture information from different vehicles together. The vehicle information fusion result is also more accurate.

[0106] In some embodiments, when the first license plate number has no characters, within a target time period, the vehicle capture information with the highest similarity to the first vehicle capture information from the pre-stored vehicle capture information to be fused is used as the second vehicle capture information. For example, if the electronic device cannot identify the license plate number from the first vehicle image, i.e., the first license plate number has no characters, the electronic device cannot determine whether the two vehicle capture information belong to the same vehicle based on the license plate number. The electronic device determines the similarity between the two vehicle capture information based on other information in the vehicle capture information, thereby determining the queue to be fused containing the vehicle capture information with the highest similarity to the first vehicle capture information, which is the vehicle capture information to be stored from the first vehicle capture information.

[0107] In this way, even if a vehicle does not have a license plate, the electronic device can determine the vehicle's capture information in other acquisition directions from the vehicle capture information to be merged based on other content in the vehicle capture information, and perform vehicle capture information fusion operation.

[0108] In some embodiments, when the first license plate number includes target characters, the electronic device determines the vehicle capture information that has the highest similarity to the first vehicle capture information and is received earliest from the pre-stored vehicle capture information to be merged as the second vehicle capture information.

[0109] Under normal circumstances, there is no network delay between the acquisition device and the electronic device. The frontal image of the vehicle is captured by the acquisition device first, that is, the electronic device first receives the frontal image of the vehicle, then the side image of the vehicle, and finally the rear image of the vehicle.

[0110] The information with the highest similarity to the first vehicle captured should meet the following conditions:

[0111] Condition 1: The lane numbers are the same.

[0112] Condition 2: The vehicles are of the same type.

[0113] Condition 3: All license plates are yellow.

[0114] Condition 4: The number of axles in all vehicles is greater than 4.

[0115] Condition 5: T2 < T1, and T3 < T1. Specifically, for each queue to be fused that satisfies conditions 1, 2, 3, and 4, the time difference T1 between the acquisition time of the acquisition device with the acquisition direction facing forward and the acquisition time of the acquisition device with the acquisition direction facing backward is determined based on the vehicle speed in the vehicle capture information with the acquisition direction facing forward and the distance between the acquisition range of the acquisition device with the acquisition direction facing backward. The time difference T2 between the acquisition time of the first vehicle image and the acquisition time of the acquisition device with the acquisition direction facing forward of the vehicle corresponding to the first vehicle image is determined based on the vehicle speed in the first vehicle capture information and the distance between the acquisition range of the acquisition device with the acquisition direction facing backward. The time difference T3 is determined based on the acquisition time of the first vehicle image and the acquisition time of the vehicle capture information with the acquisition direction facing forward in the queue to be fused.

[0116] From the queue of vehicles to be merged under conditions one through five, the vehicle capture information with the earliest collection time, i.e. the earliest reception time, is determined as the second vehicle capture information associated with the first license plate number.

[0117] In practical applications, the target character is the character "挂" (hanging). A trailer refers to a vehicle that is towed by an automobile and has no self-powered driving device. It can only form a complete transportation tool together with a tractor or other automobiles. The license plate number of the tractor is different from that of the trailer. The license plate of the tractor is located in the front of the tractor, and the license plate of the trailer is located in the back of the trailer. It is impossible to determine the tractor of the trailer from the license plate number.

[0118] After the electronic device receives the vehicle capture information, if it recognizes a license plate number containing the character "挂" (hanging) from the vehicle image in the vehicle capture information, it indicates that this vehicle image should be captured by the acquisition device that captures the vehicle's back image. That is, the images of the vehicle facing forward and sideways have been captured. Therefore, only by searching for the vehicle capture information that meets the above five conditions from the vehicle capture information to be fused can we obtain the vehicle capture information of the vehicle in other directions. The electronic device can fuse these vehicle capture information.

[0119] In this way, since the front and rear license plates of the vehicle containing the target character are different, when the target character is contained in the first license plate number, by finding the vehicle capture information to be fused that has the highest similarity and the earliest receiving time with the first vehicle capture information, we can find the second vehicle capture information associated with the first vehicle capture information and perform the vehicle capture information fusion operation. Considering the special case where the target character is contained in the license plate number, the electronic device can perform the vehicle capture information fusion operation for different vehicles.

[0120] As Figure 4 shown, the solution provided by this application will be described in detail from the perspective of the overall process.

[0121] The electronic device receives first vehicle capture information, which includes license plate number p1. It determines whether this is the first time the first vehicle capture information has been received. If it is, a fusion queue is established using p1 as the identifier. If it is not the first time, it checks the pre-stored identifiers of the fusion queues to see if pk = p1 exists. If p2 = p1 exists, the first vehicle capture information and the fusion queue corresponding to p2 are fused. If pk = p1 does not exist, the first vehicle image in the first vehicle capture information undergoes secondary recognition to obtain license plate number p3. It then checks again if pk = p3. If p4 = p3 exists, the first vehicle capture information and the fusion queue corresponding to p4 are fused. If pk = p3 does not exist, it searches the pre-stored identifiers of the fusion queues for a license plate number that differs from p1 and / or p3 by one character. If p5 differs from p1 by one character, and p6 differs from p3 by one character, then the overall credibility between p5 and p1 (p5*p1) and between p6 and p3 (p6*p3) are further obtained. From these multiple overall credibility values, the overall credibility values ​​that meet the preset credibility conditions are selected. Then, from the selected overall credibility values, the queue to be fused with the highest similarity to the first vehicle capture information is chosen. The final selected queue to be fused and the first vehicle capture information are then fused. If there is no license plate number that differs from p1 and / or p3 by one character, then the pre-stored identifier information of the queue to be fused is searched for a license plate number that differs from p1 and / or p3 by two characters. If multiple license plate numbers p5 differ from p1 or p3 by two digits, the overall confidence score p1*p5 or p3*p5 is compared with a threshold. Those with a confidence score less than the threshold are considered valid license plate numbers. If only one overall confidence score is less than the threshold, the aforementioned direction-related fusion judgment process is executed. If multiple license plate numbers have overall confidence scores less than the threshold, the most suitable license plate number is further determined based on other information in the vehicle capture data, and the direction-related fusion judgment process is then executed. If no license plate number differs from p1 or p3 by two digits, a fusion queue is established using p1 as the identifier, and the first vehicle capture data is stored in this fusion queue.

[0122] like Figure 5 As shown, the fusion process of vehicle capture information will be introduced by taking the fusion of the first vehicle capture information corresponding to p1 and the second queue to be fused corresponding to p2 as an example.

[0123] If no vehicle capture information with the same acquisition direction as the first vehicle capture information exists in the second queue to be merged, the first vehicle capture information is directly stored in the second queue to be merged. If the second queue contains second vehicle capture information with the same acquisition direction as the first vehicle capture information, the electronic device determines the same number of digits 'a' between license plate numbers p3 and p2, and the same number of digits 'b' between license plate numbers p1 and p2 in the second vehicle capture information. If a < b, the electronic device replaces the second vehicle capture information with the first vehicle capture information; if a = b, the electronic device compares the confidence levels of p1 and p3. If the confidence level of p1 is greater than that of p3, the electronic device replaces the second vehicle capture information with the first vehicle capture information; if the confidence level of p3 is greater than that of p1, the electronic device retains the second vehicle capture information; if a > b, the electronic device retains the second vehicle capture information.

[0124] The foregoing primarily describes the solutions provided by the embodiments of this application from a methodological perspective. To achieve the aforementioned functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0125] like Figure 6 As shown in the figure, this application embodiment also provides a vehicle information fusion device for the vehicle information fusion method shown in the above method embodiment. The vehicle information fusion device 400 includes: an acquisition module 401 and a processing module 402. The acquisition module 401 is used to acquire first vehicle capture information containing a first license plate number; the processing module 402 is used to, upon first acquisition of the first vehicle capture information containing the first license plate number, establish a first queue to be fused using the first license plate number as identifier information, and store the first vehicle capture information in the first queue to be fused; the processing module 402 is further used to, within a target time period after acquiring the first vehicle capture information, if second vehicle capture information is acquired, determine whether the license plate number to be compared corresponding to the second vehicle capture information is the same as the first license plate number, and obtain a first judgment result; the processing module 402 is further used to, based on the first judgment result, determine whether to fuse the second vehicle capture information and the first queue to be fused.

[0126] In one possible implementation, the second vehicle capture information includes a second vehicle image and a second license plate number, wherein the second license plate number is the license plate number identified from the second vehicle image; the license plate number to be compared corresponding to the second vehicle capture information is the second license plate number and the third license plate number, wherein the third license plate number is the license plate number obtained by secondary recognition of the second vehicle image when there is no queue of identification information that is the same as the second license plate number.

[0127] In one possible implementation, the processing module 402 is specifically used to fuse the second vehicle capture information and the first queue to be fused when the first judgment result indicates that the first license plate number is the same as the second license plate number, or when the first judgment result indicates that the first license plate number is different from the second license plate number and the first license plate number is the same as the third license plate number.

[0128] In one possible implementation, the second vehicle capture information also includes a second acquisition direction, which is the acquisition direction of the second vehicle image in the second vehicle capture information; the processing module 402 is specifically used to fuse the second vehicle capture information and the first fusion queue according to the acquisition direction in each vehicle capture information in the first fusion queue and the second acquisition direction.

[0129] In one possible implementation, the processing module 402 is specifically used to: if there is no vehicle capture information in the first queue to be fused with the same acquisition direction as the second acquisition direction, store the second vehicle capture information in the first queue to be fused. In another possible implementation, the processing module 402 is specifically used to: if there is third vehicle capture information in the first queue to be fused with the same acquisition direction as the second acquisition direction, compare the fourth license plate number in the third vehicle capture information with the first license plate number to obtain a comparison result; and based on the comparison result, fuse the second vehicle capture information and the first queue to be fused.

[0130] In one possible implementation, the processing module 402 is specifically used to replace the third vehicle capture information with the second vehicle capture information if the comparison result indicates that the fourth license plate number is different from the first license plate number.

[0131] In one possible implementation, the processing module 402 is specifically used to replace the third vehicle capture information with the second vehicle capture information if the comparison result indicates that the fourth license plate number is the same as the first license plate number, and the credibility of the license plate number to be compared corresponding to the second vehicle capture information is greater than the credibility of the fourth license plate number.

[0132] In one possible implementation, the processing module 402 is specifically used to: if there is no queue of vehicles to be fused with the same identification information as the license plate number to be compared, then within the target time period of receiving the second vehicle capture information, search for a queue of vehicles to be fused where the identification information differs from the license plate number to be compared by N bits, where N is a positive integer; if a queue of vehicles to be fused with the same identification information as the license plate number to be compared by N bits is found, then determine the comprehensive credibility of each target license plate number based on the credibility of the license plate number to be compared and the credibility of each target license plate number, where the target license plate number is the identification information of the second queue of vehicles to be fused, and the credibility of the target license plate number is the credibility of the license plate number in the earliest captured vehicle capture information in the second queue of vehicles to be fused; determine whether the comprehensive credibility of each target license plate number meets the preset credibility condition to obtain a second judgment result; and determine whether to fuse the second vehicle capture information and the second queue of vehicles to be fused based on the second judgment result. In one possible implementation, the processing module 402 is specifically used to: search for whether there exists a queue of vehicles whose identification information differs from the license plate number to be compared by i bits, where i is a positive integer; if there is no queue of vehicles whose identification information differs from the license plate number to be compared by i bits, search for whether there exists a queue of vehicles whose identification information differs from the license plate number to be compared by i+1 bits; wherein, i is 1 in the first search.

[0133] In one possible implementation, the processing module 402 is specifically used to obtain the credibility of a second or third license plate number that differs from the target license plate number by N bits; and to determine the overall credibility of each target license plate number based on the credibility of each target license plate number and the credibility of the second or third license plate number that differs from the target license plate number by N bits.

[0134] In one possible implementation, the processing module 402 is specifically used to: if the second judgment result indicates that the comprehensive credibility that meets the preset credibility condition is one, then determine whether there is vehicle capture information in the third fusion queue in the second acquisition direction, and obtain the third judgment result. The second acquisition direction is the acquisition direction of the second vehicle image in the second vehicle capture information, and the third fusion queue is the second fusion queue corresponding to the target license plate number that meets the preset credibility condition.

[0135] In one possible implementation, the processing module 402 is specifically used to: if the third judgment result is that there is no vehicle capture information in the second acquisition direction in the third queue to be fused, then store the second vehicle capture information into the third queue to be fused; if the third judgment result is that there is vehicle capture information in the second acquisition direction in the third queue to be fused, then determine whether the fifth license plate number in the vehicle capture information in the second acquisition direction in the third queue to be fused is the same as the target license plate number, and obtain a fourth judgment result; and according to the fourth judgment result, fuse the second vehicle capture information and the third queue to be fused.

[0136] In one possible implementation, the processing module 402 is specifically used to: if the fourth judgment result indicates that the fifth license plate number in the vehicle capture information in the second acquisition direction in the third fusion queue is different from the target license plate number, determine the number of identical characters between the fifth license plate number and the target license plate number as a first value, and the number of identical characters between the license plate number to be compared that differs from the target license plate number by N positions as a second value; if the second value is greater than the first value, or the second value is equal to the first value, and the credibility of the license plate number to be compared that differs from the target license plate number by N positions is greater than the credibility of the fifth license plate number, replace the vehicle capture information in the second acquisition direction in the third fusion queue with the second vehicle capture information.

[0137] In one possible implementation, the processing module 402 is specifically used to: if the second judgment result indicates that multiple comprehensive credibility levels all meet preset credibility conditions, determine the fourth fusion queue containing the vehicle capture information with the highest similarity to the second vehicle capture information from the second fusion queue corresponding to the target license plate number corresponding to the multiple comprehensive credibility levels that meet the preset credibility conditions; and fuse the second vehicle capture information and the fourth fusion queue according to the second acquisition direction. In another possible implementation, the processing module 402 is further used to: if the first license plate number has no characters and the second license plate number has no characters, and the similarity between the first vehicle capture information and the second vehicle capture information is within a preset similarity range, fuse the second vehicle capture information and the first fusion queue.

[0138] It should be noted that, Figure 6 The module division shown is illustrative and represents only one logical functional division; in actual implementation, other division methods are possible. For example, two or more functions can be integrated into one processing module. The integrated modules described above can be implemented in hardware or as software functional modules. Another embodiment of this application also provides an electronic device, such as... Figure 7As shown, the electronic device 500 includes a memory 501 and a processor 502; the memory 501 and the processor 502 are coupled; the memory 501 is used to store computer program code, which includes computer instructions. When the processor 502 executes the computer instructions, the electronic device 500 performs each step of the method flow shown in the above method embodiment.

[0139] In actual implementation, the acquisition module 401 and the processing module 402 can be composed of... Figure 7 The processor 502 shown calls the computer program code in memory 501 to implement this. The specific execution process can be found in the description of the vehicle information fusion method section above, and will not be repeated here.

[0140] Another embodiment of this application provides a computer-readable storage medium storing computer instructions that, when executed on an electronic device, cause the electronic device to perform each step of the method flow shown in the above method embodiment.

[0141] Another embodiment of this application provides a chip system applied to an electronic device. The chip system includes one or more interface circuits and one or more processors. The interface circuits and processors are interconnected via lines. The interface circuits are used to receive signals from the electronic device's memory and send the signals to the processors, the signals including computer instructions stored in the memory. When the processor of the electronic device executes the computer instructions, the electronic device performs each step of the method flow shown in the above method embodiments.

[0142] In another embodiment of this application, a computer program product is also provided, which includes computer instructions that, when executed on an electronic device, cause the electronic device to perform the various steps of the method flow shown in the above method embodiments.

[0143] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When these computer instructions are loaded and executed on a computer, all or part of the flow or function according to the embodiments of this application is generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), etc.

[0144] The above description is merely a specific embodiment of this application. Any variations or substitutions conceived by those skilled in the art based on the specific embodiments provided in this application should be covered within the protection scope of this application.

Claims

1. A vehicle information fusion method, characterized in that, Applied to electronic devices; the method includes: Upon first obtaining the first vehicle capture information containing the first license plate number, a first queue to be merged is established using the first license plate number as the identifier, and the first vehicle capture information is stored in the first queue to be merged. Within the target time period after obtaining the first vehicle capture information, if the second vehicle capture information is obtained, it is determined whether the license plate number to be compared corresponding to the second vehicle capture information is the same as the first license plate number, and a first judgment result is obtained. Based on the first judgment result, determine whether to fuse the second vehicle capture information and the first queue to be fused; The second vehicle capture information also includes a second acquisition direction, which is the acquisition direction of the second vehicle image in the second vehicle capture information; The fusion of the second vehicle capture information and the first queue to be fused includes: If there is a third vehicle capture information in the first queue to be fused with the same acquisition direction as the second acquisition direction, then the fourth license plate number in the third vehicle capture information is compared with the first license plate number to obtain the comparison result; If the comparison result indicates that the fourth license plate number is different from the first license plate number, then the third vehicle capture information is replaced with the second vehicle capture information; or, If the comparison result indicates that the fourth license plate number is the same as the first license plate number, and the credibility of the license plate number to be compared corresponding to the second vehicle capture information is greater than the credibility of the fourth license plate number, then the third vehicle capture information is replaced with the second vehicle capture information.

2. The method according to claim 1, characterized in that, The second vehicle capture information includes a second vehicle image and a second license plate number, wherein the second license plate number is the license plate number identified from the second vehicle image; The license plate numbers to be compared corresponding to the second vehicle capture information are the second license plate number and the third license plate number. The third license plate number is the license plate number obtained by secondary recognition of the second vehicle image when there is no queue of identification information that is the same as the second license plate number.

3. The method according to claim 2, characterized in that, The step of determining whether to fuse the second vehicle capture information and the first queue to be fused based on the first judgment result includes: If the first judgment result indicates that the first license plate number is the same as the second license plate number, or if the first judgment result indicates that the first license plate number is different from the second license plate number and the first license plate number is the same as the third license plate number, the second vehicle capture information and the first queue to be fused are fused.

4. The method according to claim 1, characterized in that, The fusion of the second vehicle capture information and the first queue to be fused further includes: If there is no vehicle capture information in the first queue to be fused that has the same acquisition direction as the second acquisition direction, the second vehicle capture information is stored in the first queue to be fused.

5. The method according to claim 2, characterized in that, The step of determining whether to fuse the second vehicle capture information and the first queue to be fused based on the first judgment result includes: If there is no queue to be fused that has the same identification information as the license plate number to be compared, then within the target time period after receiving the second vehicle capture information, it is searched to see if there is a queue to be fused where the identification information differs from the license plate number to be compared by N bits, where N is a positive integer; If the identification information of the second queue to be fused is found to differ from the license plate number to be compared by N bits, then the overall credibility of each target license plate number is determined based on the credibility of the license plate number to be compared and the credibility of each target license plate number. The target license plate number is the identification information of the second queue to be fused, and the credibility of the target license plate number is the credibility of the license plate number in the vehicle capture information with the earliest collection time in the second queue to be fused. Determine whether the overall credibility of each target license plate number meets the preset credibility conditions to obtain a second judgment result; Based on the second judgment result, determine whether to merge the second vehicle capture information and the second queue to be merged.

6. The method according to claim 5, characterized in that, The step of checking whether there exists a fusion queue whose identifier information differs from the license plate number to be compared by N bits includes: Check if there exists a fusion queue where the identification information differs from the license plate number to be compared by i bits, where i is a positive integer; If there is no queue of vehicles to be fused whose identification information differs from the license plate number to be compared by i bits, search for a queue of vehicles to be fused whose identification information differs from the license plate number to be compared by i+1 bits; where i is 1 in the first search.

7. The method according to claim 5, characterized in that, The step of determining the overall credibility of each target license plate number based on the credibility of the license plate number to be compared and the credibility of each target license plate number includes: Obtain the credibility of a second or third license plate number that differs from the target license plate number by N bits; Based on the credibility of each target license plate number and the credibility of a second or third license plate number that differs from the target license plate number by N positions, the overall credibility of each target license plate number is determined.

8. The method according to claim 5, characterized in that, The step of determining whether to fuse the second vehicle capture information and the second queue to be fused based on the second judgment result includes: If the second judgment result represents a comprehensive credibility that meets the preset credibility conditions, then it is determined whether there is vehicle capture information in the third fusion queue with the second acquisition direction, and a third judgment result is obtained. The second acquisition direction is the acquisition direction of the second vehicle image in the second vehicle capture information. The third fusion queue is the second fusion queue corresponding to the target license plate number that meets the preset credibility conditions. If the third judgment result is that there is no vehicle capture information in the second acquisition direction in the third queue to be fused, then the second vehicle capture information is stored in the third queue to be fused. If the third judgment result is that there is vehicle capture information in the second acquisition direction in the third queue to be fused, then it is determined whether the fifth license plate number in the vehicle capture information in the second acquisition direction in the third queue to be fused is the same as the target license plate number, and a fourth judgment result is obtained. Based on the fourth judgment result, the second vehicle capture information and the third queue to be merged are fused.

9. The method according to claim 8, characterized in that, The step of fusing the second vehicle capture information and the third queue to be fused based on the fourth judgment result includes: If the fourth judgment result indicates that the fifth license plate number in the vehicle capture information of the second acquisition direction in the third fusion queue is different from the target license plate number, the number of identical characters between the fifth license plate number and the target license plate number is determined as a first value, and the number of identical characters between the license plate number to be compared and the target license plate number that differs from the target license plate number by N positions is determined as a second value. If the second value is greater than the first value, or the second value is equal to the first value, and the credibility of the license plate number to be compared that differs from the target license plate number by N bits is greater than the credibility of the fifth license plate number, then the vehicle capture information in the second acquisition direction in the third fusion queue is replaced with the second vehicle capture information.

10. The method according to claim 5, characterized in that, The step of determining whether to fuse the second vehicle capture information and the second queue to be fused based on the second judgment result further includes: If the second judgment result indicates that multiple comprehensive credibility values ​​meet the preset credibility conditions, then from the second queue of the target license plate numbers corresponding to the multiple comprehensive credibility values ​​that meet the preset credibility conditions, the fourth queue of the vehicle capture information with the highest similarity to the second vehicle capture information is determined. According to the second acquisition direction, the second vehicle capture information and the fourth queue to be fused are fused.

11. The method according to claim 1, characterized in that, The method further includes: If the first license plate number has no characters and the second license plate number has no characters, and the similarity between the first vehicle capture information and the second vehicle capture information is within a preset similarity range, the second vehicle capture information and the first fusion queue are fused, and the second license plate number is the license plate number identified from the second vehicle image.

12. A vehicle information fusion device, characterized in that, include: The acquisition module is used to acquire the first vehicle capture information containing the first license plate number; The processing module is used to establish a first queue to be fused with the first license plate number as the identifier when the first vehicle capture information containing the first license plate number is obtained for the first time, and to store the first vehicle capture information in the first queue to be fused. The processing module is further configured to, within a target time period after obtaining the first vehicle capture information, if the second vehicle capture information is obtained, determine whether the license plate number to be compared corresponding to the second vehicle capture information is the same as the first license plate number, and obtain a first judgment result; The processing module is further configured to determine, based on the first judgment result, whether to fuse the second vehicle capture information and the first queue to be fused. The second vehicle capture information also includes a second acquisition direction, which is the acquisition direction of the second vehicle image in the second vehicle capture information; The processing module is also used for: If there is a third vehicle capture information in the first queue to be fused with the same acquisition direction as the second acquisition direction, then the fourth license plate number in the third vehicle capture information is compared with the first license plate number to obtain the comparison result; If the comparison result indicates that the fourth license plate number is different from the first license plate number, then the third vehicle capture information is replaced with the second vehicle capture information; or, If the comparison result indicates that the fourth license plate number is the same as the first license plate number, and the credibility of the license plate number to be compared corresponding to the second vehicle capture information is greater than the credibility of the fourth license plate number, then the third vehicle capture information is replaced with the second vehicle capture information.

13. The apparatus according to claim 12, characterized in that, The second vehicle capture information includes a second vehicle image and a second license plate number, wherein the second license plate number is the license plate number identified from the second vehicle image; the license plate number to be compared corresponding to the second vehicle capture information is the second license plate number and a third license plate number, wherein the third license plate number is the license plate number obtained by secondary recognition of the second vehicle image when there is no queue of identification information that is the same as the second license plate number; The processing module is specifically used to fuse the second vehicle capture information and the first fusion queue when the first judgment result indicates that the first license plate number is the same as the second license plate number, or when the first judgment result indicates that the first license plate number is different from the second license plate number and the first license plate number is the same as the third license plate number. The processing module is specifically used to store the second vehicle capture information in the first queue to be fused if there is no vehicle capture information in the first queue to be fused with the same capture direction as the second capture direction. The processing module is specifically used to: if there is no queue to be fused with the same identification information as the license plate number to be compared, then within the target time period of receiving the second vehicle capture information, search for a queue to be fused where the identification information differs from the license plate number to be compared by N bits, where N is a positive integer; if the identification information of the second queue to be fused is found to differ from the license plate number to be compared by N bits, then determine the comprehensive credibility of each target license plate number based on the credibility of the license plate number to be compared and the credibility of each target license plate number, where the target license plate number is the identification information of the second queue to be fused, and the credibility of the target license plate number is the credibility of the license plate number in the earliest captured vehicle capture information in the second queue to be fused; determine whether the comprehensive credibility of each target license plate number meets the preset credibility condition to obtain a second judgment result; and determine whether to fuse the second vehicle capture information and the second queue to be fused based on the second judgment result. The processing module is specifically used to: search for whether there is a fusion queue whose identification information differs from the license plate number to be compared by i bits, where i is a positive integer; if there is no fusion queue whose identification information differs from the license plate number to be compared by i bits, search for whether there is a fusion queue whose identification information differs from the license plate number to be compared by i+1 bits; wherein, i is 1 in the first search; The processing module is specifically used to: obtain the credibility of a second license plate number or a third license plate number that differs from the target license plate number by N positions; and determine the overall credibility of each target license plate number based on the credibility of each target license plate number and the credibility of the second license plate number or the third license plate number that differs from the target license plate number by N positions. The processing module is specifically used to: if the second judgment result represents a comprehensive credibility that meets the preset credibility conditions as one, then determine whether there is vehicle capture information in the third fusion queue with the second acquisition direction, and obtain the third judgment result. The second acquisition direction is the acquisition direction of the second vehicle image in the second vehicle capture information. The third fusion queue is the second fusion queue corresponding to the target license plate number that meets the preset credibility conditions. If the third judgment result is that there is no vehicle capture information in the second acquisition direction in the third queue to be fused, then the second vehicle capture information is stored in the third queue to be fused; if the third judgment result is that there is vehicle capture information in the second acquisition direction in the third queue to be fused, then it is determined whether the fifth license plate number in the vehicle capture information in the second acquisition direction in the third queue to be fused is the same as the target license plate number, and a fourth judgment result is obtained; according to the fourth judgment result, the second vehicle capture information and the third queue to be fused are fused. The processing module is specifically used to: if the fourth judgment result indicates that the fifth license plate number in the vehicle capture information of the second acquisition direction in the third fusion queue is different from the target license plate number, determine the number of identical characters between the fifth license plate number and the target license plate number as a first value, and the number of identical characters between the license plate number to be compared that differs from the target license plate number by N positions as a second value; if the second value is greater than the first value, or the second value is equal to the first value, and the confidence of the license plate number to be compared that differs from the target license plate number by N positions is greater than the confidence of the fifth license plate number, replace the vehicle capture information of the second acquisition direction in the third fusion queue with the second vehicle capture information; The processing module is specifically used to: if the second judgment result indicates that multiple comprehensive credibility values ​​meet the preset credibility conditions, determine the fourth fusion queue containing the vehicle capture information with the highest similarity to the second vehicle capture information from the second fusion queue corresponding to the target license plate number of the multiple comprehensive credibility values ​​that meet the preset credibility conditions; and fuse the second vehicle capture information and the fourth fusion queue according to the second acquisition direction. The processing module is further configured to, if the first license plate number has no characters and the second license plate number has no characters, and if the similarity between the first vehicle capture information and the second vehicle capture information is within a preset similarity range, fuse the second vehicle capture information and the first queue to be fused.

14. An electronic device, characterized in that, include: One or more processors; One or more memory units; The one or more memories are used to store computer program code, which includes computer instructions. When the one or more processors execute the computer instructions, the electronic device performs the vehicle information fusion method according to any one of claims 1 to 11.

15. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when executed on a computer, cause the computer to perform the vehicle information fusion method according to any one of claims 1 to 11.

16. A vehicle information fusion system, characterized in that, It includes a data acquisition device and an electronic device, wherein the data acquisition device establishes a communication connection with the electronic device; The acquisition device is used to acquire vehicle capture information and send the vehicle capture information to the electronic device. The electronic device is used to, upon first receiving first vehicle capture information containing a first license plate number, establish a first queue to be merged using the first license plate number as identification information, and store the first vehicle capture information in the first queue to be merged. The electronic device is further configured to, within a target time period after receiving the first vehicle capture information, if the second vehicle capture information is obtained, determine whether the license plate number to be compared corresponding to the second vehicle capture information is the same as the first license plate number, and obtain a first judgment result. The electronic device is further configured to determine, based on the first judgment result, whether to fuse the second vehicle capture information and the first queue to be fused. The second vehicle capture information also includes a second acquisition direction, which is the acquisition direction of the second vehicle image in the second vehicle capture information; The fusion of the second vehicle capture information and the first queue to be fused includes: If there is a third vehicle capture information in the first queue to be fused with the same acquisition direction as the second acquisition direction, then the fourth license plate number in the third vehicle capture information is compared with the first license plate number to obtain the comparison result; If the comparison result indicates that the fourth license plate number is different from the first license plate number, then the third vehicle capture information is replaced with the second vehicle capture information; or, If the comparison result indicates that the fourth license plate number is the same as the first license plate number, and the credibility of the license plate number to be compared corresponding to the second vehicle capture information is greater than the credibility of the fourth license plate number, then the third vehicle capture information is replaced with the second vehicle capture information.

Images