A high-speed scene vehicle target fusion method based on binocular unmanned aerial vehicle

Abstract

The application discloses a high-speed scene vehicle target fusion method based on binocular unmanned aerial vehicles, and relates to the technical field of image fusion, which comprises the following steps: based on two configured acquisition devices, video data of a to-be-detected road section is acquired, and a target queue corresponding to each acquisition device in a preset period is determined; for any one of the two acquisition devices, a detection frame corresponding to a target vehicle in the target queue corresponding to the acquisition device is sequentially mapped to the visual angle of the other acquisition device in combination with a pixel coordinate calibration result, and the same target vehicle in the common area is determined for target fusion processing. The application can improve the acquisition range by using two acquisition devices in cooperation, and can maintain the definition and accuracy of the fusion picture while ensuring the invariability of the acquisition range by combining the pixel coordinate calibration of the common area.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of image fusion, in particular to a high-speed scene vehicle target fusion method based on binocular unmanned aerial vehicles. BACKGROUND

[0002] At present, vehicle target detection technology in high-speed scenes is widely used. In order to cover a high-speed section, a large number of cameras are usually installed on both sides of the road or gantry. Due to the position and height of the cameras, it is often difficult to fully cover the high-speed section, and there is a lack of flexibility. During the morning and evening peak periods or holidays, the safety of vehicle driving becomes a major concern. SUMMARY

[0003] The technical problem to be solved by the present application is to overcome the deficiencies of the prior art. Specifically, a high-speed scene vehicle target fusion method based on binocular unmanned aerial vehicles is provided, which is as follows.

[0004] 1) In a first aspect, the present application provides a high-speed scene vehicle target fusion method based on binocular unmanned aerial vehicles, and the specific technical solution is as follows:

[0005] The video capture pictures of two capture devices mounted on a hovering unmanned aerial vehicle for data collection of a to-be-detected section are configured, and the common area of the capture pictures of the two capture devices for the to-be-detected section is subjected to pixel coordinate calibration processing.

[0006] Based on the two configured capture devices, video data of the to-be-detected section is collected, and a target queue corresponding to each capture device is determined within a preset period. The target queue includes at least one target vehicle basic information extracted based on video data arranged in time sequence.

[0007] For any one of the two capture devices, the detection frame corresponding to the target vehicle in the target queue corresponding to the capture device is sequentially mapped to the perspective of the other capture device of the two capture devices in combination with the pixel coordinate calibration processing result, and the same target vehicle in the common area is subjected to target fusion processing.

[0008] The high-speed scene vehicle target fusion method based on binocular unmanned aerial vehicles provided by the present application has the following beneficial effects:

[0009] Pixel coordinate calibration processing of the common area is beneficial to rapid coordinate conversion of the perspectives of the two capture devices. In addition, the use of two capture devices can improve the capture range, and the pixel coordinate calibration of the common area can maintain the clarity and accuracy of the fusion picture while ensuring the capture range.

[0010] Based on the above solution, the present invention can also be improved as follows.

[0011] Furthermore, it also includes:

[0012] For the video data collected by any of the two collection devices, the driving trajectory and speed corresponding to each target vehicle in the video data are determined in real time, and whether the target vehicle has violated traffic behavior is determined based on the driving trajectory and speed corresponding to any target vehicle. For the target vehicle that has violated traffic behavior, an approval image is generated, and an alarm message is generated based on the approval image.

[0013] Furthermore, it also includes:

[0014] For the video data collected by any of the two collection devices, the longitude and latitude coordinates of any target vehicle are uploaded in real time. For the target vehicle in the public area, when the front of the target vehicle enters the public area, the collection device corresponding to the area where the part of the vehicle body that has not entered the public area is located continues to provide video data for determining the longitude and latitude coordinates of the target vehicle.

[0015] Furthermore, it also includes:

[0016] The target fusion processing results are displayed in real time.

[0017] 2) In a second aspect, the present invention also provides a high-speed scene vehicle target fusion system based on a binocular drone, the specific technical solution of which is as follows:

[0018] The configuration module is used to configure the video collection images of two collection devices carried on the hovering drone for collecting data on the road section to be detected, and perform pixel coordinate calibration processing on the common area of ​​the collection images of the two collection devices for the road section to be detected;

[0019] The acquisition module is used to: collect video data of the road section to be detected based on the two configured acquisition devices, and determine the target queue corresponding to each acquisition device within a preset period, wherein the target queue includes basic information of at least one target vehicle extracted based on the video data and arranged in time sequence;

[0020] The fusion module is used to: for any of the two acquisition devices, combined with the pixel coordinate calibration processing results, sequentially map the detection frame corresponding to the target vehicle in the target queue corresponding to the acquisition device to the perspective of the other acquisition device of the two acquisition devices, and determine the same target vehicle in the common area for target fusion processing.

[0021] 3) In a third aspect, the present application also provides an electronic device, comprising a processor coupled with a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor to enable the electronic device to implement any of the above methods.

[0022] 4) In a fourth aspect, the present application also provides a computer readable storage medium, wherein the computer readable storage medium stores at least one computer program, and the at least one computer program is loaded and executed by a processor to enable a computer to implement any of the above methods.

[0023] It should be noted that the technical solutions of the second to fourth aspects of the present application and the corresponding possible implementation manners achieve the beneficial effects, which can be referred to the technical effects of the first aspect and the corresponding possible implementation manners described above, and will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0024] Other features, objects and advantages of the present application will become more apparent from the following detailed description of non-limiting embodiments thereof, read in conjunction with the accompanying drawings:

[0025] Figure 1 A flowchart of a high-speed scene vehicle target fusion method based on a binocular unmanned aerial vehicle according to an embodiment of the present application;

[0026] Figure 2 A structural framework diagram of an electronic device. DETAILED DESCRIPTION

[0027] In order to make the purposes, technical solutions and advantages of the present application clearer, the embodiments of the present application will be further described in detail below with reference to the accompanying drawings.

[0028] As shown in Figure 1 A high-speed scene vehicle target fusion method based on a binocular unmanned aerial vehicle according to an embodiment of the present application comprises the following steps:

[0029] S1, configuring video capture pictures of two capture devices for data collection on a to-be-detected road section mounted on a hovering unmanned aerial vehicle, and performing pixel coordinate calibration processing on a common area of the capture pictures of the two capture devices for the to-be-detected road section;

[0030] S2, based on the two configured capture devices, collecting video data on the to-be-detected road section, and determining a target queue corresponding to each capture device within a preset period, wherein the target queue comprises at least one target vehicle basic information extracted based on video data arranged in time sequence;

[0031] S3, in combination with the pixel coordinate calibration processing result, sequentially mapping the detection frame corresponding to the target vehicle in the target queue corresponding to any one of the two acquisition devices to the perspective of the other one of the two acquisition devices, and determining the same target vehicle in the public region to perform target fusion processing.

[0032] The high-speed scene vehicle target fusion method based on the binocular unmanned aerial vehicle has the following beneficial effects:

[0033] The pixel coordinate calibration processing of the public region is beneficial to quickly perform coordinate conversion of the perspectives of the two acquisition devices, and in addition, the two acquisition devices are used in cooperation to improve the acquisition range, and in combination with the pixel coordinate calibration of the public region, the clarity and accuracy of the fusion picture can be maintained while the acquisition range remains unchanged.

[0034] The to-be-detected road section usually refers to a high-speed road section, a bypass high-speed road section, and an elevated bridge road section, etc.

[0035] The acquisition device is a monocular camera or a camera that can support long-distance shooting.

[0036] The basic information of the target vehicle includes the detection frame of the vehicle, the vehicle category, the license plate number, the vehicle position, etc.

[0037] The process of configuring the video acquisition picture includes:

[0038] The aperture configuration, the ISO configuration, the frame rate configuration, the resolution configuration, the anti-shake configuration, the white balance configuration, and the focal length configuration, etc.

[0039] The configuration of the aperture:

[0040] The aperture refers to the size of the aperture of the camera lens, which is used to control the amount of light entering the camera. The larger the aperture, the greater the amount of light entering the camera, and vice versa. The setting of the aperture is very important for controlling the depth of field of the video. A large aperture can obtain a shallow depth of field, which is suitable for shooting portraits and other scenes that need to highlight the subject; a small aperture can obtain a deep depth of field, which is suitable for shooting landscapes and other scenes that need more details.

[0041] The configuration of the ISO:

[0042] ISO refers to the sensitivity of the camera, which is used to control the light sensitivity of the camera. The higher the ISO, the stronger the light sensitivity of the camera, which can obtain brighter images in darker environments, but at the same time, more noise will be introduced; the lower the ISO, the weaker the light sensitivity of the camera, which needs more light to shoot clear images, but at the same time, the occurrence of noise will be reduced.

[0043] The configuration process of the light sensitivity is specifically:

[0044] For the experimental area, multiple image data under the current configuration are collected, the definition of each image data is calculated, the proportion value of all definitions exceeding the threshold definition is determined, and when the proportion value is higher than the preset proportion value, the sensitivity configuration result in the current configuration is output as the final result.

[0045] If the proportion value is lower than the preset proportion value, then the target object in each image data is subjected to contour extraction, wherein the target object can be a vehicle, a pedestrian, a building, etc. The extracted contour is compared with the manually annotated contour to determine the target similarity corresponding to the two, determine the target difference value of the target similarity and the preset similarity, and in the difference value and the fine-tuning amount corresponding relationship, determine the target fine-tuning amount corresponding to the target difference value, and fine-tune the sensitivity under the current configuration based on the target fine-tuning amount. The target difference value includes positive and negative numbers.

[0046] In the contour extraction process of the target object:

[0047] The image is subjected to binarization processing. Binarization processing is to convert the image to black and white, with the background being black and the foreground being white. This can simplify the image and make the contour extraction more accurate.

[0048] Configuration of frame rate:

[0049] Frame rate refers to the number of frames captured per second. Common frame rates include 24 frames per second, 30 frames per second, and 60 frames per second, etc. The higher the frame rate, the smoother the picture, but it will also increase the file size and processing difficulty.

[0050] Configuration of resolution and anti-shake:

[0051] The higher the resolution, the more delicate the picture. The anti-shake function can effectively reduce the shaking during shooting and improve the stability of the video.

[0052] Configuration of white balance and focal length:

[0053] White balance is used to adjust the color balance of the picture to avoid color deviation. The selection of focal length will affect the range of viewfinder and the picture effect, and appropriate adjustment of focal length can obtain better picture effect.

[0054] Configuration of exposure compensation:

[0055] In program automatic mode, aperture priority and shutter priority mode, exposure compensation can adjust the brightness of the photo. When the photo is too dark, increase the exposure compensation; when the photo is too bright, reduce the exposure compensation.

[0056] The specific process of exposure compensation is:

[0057] The multiple image data photographed for the experimental area are acquired, and the brightness corresponding to each image data is determined, the time period of image data acquisition is combined with the current weather condition, in the historical database, all data corresponding to multiple days corresponding to the current weather condition are searched, the historical exposure compensation value corresponding to the time period in each day in the multiple days searched is extracted according to the time period of image data acquisition, the historical exposure compensation values are sorted according to the time sequence of the multiple days searched, and each historical exposure compensation value is weighted and distributed, wherein the historical exposure compensation value corresponding to the time farther away from the current time has a smaller weight value. According to the weight distribution result, all historical exposure compensation values are weighted and processed to obtain a final exposure compensation value, and exposure compensation configuration is performed according to the final exposure compensation value.

[0058] The public area refers to the overlapping part of the scenes collected by the two collection devices.

[0059] The purpose of the pixel coordinate calibration processing in the public area is to determine the pixel coordinate conversion matrix corresponding to the two collection devices, and the pixel coordinate conversion matrix can be used to convert the pixel coordinates of a point in the visual angle of any collection device to the pixel coordinates in the visual angle of another collection device.

[0060] The preset period is: according to the processing capacity of the back-end processor, determining the maximum data flow corresponding to the processing capacity, and determining the efficient range (the efficient range refers to the data flow range corresponding to the case that all data transmission channels are occupied but there is no queuing) in the maximum data flow, determining the data processing period range (preset period range) with the efficient range, that is, determining the current traffic flow, according to the current traffic flow and the road conditions of the multiple road sections corresponding to the road section, determining the preset period in the preset period range. For example: there are traffic accidents on the three road sections in front of the A lane, then a larger value in the preset period range is determined as the preset period.

[0061] Further, it further comprises:

[0062] For the video data collected by any of the two collection devices, the driving track and the speed corresponding to each target vehicle in the video data are determined in real time, whether the target vehicle has a traffic violation behavior is determined according to the driving track and the speed corresponding to any target vehicle, and for the target vehicle having a traffic violation behavior, an approval image is generated, and an alarm information is generated based on the approval image.

[0063] Further, it further comprises:

[0064] The latitude and longitude coordinates of any target vehicle are uploaded in real time for video data collected by any of the two collection devices, and for the target vehicle in the public area, the collection device corresponding to the area where the body part of the target vehicle has not entered the public area continuously provides video data for determining the latitude and longitude coordinates of the target vehicle when the head of the target vehicle enters the public area.

[0065] Further, it further comprises:

[0066] The target fusion processing result is displayed in real time.

[0067] In embodiment 1, the video detection algorithm is deployed in the airborne ARM box of the aerial hovering unmanned aerial vehicle. After the platform end obtains the push stream of the algorithm box, the video picture is configured, and the detection range of the expressway region is configured by two cameras. The pixel coordinates are calibrated on the public area of the two video regions, which facilitates the fusion of the target detection boxes of the two videos. The pixel and latitude and longitude coordinates are calibrated in the expressway region of the two video pictures, and when the vehicle target is in the corresponding region, the latitude and longitude coordinates thereof are calculated. The platform service issues the above configuration to the unmanned aerial vehicle algorithm, and starts real-time detection of the two video streams. The algorithm performs target fusion according to the target detection box, and the fused detection box enters the tracking algorithm module, thereby ensuring the uniqueness and continuity of the target. This pre-fusion method reduces the complexity of fusion compared with post-fusion. The specific algorithm processing process is as follows:

[0068] The video detection algorithm detects the targets in the detection regions of the two video streams respectively. The target queue after detection enters the fusion module. According to the pixel calibration of the public area configured in advance, all target pixel detection boxes in video picture 1 are mapped to video picture 2, and it is determined whether the target boxes in video picture 2 are the same target according to the intersection-over-union of the detection boxes. The target is fused.

[0069] The target queue after fusion passes through the tracking algorithm, thereby ensuring the uniqueness and continuity of the target Id. Through the event judgment module, traffic events such as parking, congestion, reverse driving and occupying the emergency lane are judged. When the event is satisfied, the alarm video and picture in the corresponding video picture are generated. For the target in the public area, two alarm videos and two alarm pictures are generated, thereby facilitating the user to view.

[0070] The fused target enters the twin trajectory generation module. In order to reduce the error of the latitude and longitude coordinates of the target, the pixel and latitude and longitude coordinates are calibrated in the expressway region of the two video pictures when the configuration is issued. When the vehicle target is in the corresponding region, the latitude and longitude coordinates thereof are calculated in the region. For the vehicle target in the public area, the latest region where the head enters is used as the reference, thereby reducing the fluctuation of the twin trajectory caused by the conversion of the pixel coordinates and the latitude and longitude coordinates.

[0071] The generated traffic event and target trajectory information are reported to a platform service in real time, and are displayed through a page, so that a user can conveniently know the event and vehicle target trajectory state occurring in two video pictures in real time.

[0072] In the above embodiments, although the steps are numbered S1, S2, etc., this is only a specific embodiment given by the present application, and a person skilled in the art can adjust the execution order of S1, S2, etc. according to the actual situation, which is within the protection scope of the present application. It can be understood that in some embodiments, some or all of the above embodiments can be included.

[0073] The application also provides a high-speed scene vehicle target fusion system based on a binocular unmanned aerial vehicle, and the specific technical solutions are as follows:

[0074] The configuration module is configured to configure video capture pictures of two capture devices for data collection on a to-be-detected road section carried on the hovering unmanned aerial vehicle, and perform pixel coordinate calibration processing on a common area of the capture pictures of the two capture devices for the to-be-detected road section.

[0075] The capture module is configured to collect video data of the to-be-detected road section based on the two configured capture devices, and determine a target queue corresponding to each capture device within a preset period, the target queue including at least one target vehicle basic information extracted based on the video data arranged in time sequence.

[0076] The fusion module is configured to, for any one of the two capture devices, sequentially map a detection frame corresponding to a target vehicle in a target queue corresponding to the capture device to a perspective of another capture device of the two capture devices in combination with a pixel coordinate calibration processing result, and determine the same target vehicle in the common area for target fusion processing.

[0077] It should be noted that the beneficial effects of the high-speed scene vehicle target fusion system based on the binocular unmanned aerial vehicle provided in the above embodiments are the same as those of the high-speed scene vehicle target fusion method based on the binocular unmanned aerial vehicle, and will not be repeated here. In addition, when the system provided in the above embodiments implements its functions, only the division of the above functional modules is taken as an example for illustration, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the system is divided into different functional modules according to actual conditions to complete all or part of the above described functions. In addition, the system and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is described in detail in the method embodiments, which will not be repeated here.

[0078] As Figure 2As shown, an electronic device 300 according to an embodiment of the present application includes a processor 320 coupled to a memory 310, and the memory 310 stores at least one computer program 330, and the at least one computer program 330 is loaded and executed by the processor 320, so that the electronic device 300 implements any of the above methods, in particular:

[0079] The electronic device 300 can be different in configuration or performance, and can include one or more processors 320 (Central Processing Units, CPUs) and one or more memories 310, wherein the one or more memories 310 store at least one computer program 330, and the at least one computer program 330 is loaded and executed by the one or more processors 320, so that the electronic device 300 implements the above embodiment of the method for fusing high-speed scene vehicle targets based on a binocular unmanned aerial vehicle. Of course, the electronic device 300 can also have a wired or wireless network interface, a keyboard, and an input and output interface, and other components for realizing the functions of the device, which are not described here.

[0080] A computer readable storage medium according to an embodiment of the present application stores at least one computer program, and the at least one computer program is loaded and executed by a processor, so that the computer implements any of the above methods.

[0081] Optionally, the computer readable storage medium can be a read-only memory (Read-Only Memory, ROM), a random access memory (Random Access Memory, RAM), a read-only compact disc (Compact Disc Read-Only Memory, CD-ROM), a magnetic tape, a floppy disk, and an optical data storage device, etc.

[0082] In an exemplary embodiment, a computer program product or computer program is also provided, which includes computer instructions stored in a computer readable storage medium. The processor of the electronic device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the electronic device executes any of the above methods.

[0083] It should be noted that the terms "first", "second" and the like in the specification and claims of the present application are used to distinguish similar objects, and represent a specific order or sequence. In appropriate cases, the order of use of similar objects can be interchanged, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described.

[0084] Those skilled in the art will understand that the application can be implemented as a system, method or computer program product. Therefore, the present disclosure can take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.) or a combination of both software and hardware embodiments, which can all generally be referred to herein as a "circuit," "module" or "system." Furthermore, the present disclosure can take the form of a program product on one or more computer-readable medium(s) having computer-readable program code embodied in the medium.

[0085] Any combination of one or more computer-readable medium(s) can be utilized. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer-readable storage medium can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0086] Although the embodiments of the present application have been shown and described above, it is understood that the above-described embodiments are exemplary, and are not to be interpreted as limiting the present application, and that variations, modifications, substitutions and changes can be made to the above-described embodiments by those skilled in the art without departing from the scope of the present application.

Claims

1. A high-speed scene vehicle target fusion method based on binocular UAV, characterized by: include: The video collection screens of two collection devices carried on the hovering drone for collecting data on the road section to be detected are configured, and pixel coordinate calibration processing is performed on the common area of ​​the collection screens of the two collection devices for the road section to be detected; Based on the configured two acquisition devices, video data is collected on the road section to be detected, and a target queue corresponding to each acquisition device is determined within a preset period, wherein the target queue includes basic information of at least one target vehicle extracted based on the video data and arranged in time sequence; For any of the two acquisition devices, based on the pixel coordinate calibration results, the detection frames corresponding to the target vehicles in the target queue corresponding to the acquisition device are sequentially mapped to the perspective of the other of the two acquisition devices, and the same target vehicles in the common area are determined for target fusion processing; Configuring the video capture screens of the two acquisition devices carried on the hovering drone to collect data on the road section to be inspected includes: For exposure compensation configuration: When the photo is dark, increase the exposure compensation; when the photo is bright, reduce the exposure compensation; The specific process of exposure compensation is as follows: Acquire multiple image data taken for the experimental area and determine the brightness corresponding to each image data. Combined with the time period of image data collection and the current weather conditions, search the historical database for all data corresponding to multiple days corresponding to the current weather conditions. Based on the time period of image data collection, extract the historical exposure compensation values ​​corresponding to the time period for each of the searched multiple days. Sort the historical exposure compensation values ​​in chronological order of the searched multiple days and assign a weight to each historical exposure compensation value, where the weight of the historical exposure compensation value corresponding to the time farther from the current moment is smaller. Based on the weight assignment result, perform weighted processing on all historical exposure compensation values ​​to obtain a final exposure compensation value, and perform exposure compensation configuration based on the final exposure compensation value. The specific process of configuring the sensitivity is as follows: For the experimental area, collect multiple image data under the current configuration, calculate the clarity of each image data, determine the proportion of all clarity values ​​that exceed the threshold clarity, and when the proportion value is higher than the preset proportion value, output the sensitivity configuration result in the current configuration as the final result; If the ratio value is lower than the preset ratio value, the contour of the target object in each image data is extracted, where the target object includes vehicles, pedestrians, and buildings; the extracted contour is compared with the manually marked contour to determine the target similarity between the two, and the target difference between the target similarity and the preset similarity is determined. In the corresponding relationship between the difference and the fine-tuning amount, the target fine-tuning amount corresponding to the target difference is determined, and the sensitivity under the current configuration is fine-tuned based on the target fine-tuning amount; where the target difference can include both positive and negative numbers; The preset cycle is as follows: based on the processing capacity of the backend processor, the maximum data flow corresponding to the processing capacity is determined, and an efficient range is determined within the maximum data flow. The data processing cycle range is determined based on the efficient range. The efficient range refers to the data flow range corresponding to when all data transmission channels are occupied but there is no queuing. Also includes: For video data collected by either of the two acquisition devices, determining in real time the driving trajectory and speed of each target vehicle in the video data, determining whether the target vehicle has violated a traffic behavior based on the driving trajectory and speed of the target vehicle, generating an approval image for the target vehicle that has violated the traffic behavior, and generating an alarm message based on the approval image; Also includes: For the video data collected by any of the two collection devices, the longitude and latitude coordinates of any target vehicle are uploaded in real time. For the target vehicle in the public area, when the front of the target vehicle enters the public area, the collection device corresponding to the area where the part of the vehicle body that has not entered the public area is located continues to provide video data for determining the longitude and latitude coordinates of the target vehicle.

2. The high-speed scene vehicle target fusion method based on binocular UAV according to claim 1 is characterized in that: Also includes: The target fusion processing results are displayed in real time.

3. A high-speed scene vehicle target fusion system based on a binocular drone, using the high-speed scene vehicle target fusion method based on a binocular drone as claimed in claim 1, characterized in that: The system comprises: The configuration module is used to configure the video collection images of two collection devices carried on the hovering drone for collecting data on the road section to be detected, and perform pixel coordinate calibration processing on the common area of ​​the collection images of the two collection devices for the road section to be detected; The acquisition module is used to: collect video data of the road section to be detected based on the two configured acquisition devices, and determine the target queue corresponding to each acquisition device within a preset period, wherein the target queue includes basic information of at least one target vehicle extracted based on the video data and arranged in time sequence; The fusion module is used to: for any of the two acquisition devices, combined with the pixel coordinate calibration processing results, sequentially map the detection frame corresponding to the target vehicle in the target queue corresponding to the acquisition device to the perspective of the other acquisition device of the two acquisition devices, and determine the same target vehicle in the common area for target fusion processing.

4. The high-speed scene vehicle target fusion system based on binocular UAV according to claim 3 is characterized in that: Also includes: The display module is used to display the target fusion processing results in real time.

5. An electronic device, characterized in that: The electronic device includes a processor coupled to a memory, wherein the memory stores at least one computer program, and the at least one computer program is loaded and executed by the processor so that the electronic device implements the method according to claim 1 or 2.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores at least one computer program, which is loaded and executed by a processor to enable a computer to implement the method according to claim 1 or 2.

Images