An airport monitoring panoramic video splicing method, device, medium and equipment

Abstract

This application discloses a panoramic video stitching method, apparatus, medium, and equipment for airport monitoring, relating to the field of airport monitoring technology. This application determines which parts make up the panoramic stitched image by identifying the expected display scene, i.e., the stitched composition of the monitoring video. Then, based on the monitoring cameras corresponding to the stitching positions, stitching is performed using different registered images. Finally, the panoramic images obtained from stitching different registered images are fused, using the panoramic image corresponding to the first target camera as the base. Since the registered image originates from the target camera, and the target camera includes cameras corresponding to the center and edges of the monitoring video, image distortion caused by camera distortion can be eliminated during the fusion process. It eliminates the need to calibrate all cameras, ensuring the quality of the panoramic stitched image and the monitoring effect.

Description

Technical Field

[0001] This application relates to the field of airport monitoring technology, specifically to a panoramic video stitching method, device, medium, and equipment for airport monitoring. Background Technology

[0002] Airport surveillance is a crucial means of ensuring the safe and efficient operation of airports. Real-time monitoring allows for the timely detection and response to potential security threats, and helps airport managers understand the airport's real-time operational status, optimize resource allocation, and improve operational efficiency. Airport surveillance technologies include video surveillance, radar surveillance, and infrared surveillance, with video surveillance being the most commonly used. By installing cameras and video capture equipment, it monitors various areas of the airport in real time, recording and storing the data for later review. It offers advantages such as intuitiveness, real-time monitoring, and remote monitoring capabilities.

[0003] Because airport surveillance covers a wide area, numerous cameras are typically installed, and panoramic video stitching technology is used to combine the footage from different cameras. The resulting panoramic view is then displayed in the command center, integrating information from multiple video sources to provide a more comprehensive and intuitive picture, thus improving monitoring efficiency and management. However, this method has a drawback: the effectiveness of the surveillance is directly limited by the quality of the panoramic video stitching. Airport surveillance environments are characterized by their wide coverage and numerous cameras, all of which may exhibit distortion. Calibrating all cameras for each stitch would be wasteful of resources, while without calibration, the panoramic video stitching suffers from seams and unnatural images, reducing the effectiveness of the surveillance. Summary of the Invention

[0004] The main objective of this application is to provide a panoramic video stitching method, device, medium, and equipment for airport monitoring, aiming to solve the problem of poor performance of airport monitoring based on panoramic video stitching in the prior art.

[0005] To achieve the above objectives, the technical solutions adopted in the embodiments of this application are as follows:

[0006] In a first aspect, embodiments of this application provide a panoramic video stitching method for airport monitoring, comprising the following steps:

[0007] Determine the splicing position based on the composition of the surveillance video;

[0008] The target camera is determined based on the splicing position; wherein, the target camera includes a first target camera and several second target cameras, the first target camera is the camera corresponding to the splicing position at the center of the surveillance video, and the second target cameras are the cameras corresponding to the splicing positions at the edges of the surveillance video.

[0009] Several panoramic images are obtained by stitching together images captured by the target camera as registered images;

[0010] Based on the panoramic image corresponding to the first target camera, image fusion is performed on all panoramic images to obtain the target panoramic image.

[0011] In one possible implementation of the first aspect, images captured by the target camera are stitched together as registration images to obtain several panoramic images, including:

[0012] Using the images captured by the target camera as registration images, correction information of the images captured by other cameras relative to the registration images is obtained.

[0013] Based on the correction information, the images captured by the other cameras are stitched together with the registered image to obtain several panoramic images.

[0014] In one possible implementation of the first aspect, after obtaining correction information of the images captured by the other cameras relative to the registered images, using the images captured by the target camera as registration images, the method further includes:

[0015] Based on the correction information, the images captured by the other cameras are projected and transformed to obtain the transformed image;

[0016] Based on the correction information, the images captured by the remaining cameras are stitched together with the registered image to obtain several panoramic images, including:

[0017] Based on the correction information, the transformed image is stitched together with the registered image to obtain several panoramic images.

[0018] In one possible implementation of the first aspect, images captured by the remaining cameras are stitched together with the registered image based on correction information to obtain several panoramic images, including:

[0019] Based on the correction information, the overlapping area between the images captured by the other cameras and the registered image is obtained;

[0020] Based on the overlapping areas, the images taken by the other cameras are stitched together to the registered image to obtain several panoramic images.

[0021] In one possible implementation of the first aspect, based on the panoramic image corresponding to the first target camera, image fusion is performed on all panoramic images to obtain a target panoramic image, including:

[0022] Based on the panoramic image corresponding to the first target camera, obtain the pixel value information of all panoramic images;

[0023] Based on the pixel value information of corresponding pixels in all panoramic images, a weighted average is used to perform image fusion, and the weighted average pixel value is used as the pixel value of the corresponding point in the fused image to obtain the target panoramic image.

[0024] In one possible implementation of the first aspect, determining the target camera based on the stitching position includes:

[0025] Based on the splicing location, determine the center and edges of the surveillance video;

[0026] The target camera is determined based on the center and edge of the surveillance video; the center points of the stitching positions corresponding to the second target camera are distributed in a matrix, and the center point of the stitching positions corresponding to the first target camera is located at the center of the matrix.

[0027] In one possible implementation of the first aspect, before stitching together images captured by the target camera as registration images to obtain several panoramic images, the method further includes:

[0028] Calibrate the target camera;

[0029] Several panoramic images are obtained by stitching together images captured by the target camera as registered images, including:

[0030] Several panoramic images are obtained by stitching together images taken by the calibrated target camera as registration images.

[0031] Secondly, embodiments of this application provide a panoramic video stitching device for airport monitoring, comprising:

[0032] The first determining module is used to determine the splicing position based on the splicing composition of the surveillance video.

[0033] The second determining module is used to determine the target camera based on the splicing position; wherein, the target camera includes a first target camera and a plurality of second target cameras, the first target camera is the camera corresponding to the splicing position at the center of the monitoring video, and the second target cameras are the cameras corresponding to the splicing positions at the edges of the monitoring video.

[0034] The stitching module is used to stitch together images taken by the target camera as registered images to obtain several panoramic images;

[0035] The fusion module is used to perform image fusion on all panoramic images based on the panoramic image corresponding to the first target camera to obtain the target panoramic image.

[0036] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements the panoramic video stitching method for airport monitoring as provided in any of the first aspects above.

[0037] Fourthly, embodiments of this application provide an electronic device, including a processor and a memory, wherein,

[0038] Memory is used to store computer programs;

[0039] The processor is used to load and execute computer programs to cause electronic devices to perform panoramic video stitching methods for airport surveillance as provided in any of the first aspects above.

[0040] Compared with the prior art, the beneficial effects of this application are:

[0041] This application proposes a panoramic video stitching method, apparatus, medium, and device for airport monitoring. The method includes: determining the stitching position based on the stitching composition of the monitoring video; determining the target camera based on the stitching position; wherein the target camera includes a first target camera and several second target cameras, the first target camera being the camera corresponding to the stitching position at the center of the monitoring video, and the second target cameras being the cameras corresponding to the stitching positions at the edges of the monitoring video; stitching together images captured by the target cameras as registration images to obtain several panoramic images; and performing image fusion on all panoramic images based on the panoramic image corresponding to the first target camera to obtain a target panoramic image. This application determines which parts make up the panoramic stitched image by analyzing the expected display screen, i.e., the stitched composition of the surveillance video. Then, based on the camera corresponding to the stitching position, it stitches the images using different registration images. Finally, it fuses the panoramic images obtained from the stitched images with different registration images, using the panoramic image corresponding to the first target camera as the base. Since the registration image originates from the target camera, and the target camera includes cameras corresponding to the center and edges of the surveillance video, image distortion caused by camera distortion can be eliminated during the fusion process. It eliminates the need to calibrate all cameras, ensuring the quality of the panoramic stitched image and the monitoring effect. Attached Figure Description

[0042] Figure 1 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of this application;

[0043] Figure 2 A flowchart illustrating the panoramic video stitching method for airport monitoring provided in this application embodiment;

[0044] Figure 3 A schematic diagram of the stitching position in the panoramic video stitching method for airport monitoring provided in the embodiments of this application;

[0045] Figure 4 A schematic diagram of the modules of the panoramic video stitching device for airport monitoring provided in the embodiments of this application;

[0046] The diagram is labeled as follows: 101-Processor, 102-Communication bus, 103-Network interface, 104-User interface, 105-Memory. Detailed Implementation

[0047] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0048] See attached document Figure 1 , attached Figure 1 This is a schematic diagram of the electronic device structure of the hardware operating environment involved in the embodiments of this application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. The communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display screen and an input unit such as a keyboard. Optionally, the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a Wi-Fi interface). The memory 105 may be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as at least one disk storage device. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component.

[0049] Those skilled in the art will understand that the appendix Figure 1 The structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0050] As attached Figure 1 As shown, the memory 105, which serves as a storage medium, may include an operating system, a network communication module, a user interface module, and a panoramic video stitching device for airport monitoring.

[0051] In the appendix Figure 1In the electronic device shown, the network interface 103 is mainly used for data communication with the network server; the user interface 104 is mainly used for data interaction with the user; the processor 101 and the memory 105 in this application can be set in the electronic device. The electronic device calls the panoramic video stitching device for airport monitoring stored in the memory 105 through the processor 101 and executes the panoramic video stitching method for airport monitoring provided in the embodiment of this application.

[0052] See attached document Figure 2 Based on the hardware device of the foregoing embodiments, embodiments of this application provide a panoramic video stitching method for airport monitoring, including the following steps:

[0053] S10: Determine the splicing position based on the composition of the surveillance video.

[0054] In practice, the surveillance video, which is the stitched panoramic display, is typically used in the airport monitoring center to provide an overall overview of the monitored objects. The composition of the stitched surveillance video depends on the number of surveillance cameras and the resulting images, as shown in the attached image. Figure 3 As shown, if the spliced ​​surveillance video consists of nine matrices, the splicing position is indicated by these nine small rectangles. It should be noted that there are no rectangular frames in the actual displayed image; the attached image is only for distinguishing the splicing position.

[0055] S20: Determine the target camera based on the splicing position; wherein, the target camera includes a first target camera and several second target cameras, the first target camera is the camera corresponding to the splicing position at the center of the surveillance video, and the second target cameras are the cameras corresponding to the splicing positions at the edges of the surveillance video.

[0056] In practice, each stitched frame corresponds to a monitoring camera. The target camera is selected from these cameras, as shown in the attached image. Figure 3 As shown, the first target camera is the rectangular frame at the center of the surveillance video, i.e., the camera corresponding to the stitching position. The second target camera is the rectangular frame at the edge of the surveillance video, i.e., the camera corresponding to the stitching position. Not all cameras at the edge need to be selected; only some can be selected. The purpose is to evenly cover the circumferential area. In other words, the target cameras are determined based on the stitching position, including:

[0057] Based on the splicing location, determine the center and edges of the surveillance video;

[0058] The target camera is determined based on the center and edge of the surveillance video; the center points of the stitching positions corresponding to the second target camera are distributed in a matrix, and the center point of the stitching positions corresponding to the first target camera is located at the center of the matrix.

[0059] For example, you can select only the cameras at the four corners, or the cameras at the four adjacent positions (top, bottom, left, and right) to the center. In practice, a surveillance video is composed of more stitched images. Selecting the target camera in this way will only account for a small portion of all cameras. Of course, you can select more cameras, but to ensure uniform coverage and symmetry, and to improve the effect of canceling camera distortion when fusing images later, you can use the center point as the center of symmetry when selecting. When selecting the center point of a stitching position on the edge, you must ensure that the stitching position corresponding to another center point symmetrical to the center point is also selected.

[0060] S30: Stitch together images taken by the target camera as registration images to obtain several panoramic images.

[0061] In practice, panoramic stitching basically involves selecting one image as the registration image, and then stitching other images to be stitched onto it. However, it's important to note that the stitching process proceeds step-by-step from the nearest neighboring images. First, the feature points shared by the adjacent images and the registration image are obtained. Then, the two images are superimposed using these feature points, as shown in the attached diagram. Figure 3 In the layout shown, the images at the edges are all adjacent images. If there are more stitching positions, that is, if there are still images separated by a gap, then the closest image is stitched with the registered image to form the registered image for stitching again, and the second closest image is then stitched with it.

[0062] In one embodiment, images captured by the target camera are stitched together as registered images to obtain several panoramic images, including:

[0063] Using the images captured by the target camera as registration images, correction information of the images captured by other cameras relative to the registration images is obtained.

[0064] Based on the correction information, the images captured by the other cameras are stitched together with the registered image to obtain several panoramic images.

[0065] In the specific implementation process, for panoramic image stitching, the first step is to obtain the image to be stitched, which is the correction information of the images taken by the other cameras relative to each registered image, such as image resolution scaling, size adjustment, angle rotation, etc. Then, based on this information, the image to be stitched is stitched to the registered image to obtain the panoramic image under each registered image. These panoramic images all represent the same monitoring screen.

[0066] In one embodiment, after obtaining correction information of the images captured by the other cameras relative to the registered images, using the images captured by the target camera as registration images, the method further includes:

[0067] Based on the correction information, the images captured by the other cameras are projected and transformed to obtain the transformed image.

[0068] In practice, the images to be stitched are captured by different cameras at different angles, and therefore do not lie on the same projection plane. If overlapping images are directly stitched seamlessly, it may disrupt the visual consistency of the actual scene. Therefore, a projection transformation can be performed on the images before stitching; the transformed image is the final image. Image projection transformation projects an image from one view plane to another, transferring pixel values ​​to form the target image. Common methods include affine transformation, perspective transformation, and numerical transformation.

[0069] Based on the aforementioned steps, the images captured by the remaining cameras are stitched together with the registered image according to the correction information to obtain several panoramic images, including:

[0070] Based on the correction information, the transformed image is stitched together with the registered image to obtain several panoramic images.

[0071] In one embodiment, images captured by the remaining cameras are stitched together with the registered image based on correction information to obtain several panoramic images, including:

[0072] Based on the correction information, the overlapping area between the images captured by the other cameras and the registered image is obtained;

[0073] Based on the overlapping areas, the images taken by the other cameras are stitched together to the registered image to obtain several panoramic images.

[0074] In practice, compared with the method of feature point overlap, since the image can be corrected according to the correction information during the stitching process, the image distortion retained due to feature point matching is directly eliminated. In this way, the method of stitching based on the overlapping area can obviously have a larger registration area to achieve the stitching of two images, and can achieve a smoother combination of the two stitched images.

[0075] S40: Based on the panoramic image corresponding to the first target camera, perform image fusion on all panoramic images to obtain the target panoramic image.

[0076] In practice, image fusion refers to using specific algorithms to combine two or more images into a new image. This process extracts useful information from each channel and retains this information to the maximum extent possible, ultimately generating an image that provides a more comprehensive and clear description of the scene. Its main purpose is to improve the utilization rate of image information, improve the spatial and spectral resolution of the image, thereby enhancing the accuracy and reliability of image interpretation.

[0077] Since panoramic images are acquired through different registration images, considering the selection of registration images, if the camera corresponding to a certain image to be stitched has distortion, the image distortion in one panoramic image will have a corresponding inverse distortion in another panoramic image. These two distortions can be compensated during the fusion process. The purpose is to comprehensively consider the influence of each camera on the panoramic image without camera calibration, and to avoid the fact that camera distortion will cause a large amount of image distortion that cannot be corrected when obtaining a panoramic image by single stitching.

[0078] In one embodiment, based on the panoramic image corresponding to the first target camera, image fusion is performed on all panoramic images to obtain a target panoramic image, including:

[0079] Based on the panoramic image corresponding to the first target camera, obtain the pixel value information of all panoramic images;

[0080] Based on the pixel value information of corresponding pixels in all panoramic images, a weighted average is used to perform image fusion, and the weighted average pixel value is used as the pixel value of the corresponding point in the fused image to obtain the target panoramic image.

[0081] In the specific implementation process, common image fusion methods include pyramid fusion, Poisson fusion, PCA fusion, etc. Considering that the panoramic image in this application embodiment is actually different displays of the same picture, the image is fused by superposition, and a weighted average is used in the superposition process. The pixel points of the generated target panoramic image are actually the average pixel values ​​of the corresponding points of the superimposed panoramic image, and the weights are set according to the actual situation.

[0082] In one embodiment, before stitching together images captured by the target camera as registration images to obtain several panoramic images, the method further includes:

[0083] The target camera is calibrated.

[0084] In practical implementation, it can be understood that after extracting video or images from surveillance cameras, panoramic image stitching is performed based on time series to obtain frame-by-frame images, thus generating panoramic video for monitoring. Camera calibration is performed, but only on the target cameras. Compared to calibrating all cameras, calibrating only these cameras not only reduces the workload but also contributes to improving stitching quality and monitoring effectiveness. Camera calibration refers to the process of solving for camera parameters, i.e., imaging model parameters. Due to differences in installation design and between cameras, there will be scaling, tilt, and azimuth differences between video images. Therefore, these differences need to be pre-calibrated to obtain images with good consistency, facilitating subsequent image stitching. Camera calibration is divided into intrinsic parameter calibration, extrinsic parameter calibration, and distortion coefficient calibration. By calibrating these parameters, the imaging geometric characteristics of the camera can be accurately described, effectively improving image quality.

[0085] Based on the aforementioned steps, images captured by the target camera are used as registration images and stitched together to obtain several panoramic images, including:

[0086] Several panoramic images are obtained by stitching together images taken by the calibrated target camera as registration images.

[0087] In this embodiment, the components that make up the panoramic stitched image are determined by the expected display image, i.e., the stitched composition of the surveillance video. Then, based on the surveillance camera corresponding to the stitching position, stitching is performed using different registered images. Finally, the panoramic images obtained by stitching different registered images are fused together, with the panoramic image corresponding to the first target camera as the basis. Since the registered image comes from the target camera, and the target camera includes the camera corresponding to the center and edge of the surveillance video, image distortion caused by camera distortion can be eliminated during the fusion process. It is not necessary to calibrate all cameras, thus ensuring the quality of the panoramic stitched image and the monitoring effect.

[0088] See attached document Figure 4 Based on the same inventive concept as in the foregoing embodiments, this application also provides a panoramic video stitching device for airport monitoring, comprising:

[0089] The first determining module is used to determine the splicing position based on the splicing composition of the surveillance video.

[0090] The second determining module is used to determine the target camera based on the splicing position; wherein, the target camera includes a first target camera and a plurality of second target cameras, the first target camera is the camera corresponding to the splicing position at the center of the monitoring video, and the second target cameras are the cameras corresponding to the splicing positions at the edges of the monitoring video.

[0091] The stitching module is used to stitch together images taken by the target camera as registered images to obtain several panoramic images;

[0092] The fusion module is used to perform image fusion on all panoramic images based on the panoramic image corresponding to the first target camera to obtain the target panoramic image.

[0093] Those skilled in the art should understand that the division of the various modules in the embodiments is merely a logical functional division. In actual applications, they can be fully or partially integrated into one or more actual carriers. These modules can be implemented entirely in software through processing unit calls, entirely in hardware, or a combination of software and hardware. It should be noted that each module in the panoramic video stitching device for airport monitoring in this embodiment corresponds one-to-one with each step in the panoramic video stitching method for airport monitoring in the aforementioned embodiments. Therefore, the specific implementation of this embodiment can refer to the implementation of the panoramic video stitching method for airport monitoring described above, and will not be repeated here.

[0094] Based on the same inventive concept as in the foregoing embodiments, embodiments of this application also provide a computer-readable storage medium storing a computer program, which, when loaded and executed by a processor, implements the panoramic video stitching method for airport monitoring as provided in the embodiments of this application.

[0095] Based on the same inventive concept as in the foregoing embodiments, embodiments of this application also provide an electronic device, including a processor and a memory, wherein,

[0096] Memory is used to store computer programs;

[0097] The processor is used to load and execute computer programs to cause electronic devices to perform panoramic video stitching methods for airport monitoring as provided in the embodiments of this application.

[0098] In some embodiments, the computer-readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or it may be a device including one or any combination of the above-mentioned memories. The computer may be a variety of computing devices, including smart terminals and servers.

[0099] In some embodiments, executable instructions may take the form of a program, software, software module, script, or code, written in any form of programming language (including compiled or interpreted languages, or declarative or procedural languages), and may be deployed in any form, including as a standalone program or as a module, component, subroutine, or other unit suitable for use in a computing environment.

[0100] As an example, executable instructions may, but do not necessarily, correspond to files in the file system. They may be stored as part of a file that holds other programs or data, for example, in one or more scripts in a Hyper Text Markup Language (HTML) document, in a single file dedicated to the program in question, or in multiple collaborative files (e.g., a file that stores one or more modules, subroutines, or code sections).

[0101] As an example, executable instructions can be deployed to execute on a single computing device, or on multiple computing devices located in one location, or on multiple computing devices distributed across multiple locations and interconnected via a communication network.

[0102] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0103] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0104] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as read-only memory / random access memory, magnetic disk, optical disk) and includes several instructions to cause a multimedia terminal device (which may be a mobile phone, computer, television receiver, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0105] In summary, this application provides a panoramic video stitching method, apparatus, medium, and equipment for airport monitoring. The method includes: determining the stitching position based on the stitching composition of the monitoring video; determining the target camera based on the stitching position; wherein the target camera includes a first target camera and several second target cameras, the first target camera being the camera corresponding to the stitching position at the center of the monitoring video, and the second target cameras being the cameras corresponding to the stitching positions at the edges of the monitoring video; stitching together images captured by the target cameras as registration images to obtain several panoramic images; and performing image fusion on all panoramic images based on the panoramic image corresponding to the first target camera to obtain a target panoramic image. This application determines which parts make up the panoramic stitched image by analyzing the expected display screen, i.e., the stitched composition of the surveillance video. Then, based on the camera corresponding to the stitching position, it stitches the images using different registration images. Finally, it fuses the panoramic images obtained from the stitched images with different registration images, using the panoramic image corresponding to the first target camera as the base. Since the registration image originates from the target camera, and the target camera includes cameras corresponding to the center and edges of the surveillance video, image distortion caused by camera distortion can be eliminated during the fusion process. It eliminates the need to calibrate all cameras, ensuring the quality of the panoramic stitched image and the monitoring effect.

[0106] The above description is only a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the protection scope of this application.

Claims

1. A panoramic video stitching method for airport monitoring, characterized in that, Includes the following steps: Determine the splicing position based on the composition of the surveillance video; Based on the splicing position, a target camera is determined; wherein, the target camera includes a first target camera and a plurality of second target cameras, the first target camera is the camera corresponding to the splicing position located at the center of the surveillance video, and the second target cameras are the cameras corresponding to the splicing positions located at the edges of the surveillance video; Several panoramic images are obtained by stitching together images captured by the target camera as registration images; Based on the panoramic image corresponding to the first target camera, image fusion is performed on all the panoramic images to obtain the target panoramic image.

2. The panoramic video stitching method for airport monitoring according to claim 1, characterized in that, The step of stitching together images captured by the target camera as registered images to obtain several panoramic images includes: Using the images captured by the target camera as registration images, correction information of the images captured by the other cameras relative to the registration images is obtained; Based on the correction information, the images captured by the other cameras are stitched together with the registered image to obtain several panoramic images.

3. The panoramic video stitching method for airport monitoring according to claim 2, characterized in that, After obtaining correction information of images captured by the other cameras relative to the registered images by using the images captured by the target camera as registration images, the method further includes: Based on the correction information, the images captured by the other cameras are projected and transformed to obtain the transformed image; The step involves stitching together images captured by other cameras with the registered image based on the correction information to obtain several panoramic images, including: The transformed image is stitched together with the registered image based on the correction information to obtain several panoramic images.

4. The panoramic video stitching method for airport monitoring according to claim 2, characterized in that, The step involves stitching together images captured by other cameras with the registered image based on the correction information to obtain several panoramic images, including: Based on the correction information, the overlapping area between the images captured by the other cameras and the registered image is obtained; Based on the overlapping area, the images captured by the other cameras are stitched together with the registered image to obtain several panoramic images.

5. The panoramic video stitching method for airport monitoring according to claim 1, characterized in that, The step of fusing all the panoramic images based on the panoramic image corresponding to the first target camera to obtain the target panoramic image includes: Based on the panoramic image corresponding to the first target camera, obtain the pixel value information of all the panoramic images; Based on the pixel value information of the corresponding pixels in all the panoramic images, a weighted average is used to perform image fusion, and the weighted average pixel value is used as the pixel value of the corresponding point in the fused image to obtain the target panoramic image.

6. The panoramic video stitching method for airport monitoring according to claim 1, wherein, Determining the target camera based on the stitching position includes: Based on the splicing position, determine the center and edge of the surveillance video; The target camera is determined based on the center and edge of the surveillance video; wherein the center points of the stitching positions corresponding to the second target camera are distributed in a matrix, and the center point of the stitching positions corresponding to the first target camera is located at the center of the matrix.

7. The panoramic video stitching method for airport monitoring according to claim 1, characterized in that, Before stitching together the images captured by the target camera as registered images to obtain several panoramic images, the method further includes: The target camera is calibrated; The step of stitching together images captured by the target camera as registered images to obtain several panoramic images includes: Several panoramic images are obtained by stitching together images taken by the calibrated target camera as registration images.

8. An apparatus for stitching panoramic video for airport monitoring, characterized by, include: The first determining module is used to determine the splicing position based on the splicing composition of the surveillance video; The second determining module is used to determine the target camera based on the splicing position; wherein the target camera includes a first target camera and a plurality of second target cameras, the first target camera is the camera corresponding to the splicing position located at the center of the surveillance video, and the second target cameras are the cameras corresponding to the splicing positions located at the edges of the surveillance video; A stitching module is used to stitch together images captured by the target camera as registration images to obtain several panoramic images; A fusion module is used to perform image fusion on all the panoramic images based on the panoramic image corresponding to the first target camera to obtain a target panoramic image.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is loaded and executed by the processor, it implements the panoramic video stitching method for airport monitoring as described in any one of claims 1-7.

10. An electronic device, comprising: Including processor and memory, among which, The memory is used to store computer programs; The processor is used to load and execute the computer program to cause the electronic device to perform the panoramic video stitching method for airport monitoring as described in any one of claims 1-7.

Images