CN-122002010-A - Panoramic video stitching method, device, medium and equipment for airport monitoring

CN122002010ACN 122002010 ACN122002010 ACN 122002010ACN-122002010-A

Abstract

The embodiment of the application discloses a panoramic video stitching method, a device, a medium and equipment for airport monitoring, and relates to the technical field of airport monitoring. According to the application, by expecting the displayed pictures, namely the splicing components of the monitoring video to determine which parts are spliced to form the panoramic splicing picture, so that the cameras corresponding to the monitoring are spliced according to the splicing positions, then the panoramic images spliced by the different registration images are fused finally, and the panoramic images corresponding to the first target camera are taken as the basis.

Inventors

PAN GUANGXU
XU XU
ZHAO HAIQIN
Shi Wandong
WEN XIN
LIU BIN
ZHAO YONGHONG
YANG JIAN
ZHOU YUANBING
XIANG DEGUI
DENG MAOWEI
HE PENG

Assignees

民航成都电子技术有限责任公司

Dates

Publication Date: 20260508
Application Date: 20260409

Claims (10)

1. The panoramic video stitching method for airport monitoring is characterized by comprising the following steps of: determining a splicing position according to the splicing composition of the monitoring video; Determining a target camera according to the splicing position, wherein the target camera comprises a first target camera and a plurality of second target cameras, the first target camera is a camera corresponding to the splicing position positioned at the center of the monitoring video, and the second target camera is a camera corresponding to the splicing position positioned at the edge of the monitoring video; Respectively splicing images shot by the target cameras as registration images to obtain a plurality of panoramic images; and carrying out image fusion on all the panoramic images based on the panoramic images corresponding to the first target camera to obtain a target panoramic image.
2. The method for stitching panoramic video for airport monitoring according to claim 1, wherein stitching is performed by using images shot by the target cameras as registered images, respectively, to obtain a plurality of panoramic images, including: Respectively taking images shot by the target cameras as registration images, and obtaining correction information of the images shot by the other cameras relative to the registration images; and splicing images shot by other cameras to the registration images according to the correction information to obtain a plurality of panoramic images.
3. The panoramic video stitching method for airport monitoring according to claim 2, wherein after the images shot by the target cameras are respectively used as registration images and correction information of the images shot by the remaining cameras relative to the registration images is obtained, the method further comprises: Performing projection transformation on images shot by other cameras according to the correction information to obtain a transformed image; the step of stitching the images shot by the other cameras to the registration image according to the correction information to obtain a plurality of panoramic images, including: and splicing the transformed images to the registration images according to the correction information to obtain a plurality of panoramic images.
4. The method for stitching panoramic video for airport monitoring according to claim 2, wherein stitching images captured by the remaining cameras to the registration image according to the correction information, to obtain a plurality of panoramic images, comprises: According to the correction information, an overlapping area of images shot by other cameras and the registration image is obtained; and splicing the images shot by the other cameras to the registration images according to the overlapping area to obtain a plurality of panoramic images.
5. The method for stitching panoramic video for airport monitoring according to claim 1, wherein said performing image fusion on all panoramic images based on the panoramic image corresponding to the first target camera to obtain a target panoramic image comprises: Acquiring pixel value information of all panoramic images based on the panoramic images corresponding to the first target camera; And carrying out image fusion by adopting weighted average based on the pixel value information of the corresponding pixel points of all the panoramic images, and taking the pixel value after weighted average as the pixel value of the corresponding point of the fused image to obtain the target panoramic image.
6. The method for stitching panoramic video for airport monitoring of claim 1, wherein said determining a target camera based on said stitching location comprises: determining the center of the monitoring video and the edge of the monitoring video according to the splicing position; And determining target cameras according to the center of the monitoring video and the edge of the monitoring video, wherein the center points of the splicing positions corresponding to the second target cameras are distributed in a matrix, and the center points of the splicing positions corresponding to the first target cameras are located in the center of the matrix.
7. The method for stitching panoramic video for airport monitoring according to claim 1, wherein before stitching the images shot by the target cameras as registered images respectively to obtain a plurality of panoramic images, the method further comprises: Calibrating the target camera; The stitching is performed by using the images shot by the target cameras as registration images, so as to obtain a plurality of panoramic images, including: And respectively splicing the images shot by the target cameras after calibration as registration images to obtain a plurality of panoramic images.
8. Panoramic video stitching device for airport monitoring, characterized by comprising: The first determining module is used for determining the splicing position according to the splicing composition of the monitoring video; the second determining module is used for determining a target camera according to the splicing position, wherein the target camera comprises a first target camera and a plurality of second target cameras, the first target camera is a camera corresponding to the splicing position positioned at the center of the monitoring video, and the second target camera is a camera corresponding to the splicing position positioned at the edge of the monitoring video; The splicing module is used for respectively splicing the images shot by the target cameras as registration images to obtain a plurality of panoramic images; and the fusion module is used for carrying out image fusion on all the panoramic images based on the panoramic images corresponding to the first target camera to obtain target panoramic images.
9. A computer readable storage medium storing a computer program, wherein the computer program when loaded and executed by a processor implements the panoramic video stitching method for airport monitoring according to any of claims 1-7.
10. An electronic device comprising a processor and a memory, wherein, The memory is used for storing a computer program; The processor is configured to load and execute the computer program to cause the electronic device to perform the panoramic video stitching method for airport monitoring as set forth in any one of claims 1-7.

Description

Panoramic video stitching method, device, medium and equipment for airport monitoring Technical Field The application relates to the technical field of airport monitoring, in particular to a panoramic video stitching method, a device, a medium and equipment for airport monitoring. Background Airport monitoring is an important means for ensuring safe and efficient operation of an airport, potential security threats are timely found and dealt with through real-time monitoring, airport management staff is helped to master the real-time operation condition of the airport, resource allocation is optimized, and operation efficiency is improved. Technical means of airport monitoring comprise video monitoring, radar monitoring, infrared monitoring and the like, wherein the video monitoring is the most common means, and the conditions of all areas of an airport are monitored in real time by installing a camera and video acquisition equipment and recorded and stored for subsequent viewing, so that the airport monitoring system has the advantages of intuitiveness, real-time, remote monitoring and the like. Because the airport is widely controlled, a plurality of cameras are usually arranged for monitoring, pictures of different cameras are spliced by adopting a panoramic video splicing technology, and finally panoramic display is carried out on the monitored pictures of a command center, so that information of a plurality of video sources can be integrated, a more comprehensive and visual effect is provided, and the monitoring efficiency and the management level are improved. However, the method has a disadvantage that the monitoring effect is directly limited to the quality of panoramic video splicing, the airport monitoring environment has the characteristics of wide range and more cameras, the cameras may have distortion, a great deal of resources are obviously wasted when all the cameras are calibrated in each splicing, and the defects of splicing seams, unnatural pictures and the like exist in the panoramic video splicing under the condition of not calibrating, so that the monitoring effect is reduced. Disclosure of Invention The application mainly aims to provide a panoramic video stitching method, a device, a medium and equipment for airport monitoring, and aims to solve the problem that the effect of airport monitoring based on panoramic video stitching is poor in the prior art. In order to achieve the above object, the technical scheme adopted by the embodiment of the application is as follows: In a first aspect, an embodiment of the present application provides a panoramic video stitching method for airport monitoring, including the following steps: determining a splicing position according to the splicing composition of the monitoring video; Determining a target camera according to the splicing position, wherein the target camera comprises a first target camera and a plurality of second target cameras, the first target camera is a camera corresponding to the splicing position at the center of the monitoring video, and the second target camera is a camera corresponding to the splicing position at the edge of the monitoring video; Respectively splicing images shot by a target camera as registration images to obtain a plurality of panoramic images; and carrying out image fusion on all panoramic images based on the panoramic image corresponding to the first target camera to obtain a target panoramic image. In one possible implementation manner of the first aspect, stitching is performed with images captured by the target camera as registered images, to obtain a plurality of panoramic images, including: respectively taking images shot by the target cameras as registration images, and obtaining correction information of the images shot by the other cameras relative to the registration images; and splicing images shot by other cameras to the registration images according to the correction information to obtain a plurality of panoramic images. In one possible implementation manner of the first aspect, after the images shot by the target cameras are respectively taken as registration images and correction information of the images shot by the other cameras relative to the registration images is obtained, the method further includes: Performing projection transformation on images shot by other cameras according to the correction information to obtain a transformed image; splicing images shot by other cameras to the registration image according to the correction information to obtain a plurality of panoramic images, wherein the method comprises the following steps: and splicing the transformed images to the registration images according to the correction information to obtain a plurality of panoramic images. In a possible implementation manner of the first aspect, stitching images shot by other cameras to the registration image according to the correction information to obtain a plurality of panoramic images, includin