Method for cooperative acquisition of multi-target videos under different resolutions by variable-focus array camera

Abstract

The invention discloses a method for the cooperative acquisition of multi-target videos in different resolutions by a variable-focus array camera in a monitor system with large scene and multiple targets, aiming at controlling the array camera to realize the cooperative acquisition of videos in the low-resolution scene and videos of a plurality of targets in the scene under different resolutions on the basis of the analysis and the comprehension of video images in scenes. The design proposal thereof comprises: utilizing N variable-focus low-resolution cameras to shoot the same scene, wherein one camera shoots the entire scene and the rest N-1 cameras are used for shooting the targets in the scene, computing the working parameters of the camera according to the quantity, the position and the dimension information of the targets in the scene, controlling the array camera to realize the cooperative acquisition so as to obtain the scene videos and the target videos under different resolutions, and then obtaining and displaying clear video images in the scene by an image fusion technique. The method can realize the acquisition of multi-target high-resolution videos and high-quality scene videos at low cost in case of large scene dimension, and is used for video monitor system.

Description

technical field [0001] The invention belongs to the technical field of image processing, relates to a video image monitoring method, and can be used for acquiring multi-target video images in a large scene. Background technique [0002] With the development of society and economy, people's demand for safety protection is getting higher and higher. As an effective means in the field of safety protection, video surveillance is more and more widely used, and the application requirements are constantly improving. The video surveillance system has been developed for just over 20 years, from the earliest analog surveillance to the fiery digital surveillance in the past few years, and then to the ascendant network video surveillance, earth-shaking changes have taken place. In recent years, with the rapid development of computer, network, image processing and transmission technology, it has become attractive to obtain high-quality video in video surveillance systems. [0003] Howev...

AI Technical Summary

Problems solved by technology

[0003] However, in the traditional video surveillance system, the acquisition of video is usually to arrange several low-resolution cameras in the scene to be monitored, each camera is independent of each other, they each collect video of a fixed area in the scene and The processed video is transmitted to the monitor of the remote monitoring terminal for display through the network, and the user can only see several individual low-quality videos on the remote monitoring terminal

For a single low-quality video, users often encounter such problems when using it: when the monitored scene is large, especially when there are multiple targets in the scene, the resolution of the target of interest is too small, which is not conducive to viewing

[0004] For such a situation, if a high-resolution camera is used for hardware upgrades, due to the impact of network bandwidth, a lower bit rate compression has to be used for high-resolution images, and this processing will greatly reduce the visual effect; With the improvement of camera resolution, its price also increases accordingly

Images