Method, system for analyzing, storing video as well as method, system for searching video

Abstract

The invention discloses a video analysis and storage method, a system and a video detection method and a system, respectively saving the storage space of the video image and increasing the efficiency of the video search, wherein the analysis and storage method and the system analyze the video image and store the motion segment containing the motion target, while the video detection method and the system analyze the video image and store motion segment containing the motion target, and the related motion target information and the motion segment information, search the stored motion segment according to the information and the index term input by the users. The invention can be widely applied in the video processing system, particularly the video monitoring system.

Description

technical field [0001] The invention relates to image processing technology, in particular to a video analysis and storage method and system, and a video retrieval method and system. Background technique [0002] The existing video surveillance system stores video images in a way that generally the video recorded by the camera is stored in a database in real time and completely. For general video surveillance application scenarios, such as warehouses, factories, etc., during some periods of time such as night, the monitored scenes rarely change, and few moving objects enter these monitored spaces. For an application scenario where a static camera is used for monitoring, the scene picture is generally static, that is to say, the image will remain the same picture for a long time without obvious changes. [0003] The existing technology saves the video images at every moment to storage devices such as hard disks and video tapes in real time, so as to prepare for applications ...

AI Technical Summary

Problems solved by technology

Although with the development of storage technology, large-capacity storage devices can better solve this problem, but in view of the image data itself has the defect of occupying a lot of bytes, even if a large-capacity storage device is used at any cost, it is still a problem. Difficulty saving all video images over a long period of time

[0004] In the existing technology, when performing video content retrieval and review, manual review is often used, that is, the saved video is played and the video is manually judged. This review method is inefficient and prone to omissions

When manually reviewing, the video playback speed should not be too fast, otherwise the target object may pass by without being noticed. Therefore, it takes 10 hours to review a 10-hour video from beginning to end at normal speed left and right, and it is likely that the meaningful video content is only a few seconds or tens of seconds, so the efficiency is very low

Moreover, for manual review, during the process of watching the video for a long time, the reviewer cannot maintain concentration for a long time and is prone to fatigue. Therefore, even if the review is performed at a normal speed, there may be omissions and relevant information will be missed.

Images