Online video concentration device, system and method

Abstract

The invention discloses an online video concentration device, system and method. The method can sequentially perform real-time execution on an image which is currently acquired by each frame, and the method comprises the following steps of: the segmentation step: segmenting a background image and a foreground image of each image; the extraction step: extracting a motion object from each foreground image; the step of extracting the sequence of the motion objects: accumulating the motion objects which are respectively extracted from the foreground images of the multiple frames and forming the sequence of the motion objects; the step of extracting the sequence of main backgrounds: extracting specific (n) frames of the background images from the background images of the images of the multiple frames as the sequence of the main backgrounds; and the splicing step: splicing the sequence of the main backgrounds with the sequence of the motion objects. By utilizing the online video concentration way, the length of a concentrated video is shortened and information of the motion objects in the video can be retained as far as possible. Fast and convenient video browsing and previewing can be realized, and the visual effect is better. The hardware requirements and the complexity in an algorithm can be reduced.

Description

technical field [0001] The invention relates to the field of analysis and processing of video streams, in particular to an online video concentration device, system and method. Background technique [0002] In recent years, with the rapid development of digital media, the public security situation has attracted widespread attention from the society and the public, and multimedia and security video data have exploded. The traditional time-consuming simple and original browsing method is far from meeting people's needs for accessing and querying video information. Therefore, there is an urgent need for a fast and convenient video browsing method and system with good visual effects. [0003] The current video browsing methods can be divided into three categories: Video Summary, Video Skimming and Video Synopsis: [0004] 1. Video overview is a collection of images extracted from the original video to summarize the original video content, and these images representing the orig...

AI Technical Summary

Problems solved by technology

The disadvantage is that the key frame expression mechanism loses the dynamic characteristics of the video, so the expressiveness is not vivid

Its disadvantage is that the algorithm complexity is high and the hardware requirements are high.

First of all, it needs to store all the extracted moving object information in the memory for calculation. Often the original video may be several hours long, and the large amount of moving object information that needs to be stored will be a huge challenge to the memory.

Secondly, the traditional video summarization method uses simulated annealing algorithm to solve the rearrangement of the moving object sequence into the summary video space. Due to the huge amount of data in the rearrangement problem and the complex calculation of the energy function in the simulated annealing algorithm, the whole method is complicated. High degree, difficult to use in real time

Images