Method for structurally reconstructing background for intelligent video monitoring

Abstract

The invention discloses a method for structurally reconstructing a background for intelligent video monitoring. The method comprises the following steps that: an image is acquired by an image frame and is updated by an updating module; a picture movement optical flow estimation module detects full-picture movement optical flow of the image; a picture segmenting module further segments a dynamic inter-frame picture; an image mean value module uses a static region as a mask template; a partial background reconstructing module fills a pixel mean value of the static region to a corresponding position of a background picture; a background reconstruction state detecting module calculates reconstruction percentage of the background picture and judges whether reconstruction is finished, if not, the first step is carried out again so as to acquire a new image frame, if so, the background is output by an output background module. By adopting the method disclosed by the invention, when frame image data are acquired, images acquired after a certain time interval are very high in reconstruction accuracy and are free from reconstruction error, and a static background picture of a supervised scene is reconstructed rapidly, efficiently and clearly.

Description

technical field [0001] The invention relates to the field of video monitoring, in particular to a structured background reconstruction method for intelligent video monitoring. Background technique [0002] With the continuous increase of the network of civil surveillance and security systems in our country, automatic and intelligent analysis of the collected videos can improve the effective utilization rate of massive surveillance video data. In intelligent surveillance video analysis, moving target extraction, tracking, trajectory analysis, target search, and fast positioning all rely on the background image of the surveillance scene. Effectively and accurately reconstructing the background of the scene is the basis of target extraction based on differential images. After the difference between the current frame image and the background image, the moving target area has a higher pixel value in the differential image due to the large difference, while the static background ...

AI Technical Summary

Problems solved by technology

Based on the difference of frames with a long time interval, there is no overlap in the difference image due to the overlapping of the moving target itself, and at the same time, when the gray level change of the overlapping area is small, the target area is also regarded as the background area, resulting in slow learning speed, especially When the moving target is large and the moving speed is slow, if the gray level change of the moving target area is relatively gentle, there will be a large error in the learning background

This error also accumulates over time into the background image, causing the background reconstruction to fail

Images