Improved visual background extraction method based on blind updating strategy and foreground model

Abstract

An improved visual background extraction method based on a blind updating strategy and a foreground model comprises the following steps: S1, reading the first frame of a video, and initializing and building a background model; S2, initializing and building a foreground model; S3, reading a new video frame, judging whether a point is classified as a background point according to the background model, and making classification judgment on the point based on the foreground model if the point is classified as a background point; S4, processing a binary foreground image through morphological filtering; S5, updating the foreground model and the background model; and S6, reading a new video frame, repeating S3 to S5, and detecting a moving foreground area in a video sequence in real time.

Description

technical field [0001] The invention relates to a foreground detection method for moving objects in video. Background technique [0002] With the development of modern security monitoring systems, more and more video monitoring technologies have been widely used in commercial places, tourist attractions and traffic monitoring and other fields. The main technologies include moving target detection, moving object recognition, target tracking, behavior analysis and pedestrian monitoring. counting etc. Among them, moving target detection is the basis of follow-up research, which directly affects the quality of follow-up research results. At present, due to the needs of the development of monitoring technology, many foreground detection methods have been developed, such as: frame difference method, background subtraction method (GMM, CodeBook, SOBS, ViBe), optical flow method (sparse optical flow, dense optical flow), time entropy etc. These methods have their respective adapt...

AI Technical Summary

Problems solved by technology

However, if there is a moving object in the first frame of video, the initialization of the moving area will use the pixel set of the moving object to model, causing deadlock and ghosting

Another blind update mechanism uses foreground points and background points to update the background model, which is not sensitive to deadlock, but the disadvantage is that slow moving objects in the video scene will be integrated into the background model and cannot be detected

Although the ViBe method adopts the strategy of updating the neighborhood background model in a diffuse manner and counting the foreground to eliminate the ghosting phenomenon, it still takes a certain amount of time and affects the accuracy of the foreground detection.

Images