Moving target background segmentation method based on improved Vibe+ algorithm

Abstract

The invention discloses a moving target background segmentation method based on an improved Vibe+ algorithm and relates to the field of video image processing. The method comprises the following steps: acquiring an original binary image of a target monitoring video by adopting a traditional Vibe+ algorithm, marking each connected region in the segmented image by adopting a connected region markingmethod based on region growth, setting an area screening threshold value according to boundary area block difference characteristics, and deleting connected regions lower than an area screening threshold value in a binarized image; after a Mean Shift clustering algorithm is improved, fusing with a fragmented convolutional neural network to classify and identify smear blocks, non-smear blocks andsmear edge blocks in a segmented binary image, marking the position coordinates of the smear blocks in the binarized image, and quickly deleting each smear area in the binarized image based on a smeardetection result to obtain a final segmentation result, thereby achieving the technical effect of improving the segmentation accuracy and segmentation efficiency of a moving target of the target monitoring video.

Description

technical field [0001] The invention relates to the technical field of video image processing, in particular to a moving target background segmentation method based on an improved Vibe+ algorithm. Background technique [0002] In recent years, as the construction of smart and safe cities continues to accelerate, more and more urban roads are equipped with surveillance cameras. Traffic management departments, public security departments and other institutional staff can conduct real-time identification and early warning of possible abnormal situations on urban roads based on the video data obtained by surveillance cameras deployed on urban roads, so as to better protect the safety of citizens. travel safely. [0003] Due to the complex distribution of existing urban roads, the large amount of video data acquired by surveillance cameras on each road section, and the high real-time requirements of video surveillance operations, it is difficult for staff to monitor and process ...

AI Technical Summary

Problems solved by technology

[0006] In order to solve the problem of target mis-segmentation in complex moving scenes in existing moving target segmentation methods, the present invention discloses a moving target background segmentation method based on the improved Vibe+ algorithm, which can ensure higher Accurate target segmentation accuracy, while reducing the target recognition time, to a certain extent, to supplement and improve the existing theoretical algorithm of background segmentation

Images