Semi-supervised video target segmentation method

Abstract

The invention provides a semi-supervised video target segmentation method, which comprises the steps: S1, preprocessing a video image to obtain an image of a current frame and an image of a first frame, and giving a segmentation image of the first frame; S2, constructing a semi-supervised video target segmentation network model, wherein the semi-supervised video target segmentation network model comprises a short-time network module, a long-time network module, an attention gate network module and an up-sampling module; S3, inputting the image of the previous frame, the segmentation result image of the previous frame and the image of the current frame into a short-time network module to obtain a rough segmentation image and relative change information of the current frame; inputting the image of the current frame, the image of the first frame, the segmentation map of the first frame and the rough segmentation map of the current frame into a long-term network module to obtain absolute change information; inputting the relative change information and the absolute change information into an attention gate network to obtain a segmentation result, and finally obtaining a segmentation result graph through an up-sampling module. According to the method, the segmentation performance and the segmentation speed can be improved.

Description

technical field [0001] The invention relates to the technical field of computer vision, in particular to a semi-supervised video target segmentation method. Background technique [0002] With the development of deep learning, neural network technology is applied in more and more scenarios, and video object segmentation, as a popular research direction in the field of computer vision, is also receiving more and more attention. Video target segmentation is mainly divided into two types: semi-supervised video target segmentation and unsupervised video target segmentation. Semi-supervised video target segmentation refers to the target segmentation map of the first frame to segment the target of the remaining frames; unsupervised video target segmentation It means that the target in the entire video is segmented without giving any prior information. [0003] The research on semi-supervised video object segmentation in the prior art mainly includes online fine-tuning, propagation...

AI Technical Summary

Problems solved by technology

[0005] The invention provides a semi-supervised video object segmentation method to solve the defects of the prior art problems

Images