Deep learning-based non-supervision video segmentation method

Abstract

The invention provides a deep learning-based non-supervision video segmentation method. The method comprises the following steps of: establishing a coding / decoding deep neural network, wherein the coding / decoding deep neural network comprises a static image segmentation flow network, an inter-frame information segmentation flow network and a fusion network, the static image segmentation flow network is used for carrying out foreground / background segmentation on the current video frame, and the inter-frame information segmentation flow network is used for carrying foreground / background segmentation of a movement object on optical flow field information between the current video frame and the next video frame; and obtaining a video segmentation result after fusing segmented images output bythe static image segmentation flow network and the inter-frame information segmentation flow network through the fusion network. The static image segmentation flow network is used for high-quality inter-frame segmentation, the inter-frame information segmentation flow network is used for high-quality optical flow field information segmentation, and two paths of output are fused through the final fusion operation so as to obtain the enhanced segmentation result, so that a relatively good segmentation result can be obtained according to effective two-path output and fusion operation.

Description

technical field [0001] The present invention relates to the technical field of video processing, in particular, to an unsupervised video segmentation method based on deep learning. Background technique [0002] Video segmentation refers to the process of segmenting the foreground and background of objects in each frame of the video to obtain a binary image. information) the continuity of segmentation. High-quality video segmentation is the basis of video editing, video object recognition, and video semantic analysis, so it is of great significance. [0003] Existing video segmentation methods can be roughly divided into the following three categories according to their principles: [0004] 1) Based on unsupervised traditional video segmentation method [0005] This type of method does not require manual participation in labeling key frames such as (the first frame) information. The general steps are image segmentation and similar block matching between frames to automatic...

AI Technical Summary

Problems solved by technology

This method has the possibility of overfitting and cannot be applied to large-scale video segmentation scenarios

Images