Unsupervised video segmentation method based on deep learning
A video segmentation and deep learning technology, applied in the field of video processing, can solve problems such as inapplicability to large-scale video segmentation
Active Publication Date: 2020-04-17
SHANGHAI JIAOTONG UNIV
View PDF2 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method has the possibility of overfitting and cannot be applied to large-scale video segmentation scenarios
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0079] The present invention will be described in detail below in conjunction with specific embodiments. The following examples will help those skilled in the art to further understand the present invention, but do not limit the present invention in any form. It should be noted that those skilled in the art can make several changes and improvements without departing from the concept of the present invention. These all belong to the protection scope of the present invention.
[0080] Such as figure 1 As shown, this implementation provides an unsupervised video segmentation method based on deep learning. The specific implementation details are as follows, and the parts that are not described in detail in the following implementations are referred to the content of the invention.
[0081] Firstly, two networks are built, including static image segmentation flow and inter-frame information segmentation flow network. The structure of the two networks is exactly the same, and the...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The present invention provides an unsupervised video segmentation method based on deep learning, including: establishing a coding and decoding deep neural network, and the coding and decoding deep neural network includes: static image segmentation flow network, inter-frame information segmentation flow network and fusion network; static image The segmentation flow network is used to perform foreground and background segmentation processing on the current video frame, and the inter-frame information segmentation flow network is used to perform foreground and background segmentation of moving objects on the optical flow field information between the current video frame and the next video frame; the static image The segmented images output by the segmentation flow network and the inter-frame information segmentation flow network are fused through the fusion network to obtain the video segmentation result. The static image segmentation flow network of the present invention is used for high-quality intra-frame segmentation, and the inter-frame information segmentation flow network is used for high-quality optical flow field information segmentation. The two-way output obtains the improved segmentation result through the final fusion operation, so that Better segmentation results can be obtained based on effective dual output and fusion operations.
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...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/215G06T7/194G06N3/04G06N3/08
CPCG06N3/088G06T7/194G06T7/215G06T2207/10016G06N3/045
Inventor 宋利许经纬解蓉张文军
Owner SHANGHAI JIAOTONG UNIV