Video object segmentation method and system based on diversified interaction

A video object and interactive technology, applied in neural learning methods, image analysis, image enhancement, etc., can solve the problems of low generalization, difficulty in obtaining multi-dimensional feature information, lack of versatility and performance, etc., to improve The effect of precision

Pending Publication Date: 2022-06-28
XI AN JIAOTONG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The existing video object segmentation technology mostly adopts the linear weighting method when fusing video frames with different segmentation results. This method cannot effectively convey the user's intention during the fusion process.
This can make it difficult to blend the differences between video frames
In addition, the existing technology cannot make good use of the precise location information of the features, ma

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Video object segmentation method and system based on diversified interaction
  • Video object segmentation method and system based on diversified interaction
  • Video object segmentation method and system based on diversified interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0072] A video object segmentation method based on diverse interactions, comprising the following steps:

[0073] S1. Preprocess the PASCAL source data to make it suitable for model training, and divide it into a training set and a test set.

[0074] The specific workflow is as follows:

[0075] (1.1), use the public data set DAVIS as the training set and test set;

[0076] (1.2), to the data described in step (1.1), input the data to the first module interaction module, and the user interacts with a frame in the video sequence in the interaction module;

[0077] (1.3), and then the segmentation model uses the user's interaction information to segment this frame of image;

[0078] (1.4) After step (1.3), the user can check the segmentation mask effect output by the segmentation model. If the expected segmentation effect cannot be achieved, the user can continue to interact until the user's expected effect is achieved. The interaction methods are diverse, including Click, dr...

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

No PUM Login to view more

Abstract

The invention discloses a video object segmentation method and system based on diversified interaction, and belongs to the technical field of video image processing, and the method comprises the steps: constructing a network segmentation model for interactive video object segmentation, and carrying out the user interaction processing of a training set, and obtaining an expected segmented image; performing bidirectional propagation on the segmented single-frame image, and segmenting each frame image in the propagation process to obtain a propagation output image; performing difference fusion on the propagation output image to obtain a fused segmentation result; and training the network segmentation model by using the segmented image, the propagated output image, the fused segmentation result and the training set corresponding to the segmented image until a convergence condition is satisfied, and performing video object segmentation by using the trained network segmentation model, so that the precision of the segmentation result can be effectively improved through various interaction factors.

Description

technical field [0001] The invention belongs to the technical field of video image processing, and in particular relates to a method and system for segmentation of video objects based on diverse interactions. Background technique [0002] Video object segmentation aims to perform high-quality segmentation of target objects in input video sequences, and has a wide range of applications in video understanding and video editing. Existing VOS methods can be classified according to the user's input type, semi-supervised methods require pixel labeling of the first frame, and interactive VOS methods take user interaction as input, and users can iteratively optimize the results until they are satisfied. Interactive VOS has more applications in video editing because typical user interactions like clicking or scribbling are much easier than specifying full annotations. Interactive VOS can be thought of as a combination of two tasks, interaction understanding and time propagation. ...

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
no application Login to view more
IPC IPC(8): G06T7/10G06N3/04G06N3/08
CPCG06T7/10G06N3/084G06N3/08G06T2207/10016G06T2207/20081G06T2207/20084G06N3/045
Inventor 田智强柳嘉乐郑军令郑尧月
Owner XI AN JIAOTONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap