Unlock instant, AI-driven research and patent intelligence for your innovation.

Method and device for fast video object segmentation based on pixel and region feature matching

A technology for regional feature and object segmentation, applied in character and pattern recognition, instruments, computing, etc., can solve the problems of being easily affected by noise and abnormal points, ignoring object structure information, etc., to achieve fast and accurate video object segmentation method, high efficiency The effect of positioning

Active Publication Date: 2022-08-09
TSINGHUA UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since this type of method only uses the similarity information of pixels and ignores the structural information of objects, it is easily affected by noise and abnormal points.

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
  • Method and device for fast video object segmentation based on pixel and region feature matching
  • Method and device for fast video object segmentation based on pixel and region feature matching
  • Method and device for fast video object segmentation based on pixel and region feature matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The following examples of the present invention are described in detail. The example of the embodiment is shown in the attached figure. The same or similar labels from beginning to end indicate the same or similar components or components with the same or similar function. The implementation examples described by reference to the attachment are examples, which are designed to explain the present invention, and cannot be understood as restrictions on the invention.

[0036] The traditional method of online learning is high, but the speed is slower than the other two methods, and it is difficult to meet the real -time requirements of realistic applications. Although the method of object tracking is relatively fast, the accuracy is relatively low, and it is easy to be affected by the results of object tracking. Based on feature matching methods, the structured information of the object itself is neglected, and it is easily affected by noise and abnormal points. Based on the ab...

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 present invention provides a fast video object segmentation method and device based on pixel and region feature matching, wherein the method includes: extracting the features of the search frame and the query frame; The pixel similarity features between the search frames and the query frames are extracted; the regional correlation features between the search frames and the query frames are extracted; the pixel similarity features and the regional correlation features are fused to obtain the fusion features; the mask type of the query frame is determined according to the fusion features. Thus, the proposed method improves the inference speed of the algorithm while ensuring the accuracy.

Description

Technical field [0001] The invention involves semi -supervised video object division technology fields, especially a fast video object division method and device based on pixels and regional characteristics matching. Background technique [0002] Video object segmentation is an important and challenging computer visual task. Over the past few years, this visual task has attracted widespread attention in real applications such as object re -recognition, augmented reality, and scene understanding. Generally speaking, the division of video objects can be divided into two sub -tasks: 1) unsupervised video object segmentation; 2) semi -supervised video object segmentation. The purpose of unsupervised video segmentation is to divide significant objects in the video without using any supervision signals. However, the purpose of semi -supervised objects is to obtain the mask of specified objects in other frames in other frames when the first frame is marked with the first frame. The semi...

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
Patent Type & Authority Patents(China)
IPC IPC(8): G06V20/40G06V10/26G06V10/74G06V10/75G06K9/62
CPCG06V20/48G06V20/49G06V10/267G06V10/759G06V10/757G06F18/22
Inventor 鲁继文周杰朱文成李家昊
Owner TSINGHUA UNIV