Video object segmentation method and device and computer equipment

A technology of object segmentation and video object, applied in the field of image processing, can solve problems such as objects being dragged out, disrupting segmentation results, and unstable segmentation results

Pending Publication Date: 2021-07-02
LENOVO (BEIJING) LTD
View PDF0 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in practical applications, taking a video conference as an example, if the users participating in the video conference move quickly, the object segmentation effect of the mask image output in the previous frame will be unstable, and the object segmentation result of the current video frame will be disturbed. , leading to worse and worse object segmentation results in subsequent frames, and even other objects in the video conference such as tables and chairs may be dragged out

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 device and computer equipment
  • Video object segmentation method and device and computer equipment
  • Video object segmentation method and device and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0055] Aiming at the technical problems described in the background technology section, this application proposes to perform object segmentation using the mask image output from the previous frame and the current video frame to obtain the mask image of the current video frame, and to verify the reliability of the mask image. To determine whether to use the mask image of the current video frame when performing object segmentation on the next video frame, so that it can be calibrated or cleared in time if the mask image of the current video frame is verified to be unreliable , so as to avoid the problem that the unreliable mask image continues to guide the object segmentation of the subsequent video frames, resulting in the object segmentation effect of the subsequent video frames getting worse and worse, which in turn leads to the problem that the output video picture is abnormal.

[0056] Among them, for the above-mentioned reliability verification process, this application pro...

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 provides a video object segmentation method and device and computer equipment, obtaining wherein the method comprises the steps: obtaining a historical mask image of a first video frame and a historical video frame adjacent to the first video frame; carrying out the object segmentation processing through employing the historical mask image and the first video frame according to a first segmentation mode; and obtaining a first mask image of the first video frame; according to a second segmentation mode, carrying out object segmentation processing by using the first video frame to obtain a calibration mask image of the first video frame. It is ensured that the calibration mask image is not adversely affected by the historical mask image, and under the condition that a comparison result of the calibration mask image and the first mask image meets a video segmentation calibration condition, it can be determined that the first mask image is inaccurate, and the calibration mask image is directly used as the target mask image of the first video frame to be output, so that the technical problem that the video object segmentation effect is worse and worse when the video object moves quickly and the like when the first mask image is directly output is solved.

Description

technical field [0001] The present application mainly relates to the technical field of image processing, and more specifically relates to a video object segmentation method, device and computer equipment. Background technique [0002] With the development of artificial intelligence and image processing technology, artificial intelligence methods are usually applied to video object segmentation. Specifically, the mask (Mask) image output from the previous frame will be used to guide the object segmentation processing of the current video frame. , so as to quickly and accurately segment the object area from the video to meet the needs of subsequent image processing. [0003] However, in practical applications, taking a video conference as an example, if the users participating in the video conference move quickly, the object segmentation effect of the mask image output in the previous frame will be unstable, which will disturb the object segmentation result of the current vid...

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 Applications(China)
IPC IPC(8): G06T7/11G06N3/08
CPCG06N3/08G06T2207/10016G06T2207/20081G06T2207/20084G06T7/11
Inventor 袁瑞峰周梦涵鲍海明
Owner LENOVO (BEIJING) LTD
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