Automatic image cutout with hand motion blur and its application in human body soft segmentation and background replacement

A hand motion and motion blur technology, which is applied in image analysis, graphic image conversion, 3D image processing and other directions, can solve the problems of inability to obtain a large number of motion blurred hand maps, and the lack of training samples can be solved. Effect

Active Publication Date: 2021-02-12
INST OF AUTOMATION CHINESE ACAD OF SCI
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems in the prior art, that is, the motion blurred hand matting effect is not good and a large amount of labeled training data cannot be obtained, the present invention provides a hand motion blur automatic matting method, including:

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
  • Automatic image cutout with hand motion blur and its application in human body soft segmentation and background replacement
  • Automatic image cutout with hand motion blur and its application in human body soft segmentation and background replacement
  • Automatic image cutout with hand motion blur and its application in human body soft segmentation and background replacement

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] The application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain related inventions, not to limit the invention. It should also be noted that, for the convenience of description, only the parts related to the related invention are shown in the drawings.

[0060] It should be noted that, in the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and embodiments.

[0061] A kind of hand motion blur automatic cutout method of the present invention, comprises:

[0062] Step S10, acquiring a motion-blurred hand image as an input image;

[0063] Step S20, based on the input image, the hand motion blur automatic matting network is used to obtain t...

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 belongs to the fields of image recognition, segmentation, map-out and virtual data generation, and in particular relates to the automatic map-out of hand motion blur and its application in soft segmentation and background replacement of the human body, and aims to solve the problem that the automatic map-out effect of the motion-blurred hand is not good. And the problem of inability to obtain a large number of labeled motion blur matting training data. The method of the invention includes: using a hand motion blur automatic matting network to automatically matte the acquired motion blurred hand image, obtaining a hand matting alpha result map and outputting; wherein, the hand motion blur automatic matting network The training samples are obtained by the virtual image generation method. On the one hand, when the human hand in the image has severe motion blur, the present invention can still accurately cut out the human body and switch the background, bringing the user an excellent immersive experience; on the other hand, the method for generating a virtual motion blurred hand image can A large amount of virtual data is generated in a short time, which effectively solves the problems of insufficient training samples and difficulty in labeling the true value.

Description

technical field [0001] The invention belongs to the fields of image recognition, segmentation, matting and virtual data generation, and specifically relates to automatic matting of hand motion blur and its application in human body soft segmentation and background replacement. Background technique [0002] Nowadays, more and more people like to use video to communicate, such as: video chat, video conference, online classroom and so on. Human body segmentation technology can help people replace the background in the video, so as to make the video communication more vivid and interesting, and also enable users to have a better immersive experience. In addition, accurate human body segmentation is also of great significance for further human behavior analysis. However, existing segmentation methods are mainly aimed at clear images, and when people use video to communicate, they often use gesture language. At this time, hand movements are rapid, which causes motion blur. Accur...

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): G06T7/215G06T3/00G06T15/50
CPCG06T3/0012G06T15/503G06T2207/10016G06T2207/10024G06T2207/20081G06T2207/20084G06T2207/30196G06T7/215
Inventor 赵晓梅吴毅红
Owner INST OF AUTOMATION CHINESE ACAD OF SCI
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