Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Segmentation method and device for video image, storage medium and terminal equipment

A video image and image technology, applied in the field of information processing, can solve problems such as incoherent motion and high segmentation complexity, and achieve the effect of avoiding sudden changes, simplifying complexity, and clear and coherent video images

Active Publication Date: 2018-09-11
广州方硅信息技术有限公司
View PDF7 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The invention provides a video image segmentation method, segmentation device, storage medium and terminal equipment, which solves the problems of high segmentation complexity and incoherent motion after segmentation of existing video images

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
  • Segmentation method and device for video image, storage medium and terminal equipment
  • Segmentation method and device for video image, storage medium and terminal equipment
  • Segmentation method and device for video image, storage medium and terminal equipment

Examples

Experimental program
Comparison scheme
Effect test

no. 1 example

[0047] The present invention proposes a video image segmentation method, which can cut out the video image of the mobile terminal, such as figure 1 The first shown embodiment comprises the following steps:

[0048] Step S10: Obtain the heat map annotation information of the previous frame image in the video and the current frame image;

[0049] Step S20: Input the heat map annotation information of the previous frame image and the current frame image into the neural network model, and output the heat map annotation information of the current frame image; wherein, the neural network model is used to represent the heat map annotation of the previous frame image information, the image of this frame, and the relationship between the heat map annotation information of the image of this frame;

[0050] Step S30: Segment the frame image according to the heat map annotation information of the frame image;

[0051] Among them, each step is as follows:

[0052] Step S10: Obtain the h...

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 segmentation method and device, a storage medium and terminal equipment for a video image. The segmentation method of the video image comprises the following steps that the heatmap labeling information and the frame image of the previous frame of image in the video are acquired; the heatmap labeling information and the frame image of the previous frame of image are input into a neural network model, and the heatmap labeling information of the frame of image is output. The neural network model is used for representing the heatmap labeling information of the previous frame of image, the frame image, and the correlation between the frame image and the thermal graph labeling information of the frame image. The frame image is segmented according to the thermal image labeling information of the frame image. According to the invention, the complexity of the neural network model is reduced, and the neural network model is suitable for being applied to the mobile terminal.

Description

technical field [0001] The invention relates to information processing technology, in particular to a video image segmentation method, segmentation device, storage medium and terminal equipment. Background technique [0002] Deep learning is a machine learning method that stacks multiple layers of neural networks. Because the number of layers of the neural network is much more than that of the traditional method, it is called deep learning. With the possibility of obtaining a large amount of training data in recent years and the improvement of computer computing performance (mainly the computing performance of graphics cards), it is possible to train large-scale deep learning models. With the development of deep learning algorithms, deep learning has reached the state-of-the-art in many fields. Such as image recognition, image segmentation and natural language processing and other fields. [0003] Traditional cutouts are blue screen cutouts / green screen cutouts, which gen...

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): G06K9/00G06K9/62G06N3/08
CPCG06N3/084G06V20/49G06V20/41G06V20/46G06F18/24
Inventor 刘凌海王雷
Owner 广州方硅信息技术有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com