Image segmentation model generation method, image segmentation method and computer equipment

An image segmentation and image technology, applied in the field of image segmentation model generation, can solve problems such as poor segmentation effect

Active Publication Date: 2022-07-22
ALIBABA DAMO (HANGZHOU) TECH CO LTD
View PDF12 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The embodiment of the present application provides a method for generating an image segmentation model, an image segmentation method, and a computer device, so as to at least solve the technical problem that the segmentation effect of the image is poor using the existing image segmentation algorithm.

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
  • Image segmentation model generation method, image segmentation method and computer equipment
  • Image segmentation model generation method, image segmentation method and computer equipment
  • Image segmentation model generation method, image segmentation method and computer equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0048] According to an embodiment of the present application, an embodiment of a method for generating an image segmentation model is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings may be executed in a computer system such as a set of computer-executable instructions and, although a logical order is shown in the flowcharts, in some cases the steps shown or described may be performed in an order different from that herein.

[0049] The method embodiment provided in Embodiment 1 of the present application may be executed in a mobile terminal, a computer terminal, or a similar computing device. figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing a method for generating an image segmentation model is shown. like figure 1 As shown, the computer terminal 10 (or mobile device 10 ) may include one or more (shown as 102a, 102b, . or a processing device such as a programmable logic...

Embodiment 2

[0104] Figure 8 is a flowchart of an image segmentation method according to an embodiment of the present application, such as Figure 8 As shown, the method includes the following steps:

[0105] Step S802, acquiring an image to be processed.

[0106] In the embodiment of the present application, the above image to be processed is a picture with a green screen background.

[0107] Step S804, input the image to be processed into the pre-trained first image segmentation model for processing, and obtain a first foreground image and a first mask corresponding to the image to be processed, wherein the first mask is the size of the image to be processed. the same image.

[0108] In this step, the image to be processed is input to a coarse model, and a small-resolution mask prediction is performed on the input image.

[0109] Step S806, stitching the to-be-processed image and the first mask to obtain a stitched image.

[0110] Step S808, input the spliced ​​image into the pre-t...

Embodiment 3

[0114] Figure 9 is an application schematic diagram of another image segmentation method according to an embodiment of the present application, such as Figure 9 As shown in the figure, taking the application of VR equipment or AR equipment in virtual games as an example, the VR equipment or AR equipment worn by the user collects a target image (which may be a game scene picture), and the processor obtains the target image, and follows steps S902 to S902 to Step S910 performs image segmentation processing on the target object:

[0115] Step S902, acquiring a target image collected by a virtual reality VR device or an augmented reality AR device.

[0116] VR (Virtual Reality) and AR (Augmented Reality) are two different virtual technologies.

[0117] VR is virtual reality technology, which consists of pure virtual digital images, allowing users to immerse themselves in a three-dimensional virtual environment generated by a computer, and isolate them from the real environment...

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 an image segmentation model generation method, an image segmentation method and computer equipment. The method comprises the following steps: acquiring a training data set; inputting the training data set into a first neural network model for training to obtain a first target model, and determining a first foreground image and a first mask obtained by using the first target model to segment an image in the training data set; splicing an image in the training data set with the first mask to obtain a spliced image; inputting the spliced image into a second neural network model for training to obtain a second target model, and determining a second foreground image and a second mask obtained by segmenting the image in the training data set by using the second target model; and generating an image segmentation model according to the first target model and the second target model. The technical problem that the segmentation effect is poor when an existing image segmentation algorithm is used for carrying out segmentation processing on the image is solved.

Description

technical field [0001] The present application relates to the field of image segmentation, and in particular, to a method for generating an image segmentation model, a method for segmenting an image, and a computer device. Background technique [0002] Image segmentation algorithm, which can be commonly understood as a matting algorithm, is an algorithm for semantic analysis of image content and extraction of target objects. The task of the image segmentation algorithm is to semantically analyze the image content and extract the target object. It is the basic operation of image beautification, poster production, film and television special effects and other processes. It can be widely used in film and television post-production, online static and dynamic advertising automation in e-commerce. In the image segmentation service of generation and visual intelligence platform, it has a strong AI-enabled role in interactive entertainment (such as live broadcast, beauty application...

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): G06T7/10G06T7/194G06N3/08G06T3/40
CPCG06T7/10G06T7/194G06N3/08G06T3/4038G06T2207/20081G06T2207/20084G06T2207/20221
Inventor 庾涵
Owner ALIBABA DAMO (HANGZHOU) TECH CO 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

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