Check patentability & draft patents in minutes with Patsnap Eureka AI!

A method and system for image stereo matching based on semantic segmentation and neural network

A technology of semantic segmentation and neural network, applied in the field of artificial intelligence, can solve the problem that the calculation speed and accuracy cannot meet the needs of 3D reconstruction

Active Publication Date: 2021-03-30
武汉环宇智行科技有限公司
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional stereo matching algorithm can no longer meet the needs of the current scene 3D reconstruction in terms of calculation speed and accuracy

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
  • A method and system for image stereo matching based on semantic segmentation and neural network
  • A method and system for image stereo matching based on semantic segmentation and neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] In order to make the object, technical solution and advantages of the present invention clearer, the present invention 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 the present invention, not to limit the present invention.

[0017] The invention provides a kind of image stereo matching method based on semantic segmentation and neural network, comprising:

[0018] S1. Obtain an initial disparity map of a scene image;

[0019] S2. Use the semantic segmentation map to obtain the region of interest of the scene image, and combine the region of interest and the initial disparity Figure 1 input into the residual network;

[0020] S3. Using the deconvolution module to map the region of interest to the disparity map to obtain an accurate disparity map.

[0021] The image stereoscopic matching method based on semantic segmen...

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 stereo matching method and system based on semantic segmentation and neural network, wherein the method includes: first obtaining the initial disparity map of the scene image; using the semantic segmentation map to obtain the region of interest of the scene image, and combining the region of interest and The initial disparity map is input into the residual network together; the deconvolution module is used to map the region of interest to the disparity map to obtain an accurate disparity map. The semantic segmentation map in the present invention provides a wealth of information for the network, and only processes the area of ​​interest in the image, and because of the use of the residual network, the present invention has been improved in terms of matching accuracy and speed .

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to an image stereo matching method and system based on semantic segmentation and neural network. Background technique [0002] Stereo matching of images is a key step in applications such as 3D reconstruction of scenes. Traditional stereo matching algorithms include four steps: cost computation (matching cost calculation), cost aggregation (cost aggregation), disparity computation (parallax calculation), and refinement (parallax refinement). change). Cost computation mainly calculates the calculation cost of each pixel on all possible disparity values; in the cost aggregation step, the calculation cost of all pixels in a certain area is aggregated; in the disparity computation step, the global or local algorithm is used to calculate the visual difference; finally, the parallax is corrected in subsequent processing steps, and an appropriate parallax is selected. The...

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): G06K9/62G06K9/34G06K9/32G06K9/72
CPCG06V10/25G06V10/267G06V30/274G06F18/22
Inventor 曹晶陈星辉
Owner 武汉环宇智行科技有限公司
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

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

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com