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

Semantic segmentation improved algorithm based on point cloud local structure

A local structure and semantic segmentation technology, applied in computing, image analysis, image data processing, etc., can solve the problem of not making full use of local neighborhoods and achieve good robustness

Pending Publication Date: 2019-09-10
SOUTHEAST UNIV
View PDF0 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, it does not fully utilize the local neighborhood of points containing fine-grained structural information, which contributes to better semantic learning

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
  • Semantic segmentation improved algorithm based on point cloud local structure
  • Semantic segmentation improved algorithm based on point cloud local structure
  • Semantic segmentation improved algorithm based on point cloud local structure

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0028] Below in conjunction with accompanying drawing and specific embodiment the present invention is described in further detail:

[0029] The present invention provides an improved semantic segmentation algorithm based on the local structure of the point cloud, which improves the accuracy rate to 80.6% under the S3DIS data set, and assists ORB-SLAM2 with the function of dense point cloud mapping, so that the SLAM system has the capability of semantic mapping Function.

[0030] The present invention provides an improved semantic segmentation algorithm based on the local structure of the point cloud, and the specific implementation steps are as follows;

[0031] Step 1: Learning Local Geometry

[0032] At the front end of the KCNet network, we take inspiration from kernel-correlation-based point cloud registration, and consider the local neighborhood of points as a source, and a set of learnable points (i.e., kernels) as a reference to characterize certain types of local ge...

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 a semantic segmentation improved algorithm based on a point cloud local structure, which is used for assisting the dense mapping and belongs to the field of multimedia signal processing. The semantic segmentation improved algorithm comprises the following steps of 1, learning a local geometric structure; 2, learning a local feature structure; 3 fusing the ORB-SLAM2 systems.The present invention provides the algorithm for executing the semantic segmentation service based on a kernel association network for the first time, the algorithm enables the accuracy to be improved to 80.6% under an S3DIS data set and assists the ORB-SLAM2 with a dense point cloud mapping function, so that the SLAM system has the semantic mapping function.

Description

technical field [0001] The invention relates to the field of multimedia signal processing, in particular to an improved semantic segmentation algorithm based on point cloud local structure. Background technique [0002] A point cloud is a map represented by a set of discrete points. The most basic point contains XYZ three-dimensional coordinates, and can also carry RGB color information. The point cloud itself is just some points that are not logically independent from each other, there can be hundreds or thousands, and it is sparse and disordered. When people see a cluster of point clouds and identify them based on years of life experience, they can recognize the object represented by the point cloud. However, this is not an easy task for a computer. [0003] The application of point cloud object classification and semantic segmentation came into being. It is hoped that through deep learning, the training model can effectively identify the objects represented by the poin...

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): G06T7/10G06T7/60G06T7/80
CPCG06T7/10G06T7/60G06T7/80G06T2207/10028G06T2207/20081
Inventor 李春国宋涣杨绿溪
Owner SOUTHEAST UNIV
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