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

Semantic SLAM object association and pose updating method and system based on hierarchical grouping

An update method and object technology, applied in the field of robot vision, can solve the problems of weak scene generalization ability, low accuracy of object association, insufficient optimization of object pose, etc., and achieve the effect of promoting camera pose estimation

Active Publication Date: 2021-12-14
紫东信息科技(苏州)有限公司
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] For this reason, the technical problem to be solved by the present invention is to overcome the problems of low object association accuracy, weak scene generalization ability and object pose optimization in the semantic SLAM object association method in the prior art when multiple identical objects are very close to each other. Insufficient defects

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 SLAM object association and pose updating method and system based on hierarchical grouping
  • Semantic SLAM object association and pose updating method and system based on hierarchical grouping
  • Semantic SLAM object association and pose updating method and system based on hierarchical grouping

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] see Figure 1 to Figure 3 As shown, the present embodiment provides a semantic SLAM object association and pose update method based on hierarchical grouping, specifically comprising the following steps:

[0043] S1: Acquire moving images of dynamic objects.

[0044] For example, a camera device can be used to capture its moving image. As a preferred solution, the imaging device can be a camera, which uses the camera to capture moving images of dynamic objects, and calculates the pose of the camera and the position of the camera on the map for each frame of image. During this movement, the motion equation of the camera Expressed as follows:

[0045] x t =f(x t-1 , μ t )+ωt , ω t ~N(0,R t )

[0046] Among them, f(x t-1 , μ t ) represents the ideal pose change relationship from time t-1 to time t, μ t represents the motion measure, ω t Indicates that it obeys the mean, its value is 0, and the variance R t Represents the noise of the Gaussian distribution; and ...

Embodiment 2

[0086] A hierarchical grouping-based semantic SLAM object association and pose update system disclosed in Embodiment 2 of the present invention is introduced below. The hierarchical grouping-based semantic SLAM object association and pose update system described below is the same as the one described above. A semantic SLAM object association and pose update method based on hierarchical grouping can be referred to each other.

[0087] see Figure 4 As shown, the embodiment of the present invention provides a semantic SLAM object association and pose update system based on hierarchical grouping, including:

[0088] Acquisition module 10, the acquisition module 10 is used to acquire the moving image of dynamic object;

[0089] The key frame group construction module 20, the key frame group construction module 20 is used to construct the key frame queue according to the moving image, and selects continuous key frames as the key frame group from the key frame queue, wherein adjace...

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 relates to a semantic SLAM object association and pose updating method and system based on hierarchical grouping. The method comprises the following steps of: acquiring a moving image of a dynamic object; constructing a key frame queue according to the moving image, and selecting key frames from the key frame queue as key frame groups; performing object association operation on the key frames in each key frame group to obtain an object road sign and pose information thereof; constructing a Gaussian mixture model according to the object road sign and the pose information thereof, and judging whether the object road sign in each key frame group is associated with each object road sign in the other key frame groups by using the Gaussian mixture model to obtain a judgment result; and updating the object road sign and the pose information thereof in the maps according to the judgment result. According to the method and system, object association can be realized with high precision, wrong association of a plurality of similar objects is avoided, and the defects of low object association accuracy, weak scene generalization ability and insufficient pose optimization under the condition that a plurality of same objects are very close in the prior art are overcome.

Description

technical field [0001] The present invention relates to the technical field of robot vision, in particular to a semantic SLAM object association and pose update method and system based on hierarchical grouping. Background technique [0002] Although pure visual SLAM has better robust performance, it is easy to track failures in dynamic scenes, fast motion, texture loss, illumination changes and other situations. Therefore, combining traditional SLAM with semantic information can improve the robustness of the system, and it is more in line with human cognition of exploring unknown environments. However, traditional visual SLAM uses very little semantic information in localization and construction, so it is limited in some application scenarios. [0003] Accurate object association and real-time update of optimized object poses are crucial components in semantic SLAM. To establish an accurate 3D semantic map, accurate object association and object pose are prerequisites. Ac...

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): G06T7/70G06T7/20G06T5/00
CPCG06T7/70G06T7/20G06T5/80
Inventor 张剑华陈凯祺刘嘉玲孙波
Owner 紫东信息科技(苏州)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