Monocular vision SLAM method based on object size prior information

A technology of prior information and monocular vision, applied in the field of intelligent robots, can solve the problems of limited scope of application, low portability and low generalization of scale recovery methods, and achieves elimination of local map drift and strong system portability. , Improve the effect of mapping accuracy

Active Publication Date: 2021-06-18
UNIV OF SCI & TECH OF CHINA
View PDF9 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] 1) The scope of scale restoration method is limited, the generalization is low, and there is a problem of low transplantability
[0005] 2) The existing object-based SLAM system has a large computational burden, and it is difficult to guarantee real-time performance, which cannot meet the needs of robots for accurate scale perception of scenes in practical applications

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
  • Monocular vision SLAM method based on object size prior information
  • Monocular vision SLAM method based on object size prior information
  • Monocular vision SLAM method based on object size prior information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0018] In order to overcome the shortcomings of the mobile robot with a monocular camera as the only sensor in the scale perception of scene exploration, the embodiment of the present invention provides a monocular vision SLAM method based on the prior information of the object size. Real-time and high-precision requirements, to achieve high-precision real-time online scale recovery, and at the same time widely applicable, strong portability; such a...

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 monocular vision SLAM (Simultaneous Localization and Mapping) method based on object size prior information, which comprises the following steps of: acquiring object semantic information through a target detection method, and reducing the scale uncertainty in a monocular vision SLAM process by utilizing prior object scale information; enabling a trajectory smoothing module using inter-frame object information to construct a local map when a new object is detected at the front end to reduce local map drift. According to the cluster adjustment pose optimization framework combined with the object scale priori information, the constraint of object scale priori is added, and road sign points and camera poses are optimized at the same time, so that the overall mapping precision of the system is improved. According to the scheme, only the monocular camera is used as a unique sensor, the cost is low, and the system transportability is high.

Description

technical field [0001] The invention relates to the technical field of intelligent robots, in particular to a monocular vision SLAM method based on object size prior information. Background technique [0002] With the development of science and technology, the relationship between robots and people's lives is getting closer and closer. Simultaneous localization and mapping (SLAM) technology is the core technology for autonomous environment exploration and navigation of robots. The monocular vision SLAM system is a SLAM system that uses a monocular camera as the main external sensor. Compared with binocular cameras and RGB-D cameras, monocular cameras are cheap, compact and flexible in installation, so they are widely used in current visual SLAM systems. Monocular visual SLAM has received extensive attention and has been greatly developed in recent years. However, due to the characteristics of the sensor itself in monocular visual SLAM, the scene depth cannot be obtained d...

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): G06T7/70G06T7/60G01C21/20
CPCG06T7/70G06T7/60G01C21/20Y02T10/40
Inventor 陈宗海李晓晗王纪凯戴德云林士琪徐萌
Owner UNIV OF SCI & TECH OF CHINA
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