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

Visual SLAM loopback detection improvement method based on instance segmentation

A detection method and a loopback technology, which are applied in the direction of instruments, character and pattern recognition, and computer components, can solve problems such as time-consuming, neglect, and low accuracy of closed-loop detection, and achieve improved stability and accuracy, and mobile construction Figure efficient effect

Active Publication Date: 2019-11-29
GUANGDONG UNIV OF TECH
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, its method has great application limitations. The extraction of these features takes a lot of time. At the same time, in scenes with obvious lighting changes, these methods ignore useful information in the environment, resulting in low accuracy of closed-loop detection.

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
  • Visual SLAM loopback detection improvement method based on instance segmentation
  • Visual SLAM loopback detection improvement method based on instance segmentation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0031] The present invention will be further described in detail below in conjunction with the embodiments and the accompanying drawings, but the embodiments of the present invention are not limited thereto.

[0032] Such as Figure 1~2 As shown, an improved method for visual SLAM loop closure detection based on instance segmentation, including the following steps:

[0033] (1) Use the RGB-D camera to obtain RGB information and depth information, and divide the collected data set samples into multiple equal data sets;

[0034] (2) Send each picture in the data set to CNN for feature extraction;

[0035] (3) On the last layer of convolution featuremap, the ROI is generated by RPN, and n suggestion windows are fixed for each picture, where n is set to 300;

[0036] (4) Through the RoIAlign layer, each proposal window generates a fixed-size featuremap;

[0037] (5) Get three output vectors, the first is softmax classification, the second is the bounding box regression of each ...

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 visual SLAM loopback detection improvement method based on instance segmentation. Instance segmentation is carried out on an image through a Mask R-CNN framework, and three improvement measures combined with the example segmentation are provided, so that the loop-back detection problem of the mobile intelligent robot in visual navigation is solved, and the robot is more accurate in mobile mapping; compared with the prior art, the Mask R-CNN is used for off-line training, and the examples in the image are finely segmented. The segmented instances with relatively low correlation are selected and removed, so that the stability and the accuracy of the whole loop detection are improved, and the high efficiency and the accuracy of the intelligent mobile robot navigationare improved; besides, in the loop detection, three detection methods combined with an instance segmentation framework are used for describing an image space relationship, so that the loop detectionis further inspected. Due to the two characteristics, the accuracy of the whole system is remarkably improved.

Description

technical field [0001] The invention relates to the technical field of instance segmentation and visual SLAM, in particular to an improved method for loop closure detection of visual SLAM based on instance segmentation. Background technique [0002] At present, with the further development of mobile robot systems, visual simultaneous localization and mapping (visual SLAM) has been highly valued by the government, society, and enterprises, and it has attracted the active participation of many manufacturers in related industrial chains and links. Visual SLAM obtains image information through binocular cameras to achieve functions such as establishing the environment during motion and estimating its own motion without prior information about the environment. Under the interference of complex environments, how to ensure and improve the mapping accuracy of mobile robots is a key application basic problem in the industrialization process of visual SLAM. [0003] SLAM is Simultane...

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): G06K9/00G06K9/62
CPCG06V20/10G06F18/241Y02P90/30
Inventor 赖瑨刘治章云
Owner GUANGDONG UNIV OF TECH
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