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

Laser SLAM loopback detection system and method based on graph descriptor

A detection system and descriptor technology, applied in image enhancement, image analysis, image data processing, etc., can solve the problem that the real-time performance of detection loopback is difficult to meet the actual use requirements, and achieves the task of avoiding normal vector calculation, fast and robust. Detect loopback and avoid the effect of large changes in viewing angle

Active Publication Date: 2020-03-24
SUN YAT SEN UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the currently existing lidar loop detection algorithm is difficult to meet the actual use requirements in terms of the performance and real-time performance of 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
  • Laser SLAM loopback detection system and method based on graph descriptor
  • Laser SLAM loopback detection system and method based on graph descriptor

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0030] like figure 1 As shown, a laser SLAM loop closure detection system based on graph descriptors, including semantic segmentation module, whole graph descriptor extraction module, whole graph descriptor matching module, vertex descriptor extraction module, vertex descriptor matching module and geometric consistency Authentication module, where:

[0031] Semantic segmentation module: used to perceive the external environment, extract the semantic object information in the unordered point cloud data, obtain the prediction confidence of the object and the three-dimensional space coordinates of its center of mass, and output it to the whole image descriptor extraction module and the vertex descriptor extraction module;

[0032] Full Graph Descriptor Extraction Module: It is used to take the centroid of the object in the point cloud data as the vertex, and the Euclidean distance between the vertex and the vertex as the edge to form a complete graph, and store all the edges in t...

Embodiment 2

[0044] like figure 2As shown, the present invention also provides a laser SLAM loopback detection method based on graph descriptors, which includes the following steps. The application scene of this method is an indoor and outdoor scene with rich semantic information:

[0045] S1. Use the point cloud data scanned by the lidar as the input of the PointRCNN or SECOND neural network to obtain the prediction confidence and spatial position of the semantic object;

[0046] S2. Using the spatial position of each object, taking the object as the vertex and the Euclidean distance between the objects as the edge to form a complete graph, store all the edges in the complete graph into a one-dimensional counting vector according to their length, and obtain the complete graph graph descriptor;

[0047] S3. Add the full-image descriptor of the query frame to the KD tree with historical frame data, use the nearest neighbor algorithm to find n historical frames similar to the query frame, ...

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 laser SLAM loopback detection system and method based on a graph descriptor. The system comprises a semantic segmentation module, a full-graph descriptor extraction module,a full-graph descriptor matching module, a vertex descriptor extraction module, a vertex descriptor matching module and a geometric consistency verification module. According to the method, semantic information extracted from point cloud data is utilized to form two graph descriptors, namely a full graph descriptor and a vertex descriptor, so as to characterize a point cloud frame and a semantic object. Compared with a traditional algorithm for extracting the descriptors from the pixel level, the invention can avoid heavy normal vector calculation tasks and avoid the problems caused by great change of the visual angle, and can detect loopback more quickly and robustly. The potential loopback candidate frames are roughly screened out through the full-graph descriptors, then detail information of the query frame and the loopback candidate frames is matched more finely through the vertex descriptors, the method is a coarse-to-fine search process, and theoretical guarantee is provided forthe real-time performance of the method.

Description

technical field [0001] The invention belongs to the field of simultaneous positioning and mapping of robots, and more specifically relates to a laser SLAM loopback detection system and method based on graph descriptors. Background technique [0002] With the improvement of my country's economic level and the development of science and technology, the simultaneous positioning and mapping (SLAM) technology of robots has become a hot focus. However, it is very challenging to carry out accurate positioning and mapping. The front-end odometer always brings inevitable drift error, therefore, we need to optimize the state estimation error of the scan-matching odometer through loop-closing detection technology. [0003] GPS is often used as a sensor to assist precise positioning, but under certain conditions, such as high-rise buildings in cities will cause signal blockage, and the measurement error of GPS signals can reach 10m. Although the loopback detection technology of the ca...

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): G06T7/10G06N3/04
CPCG06T7/10G06T2207/10044G06T2207/10028G06T2207/20084G06N3/045
Inventor 朱亚琛陈龙刘聪
Owner SUN YAT SEN 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