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

A laser slam loopback detection method and system

A detection method and loopback technology, applied in image analysis, instrumentation, calculation, etc., can solve problems such as large amount of calculation and large amount of calculation, and achieve the effect of improving efficiency and reducing the amount of data calculation.

Active Publication Date: 2022-05-31
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the current problems of this method are: 1) The direct instance segmentation of the point cloud requires a large amount of calculation; 2) Most of the current detection modes use the method of verifying all the feature vectors of all key frames, which also has a large amount of calculation
In addition, most of the existing loop closure detection methods ignore the interference of dynamic objects on the detection accuracy.

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
  • A laser slam loopback detection method and system
  • A laser slam loopback detection method and system
  • A laser slam loopback detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Step 100: Convert the key frame point cloud data into a BEV (Bird Eye View, bird's eye view) visual image. in real

[0058] Step 102: Determine the geometric center coordinates of the instance in the instance segmentation image. Specifically, the segmented image

[0059] Step 103: construct an instance map according to the geometric center coordinates of the instance and the semantic information of the instance. Specifically, the first

[0061] Step 104: Perform loop closure detection based on the instance map. The loopback detection mechanism of this method is a step-by-step comparison based on two

[0064] During slam high-frequency mapping, a separate thread is used to obtain key frames at 1 Hz and convert them into BEVs

[0068] The image conversion module 300 is used to convert the key frame point cloud data into a BEV visual image.

[0070] The coordinate determination module 302 is used to determine the geometric center coordinates of the instances in the instance...

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 method and system. The laser SLAM loop closure detection method converts the key frame point cloud data into a BEV visual image, performs instance segmentation on the image and removes potential dynamic objects to obtain an instance segmentation image, and, according to the instance number and semantic information in the instance segmentation image and geometric center coordinates to construct the instance map corresponding to the key frame, and then use the instance map to perform loop closure detection. The method reduces the amount of data computation, optimizes the loopback detection strategy, and can increase the computing speed while ensuring the accuracy of the loopback detection, thereby improving the efficiency of the loopback detection.

Description

A laser SLAM loopback detection method and system technical field [0001] The present invention relates to the technical field of loopback detection, in particular to a method and system for laser SLAM loopback detection. Background technique [0002] In the simultaneous localization and mapping based on lidar (Simultaneous localization and mapping, During the SLAM) process, the pose constraints of the current frame are calculated based on the previous frame. In the process of building the map, as the errors continue to accumulate, the built map is deviated, so it is necessary to pass the loopback detection and judgment machine. Whether the robot passes through the same position again during the mapping process, and if it passes through the same position, loopback correction is performed to reduce the amount of mapping deviation. At present, loopback detection mainly adopts three paths: 1. A method of matching between arbitrary key frames is adopted. this method The...

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 Patents(China)
IPC IPC(8): G06T7/73G06T7/10G06T7/136G06T7/66
Inventor 张旭东邹渊唐嘉乔李圆圆尹鑫
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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