Automatic driving laser radar data amplification method based on regular variation

An autonomous driving and lidar technology, applied in the field of lidar point cloud data augmentation, which can solve the problems of high data acquisition cost and difficult interpretation and analysis of output results.

Pending Publication Date: 2020-11-03
深圳慕智科技有限公司
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Our invention can obtain enhanced lidar point cloud data, which solves the completeness and adequacy of the test to a certain extent, the high cost of data acquisition, and the difficulty of interpreting and analyzing the output results.

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
  • Automatic driving laser radar data amplification method based on regular variation
  • Automatic driving laser radar data amplification method based on regular variation
  • Automatic driving laser radar data amplification method based on regular variation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0019] Embodiments of the present invention are described below through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification.

[0020] This patent uses the PCL point cloud operation library to implement rule-based point cloud data amplification, which is mainly divided into the design of point cloud data mutation rules, point cloud data mutation technology, and amplified data evaluation schemes.

[0021] Design of point cloud data variation rules: At present, the equivalent variation rules to be designed in the present invention include: rainfall influence rules, snowfall influence rules, and smog influence rules. The above three rules respectively simulate the influence of different weather factors on the point cloud data in reality, and represent the point cloud information received by the automatic driving system in various weather environments. At the sam...

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 provides an automatic driving laser radar data amplification method based on rule variation, so as to obtain enhanced point cloud data, and finally perform quality evaluation on the enhanced data, and the method comprises the following steps: designing a variation rule and an automatic variation technology which accord with the point cloud data, and performing variation on seed pointcloud data to serve as a theoretical support for point cloud data amplification; based on the open-source large-scale point cloud data set data and the PCL point cloud operation library, further integrating the enhanced data to form an open-source point cloud test data set, and selecting an industrial-grade automatic driving software system for experimental verification; finally, introducing a metamorphic relation into variation amplification data evaluation, and evaluating and verifying the effectiveness of the laser radar point cloud test data generation technology based on a metamorphic test verification process and an actual system feedback result.

Description

technical field [0001] The invention belongs to the field of automatic driving testing in intelligent software testing, and relates to laser radar point cloud data amplification. After defining the mutation rules of the point cloud data, the mutation rules are automatically applied to the seed point cloud data to obtain the enhanced lidar point cloud dataset. Background technique [0002] With the rapid development of artificial intelligence, intelligence has become a new trend in the application of software systems. As today's popular intelligent software systems, autonomous driving systems are usually deployed in safety-critical environments, and their software defects are likely to lead to catastrophic consequences. Under such circumstances, major companies and research institutions have proposed a series of autonomous driving test technologies, and this field has received great attention from industry and academia. [0003] The automatic driving system relies on variou...

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): G06Q10/06G06Q50/10
CPCG06Q10/06395G06Q50/10
Inventor 陈振宇郭安邓靖琦冯洋夏志龙
Owner 深圳慕智科技有限公司
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