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

Road scene point cloud classification method and storage medium

A technology of cloud classification and scene points, applied in instruments, biological neural network models, computing, etc., can solve problems such as low accuracy

Active Publication Date: 2022-04-26
成都奥伦达科技有限公司 +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The present invention intends to provide a road scene point cloud classification method to solve the problem of low accuracy of existing classification methods

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
  • Road scene point cloud classification method and storage medium
  • Road scene point cloud classification method and storage medium
  • Road scene point cloud classification method and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0055] Road scene point cloud classification methods, such as figure 1 shown, including the following steps:

[0056] Step 1. Obtain sample data and road collection data. The sample data collects data on the roads of Wuhan Optics Valley Third Ring Road through the existing vehicle-mounted LiDAR system. Carry out data collection, road collection data such as figure 2 As shown; the sample data is sequentially intercepted from a single point cloud object, the farthest point is sampled and normalized to obtain a training sample, and the road collection data is preprocessed to obtain a segmented object.

[0057] The preprocessing operation includes the following substeps:

[0058] In sub-step 1.1, the ground points and non-ground points are first separated from the road collection data by a preset filtering algorithm. The preset filtering algorithm is the existing cloth filtering algorithm or ground filtering algorithm.

[0059] Sub-step 1.2, and then cluster the non-ground poi...

Embodiment 2

[0080] The difference between the road scene point cloud classification method and Embodiment 1 is that it also includes step 5, identifying the target types of the point cloud classification results on both sides of the road in step 4 including railings, low sidewalk plants, light poles, and high sidewalk plants, and judging Whether the target type is the preset type, which can be railing or low street plant.

[0081] When the target type is a preset type, identify the position information at the center of the target type. The position information is identified based on the coordinate data of the collected point cloud to determine whether the position information is located on both sides of the road. When the position information is located on both sides of the road , calculate the target width according to the position information at the center of gravity of the target type on both sides of the road.

[0082] The distance difference is obtained by making a difference between...

Embodiment 3

[0085] This embodiment provides a storage medium, and the storage medium is used for storing computer-executable instructions. When the computer-executable instructions are executed, the steps of the methods for classifying road scene point clouds in Embodiment 1 and Embodiment 2 are implemented.

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 the field of laser radar data processing, in particular to a road scene point cloud classification method and a storage medium, and the method comprises the steps: obtaining sample data and road collection data, carrying out the initial processing of the sample data, obtaining a training sample, and carrying out the preprocessing of the road collection data, and obtaining a segmentation object; performing data enhancement processing on the sample data by using a data enhancement algorithm, performing model training on the training samples subjected to the data enhancement processing to obtain a pre-training model, and adjusting an initial learning rate, a batch size and a learning rate attenuation parameter of the pre-training model according to a training result; performing classification prediction on the segmented objects in the step 1 by using a pre-training model to obtain a preliminary classification result; and performing adhesion object segmentation processing on the preliminary classification result through a minimum cut algorithm to obtain a segmentation result, and performing refined classification on the segmentation result by using a pre-training model to obtain a road scene point cloud classification result. According to the invention, the point cloud data is effectively classified, and the point cloud classification precision is improved.

Description

technical field [0001] The invention relates to the field of laser radar data processing, in particular to a road scene point cloud classification method and a storage medium. Background technique [0002] Geographic information is an important basic information resource and an important part of national information resources. It is widely used in various fields of economic and social development. The acquisition and processing of geographic information data is the basis for the application of geographic information resources in economic and social fields. In order to obtain the accuracy and comprehensiveness of geographic information data and improve the processing capability of geographic information data, high-end ground surveying and mapping equipment such as 3D laser scanners and mobile geographic information data acquisition systems have emerged as the times require. Using ground surveying and mapping equipment to collect geographic information data, a large amount of ...

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
IPC IPC(8): G06V20/64G06V10/26G06V10/762G06V10/82G06K9/62G06N3/04
CPCG06N3/045G06F18/2321
Inventor 刘健飞陈薪宇江亮亮张波魏新元
Owner 成都奥伦达科技有限公司
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