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

A 3D object detection method based on simple encoding of point cloud data

A technology for point cloud data and target detection, applied in instruments, computing, character and pattern recognition, etc., can solve problems such as difficult to apply algorithms, and achieve the effect of reducing the number of channels, improving feature expression capabilities, and improving coding efficiency

Active Publication Date: 2022-05-13
BEIHANG UNIV
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, due to the many characteristics of the lidar point cloud data, it is difficult to apply these related algorithms. In order to use the target detection algorithm based on the convolutional neural network, the point cloud data can be encoded by rasterization. Usually, the point cloud The data is transformed into a feature map form similar to natural images

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 3D object detection method based on simple encoding of point cloud data
  • A 3D object detection method based on simple encoding of point cloud data
  • A 3D object detection method based on simple encoding of point cloud data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0044] The following will clearly and completely describe the technical solutions in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only for illustration, and are not intended to limit the present application.

[0045] Attached below figure 1 Embodiments of the present invention are described in detail.

[0046] figure 1 It is a schematic flow chart of the 3D object detection method based on simple coding of point cloud data provided by the present invention. In this embodiment, the following steps are included:

[0047] S1 The on-board computing platform accepts the point cloud data input by the lidar, the point cloud is a collection of isolated points, and P cloud To represent the set of all points recorded in a certain frame, P cloud ={p 1 ,p 2 ,p 3 ,...p i ,...,p n}, where p i for P cloud Any point in each point, the specific feature of...

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 3D target detection method based on simple coding of point cloud data. The method rasterizes the point cloud data, and then completes the point set in a single grid by calculating the geometric information and density information in a single grid. Coding, through feature splicing and M×N convolution, perform efficient feature dimensionality reduction, and finally construct a two-dimensional feature map based on point cloud data that can be applied to convolutional neural networks, and finally use a set of multi-scale convolution The feature extraction network performs feature extraction and 3D object detection. The method can efficiently reduce the dimensionality of a 3D feature map into a 2D feature map, so that it can be applied to different 2D convolutional neural networks for feature extraction and 3D object detection.

Description

technical field [0001] The invention relates to the technical field of laser radar data processing and target recognition, in particular to a method for rasterizing and simply encoding laser radar-based point cloud data into a two-dimensional feature map. Background technique [0002] For the on-board intelligent computing platform that supports the automatic driving function, lidar is an important device for the vehicle to perceive the surrounding environment. 3D object detection based on lidar point cloud data is an important way to achieve 3D perception. 3D object detection refers to detecting the category and specific 3D position of objects in the surrounding environment. Lidar is an important means for vehicles and robots to perceive the surrounding environment. Lidar includes a laser emitting system, a laser receiving system and a rotating component. The laser emitting system generally consists of a single-beam multi-line narrow-band laser. The laser pulse is emitted...

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): G06V20/56G06V20/64G06V10/774G06V10/77G06V10/764G06V10/766G06K9/62
CPCG06V20/64G06V20/56G06V2201/07G06F18/213G06F18/24G06F18/214
Inventor 李炜宁亚光杨明董铮
Owner BEIHANG 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