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

Laser radar point cloud data obstacle detection algorithm

A technology of lidar and point cloud data, which is applied in image data processing, calculation, and measurement devices, and can solve problems such as missing detection, missing 3D point clouds, and broken grids

Active Publication Date: 2017-07-04
WUHU LION AUTOMOTIVE TECH CO LTD
View PDF4 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Although the efficiency of grid obstacle detection is relatively high in processing data, the main disadvantages are: due to occlusion between multiple obstacles, fractures, and missing detection of distant grids due to missing parts of 3D point clouds

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 radar point cloud data obstacle detection algorithm
  • Laser radar point cloud data obstacle detection algorithm
  • Laser radar point cloud data obstacle detection algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be further described in detail below in conjunction with the examples.

[0040] Obtain the original data of multi-dimensional lidar through real-time UDP data packets. Each data packet contains the distance information and angle information returned by each laser beam. We define the data output by the lidar for one revolution as one frame of data.

[0041] After analyzing the original data, each lidar point data contains three-dimensional space position coordinates (x, y, z), vertical angle verAngle, horizontal angle horAngle, intensity, and laser beam ID.

[0042] Create a first-level grid map grid[(M+1),(N+1)], the grid size is G. Project the 3D points in the Cartesian coordinate system onto the (M,N) grid plane. Each grid only saves the maximum height zmax and the minimum height zmin. Calculate the grid coordinates (i, j) (0≤i≤M; 0≤j≤N) data information of the three-dimensional point, so that the amount of data to be processed is reduce...

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 present invention relates to a laser radar point cloud data obstacle detection algorithm. The algorithm comprises: obtaining original data and performing analysis, employing a grid map projection algorithm, performing first-stage grid extraction, establishing a second-stage grid and extracting information, performing barrier determination through adoption of a blocking domain expansion calendar algorithm, and obtaining barrier coordinates. The laser point cloud data is obtained to establish a two-stage grid map, a hanger is rejected to perform eight neighborhood expansion of the second-stage grid to traverse the first-stage grid, and an algorithm of calculating a height difference in a partition mode is employed to determine the barriers. The laser radar point cloud data obstacle detection algorithm reserves the feature of a rapid and stable grid method and solves the problem of the shielding and fracture among barriers and the problem that the grid at a distance is lack of three-dimensional point cloud to caused check leakage.

Description

technical field [0001] The invention relates to a laser radar point cloud data obstacle detection algorithm. Background technique [0002] As an active sensor, lidar has the characteristics that the perception information of objects comes from itself, and is less affected by the external environment. In terms of depth information acquisition, its reliability and accuracy are higher than those of passive sensors, so it is widely used. Applied to the environment perception system. [0003] Unmanned vehicles are high-speed mobile robots with extremely high real-time requirements. However, the amount of raw data of 3D LiDAR is too large, and it is difficult to meet the real-time requirements if the follow-up processing is performed directly on the raw data. Therefore, an efficient and fast lidar point cloud data processing algorithm is needed. [0004] The representation based on the grid map is currently the most commonly used representation method for 3D data, and this type...

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): G01S17/93G06T7/70G06T7/521
CPCG01S17/931G06T2207/10028
Inventor 周倪青曾庆喜徐达学
Owner WUHU LION AUTOMOTIVE TECH CO LTD
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