Multi-line lidar-based obstacle clustering method

Abstract

The invention relates to a multi-line lidar-based obstacle clustering method. According to the method, an obstacle clustering system is adopted; the obstacle clustering system comprises a data processing module; and the data processing module is connected with a data acquisition module through an Ethernet, performs analysis and algorithm processing on point cloud data acquired by the data acquisition module, clusters obstacles and outputs the sizes and positions of the obstacles in real time. The multi-line lidar-based obstacle clustering method is based on an existing clustering algorithm; grid filtering and adaptive neighborhood parameters are adopted; density-based spatial clustering of application with noise (DBSCAN) is used in combination; and therefore, the accuracy and real-time performance of obstacle clustering recognition can be improved.

Description

technical field [0001] The invention relates to an obstacle clustering method based on multi-line laser radar, belonging to the technical fields of intelligent assisted driving and unmanned driving. Background technique [0002] Low traffic efficiency and frequent traffic accidents have become the most troublesome problems for the public at present, and liberation from driving and congestion has become a new social appeal. After two hundred years of development, automobiles have gradually entered the era of electronics, and mature active safety systems have been developed to assist or replace part of the driver's work, but this is far from enough. With the maturity of artificial intelligence, especially deep learning technology, algorithms are beginning to be able to identify the attributes of objects and make reasonable human-like decisions. Unmanned driving is gradually becoming possible, and the infinite imagination behind it is also yearning for the industry; on this bas...

AI Technical Summary

Problems solved by technology

However, the uncertainty of obstacles, the incompleteness of data, and the complex dynamic environment, etc., have caused varying degrees of difficulty in obstacle clustering. How to determine performance metrics and distance metrics, improve the shortcomings of clustering algorithms, and Improving the accuracy and real-time performance of obstacle clustering has become an urgent technical problem to be solved

Images