Laser radar data processing method

Abstract

The invention discloses a laser radar data processing method, and effectively solves the problems that an offline grid map cannot effectively reduce redundant point cloud data, the extraction rate ofan effective area is not high, the calculation time and the calculation duration cannot be effectively improved, and the normal driving of a vehicle is influenced. The method comprises the following steps: determining a vehicle driving area according to vehicle position information; using the vehicle-mounted processor for making a vehicle driving area into an offline grid map; the laser radar converting the surrounding environment of the vehicle into point cloud data; partitioning point cloud data by using a data processing method; then, performing AND operation with offline grid map. According to the method, redundant point cloud data is filtered out in multiple driving scenes of the vehicle, the calculation amount of the point cloud data is reduced, the calculation time is shortened, theimplementation efficiency of the point cloud data is improved, the extraction rate of an effective area is improved, and the influence of the redundant point cloud data on normal driving of the vehicle is reduced.

Description

technical field [0001] The invention relates to the field of data processing, in particular to a laser radar data processing method. Background technique [0002] When the lidar detects the environment, tens of thousands of point cloud data are generated, and only 16-line mechanical lidar produces about 300,000 point cloud data per second, including all obstacle information around the radar at 360°. The converted point cloud data is redundant and sparse, and it is necessary to filter out the point cloud data in irrelevant areas to extract valid areas for subsequent processing. The existing technology uses an offline grid map and rasterizes the lidar scanning range to perform an "AND" operation to filter out point cloud data in irrelevant areas, but the labels of the grids within the scanning range of the lidar are all 1 , resulting in a 10cm*10cm offline grid map. Although a part of the calculation amount in the vehicle driving process has been reduced, the scope of the "AN...

AI Technical Summary

Problems solved by technology

[0004] In view of the deficiencies in the existing technology, the purpose of the present invention is to provide a laser radar data processing method, which effectively solves the problem that the offline grid map cannot effectively reduce redundant point cloud data, so that the calculation time and calculation duration cannot be effectively obtained. Improvement, which in turn affects the normal driving of the vehicle

Images