A road surface three-dimensional feature collection method and device based on a laser grid

Abstract

The invention relates to a road ground three-dimensional feature collection method and device based on a laser grid. The device includes a housing; two cameras, a laser grid generator and a central control processing system are arranged in the shell; the two cameras are symmetrically arranged at the positions, on the left side and the right side of the laser grid generator, of the shell, the lasergrid generator is parallel to the optical axes of the two cameras, the laser grid generator and the binocular camera are both controlled by the central control module, and image signals of the cameras are transmitted to the central control processing module through link communication. the topographic features of the ground are obtained in real time by adopting a method of combining stereoscopic vision and laser grid projection, real-time data are provided for path planning and decision making in automatic driving or auxiliary driving, dangers such as road pits and obstacles are avoided in time, and the driving safety is greatly improved.

Description

technical field [0001] The invention belongs to the field of intelligent service systems, and relates to automobile driving equipment, in particular to a laser grid-based method and device for collecting three-dimensional features of road surfaces. Background technique [0002] Road environment perception technology is the "eye" for automatic driving, and it is also the basis for obtaining information about vehicles and their surrounding environment for path planning and calculation. It uses the sensors on the vehicle to collect data on the surrounding driving environment information, providing decision-making basis for path planning of automatic driving or assisted driving, and ensuring driving safety. [0003] The currently used environmental perception sensors mainly include laser radar, machine vision camera, millimeter wave radar, ultrasonic radar, etc. Among them, lidar has fast response speed, long detection distance, and high accuracy. It is a solution with high mea...

AI Technical Summary

Problems solved by technology

Stereo matching is the key to the 3D reconstruction of the binocular vision system. However, during the driving process of the car, the road conditions are complex, the weather and light are changeable, and the camera is too much interfered by the external environment. The collected images contain a lot of invalid information and noise, which increases the The difficulty of image stereo matching, the calculation load of the entire 3D reconstruction is very large, the algorithm complexity is high, and it is difficult to meet the real-time requirements in the process of vehicle automatic driving

Therefore, ordinary stereo vision technology based on binocular cameras can only be used as an auxiliary measurement technology for lidar.

Images