Distance measuring method based on monocular camera and laser radar

Abstract

The invention provides a distance measuring method based on a monocular camera and a laser radar. The distance measuring method comprises the following steps: firstly, collecting historical traffic scene image data and point cloud data; processing the data, and respectively training an initial target detection model and an initial depth completion model by using the processed historical image data and historical point cloud data; obtaining a trained target detection model and a depth completion model, wherein the target detection model takes real-time image data as input and outputs information of obstacles in the traffic scene, the depth completion model takes the real-time image data and the real-time sparse depth map as input, outputs a dense depth map; and finally calculating the distance of an obstacle in the traffic scene according to the output of the target detection model and the depth completion model. The advantages of the monocular camera and the laser radar are fully combined, the output results of the target detection model and the depth completion model are fused, object-level distance measurement is realized, the result is reliable, and the precision is high.

Description

technical field [0001] The invention relates to the technical field of intelligent driving, in particular to a ranging method based on a monocular camera and a laser radar. Background technique [0002] A smart driving car is a car that uses on-board sensors to achieve assisted driving or even unmanned driving through intelligent algorithms. Vehicle-mounted sensors include cameras, millimeter-wave radars, ultrasonic radars, lidars, infrared sensors, etc. Each sensor independently collects surrounding environment information, applies algorithms to extract useful information, and fuses the extracted useful information to accurately assist the car in making decisions and control, so as to achieve the purpose of intelligent driving. The key technologies of intelligent driving include perception, fusion, decision-making, control, etc., and distance measurement is an extremely important part of the perception module. It can transmit the distance information of obstacles to the de...

AI Technical Summary

Problems solved by technology

[0003] The main purpose of the present invention is to solve the problem of low ranging accuracy of laser radar or camera alone, and provides a ranging method based on monocular camera and laser radar, which fully combines the advantages of monocular camera and laser radar, and integrates target detection The output results of the model and depth complement the model to achieve object-level distance measurement, with reliable results and high precision

Images