Method and device for determining conversion pose between radar and camera and electronic equipment

Abstract

The invention provides a method and a device for determining a conversion pose between radar and a camera, electronic equipment and a storage medium, and relates to the technical field of images. Themethod comprises the steps of acquiring a first calibration object plane equation and a first center point coordinate of a calibration object and a calibration object center point under a radar coordinate system based on first point cloud data acquired by radar; obtaining a second calibration object plane equation and a second center point coordinate of the calibration object and the calibration object center point under the camera coordinate system based on the image data collected by the camera; and determining a conversion pose between the radar coordinate system and the camera coordinate system according to the first normal vector of the first calibration object plane equation, the second normal vector of the second calibration object plane equation, the first center point coordinate and the second center point coordinate. According to the method and the device, the electronic equipment and the storage medium, automation of the calibration process is achieved, manual participationof the calibration process is reduced, the degree of dependence on the calibration board state and the external environment is low, and calibration results are stable.

Description

technical field [0001] The present disclosure relates to the field of computer technology, and in particular to a method and device for determining a conversion pose between a radar and a camera, electronic equipment, and a storage medium. Background technique [0002] Self-driving cars are equipped with various sensors such as radars and cameras. Calibrating the conversion pose relationship between the radar and the camera is a prerequisite for realizing the information fusion of the radar and the camera. By determining the conversion pose between the radar and the camera, the advantages of the two sensors can be complemented and more effective perception information can be obtained. At present, there are usually two schemes for calibrating the conversion pose relationship between radar and camera: calibration schemes based on calibration boards and calibration schemes based on natural scenes. The calibration scheme based on the calibration board usually reconstructs the a...

AI Technical Summary

Problems solved by technology

[0003] However, for the calibration scheme based on the calibration plate, it is easily affected by the camera’s internal parameters and the flatness of the calibration plate, and its robustness is poor; for the calibration scheme based on natural scenes, a higher-precision initial value is required, otherwise the convergence result is poor. However, this is difficult to meet in many practical applications; and the requirements for the external environment are high, and it needs to have obvious, easy to extract, and strong contrast features, which is difficult to apply to most scenarios

Images