Camera and laser radar time synchronization method and device and storage medium

Abstract

The invention discloses a camera and laser radar time synchronization method and device, and a storage medium. The method comprises the steps of obtaining an image of a camera at a first moment and a point cloud of a laser radar at a second moment; constructing a pose resolving model based on the pose coordinate change within the time difference between the first moment and the second moment; and performing time synchronization on the camera and the laser radar according to the pose resolving model. According to the invention, online time synchronization when the time difference exists between the acquired camera image and the radar point cloud data is realized through the pose resolving model constructed in the time difference, and the time synchronization result is ensured to be accurate and reliable. Meanwhile, according to the method, clock signals do not need to be unified, model selection limitation of a hardware triggering interface on the sensor is avoided, and the problem that a time synchronization hard triggering mode between the camera and the laser radar has too high hardware requirements and does not have universality is solved.

Description

technical field [0001] The invention relates to the field of automatic driving sensor synchronization, in particular to a camera and laser radar time synchronization method, device and storage medium. Background technique [0002] The core sensors of the current autonomous driving perception system are cameras and radars. The premise of their cooperative work is to synchronize the time of their sensor sources. The existing time synchronization methods between cameras and lidars are divided into time hard synchronization and time soft synchronization. One, the time hard synchronization method requires a unified clock signal, and uses the global time stamp as the reference for hardware triggering. This method must reserve a hardware trigger interface for the sensor, which has high requirements for the sensor and is not suitable for common scenarios; the soft synchronization interpolation method will The observation data of one sensor obtains a curve about time through a specif...

AI Technical Summary

Problems solved by technology

[0003] In view of this, the embodiments of the present invention provide a camera and lidar time synchronization method, device, and storage medium to solve the problem that the hard trigger method of time synchronization between the camera and lidar has too high hardware requirements and is not universally applicable. and time-soft synchronous interpolation because the data stems from the problem of fitting non-real

Images