A calibration method for laser radar and camera data

Abstract

The embodiment of the invention relates to a calibration method for data of a laser radar and a camera, which comprises three parts, namely automatic data acquisition of the laser radar and the camera, external parameter calibration of the laser radar and the camera and external parameter calibration result evaluation, and the method is simple in process, easy to operate and high in efficiency; for external parameter calibration of a low-wire-harness laser radar and a camera, relatively high external parameter calibration precision is achieved; external parameter calibration results are good in consistency, and the requirements of automatic driving vehicle calibration task process, high efficiency, good consistency, high precision and the like can be met.

Description

technical field [0001] The invention relates to the field of image data processing, in particular to a calibration method for laser radar and camera data. Background technique [0002] Self-driving cars rely on a variety of sensors to perceive their environment, and each type of sensor has its own advantages and disadvantages. Lidar can provide accurate distance information and can work well at night, but it cannot provide color information of obstacles, etc. The camera can perceive information such as the color and texture of obstacles, which can be used for target classification, but the detection range is limited and sensitive to lighting conditions. Therefore, through the fusion of lidar and camera, it is possible to learn from each other and improve perception performance. The data fusion of multiple sensors requires very precise calibration of the external parameters of the sensors, so as to ensure that the sensor's perception data of the environment can be accuratel...

AI Technical Summary

Problems solved by technology

Therefore, the existing first-class lidar and camera extrinsic calibration schemes cannot meet the calibration requirements

For the existing non-target external parameter calibration methods, it is necessary to address the shortcomings of this type of method, that is, the calibration accuracy of low-beam lidar is not high, and the consistency of calibration results is low, and corresponding improvements can be made to meet the calibration requirements.

Images