Extrinsic Calibration for Lidar and Stereo Vision Using 3D Feature Points

Lidar and stereo cameras arc important environmental sensors for unmanned driving. Calibrating external parameters between these two sensors is an important basis for their combination; however, combining two types of information requires a complex calibration process. This paper proposes a method based on feature point pair matching. Two rectangular planks arc used to extract the 3D point cloud of the edge of the board in stereo vision and lidar coordinate systems, which is then used to obtain the corner coordinates. Finally, the Kabsch algorithm is used to solve the coordinate transformation between the paired feature points, and a clustering method is used to remove outliers from the multiple measurements and obtain the average value. By setting up an experiment, this method can be implemented on the Nvidia Jetson Tx2 embedded development board, and accurate registration parameters can be obtained, thus verifying the theoretical method's feasibility. This registration method is simple and easy to execute, can automatically perform multiple measurements, and is improved compared with similar methods.