Robust regression in extrinsic calibration between camera and single line scan laser rangefinder

摘要

This paper presents an improvement for error reduction of the cost function for non-linear optimization of extrinsic parameters estimation between single line scan LiDAR and RGB camera. The non-linear optimization utilizes a least square scheme by assigning equal weights to all LiDAR measurement points. With robust regression, we used all LiDAR measurement points and removed RANSAC outlier removal with a weighting scheme dependent on the defined geometric constraint. The methods aims to minimize the error from the inaccuracy of the LiDAR measurement points using robust regression with M-estimator. The methods are tested with 100 random trials with noise magnitude from 5 to 40mm and a 10 percent chance of outliers of 3 times the normal noise magnitude. The results show that M-estimator is more resistant to noise than current state of art.