engleski

Extrinsic 6DoF Calibration of a Radar-LiDAR- Camera System Enhanced by Radar Cross Section Estimates Evaluation

Autonomous navigation of mobile robots is often based on information from a variety of heterogeneous sensors ; hence, extrinsic sensor calibration is a fundamental step in the fusion of such information. In this paper, we address the problem of extrinsic calibration of a radar – LiDAR – camera sensor system. This problem is primarily challenging due to sparse informativeness of radar measurements. Namely, radars cannot extract rich structural information about the environment, while their lack of elevation resolution, that is nevertheless accompanied by substantial elevation field of view, introduces uncertainty in the origin of the measurements. We propose a novel calibration method which involves a special target design and two-step optimization procedure to solve the aforementioned challenges. First step of the optimization is minimization of a reprojection error based on an introduced point-circle geometric constraint. Since the first step is not able to provide reliable estimates of all the six extrinsic parameters, we introduce a second step to refine the subset of parameters with high uncertainty. We exploit a pattern discovered in the radar cross section estimation that is correlated to the missing elevation angle. Additionally, we carry out identifiability analysis based on the Fisher Information Matrix to show minimal requirements on the dataset and to verify the method through simulations. We test the calibration method on a variety of sensor configurations and address the problem of radar vertical misalignment. In the end, we show via extensive experiment analysis that the proposed method is able to reliably estimate all the six parameters of the extrinsic calibration.

Sensor calibration ; Radar ; LiDAR ; Camera ; Radar cross section

nije evidentirano