A Target-based co-calibration framework for 3DRadar-camera using a modified corner reflector

Abstract

Most intelligent transportation and autonomous driving systems use the combination of millimeter-wave (MMW) radar and camera to achieve strong perception, and correct extrinsic calibration is a prerequisite for sensor fusion. Most prior calibration methods rely on specific calibration environment, resulting in low calibration efficiency, and are unsuitable for practical scenarios. This paper proposes a progressive and efficient extrinsic calibration method for 3D MMW radar and camera, which only requires testers to walk around the testing range with the calibration target, and the progressive process of extrinsic parameters regression is visualized. The proposed method has been tested on the View-of-Delft dataset and in the real world, and the results show that the method proposed in this paper can converge the calibrated extrinsic parameters quickly and has strong robustness to the noise present during the testing process. Compared to EPNP, LM, P3P (based on RANSAC), and LM (based on RANAC), our proposed calibration method demonstrates a smaller re-projection error and higher accuracy in terms of extrinsic parameters. All results indicate that our calibration method has good accuracy and efficiency for practical calibration scenarios.