3-D LiDAR and Monocular Camera Calibration: A Review

Cameras and light detection and ranging (LiDAR) sensors have been extensively utilized in autonomous systems to enhance perception accuracy and robustness, due to the highly complementary nature of their characteristics. The spatial and temporal relationships between these sensors are crucial for multisensor fusion technology, making calibration between heterogeneous sensors extremely important. This calibration process typically involves estimating the extrinsic parameters between sensors. Over the past two decades, with the advancement of camera and LiDAR technologies, numerous spatial calibration solutions have been proposed for various sensor configurations. The question of whether LiDAR-camera calibration (LCC) has been fully resolved has arisen and been extensively discussed. This review addresses this question by thoroughly analyzing the anatomy of mainstream LCC systems. Consequently, we thoroughly dissect the key technologies in each component of the calibration framework and discuss the future efforts in each direction. Furthermore, we summarize and list available open-source codes and datasets for LCC to facilitate other researchers’ use and comparison of these tools. To further contribute to the community, the latest open-source code and datasets in this research field will be continuously maintained and updated on our homepage https://github.com/haoxinnihao/LiDAR-camera-calibration-summary.