Automatic targetless LiDAR–camera calibration: a survey

The recent trend of fusing complementary data from LiDARs and cameras for more accurate perception has made the extrinsic calibration between two sensors critically important. Indeed, to align spatially proper fusion, process usually involves estimating parameters them. Traditional LiDAR–camera methods often depend on explicit targets or human intervention, which can be prohibitively expensive cumbersome. Recognizing these weaknesses, adopt autonomic targetless approach, conducted at a much lower cost. This paper presents thorough review automatic methods. Specifically, based how potential cues in environment are retrieved utilized process, we divide into four categories: information theory based, feature ego-motion learning For each category, provide an in-depth overview with insights have gathered, hoping serve as guidance researchers related fields.