METRIC - Multi-Eye To Robot Indoor Calibration Dataset

The METRIC dataset comprises more than 10,000 synthetic and real images of ChAruCo and checkerboard patterns. Each pattern is securely attached to the robot's end-effector, which is systematically moved in front of four cameras surrounding the manipulator. This movement allows for image acquisition from various viewpoints. The real images in the dataset encompass multiple sets of images captured by three distinct types of sensor networks: Microsoft Kinect V2, Intel RealSense Depth D455, and Intel RealSense Lidar L515. The purpose of including these images is to evaluate the advantages and disadvantages of each sensor network for calibration purposes. Additionally, to accurately assess the impact of the distance between the camera and robot on calibration, we obtained a comprehensive synthetic dataset. This dataset contains associated ground truth data and is divided into three different camera network setups, corresponding to three levels of calibration difficulty based on the cell size.METRIC数据集包含超过10000张涵盖查鲁科（ChAruCo）与棋盘格两种图案的合成及实拍图像。将每种图案牢固固定于机器人末端执行器，随后使该执行器在环绕机械臂的四台相机前方按既定规则移动，以此实现多视角的图像采集。本数据集内的实拍图像由三类不同的传感器网络采集得到，分别为Microsoft Kinect V2、Intel RealSense Depth D455以及Intel RealSense Lidar L515；收录此类图像的目的是针对相机校准场景评估各传感器网络的优劣表现。此外，为精准评估相机与机器人间距对校准流程的影响，本研究构建了一套完整的合成数据集。该数据集附带配套的真值标注数据，并按照三种不同的相机网络布局进行划分，每种布局根据图案单元尺寸对应不同的校准难度等级。