Camera, LiDAR, and robot inputs¶
Camera workflows are available in both editions. LiDAR and robot workflows require Calib GEOM Pro.
Add your devices in Set Images. Each sequence must follow the same pose order: an image, point cloud, and robot record at the same position in their sequences must describe the same physical placement.
Cameras¶
Add one camera card per image sequence. All cameras must have the same number of images, ordered consistently. Common formats including JPEG, PNG, BMP, and TIFF are supported.
See Set Images for file patterns and browser access.
LiDAR¶
Pro feature
LiDAR input, target detection, and calibration require Calib GEOM Pro.
Add a LiDAR card and select its PCD (.pcd) point-cloud sequence, with one
cloud per camera pose.
Supply XYZ coordinates in the LiDAR's own coordinate frame, in metres. Calib GEOM does not change the input scale. The target geometry must use a consistent physical scale.
LiDAR detection uses the selected target geometry. Advanced optional settings can limit the cloud region used for detection or specify physical target bounds. Choose these in the point cloud's coordinate frame.
Robot poses¶
Pro feature
Robot pose input and calibration require Calib GEOM Pro.
Add a robot card and select either:
- One CSV/TXT file containing one pose per line, or
- A sequence of CSV/TXT files containing one pose each.
The record count and order must match the camera poses. Use numeric records without headers; commas, tabs, and spaces are accepted as separators.
Pose formats¶
| Values per record | Format |
|---|---|
| 6 | Angle-scaled axis rotation rx, ry, rz in radians, followed by translation tx, ty, tz in metres |
| 7 | Quaternion w, x, y, z, followed by translation tx, ty, tz in metres |
| 12 | A 3×4 rigid transform, written row by row |
| 16 | A 4×4 homogeneous transform, written row by row |
For example:
0, 0, 1.57079632679, 0.3, 0.0, 0.5
Provide the gripper pose in the robot base frame. Do not invert the poses before importing. Confirm the convention used by your robot's export, particularly rotation order and translation units.
Before calibration¶
Check corresponding observations across every device. Consistent pose order, units, and coordinate conventions are essential: optimization cannot correct an incorrectly paired sequence or an inconsistent scale.
You can exclude individual observations or a whole pose before optimizing. See Refining the calibration.