Feature detection¶
Open Calibration → Detect Features to find target points in your images. Choose the target you used and enter its geometry carefully. Incorrect dimensions or spacing can produce a plausible-looking but incorrect calibration.
Choose your target¶
| Target | What to check |
|---|---|
| Checkerboard / Checkerboard Marker | Number of internal corner features in columns and rows. |
| ChAruCo | Corner count, checker count, dictionary, and first marker ID. |
| Kalibr | Feature count, tag size, and first tag ID. |
| Symmetric / Asymmetric Circles | Number of circles in columns and rows. |
| Caliboard CC | Feature count and first target ID. |
| AruCo Targets / AruCo Markers | Marker size and dictionary. |
For checkerboards, Feature count means internal corner points, not squares. Checker count is one greater in each direction. For circle grids, count the circles.
Spacing is entered in millimetres:
- Checkerboards: square width.
- Symmetric circles: distance between adjacent centres.
- Asymmetric circles: diagonal spacing.
- Kalibr: tag size.
For marker-only targets, the control is labelled Marker size. Use the dictionary specified for your ChAruCo or AruCo target.
For multiple ChAruCo boards, enter their first marker IDs separated by commas. Their ID ranges must not overlap.
To learn more about target designs and their trade-offs, read Calibration Patterns Explained.
Presets and barcode¶
Choose a Calib.io preset when it matches your target, or use Custom. New preset saves your settings for reuse. Editing a built-in preset does not change the original.
If your target has a supported barcode, use the barcode control to read its settings from a loaded image. Confirm the settings before starting detection.
Refinement¶
Refinement improves the feature positions after their initial detection. The available methods depend on the target:
| Method | Purpose |
|---|---|
| Unbiased symmetry | General-purpose corner refinement. |
| Perspective symmetry | Refinement using target geometry. |
| Foerstner operator | Gradient-based corner refinement. |
| Edge crossing | Refinement based on intersecting edges. |
| Polynomial | Refinement using a local intensity fit. |
| Ellipse fit | Circle-grid refinement. |
| None | Keeps the initial detected positions. |
For circle grids, Perspective bias correction can improve the estimated circle centres in tilted views. AruCo Markers use unrefined marker detections.
Neural Detection, where available, provides an alternative detector for supported targets. It requires a matching installed model and is not available in the browser.
Inspect the result¶
Check detections in representative images, especially near the image edges, at strong tilts, and where glare or blur is present. Verify that points lie on the intended features and that target identities are correct.
If detection is poor, first check target settings and image quality. Advanced Optional settings are available for specialist adjustments; leave them unchanged unless you have a specific reason to adjust them.
Good detection cannot compensate for weak capture geometry. See Analysis before collecting more images.