Back to FabImage Studio website

You are here: Start » Filter Reference » Camera Calibration » DetectCalibrationGrid_Circles

DetectCalibrationGrid_Circles


Detects an arbitrary size symmetric circle pattern on the image.

Name Type Range Description
inImage Image Input image
inCircleRadius Real 1.0 - Circle radius measured in input image pixels.
inWorldCircleSpacing Real 0.0 - Real-world distance between adjacent circles centers.
inCircleDetectionMinScore Real 0.0 - Minimum matching score for circle detector.
inMaxCircleSpacing Real* 1.0 - Maximum distance between adjacent circle centers in the image measured in pixels. Defaults to 8*inCircleRadius.
outImagePoints Point2DArray Image coordinates of detected calibration points.
outWorldPlanePoints Point2DArray World plane coordinates of detected calibration points.
diagCircleCandidates Circle2DArray Detected circles, before the grid construction step

Applications

Camera calibration, image to world coordinates transformations.

Hints

In a case of sparse circle pattern (i.e. distances between circles relatively large in comparison to their radius), output point arrays may be empty despite properly detected diagCircleCandidates. In such a case it may be needed to set the inMaxCircleSpacing.

Examples

Input image for DetectCalibrationGrid_Circles executed with inCircleRadius = 5

Detected calibration points

Remarks

The circle pattern must be a rectangular grid, with equal spacing in both dimensions.

Works only for slightly distorted images (circles cannot appear as ellipses).

Complexity Level

This filter is available on Basic Complexity Level.

Filter Group

This filter is member of DetectCalibrationGrid filter group.

See Also