OrbKeypointMatcher

class giant.image_processing.feature_matchers.OrbKeypointMatcher(options=None)

Implementation of KeypointMatcher using ORB for detection and FLANN for matching.

Initialize the OrbKeypointMatcher.

Parameters:

• ratio_threshold – Value used to filter keypoint matches (Lowe’s ratio test)

• detect_kwargs – Dictionary of kwargs for cv2.ORB_create

• index_params – Dictionary of kwargs for FlannBasedMatcher

• search_params – Dictionary of kwargs for FlannBasedMatcher.knnMatch

• options (ORBKeypointMatcherOptions | None)

allowed_dtypes: list[type[Any] | dtype[Any] | _SupportsDType[dtype[Any]] | tuple[Any, Any] | list[Any] | _DTypeDict | str | None] = [<class 'numpy.uint8'>]

A list of dtypes allowed by the detector.

This must be implemented by subclasses.

detect_keypoints(image)

Detect keypoint descriptors using ORB.

Parameters:

image (ndarray[tuple[Any, ...], dtype[_ScalarT]]) – The image to search for keypoints

Returns:

Tuple of (keypoints, descriptors)

Return type:

tuple[Sequence[KeyPoint], ndarray[tuple[Any, …], dtype[_ScalarT]]]