robokudo.utils.comparators¶

Classes¶

`FeatureComparator`	Base class for feature comparators.
`TranslationComparator`	Extended FeatureComparator that computes similarity based on translation distance between query and object values.
`OrientationComparator`	Extended FeatureComparator that computes orientation similarity by dot product.
`BboxComparator`	Extended FeatureComparator that computes similarity based on the bounding box size difference between query and object values.
`SizeComparator`	Extended FeatureComparator that computes similarity based on the sum difference between query and object values.
`HistogramComparator`	Extended FeatureComparator that computes similarity based on the cv2.HISTCMP_CORREL comparison between query and object values.
`SemanticColorComparator`	Extended FeatureComparator that computes similarity based on string similarity and color ratio difference between query and object values.
`ClassificationComparator`	Extended FeatureComparator that computes similarity based on type, classname and confidence.
`AdditionalDataComparator`	Extended FeatureComparator that computes similarity based on numerical difference or simple value comparison between query and object values.
`RoiComparator`	Extended FeatureComparator that computes similarity based on overlap percentage between query and object values.
`MaskComparator`	Extended FeatureComparator that computes the IoU of two masks.
`ImageROIComparator`	Extended FeatureComparator that computes the IoU of two images ROIs.
`PoseComparator`	Extended FeatureComparator that computes the similarity of two poses.

Module Contents¶

class robokudo.utils.comparators.FeatureComparator(weight: float)¶

Base class for feature comparators.

weight¶: Weight of this comparator in the final similarity score.

abstract compute_similarity(query_value: typing_extensions.Any, obj_value: typing_extensions.Any) → float¶

Computes similarity between query and object values.

Parameters:

query_value – The translation to use as a baseline for comparison.
obj_value – The value to compare against query_value.

Returns:

A similarity score between 0.0 (no similarity at all) and 1.0 (completely identical).

class robokudo.utils.comparators.TranslationComparator(weight: float, max_distance: float = 1.0)¶

Bases: FeatureComparator

Extended FeatureComparator that computes similarity based on translation distance between query and object values.

max_distance = 1.0¶: Maximum distance between query and object values for which the similarity is 0.0.

compute_similarity(query_value: typing_extensions.Union[typing_extensions.Iterable[float], robokudo.types.annotation.PositionAnnotation], obj_value: typing_extensions.Union[typing_extensions.Iterable[float], robokudo.types.annotation.PositionAnnotation]) → float¶

Computes similarity based on translation distance between query and object values.

Parameters:

query_value – The translation to use as a baseline for comparison.
obj_value – The translation to compare against query_value.

Returns:

A similarity score between 0.0 (distance equal to or larger than self.max_distance) and 1.0 (completely identical).

class robokudo.utils.comparators.OrientationComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes orientation similarity by dot product.

compute_similarity(query_value: typing_extensions.Union[typing_extensions.Iterable[float], numpy.typing.NDArray[numpy.float64]], obj_value: typing_extensions.Union[typing_extensions.Iterable[float], numpy.typing.NDArray[numpy.float64]]) → float¶

Computes similarity of both orientation quaternions by dot product.

Parameters:

query_value – The quaternion to use as a baseline for comparison.
obj_value – The quaternion to compare against query_value.

Returns:

A similarity score between 0.0 (angle=180d) and 1.0 (angle=0d).

class robokudo.utils.comparators.BboxComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes similarity based on the bounding box size difference between query and object values.

compute_similarity(query_value: robokudo.types.annotation.BoundingBox3DAnnotation, obj_value: robokudo.types.annotation.BoundingBox3DAnnotation) → float¶

Computes similarity between bounding boxes based on their sizes.

Parameters:

query_value – The bounding box to use as a baseline for comparison.
obj_value – The bounding box to compare against query_value.

Returns:

A similarity score between 0.0 (obj_value is 0% the size of query_value) and 1.0 (identical bounding box sizes).

class robokudo.utils.comparators.SizeComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes similarity based on the sum difference between query and object values.

compute_similarity(query_value: typing_extensions.List, obj_value: typing_extensions.List) → float¶

Computes similarity of two lists based on their sum differences.

Parameters:

query_value – The list to use as a baseline for comparison.
obj_value – The list to compare against query_value.

Returns:

A similarity score between 0.0 (sum of obj_value is 100% smaller or larger than sum of query_value) and 1.0 (identical sums).

class robokudo.utils.comparators.HistogramComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes similarity based on the cv2.HISTCMP_CORREL comparison between query and object values.

compute_similarity(query_value: robokudo.types.annotation.ColorHistogram, obj_value: robokudo.types.annotation.ColorHistogram) → float¶

Computes similarity between ColorHistogram objects based on the cv2.HISTCMP_CORREL metric.

Parameters:

query_value – The histogram to use as a baseline for comparison.
obj_value – The histogram to compare against query_value.

Returns:

A similarity score between 0.0 (completely different) and 1.0 (identical).

class robokudo.utils.comparators.SemanticColorComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes similarity based on string similarity and color ratio difference between query and object values.

compute_similarity(query_value: robokudo.types.annotation.SemanticColor, obj_value: robokudo.types.annotation.SemanticColor) → float¶

Computes similarity between SemanticColor objects based on the cv2.HISTCMP_CORREL metric.

Parameters:

query_value – The semantic color annotation to use as a baseline for comparison.
obj_value – The semantic color annotation to compare against query_value.

Returns:

A similarity score between 0.0 (completely different colors or color ratio) and 1.0 (identical color and color ratio).

class robokudo.utils.comparators.ClassificationComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes similarity based on type, classname and confidence.

compute_similarity(query_value: robokudo.types.annotation.Classification, obj_value: robokudo.types.annotation.Classification) → float¶

Computes similarity between SemanticColor objects based on the cv2.HISTCMP_CORREL metric.

Parameters:

query_value – The semantic color annotation to use as a baseline for comparison.
obj_value – The semantic color annotation to compare against query_value.

Returns:

A similarity score between 0.0 (completely different colors or color ratio) and 1.0 (identical color and color ratio).

class robokudo.utils.comparators.AdditionalDataComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes similarity based on numerical difference or simple value comparison between query and object values.

compute_similarity(query_value: typing_extensions.Any, obj_value: typing_extensions.Any) → float¶

Computes similarity between any value or object based on numerical difference or value equality.

If query_value and obj_value are numerical this FeatureComparator will normalize their numerical difference. Otherwise a simple equality check is performed, 0.0 is returned if they are not equal, 1.0 if they are equal.

Parameters:

query_value – The object or value to use as a baseline for comparison.
obj_value – The object or value to compare against query_value.

Returns:

A similarity score between 0.0 (no similarity) and 1.0 (identical values).

class robokudo.utils.comparators.RoiComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes similarity based on overlap percentage between query and object values.

compute_similarity(query_value: robokudo.types.cv.Rect, obj_value: robokudo.types.cv.Rect) → float¶

Computes the similarity of two Region of Interests by calculating their IoU.

Parameters:

query_value – The rectangle to use as a baseline for comparison.
obj_value – The rectangle to compare against query_value.

Returns:

A similarity score between 0.0 (no overlap) and 1.0 (100% overlap).

class robokudo.utils.comparators.MaskComparator(weight: float)¶

Bases: FeatureComparator

Extended FeatureComparator that computes the IoU of two masks.

compute_similarity(query_value: numpy.typing.NDArray, obj_value: numpy.typing.NDArray) → float¶

Computes the similarity of two masks by calculating their IoU.

Parameters:

query_value – The mask to use as a baseline for comparison.
obj_value – The mask to compare against query_value.

Returns:

A similarity score between 0.0 (no overlap) and 1.0 (100% overlap).

class robokudo.utils.comparators.ImageROIComparator(weight: float = 1.0)¶

Bases: FeatureComparator

Extended FeatureComparator that computes the IoU of two images ROIs.

roi_comparator¶: Comparator to compute the IoU of two images ROIs.

mask_comparator¶: Comparator to compute the IoU of two image masks.

compute_similarity(query_value: robokudo.types.cv.ImageROI, obj_value: robokudo.types.cv.ImageROI) → float¶

Computes the similarity of two ImageROI annotations by calculating the average IoU of both bounding boxes and masks.

Parameters:

query_value – The ImageROI to use as a baseline for comparison.
obj_value – The ImageROI to compare against query_value.

Returns:

A similarity score between 0.0 (no overlap) and 1.0 (100% overlap).

class robokudo.utils.comparators.PoseComparator(weight: float = 1.0, max_distance: float = 1.0)¶

Bases: FeatureComparator

Extended FeatureComparator that computes the similarity of two poses.

translation_comparator¶: Comparator to compute the similarity of two positions.

orientation_comparator¶: Comparator to compute the similarity of two orientations.

compute_similarity(query_value: robokudo.types.tf.Pose, obj_value: robokudo.types.tf.Pose) → float¶

Computes the similarity of two poses by comparing translation and orientation values.

Parameters:

query_value – The Pose to use as a baseline for comparison.
obj_value – The Pose to compare against query_value.

Returns:

A similarity score between 0.0 (no similarity at all) and 1.0 (completely identical).