RandomTranslationPerturber

class nrtk.impls.perturb_image.generic.translation_perturber.RandomTranslationPerturber(box_alignment_mode: str = 'extent', seed: int | Generator | None = 1, color_fill: Sequence[int] | None = [0, 0, 0])

RandomTranslationPerturber randomly translates an image and adjusts bounding boxes accordingly. Methods: perturb: Applies a random translation to an input image and adjusts bounding boxes. __call__: Calls the perturb method with the given input image. get_config: Returns the current configuration of the RandomTranslationPerturber instance.

Methods

from_config	Instantiate a new instance of this class given the configuration JSON-compliant dictionary encapsulating initialization arguments.
get_config	Returns the current configuration of the RandomTranslationPerturber instance.
get_default_config	Generate and return a default configuration dictionary for this class.
get_impls	Discover and return a set of classes that implement the calling class.
get_type_string	Returns the fully qualified type string of the PerturbImage class or its subclass.
is_usable	Check whether this class is available for use.
perturb	Randomly translates an image and adjusts bounding boxes.

__call__(image: ndarray, boxes: Iterable[tuple[AxisAlignedBoundingBox, dict[Hashable, float]]] | None = None, additional_params: dict[str, Any] | None = None) → tuple[ndarray, Iterable[tuple[AxisAlignedBoundingBox, dict[Hashable, float]]] | None]

Calls perturb with the given input image.

__init__(box_alignment_mode: str = 'extent', seed: int | Generator | None = 1, color_fill: Sequence[int] | None = [0, 0, 0]) → None

RandomTranslationPerturber applies a random translation perturbation to an input image. It ensures that bounding boxes are adjusted correctly to reflect the translated image coordinates.

Attributes:

rng (numpy.random.Generator): Random number generator for deterministic behavior. color_fill: Background color fill for RGB image.

get_config() → dict[str, Any]

Returns the current configuration of the RandomTranslationPerturber instance.

Returns:

dict[str, Any]: Configuration dictionary with current settings.

perturb(image: ndarray, boxes: Iterable[tuple[AxisAlignedBoundingBox, dict[Hashable, float]]] | None = None, additional_params: dict[str, Any] | None = None) → tuple[ndarray, Iterable[tuple[AxisAlignedBoundingBox, dict[Hashable, float]]] | None]

Randomly translates an image and adjusts bounding boxes.

Parameters:

• image – Input image as a numpy array of shape (H, W, C).

• boxes – List of bounding boxes in AxisAlignedBoundingBox format and their corresponding classes.

• additional_params – Dictionary containing:

• “max_translation_limit” (tuple[int, int]): Max translation magnitude (translate_h, translate_w) lesser than or equal to the size of the input image.

Returns:

Translated image as numpy array with the modified bounding boxes