RandomTranslationPerturber

class nrtk.impls.perturb_image.geometric.random.RandomTranslationPerturber(*, seed: int | None = None, is_static: bool = False, color_fill: Sequence[int] | None = [0, 0, 0])

RandomTranslationPerturber randomly translates an image and adjusts bounding boxes accordingly.

Attributes:

seed (int | None):

Random seed for reproducibility. None for non-deterministic behavior.

is_static (bool):

If True, resets RNG after each call for consistent results.

color_fill (numpy.array):

Background color fill for RGB image.

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 plugins, skipping any entrypoints that fail to load.
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.

__init__(*, seed: int | None = None, is_static: bool = False, 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.

Args:

seed:

Random seed for reproducible results. Defaults to None for non-deterministic behavior.

is_static:

If True and seed is provided, resets RNG after each perturb call for consistent results across multiple calls (useful for video frame processing).

color_fill:

Background color fill for RGB image. Defaults to [0, 0, 0] (black).

get_config() → dict[str, Any]

Returns the current configuration of the RandomTranslationPerturber instance.

perturb(*, image: ndarray[Any, Any], boxes: Iterable[tuple[AxisAlignedBoundingBox, dict[Hashable, float]]] | None = None, max_translation_limit: tuple[int, int] | None = None, **kwargs: Any) → tuple[ndarray[Any, Any], Iterable[tuple[AxisAlignedBoundingBox, dict[Hashable, float]]] | None]

Randomly translates an image and adjusts bounding boxes.

Args:

image:

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

boxes:

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

max_translation_limit:

Max translation magnitude (translate_h, translate_w) lesser than or equal to the size of the input image.

kwargs:

Additional perturbation keyword arguments (currently unused).

Returns:

Translated image with the modified bounding boxes.