imfusion.data#

Submodule for Data and Data-derived types.

class imfusion.data.Data#

Bases: pybind11_object

class Kind(value, names=<not given>, *values, module=None, qualname=None, type=None, start=1, boundary=None)#

Bases: Enum

IMAGE = 1#

IMAGE_SET = 3#

IMAGE_STREAM = 5#

POINT_SET = 7#

STEREOIMAGESET = 14#

SURFACE = 8#

TRACKING_DATA = 10#

TRACKING_STREAM = 9#

UNKNOWN = 0#

VOLUME = 2#

VOLUME_SET = 4#

VOLUME_STREAM = 6#

class Modality(value, names=<not given>, *values, module=None, qualname=None, type=None, start=1, boundary=None)#

Bases: Enum

CT = 2#

LABEL = 8#

MRI = 3#

NA = 0#

NM = 6#

OCT = 7#

ULTRASOUND = 4#

VIDEO = 5#

XRAY = 1#

matrix_from_world(self: Data) → Annotated[numpy.typing.NDArray[numpy.float64], '[4, 4]']#

matrix_to_world(self: Data) → Annotated[numpy.typing.NDArray[numpy.float64], '[4, 4]']#

set_matrix_from_world(self: Data, arg0: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]']) → None#

set_matrix_to_world(self: Data, arg0: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]']) → None#

property components#

Type:: DataComponentList

property kind#

Type:: Kind

property name#

Type:: str

class imfusion.data.DataGroup#

Bases: Data

__iter__(self: DataGroup) → Iterator#

children_recursive(self: DataGroup) → list[Data]#

property children#

Type:: list[Data]

property proxy_child#

Type:: Data

class imfusion.data.Mesh(*args, **kwargs)#

Bases: Data

Function overload documentation:

__init__(self: Mesh, mesh: Mesh) → None

__init__(self: Mesh, name: str = '') → None

class Primitive(value, names=<not given>, *values, module=None, qualname=None, type=None, start=1, boundary=None)#

Bases: Enum

Enumeration of supported mesh primitives.

CONE = 5#

CUBE = 3#

CYLINDER = 1#

GRID = 6#

ICOSAHEDRON_SPHERE = 4#

PYRAMID = 2#

SPHERE = 0#

add_face(self: Mesh, index: Annotated[numpy.typing.ArrayLike, numpy.int32, '[3, 1]'], force: bool) → int#

add_vertex(self: Mesh, position: Annotated[numpy.typing.ArrayLike, numpy.float64, '[3, 1]']) → int#

static create(shape: Primitive) → Mesh#

Create a mesh primitive.

Args:
shape: The shape of the primitive to create.

face_normal(self: Mesh, index: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float64], '[3, 1]']#

face_vertices(self: Mesh, index: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.int32], '[3, 1]']#

halfedge_color(self: Mesh, vertex_index: SupportsInt | SupportsIndex, face_index: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float32], '[4, 1]']#

halfedge_normal(self: Mesh, vertex_index: SupportsInt | SupportsIndex, face_index: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float64], '[3, 1]']#

halfedge_vertices(self: Mesh, vertex_index: SupportsInt | SupportsIndex, face_index: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.int32], '[2, 1]']#

is_closed(self: Mesh) → bool#

is_manifold(self: Mesh) → bool#

is_self_intersecting(self: Mesh) → bool#

is_vertex_manifold(self: Mesh, index: SupportsInt | SupportsIndex) → bool#

is_watertight(self: Mesh, check_self_intersection: bool) → bool#

remove_face(self: Mesh, index: SupportsInt | SupportsIndex, remove_isolated_vertices: bool) → bool#

remove_faces(self: Mesh, indices: Sequence[SupportsInt | SupportsIndex], remove_isolated_vertices: bool) → None#

remove_halfedge_colors(self: Mesh) → None#

remove_halfedge_normals(self: Mesh) → None#

remove_vertex_colors(self: Mesh) → None#

remove_vertex_normals(self: Mesh) → None#

remove_vertices(self: Mesh, indices: Sequence[SupportsInt | SupportsIndex], remove_isolated_vertices: bool) → None#

set_halfedge_color(self: Mesh, vertex_index: SupportsInt | SupportsIndex, face_index: SupportsInt | SupportsIndex, color: Annotated[numpy.typing.ArrayLike, numpy.float32, '[4, 1]']) → None#

Function overload documentation:

set_halfedge_color(self: Mesh, vertex_index: SupportsInt | SupportsIndex, face_index: SupportsInt | SupportsIndex, color: Annotated[numpy.typing.ArrayLike, numpy.float32, '[4, 1]']) → None

set_halfedge_color(self: Mesh, vertex_index: SupportsInt | SupportsIndex, face_index: SupportsInt | SupportsIndex, color: Annotated[numpy.typing.ArrayLike, numpy.float32, '[3, 1]'], alpha: SupportsFloat | SupportsIndex) → None

set_halfedge_normal(self: Mesh, vertex_index: SupportsInt | SupportsIndex, face_index: SupportsInt | SupportsIndex, normal: Annotated[numpy.typing.ArrayLike, numpy.float64, '[3, 1]']) → None#

set_vertex(self: Mesh, index: SupportsInt | SupportsIndex, vertex: Annotated[numpy.typing.ArrayLike, numpy.float64, '[3, 1]']) → None#

set_vertex_color(self: Mesh, index: SupportsInt | SupportsIndex, color: Annotated[numpy.typing.ArrayLike, numpy.float32, '[4, 1]']) → None#

set_vertex_color(self: Mesh, index: SupportsInt | SupportsIndex, color: Annotated[numpy.typing.ArrayLike, numpy.float32, '[3, 1]'], alpha: SupportsFloat | SupportsIndex) → None

Function overload documentation:

set_vertex_color(self: Mesh, index: SupportsInt | SupportsIndex, color: Annotated[numpy.typing.ArrayLike, numpy.float32, '[4, 1]']) → None

set_vertex_color(self: Mesh, index: SupportsInt | SupportsIndex, color: Annotated[numpy.typing.ArrayLike, numpy.float32, '[3, 1]'], alpha: SupportsFloat | SupportsIndex) → None

set_vertex_normal(self: Mesh, index: SupportsInt | SupportsIndex, normal: Annotated[numpy.typing.ArrayLike, numpy.float64, '[3, 1]']) → None#

vertex(self: Mesh, index: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float64], '[3, 1]']#

vertex_color(self: Mesh, index: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float32], '[4, 1]']#

vertex_normal(self: Mesh, index: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float64], '[3, 1]']#

property center#

Type:: Annotated[numpy.typing.NDArray[numpy.float64], ”[3, 1]”]

property extent#

Type:: Annotated[numpy.typing.NDArray[numpy.float64], ”[3, 1]”]

property filename#

Type:: str

property has_halfedge_colors#

Type:: bool

property has_halfedge_normals#

Type:: bool

property has_vertex_colors#

Type:: bool

property has_vertex_normals#

Type:: bool

property number_of_faces#

Type:: int

property number_of_vertices#

Type:: int

class imfusion.data.PointCloud(self: PointCloud, points: Sequence[Annotated[numpy.typing.ArrayLike, numpy.float64, '[3, 1]']] = [], *, normals: Sequence[Annotated[numpy.typing.ArrayLike, numpy.float64, '[3, 1]']] = [], colors: Sequence[Annotated[numpy.typing.ArrayLike, numpy.float64, '[3, 1]']] = [])#

Bases: Data

Data structure representing a point cloud in 3d space. Each point can have an associated color and normal vector.

Constructs a point cloud with the specified points, normals and colors. If the number of colors / normals does not match the number of points, they will be ignored with a warning.

Parameters:

points – Vertices of the point cloud.
normals – Normals of the point cloud. If the length does not match points, normals will be dropped with a warning.
colors – Colors (RGB) of the point cloud. If the length does not match points, colors will be dropped with a warning.

clone(self: PointCloud) → PointCloud#: Create a new point cloud by deep copying an all data from this instance.

transform_point_cloud(self: PointCloud, transformation: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]']) → None#

property colors#

Type:: list[Annotated[numpy.typing.NDArray[numpy.float64], ”[3, 1]”]]

property has_normals#

Type:: bool

property is_dense#

Type:: bool

property normals#

Type:: list[Annotated[numpy.typing.NDArray[numpy.float64], ”[3, 1]”]]

property points#

Type:: list[Annotated[numpy.typing.NDArray[numpy.float64], ”[3, 1]”]]

property weights#

Type:: list[float]

class imfusion.data.SharedImageSet(*args, **kwargs)#

Bases: Data

Set of images independent of their storage location.

This class is the main high-level container for image data consisting of one or multiple images or volumes, and should be used both in algorithms and visualization classes. Both a single focus and multiple selection is featured, as well as providing transformation matrices for each image.

The focus image of a SharedImageSet can be directly converted from and to a numpy array:

>>> img = imfusion.SharedImageSet(np.ones([1, 10, 10, 10, 1], dtype='uint8'))
>>> arr = np.array(img)

See MemImage for details.

Function overload documentation:

__init__(self: SharedImageSet) → None: Creates an empty SharedImageSet.

__init__(self: SharedImageSet, mem_image: MemImage) → None

__init__(self: SharedImageSet, shared_image: SharedImage) → None

__init__(self: SharedImageSet, array: Annotated[numpy.typing.ArrayLike, numpy.int8], greyscale: bool = False) → None

__init__(self: SharedImageSet, array: Annotated[numpy.typing.ArrayLike, numpy.uint8], greyscale: bool = False) → None

__init__(self: SharedImageSet, array: Annotated[numpy.typing.ArrayLike, numpy.int16], greyscale: bool = False) → None

__init__(self: SharedImageSet, array: Annotated[numpy.typing.ArrayLike, numpy.uint16], greyscale: bool = False) → None

__init__(self: SharedImageSet, array: Annotated[numpy.typing.ArrayLike, numpy.int32], greyscale: bool = False) → None

__init__(self: SharedImageSet, array: Annotated[numpy.typing.ArrayLike, numpy.uint32], greyscale: bool = False) → None

__init__(self: SharedImageSet, array: Annotated[numpy.typing.ArrayLike, numpy.float32], greyscale: bool = False) → None

__init__(self: SharedImageSet, array: Annotated[numpy.typing.ArrayLike, numpy.float64], greyscale: bool = False) → None

__getitem__(self: SharedImageSet, index: SupportsInt | SupportsIndex) → SharedImage#

__iter__(self: SharedImageSet) → Iterator[SharedImage]#

add(self: SharedImageSet, shared_image: SharedImage) → None#

add(self: SharedImageSet, mem_image: MemImage) → None

Function overload documentation:

add(self: SharedImageSet, shared_image: SharedImage) → None

add(self: SharedImageSet, mem_image: MemImage) → None

all(self: SharedImageSet) → bool#: Returns True if all pixels / voxels is non-zero

any(self: SharedImageSet) → bool#: Returns True if at least one pixel / voxel is non-zero

apply_shift_and_scale(arr)#

Return a copy of the array with storage values converted to original values.

Parameters:

self – instance of a SharedImageSet which provides shift and scale
arr – array to be converted from storage values into original values

Returns:

numpy.ndarray

argmax(self: SharedImageSet) → list[Annotated[numpy.typing.NDArray[numpy.int32], '[4, 1]']]#

Return a list of the indices of maximum values, channel-wise. The indices are represented as (x, y, z, image index).

Returns:: List of indices (x, y, z, image index) returned as a list of numpy arrays.

argmin(self: SharedImageSet) → list[Annotated[numpy.typing.NDArray[numpy.int32], '[4, 1]']]#

Return a list of the indices of minimum values, channel-wise. The indices are represented as (x, y, z, image index).

Returns:: List of indices (x, y, z, image index) returned as a list of numpy arrays.

assign_array(arr)#: Copies the contents of arr to the MemImage. Automatically calls setDirtyMem.

astype(self: SharedImageSet, pixel_type: object) → SharedImageSet#

Returns a new SharedImageSet formed by new SharedImage instances obtained by converting the original ones into the requested PixelType.

This function accepts either: - a PixelType (e.g. imfusion.PixelType.UInt); - most of the numpy’s dtypes (e.g. np.uint); - python’s float or int types.

If the requested type already matches the input type, the returned SharedImageSet will contain clones of the original images.

channel_swizzle(self: SharedImageSet, indices: Sequence[SupportsInt | SupportsIndex]) → SharedImageSet#

Reorders the channels of an image based on the input indices, e.g. indices[0] will correspond to the first channel of the output image.

Parameters:: indices – List of channel indices to swizzle the channels of the input.
Returns:: SharedImageSet instance with reordered channels.

clear(self: SharedImageSet) → None#

clone(self: SharedImageSet, with_data: bool = True) → SharedImageSet#

deformation(self: SharedImageSet, which: SupportsInt | SupportsIndex = -1) → Deformation#

descriptor(self: SharedImageSet, which: SupportsInt | SupportsIndex = -1) → BoundImageDescriptor#: Return a read-only descriptor view for a specific or selected image.

elementwise_components(self: SharedImageSet, which: SupportsInt | SupportsIndex = -1) → DataComponentList#

static from_images(path: str) → SharedImageSet#

static from_images(path: Sequence[str]) → SharedImageSet

Function overload documentation:

from_images(path: str) → SharedImageSet

Load different images as a single SharedImageSet.

Currently supported image formats are: [bmp, pgm, png, ppm, jpg, jpeg, tif, tiff, jp2].

Parameters:: folder_path – The directory where all images are located to be loaded as a SharedImageSet.
Raises:: IOError if the file cannot be opened or if the extensions is not supported. –

from_images(path: Sequence[str]) → SharedImageSet

Load different images as a single SharedImageSet.

Currently supported image formats are: [bmp, pgm, png, ppm, jpg, jpeg, tif, tiff, jp2].

Parameters:: file_paths – paths to image files to be loaded as a SharedImageSet.
Raises:: IOError if the file cannot be opened or if the extensions is not supported. –

classmethod from_torch(tensor: Tensor, get_metadata_from: SharedImageSet | None = None) → SharedImageSet#

Create a SharedImageSet from a torch Tensor. If you want to copy metadata from an existing SharedImageSet you can pass it as the get_metadata_from argument. If you are using this, make sure that the size of the tensor’s batch dimension and the number of images in the SIS are equal. If get_metadata_from is provided, properties will be copied from the SIS and world_to_image_matrix, spacing and modality from the contained SharedImages.

Parameters:

cls – Instance of type i.e. SharedImageSet (this function is bound as a classmethod to SharedImageSet)
tensor (Tensor) – Instance of torch.Tensor
get_metadata_from (SharedImageSet | None) – Instance of SharedImageSet from which metadata should be copied.

Returns:

New instance of SharedImageSet

Return type:

SharedImageSet

get(self: SharedImageSet, which: SupportsInt | SupportsIndex = -1) → SharedImage#

mask(self: SharedImageSet, which: SupportsInt | SupportsIndex = -1) → Mask#

matrix(self: SharedImageSet, which: SupportsInt | SupportsIndex = -1) → Annotated[numpy.typing.NDArray[numpy.float64], '[4, 4]']#

matrix_from_world(self: SharedImageSet, which: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float64], '[4, 4]']#

matrix_to_world(self: SharedImageSet, which: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float64], '[4, 4]']#

max(self: SharedImageSet) → Annotated[numpy.typing.NDArray[numpy.float64], '[m, 1]']#

Return the list of the maximum elements of images, channel-wise.

Returns:: Channel-wise values returned as a numpy array.

mean(self: SharedImageSet) → Annotated[numpy.typing.NDArray[numpy.float64], '[m, 1]']#

Return a list of channel-wise average of image elements.

Returns:: Channel-wise values returned as a numpy array.

mem(self: SharedImageSet, which: SupportsInt | SupportsIndex = -1) → MemImage#

min(self: SharedImageSet) → Annotated[numpy.typing.NDArray[numpy.float64], '[m, 1]']#

Return the list of the minimum elements of images, channel-wise.

Returns:: Channel-wise values returned as a numpy array.

norm(self: SharedImageSet, order: SupportsInt | SupportsIndex | SupportsFloat | SupportsIndex | str = 2) → Annotated[numpy.typing.NDArray[numpy.float64], '[m, 1]']#

Returns the norm of an image instance, channel-wise.

Parameters:: order – Order of the norm. Use a number (e.g., 1 or 2) or ‘inf’. The default is the L2 norm.
Returns:: Norm values per channel returned as a numpy array.

numpy()#

Convenience method for reading a SharedImageSet as original values, with shift and scale already applied.

Parameters:: self – instance of a SharedImageSet
Returns:: numpy.ndarray

prod(self: SharedImageSet) → Annotated[numpy.typing.NDArray[numpy.float64], '[m, 1]']#

Return a list of channel-wise production of image elements.

Returns:: Channel-wise values returned as a numpy array.

remove(self: SharedImageSet, shared_image: SharedImage) → None#: Removes and deletes the SharedImage from the set.

selected_images(self: SharedImageSet, arg0: NonePolicy) → list[SharedImage]#

set_deformation(self: SharedImageSet, deformation: Deformation, which: SupportsInt | SupportsIndex = -1) → None#

set_dirty_mem(self: SharedImageSet) → None#

set_mask(self: SharedImageSet, mask: Mask, which: SupportsInt | SupportsIndex = -1) → None#

set_matrix(self: SharedImageSet, matrix: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], which: SupportsInt | SupportsIndex = -1, update_all: bool = False) → None#

set_matrix_from_world(self: SharedImageSet, matrix: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], which: SupportsInt | SupportsIndex, update_all: bool = False) → None#

set_matrix_to_world(self: SharedImageSet, matrix: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], which: SupportsInt | SupportsIndex, update_all: bool = False) → None#

set_timestamp(self: SharedImageSet, time: SupportsFloat | SupportsIndex, which: SupportsInt | SupportsIndex = -1) → None#

sum(self: SharedImageSet) → Annotated[numpy.typing.NDArray[numpy.float64], '[m, 1]']#

Return a list of channel-wise sum of image elements.

Returns:: Channel-wise values returned as a numpy array.

timestamp(self: SharedImageSet, which: SupportsInt | SupportsIndex = -1) → float#

torch(device: device = None, dtype: dtype = None, same_as: Tensor = None) → Tensor#

Convert SharedImageSet or a SharedImage to a torch.Tensor.

Parameters:

self (DataElement | SharedImageSet | SharedImage) – Instance of SharedImageSet or SharedImage (this function bound as a method to SharedImageSet and SharedImage)
device (device) – Target device for the new torch.Tensor
dtype (dtype) – Type of the new torch.Tensor
same_as (Tensor) – Template tensor whose device and dtype configuration should be matched. device and dtype are still applied afterwards.

Returns:

New torch.Tensor

Return type:

Tensor

property all_same_descriptor#

Type:: bool

property all_timestamped#

Type:: bool

property focus#

Type:: int

property modality#

Type:: Modality

property properties#

Type:: Properties

property selection#

Type:: Selection

property shape#

Return a numpy compatible shape descripting the dimensions of this image.

The returned tuple has 5 entries: #frames, slices, height, width, channels

Type:: tuple[int, int, int, int, int]

property size#

Type:: int

class imfusion.data.TrackedSharedImageSet(*args, **kwargs)#

Bases: SharedImageSet

Set of images with arbitrarily sampled tracking data.

Replaces per-image matrices of SharedImageSet from TrackingSequence instances.

Construct from an existing SharedImageSet (cloned, original stays valid) and a TrackingSequence, copy another TrackedSharedImageSet (including trackings), or build an empty set and call add() / add_tracking().

Function overload documentation:

__init__(self: TrackedSharedImageSet) → None: Creates an empty TrackedSharedImageSet.

__init__(self: TrackedSharedImageSet, tracked_shared_image_set: TrackedSharedImageSet) → None: Creates a deep copy of tracked_shared_image_set, including images and tracking sequences. The original set is left unchanged.

__init__(self: TrackedSharedImageSet, shared_image_set: SharedImageSet, tracking_sequence: TrackingSequence) → None

Creates a TrackedSharedImageSet by cloning shared_image_set (images, timestamps, properties, and name) and attaching a copy of tracking_sequence. The original set is left unchanged.

For a full copy of an existing TrackedSharedImageSet (including trackings), use the single-argument copy constructor instead.

add_tracking(self: TrackedSharedImageSet, tracking_sequence: TrackingSequence) → None#: Attaches a copy of tracking_sequence to this set.

clear_trackings(self: TrackedSharedImageSet) → None#

from_shared_image_set(self: TrackedSharedImageSet, image_set: SharedImageSet) → None#: Swaps all images, timestamps, properties, and the name with image_set. After the call, this TrackedSharedImageSet holds the former contents of image_set, and image_set holds the former contents of this set (typically empty if this set was empty). Does not create or modify tracking sequences. Prefer the constructor when you need a non-destructive copy.

remove_tracking(self: TrackedSharedImageSet, num: SupportsInt | SupportsIndex = -1) → TrackingSequence#

tracking(self: TrackedSharedImageSet, num: SupportsInt | SupportsIndex = -1) → TrackingSequence#

property has_transformations#

Type:: bool

property height#

Type:: int

property num_tracking#

Type:: int

property tracking_used#

Type:: int

property trackings#

List of tracking sequences owned by this set (references, not copies).

Type:: list

property use_timestamps#

Type:: bool

property width#

Type:: int

class imfusion.data.TrackingSequence(self: TrackingSequence, name: str = '')#

Bases: Data

add(self: TrackingSequence, mat: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]']) → None#

add(self: TrackingSequence, mat: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], timestamp: SupportsFloat | SupportsIndex) → None

add(self: TrackingSequence, mat: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], timestamp: SupportsFloat | SupportsIndex, quality: SupportsFloat | SupportsIndex) → None

add(self: TrackingSequence, mat: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], timestamp: SupportsFloat | SupportsIndex, quality: SupportsFloat | SupportsIndex, flags: SupportsInt | SupportsIndex) → None

Function overload documentation:

add(self: TrackingSequence, mat: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]']) → None

add(self: TrackingSequence, mat: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], timestamp: SupportsFloat | SupportsIndex) → None

add(self: TrackingSequence, mat: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], timestamp: SupportsFloat | SupportsIndex, quality: SupportsFloat | SupportsIndex) → None

add(self: TrackingSequence, mat: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]'], timestamp: SupportsFloat | SupportsIndex, quality: SupportsFloat | SupportsIndex, flags: SupportsInt | SupportsIndex) → None

clear(self: TrackingSequence) → None#

flags(self: TrackingSequence, num: SupportsInt | SupportsIndex = -1) → int#

matrix(self: TrackingSequence, num_or_time: SupportsInt | SupportsIndex | SupportsFloat | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float64], '[4, 4]']#

quality(self: TrackingSequence, num: SupportsInt | SupportsIndex) → float#

quality(self: TrackingSequence, time: SupportsFloat | SupportsIndex, check_distance: bool = True, ignore_relative: bool = False) → float

Function overload documentation:

quality(self: TrackingSequence, num: SupportsInt | SupportsIndex) → float

quality(self: TrackingSequence, time: SupportsFloat | SupportsIndex, check_distance: bool = True, ignore_relative: bool = False) → float

raw_matrix(self: TrackingSequence, num: SupportsInt | SupportsIndex) → Annotated[numpy.typing.NDArray[numpy.float64], '[4, 4]']#

remove(self: TrackingSequence, pos: SupportsInt | SupportsIndex, count: SupportsInt | SupportsIndex = 1) → None#

set_raw_matrix(self: TrackingSequence, idx: SupportsInt | SupportsIndex, value: Annotated[numpy.typing.ArrayLike, numpy.float64, '[4, 4]']) → None#