Pinhole Camera

Pinhole Camera Data

class py123d.datatypes.sensors.PinholeCamera

Represents the recording of a pinhole camera including its metadata, image, extrinsic pose, and timestamp.

Public Data Attributes:

metadata	The static PinholeCameraMetadata associated with the pinhole camera.
image	The image captured by the pinhole camera, as a numpy array.
extrinsic	The extrinsic PoseSE3 of the pinhole camera, relative to the ego vehicle frame.
timestamp	The TimePoint of the image capture, if available.

---

property metadata: PinholeCameraMetadata

The static PinholeCameraMetadata associated with the pinhole camera.

property image: ndarray[tuple[Any, ...], dtype[uint8]]

The image captured by the pinhole camera, as a numpy array.

property extrinsic: PoseSE3

The extrinsic PoseSE3 of the pinhole camera, relative to the ego vehicle frame.

property timestamp: TimePoint | None

The TimePoint of the image capture, if available.

Pinhole Metadata

class py123d.datatypes.sensors.PinholeCameraMetadata

Static metadata for a pinhole camera, stored in a log.

Public Data Attributes:

camera_name	The name of the pinhole camera, according to the dataset naming convention.
camera_type	The PinholeCameraType of the pinhole camera.
intrinsics	The PinholeIntrinsics of the pinhole camera.
distortion	The PinholeDistortion of the pinhole camera.
width	The image width in pixels.
height	The image height in pixels.
static_extrinsic	The static extrinsic PoseSE3 of the pinhole camera, if available.
is_undistorted	Whether the camera images are already undistorted.
aspect_ratio	The aspect ratio (width / height) of the pinhole camera.
fov_x	The horizontal field of view (FOV) of the pinhole camera in radians, if available.
fov_y	The vertical field of view (FOV) of the pinhole camera in radians, if available.

Public Methods:

from_dict(data_dict)	Create a PinholeCameraMetadata from a dictionary.
to_dict()	Converts the PinholeCameraMetadata to a dictionary.

---

classmethod from_dict(data_dict)

Create a PinholeCameraMetadata from a dictionary.

Parameters:

data_dict (Dict[str, Any]) – A dictionary containing the metadata.

Return type:

PinholeCameraMetadata

Returns:

A PinholeCameraMetadata instance.

to_dict()

Converts the PinholeCameraMetadata to a dictionary.

Return type:

Dict[str, Any]

Returns:

A dictionary representation of the PinholeCameraMetadata instance, with default Python types.

property camera_name: str

The name of the pinhole camera, according to the dataset naming convention.

property camera_type: PinholeCameraType

The PinholeCameraType of the pinhole camera.

property intrinsics: PinholeIntrinsics | None

The PinholeIntrinsics of the pinhole camera.

property distortion: PinholeDistortion | None

The PinholeDistortion of the pinhole camera.

property width: int

The image width in pixels.

property height: int

The image height in pixels.

property static_extrinsic: PoseSE3 | None

The static extrinsic PoseSE3 of the pinhole camera, if available.

property is_undistorted: bool

Whether the camera images are already undistorted.

property aspect_ratio: float

The aspect ratio (width / height) of the pinhole camera.

property fov_x: float | None

The horizontal field of view (FOV) of the pinhole camera in radians, if available.

property fov_y: float | None

The vertical field of view (FOV) of the pinhole camera in radians, if available.

Pinhole Intrinsics

class py123d.datatypes.sensors.PinholeIntrinsics

Pinhole camera intrinsics representation.

Public Data Attributes:

array	A numpy array representation of the pinhole intrinsics, indexed by PinholeIntrinsicsIndex.
fx	Focal length in x direction.
fy	Focal length in y direction.
cx	Optical center x coordinate.
cy	Optical center y coordinate.
skew	Skew coefficient.
camera_matrix	The 3x3 camera intrinsic matrix K.

Inherited from ArrayMixin

array	The array representation of the geometric entity.
shape	Return the shape of the array.

Public Methods:

from_array(array[, copy])	Creates a PinholeIntrinsics from a numpy array, indexed by PinholeIntrinsicsIndex.
from_camera_matrix(intrinsic)	Create a PinholeIntrinsics from a 3x3 intrinsic matrix.

Inherited from ArrayMixin

from_array(array[, copy])	Create an instance from a NumPy array.
from_list(values)	Create an instance from a list of values.
tolist()	Convert the array to a Python list.
to_list()	Convert the array to a Python list.
copy()	Return a copy of the object with a copied array.

---

classmethod from_array(array, copy=True)

Creates a PinholeIntrinsics from a numpy array, indexed by PinholeIntrinsicsIndex.

Parameters:

• array (ndarray[tuple[Any, ...], dtype[float64]]) – A 1D numpy array containing the intrinsic parameters.

• copy (bool) – Whether to copy the array, defaults to True

Return type:

PinholeIntrinsics

Returns:

A PinholeIntrinsics instance.

classmethod from_camera_matrix(intrinsic)

Create a PinholeIntrinsics from a 3x3 intrinsic matrix.

Parameters:

intrinsic (ndarray[tuple[Any, ...], dtype[float64]]) – A 3x3 numpy array representing the intrinsic matrix.

Return type:

PinholeIntrinsics

Returns:

A PinholeIntrinsics instance.

property array: ndarray[tuple[Any, ...], dtype[float64]]

A numpy array representation of the pinhole intrinsics, indexed by PinholeIntrinsicsIndex.

property fx: float

Focal length in x direction.

property fy: float

Focal length in y direction.

property cx: float

Optical center x coordinate.

property cy: float

Optical center y coordinate.

property skew: float

Skew coefficient. Not used in most cases.

property camera_matrix: ndarray[tuple[Any, ...], dtype[float64]]

The 3x3 camera intrinsic matrix K.

Pinhole Distortion

class py123d.datatypes.sensors.PinholeDistortion

Pinhole camera distortion representation.

Public Data Attributes:

array	A numpy array representation of the pinhole distortion, indexed by PinholeDistortionIndex.
k1	Radial distortion coefficient k1.
k2	Radial distortion coefficient k2.
p1	Tangential distortion coefficient p1.
p2	Tangential distortion coefficient p2.
k3	Radial distortion coefficient k3.

Inherited from ArrayMixin

array	The array representation of the geometric entity.
shape	Return the shape of the array.

Public Methods:

from_array(array[, copy])

Creates a PinholeDistortion from a numpy array, indexed by PinholeDistortionIndex.

Inherited from ArrayMixin

from_array(array[, copy])	Create an instance from a NumPy array.
from_list(values)	Create an instance from a list of values.
tolist()	Convert the array to a Python list.
to_list()	Convert the array to a Python list.
copy()	Return a copy of the object with a copied array.

---

classmethod from_array(array, copy=True)

Creates a PinholeDistortion from a numpy array, indexed by PinholeDistortionIndex.

Parameters:

• array (ndarray[tuple[Any, ...], dtype[float64]]) – A 1D numpy array containing the distortion parameters.

• copy (bool) – Whether to copy the array, defaults to True

Return type:

PinholeDistortion

Returns:

A PinholeDistortion instance.

property array: ndarray[tuple[Any, ...], dtype[float64]]

A numpy array representation of the pinhole distortion, indexed by PinholeDistortionIndex.

property k1: float

Radial distortion coefficient k1.

property k2: float

Radial distortion coefficient k2.

property p1: float

Tangential distortion coefficient p1.

property p2: float

Tangential distortion coefficient p2.

property k3: float

Radial distortion coefficient k3.

Pinhole Camera Types

class py123d.datatypes.sensors.PinholeCameraType

Enumeration of pinhole camera types.

PCAM_F0 = 0

Front camera.

PCAM_B0 = 1

Back camera.

PCAM_L0 = 2

Left camera, first from front to back.

PCAM_L1 = 3

Left camera, second from front to back.

PCAM_L2 = 4

Left camera, third from front to back.

PCAM_R0 = 5

Right camera, first from front to back.

PCAM_R1 = 6

Right camera, second from front to back.

PCAM_R2 = 7

Right camera, third from front to back.

PCAM_STEREO_L = 8

Left stereo camera.

PCAM_STEREO_R = 9

Right stereo camera.