Pinhole Camera¶

Pinhole Metadata¶

class py123d.datatypes.PinholeCameraMetadata[source]¶

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

Public Data Attributes:

`camera_model`	The projection model of this camera.
`camera_name`	The name of the pinhole camera, according to the dataset naming convention.
`camera_id`	The `CameraID` 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.
`camera_to_imu_se3`	The camera-to-IMU extrinsic `PoseSE3` of the pinhole camera.
`is_undistorted`	Whether the camera images are already undistorted.
`is_distorted`	Whether the camera images are distorted.
`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.

Inherited from BaseCameraMetadata

`camera_model`	The projection model of the camera.
`camera_id`	The camera ID, unique within a sensor rig.
`camera_name`	The camera name, according to the dataset naming convention.
`camera_to_imu_se3`	The static extrinsic pose of the camera relative to the IMU frame.
`width`	The width of the camera image in pixels.
`height`	The height of the camera image in pixels.
`channel_type`	The channel type of the camera image.
`modality_type`	Returns the type of the modality that this metadata describes.
`modality_id`	Returns the camera ID as the modality ID.
`aspect_ratio`	The aspect ratio (width / height) of the camera.

Inherited from BaseModalityMetadata

`modality_type`	Returns the type of the modality that this metadata describes.
`modality_id`	Optional identifier for the modality, e.g. sensor ID for sensor modalities.
`modality_key`	Returns a unique key for this modality, combining type and id if applicable.

Public Methods:

`from_dict`(data_dict)	Create a `PinholeCameraMetadata` from a dictionary.
`to_dict`()	Converts the `PinholeCameraMetadata` to a dictionary.
`project_to_image`(points_cam)	Project 3D points in camera frame to image pixel coordinates using the pinhole model.

Inherited from BaseCameraMetadata

project_to_image(points_cam)

Project 3D points in camera frame to image pixel coordinates.

Inherited from BaseMetadata

`to_dict`()	Serialize the metadata instance to a plain Python dictionary.
`from_dict`(data_dict)	Construct a metadata instance from a plain Python dictionary.

Private Methods:

Inherited from BaseCameraMetadata

_compute_in_fov_mask(pixel_coords, depth[, eps])

Compute a boolean mask for points in front of the camera and within image bounds.

classmethod from_dict(data_dict)[source]¶

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()[source]¶

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_model: CameraModel¶: The projection model of this camera.

property camera_name: str¶: The name of the pinhole camera, according to the dataset naming convention.

property camera_id: CameraID¶: The CameraID of the pinhole camera.

property aspect_ratio: float¶: The aspect ratio (width / height) of the camera.

property channel_type: CameraChannelType¶: The channel type of the camera image. Defaults to RGB.

property intrinsics: PinholeIntrinsics | None¶: The PinholeIntrinsics of the pinhole camera.

property modality_id: str | SerialIntEnum | None¶: Returns the camera ID as the modality ID.

property modality_key: str¶: Returns a unique key for this modality, combining type and id if applicable.

property modality_type: ModalityType¶: Returns the type of the modality that this metadata describes.

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 camera_to_imu_se3: PoseSE3¶: The camera-to-IMU extrinsic PoseSE3 of the pinhole camera.

property is_undistorted: bool¶: Whether the camera images are already undistorted.

property is_distorted: bool¶: Whether the camera images are distorted.

project_to_image(points_cam)[source]¶

Project 3D points in camera frame to image pixel coordinates using the pinhole model.

If the camera has distortion parameters and images are not pre-undistorted, the OpenCV radial-tangential distortion model is applied so that projected pixels match the raw (distorted) image.

Parameters:: points_cam (ndarray[tuple[Any, ...], dtype[float64]]) – (N, 3) array of 3D points in the camera coordinate frame.
Return type:: Tuple[ndarray[tuple[Any, ...], dtype[float64]], ndarray[tuple[Any, ...], dtype[bool]], ndarray[tuple[Any, ...], dtype[float64]]]
Returns:: A tuple of (pixel_coords (N,2), in_fov_mask (N,), depth (N,)).
Raises:: ValueError – If intrinsics are not set.

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.PinholeIntrinsics[source]¶

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)[source]¶

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)[source]¶

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.PinholeDistortion[source]¶

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)[source]¶

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.