pandora.cost_volume_confidence.cost_volume_confidence
This module contains classes and functions to estimate confidence.
Module Contents
Classes
Abstract Cost Volume Confidence class |
- class pandora.cost_volume_confidence.cost_volume_confidence.AbstractCostVolumeConfidence[source]
Abstract Cost Volume Confidence class
- classmethod register_subclass(short_name: str)[source]
Allows to register the subclass with its short name
- Parameters:
short_name (string) – the subclass to be registered
- abstract confidence_prediction(disp: xarray.Dataset, img_left: xarray.Dataset, img_right: xarray.Dataset, cv: xarray.Dataset) Tuple[xarray.Dataset, xarray.Dataset] [source]
Computes a confidence prediction.
- Parameters:
disp (xarray.Dataset or None) – the disparity map dataset or None
img_left – left Dataset image
img_right (xarray.Dataset) – right Dataset image
cv (xarray.Dataset) – cost volume dataset
- Tye img_left:
xarray.Dataset
- Returns:
None
- static allocate_confidence_map(name_confidence_measure: str, confidence_map: numpy.ndarray, disp: xarray.Dataset, cv: xarray.Dataset) Tuple[xarray.Dataset, xarray.Dataset] [source]
Create or update the confidence measure : confidence_measure (xarray.DataArray of the cost volume and the disparity map) by adding a the indicator
- Parameters:
name_confidence_measure (string) – the name of the new confidence indicator
confidence_map (2D np.array (row, col) dtype=np.float32) – the condidence map
disp (xarray.Dataset or None) – the disparity map dataset or None
cv (xarray.Dataset) – cost volume dataset
- Returns:
the disparity map and the cost volume with updated confidence measure
- Return type:
- Tuple(xarray.Dataset, xarray.Dataset) with the data variables:
confidence_measure 3D xarray.DataArray (row, col, indicator)