`pandora.semantic_segmentation.semantic_segmentation`

This module contains classes and functions associated to the semantic segmentation step.

Module Contents

Abstract SemanticSegmentation class

class pandora.semantic_segmentation.semantic_segmentation.AbstractSemanticSegmentation[source]

Abstract SemanticSegmentation class

classmethod register_subclass(short_name: str)[source]

Allows to register the subclass with its short name

abstract desc() → None[source]: Describes the semantic segmentation method :return: None

abstract compute_semantic_segmentation(cv: xarray.Dataset, img_left: xarray.Dataset, img_right: xarray.Dataset) → xarray.Dataset[source]

Compute semantic segmentation

Parameters:

cv (xarray.Dataset) –
the cost volume, with the data variables:
- cost_volume 3D xarray.DataArray (row, col, disp)
- confidence_measure (optional): 3D xarray.DataArray (row, col, indicator)
img_left (xarray) –
left Dataset image containing :
- im: 3D (band_im, row, col) xarray.DataArray float32
- disparity (optional): 3D (disp, row, col) xarray.DataArray float32
- msk (optional): 2D (row, col) xarray.DataArray int16
- classif (optional): 3D (band_classif, row, col) xarray.DataArray int16
- segm (optional): 2D (row, col) xarray.DataArray int16
img_right (xarray) –
right Dataset image containing :
- im: 3D (band_im, row, col) xarray.DataArray float32
- disparity (optional): 3D (disp, row, col) xarray.DataArray float32
- msk (optional): 2D (row, col) xarray.DataArray int16
- classif (optional): 3D (band_classif, row, col) xarray.DataArray int16
- segm (optional): 2D (row, col) xarray.DataArray int16

Returns:

The semantic segmentation in the left image dataset with the data variables:

Return type:

xarray.Dataset