Mean probability boundary hierarchy

oriented_watershed(graph, edge_weights, shape)

Creates a region adjacency graph (rag) with the oriented watershed transform.

mean_pb_hierarchy(graph, edge_weights, shape)

Mean probability boundary hierarchy.

multiscale_mean_pb_hierarchy(graph, …[, …])

Multiscale mean probability boundary hierarchy.

oriented_watershed(graph, edge_weights, shape, edge_orientations=None)[source]

Creates a region adjacency graph (rag) with the oriented watershed transform.

The method is described in:

P. Arbelaez, M. Maire, C. Fowlkes and J. Malik, “Contour Detection and Hierarchical Image Segmentation,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 898-916, May 2011. doi: 10.1109/TPAMI.2010.161

If no edge orientations are provided, then the weight of a rag edge between region i and j is the mean weight of the edges linking a vertex of i to a vertex of j.

This does not include gradient estimation.

Parameters:
  • graph – must be a 4 adjacency graph (Concept CptGridGraph)

  • edge_weights – gradient value on edges

  • shape – shape of the graph, i.e. a pair (height, width) (deduced from CptGridGraph)

  • edge_orientations – estimated orientation of the gradient on edges (optional)

Returns:

a pair (rag, rag_edge_weights): the region adjacency graph (Concept CptRegionAdjacencyGraph) and its estimated edge_weights

mean_pb_hierarchy(graph, edge_weights, shape, edge_orientations=None)[source]

Mean probability boundary hierarchy.

The method is described in:

P. Arbelaez, M. Maire, C. Fowlkes and J. Malik, “Contour Detection and Hierarchical Image Segmentation,” in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 33, no. 5, pp. 898-916, May 2011. doi: 10.1109/TPAMI.2010.161

This does not include gradient estimation.

The returned hierarchy is defined on the gradient watershed super-pixels.

The final sigmoid scaling of the hierarchy altitude is not performed.

Parameters:
  • graph – must be a 4 adjacency graph (Concept CptGridGraph)

  • edge_weights – gradient value on edges

  • shape – shape of the graph, i.e. a pair (height, width) (deduced from CptGridGraph)

  • edge_orientations – estimated orientation of the gradient on edges (optional)

Returns:

a tree (Concept CptHierarchy) and its node altitudes

multiscale_mean_pb_hierarchy(graph, fine_edge_weights, others_edge_weights, shape, edge_orientations=None)[source]

Multiscale mean probability boundary hierarchy.

The method is described in:

J. Pont-Tuset, P. Arbeláez, J. Barron, F. Marques, and J. Malik Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 39, no. 1, pp. 128 - 140, 2017.

and in:

K.K. Maninis, J. Pont-Tuset, P. Arbeláez and L. Van Gool Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), vol. 40, no. 4, pp. 819 - 833, 2018.

This does not include gradient estimation.

The returned hierarchy is defined on the gradient watershed super-pixels.

The final sigmoid scaling of the hierarchy altitude is not performed.

Parameters:
  • graph – must be a 4 adjacency graph (Concept CptGridGraph)

  • fine_edge_weights – edge weights of the finest gradient

  • others_edge_weights – tuple of gradient value on edges

  • shape – shape of the graph, i.e. a pair (height, width) (deduced from CptGridGraph)

  • edge_orientations – estimated orientation of the gradient on edges (optional)

Returns:

a tree (Concept CptHierarchy) and its node altitudes