:orphan:

:py:mod:`traccuracy.matchers._compute_overlap`
==============================================

.. py:module:: traccuracy.matchers._compute_overlap

.. autoapi-nested-parse::

   Fast R-CNN via numba

   adapted from Fast R-CNN
   Written by Sergey Karayev
   Licensed under The MIT License [see LICENSE for details]
   Copyright (c) 2015 Microsoft



Module Contents
---------------


Functions
~~~~~~~~~

.. autoapisummary::

   traccuracy.matchers._compute_overlap.graph_bbox_and_labels
   traccuracy.matchers._compute_overlap.get_labels_with_overlap
   traccuracy.matchers._compute_overlap.compute_overlap
   traccuracy.matchers._compute_overlap.compute_overlap_3D



Attributes
~~~~~~~~~~

.. autoapisummary::

   traccuracy.matchers._compute_overlap.signature


.. py:function:: graph_bbox_and_labels(graph: networkx.DiGraph, nodes: collections.abc.Iterable[collections.abc.Hashable], label_key: str | None = 'segmentation_id') -> tuple[numpy.ndarray | None, numpy.ndarray | None]

   Get bounding boxes and labels for a list of nodes in a graph.
   If a node is missing the 'bbox' or 'segmentation_id' attributes,
   it returns None for both bounding boxes and labels.

   :param graph: The graph to get the bounding boxes and labels from.
   :type graph: nx.DiGraph
   :param nodes: The nodes to get the bounding boxes and labels for.
   :type nodes: list[Hashable]
   :param label_key: The key to use for the labels. Defaults to 'segmentation_id'.
   :type label_key: str, optional

   :returns: The bounding boxes and labels for the nodes.
   :rtype: tuple[np.ndarray | None, np.ndarray | None]


.. py:function:: get_labels_with_overlap(gt_frame: numpy.ndarray, res_frame: numpy.ndarray, gt_boxes: numpy.ndarray | None = None, res_boxes: numpy.ndarray | None = None, gt_labels: numpy.ndarray | None = None, res_labels: numpy.ndarray | None = None, overlap: str = 'iou') -> list[tuple[int, int, float]]

   Get all labels IDs in gt_frame and res_frame whose bounding boxes overlap,
   and a metric of pixel overlap (either ``iou`` or ``iogt``).

   :param gt_frame: ground truth segmentation for a single frame
   :type gt_frame: np.ndarray
   :param res_frame: result segmentation for a given frame
   :type res_frame: np.ndarray
   :param gt_boxes: ground truth bounding boxes for a single frame
   :type gt_boxes: np.ndarray
   :param res_boxes: result bounding boxes for a given frame
   :type res_boxes: np.ndarray
   :param gt_labels: ground truth labels for a single frame
   :type gt_labels: np.ndarray
   :param res_labels: result labels for a given frame
   :type res_labels: np.ndarray
   :param overlap: Choose between intersection-over-ground-truth (``iogt``)
                   or intersection-over-union (``iou``). Defaults to ``iou``.
   :type overlap: str, optional

   Returns: list[tuple[int, int, float]] A list of tuples of overlapping labels and their
       overlap values. Each tuple contains (gt_label, res_label, overlap_value).


.. py:function:: compute_overlap(boxes: numpy.ndarray, query_boxes: numpy.ndarray) -> numpy.ndarray

   Args
       boxes: (N, 4) ndarray of float
       query_boxes: (K, 4) ndarray of float

   Returns
       overlaps: (N, K) ndarray of overlap between boxes and query_boxes


.. py:function:: compute_overlap_3D(boxes: numpy.ndarray, query_boxes: numpy.ndarray) -> numpy.ndarray

   Args
       boxes: (N, 6) ndarray of float
       query_boxes: (K, 6) ndarray of float

   Returns
       overlaps: (N, K) ndarray of overlap between boxes and query_boxes


.. py:data:: signature