`traccuracy.metrics._track_overlap`

This submodule implements routines for Track Purity (TP) and Target Effectiveness (TE) scores.

Definitions (Bise et al., 2011; Chen, 2021; Fukai et al., 2022):

TE for a single ground truth track T^g_j is calculated by finding the predicted track T^p_k that overlaps with T^g_j in the largest number of the frames and then dividing the overlap frame counts by the total frame counts for T^g_j. The TE for the total dataset is calculated as the mean of TEs for all ground truth tracks, weighted by the length of the tracks.
TP is defined analogously, with T^g_j and T^p_j being swapped in the definition.

Module Contents

Calculate metrics for longest track overlaps.

class traccuracy.metrics._track_overlap.TrackOverlapMetrics(include_division_edges: bool = True)[source]

Calculate metrics for longest track overlaps.

Target Effectiveness: fraction of longest overlapping prediction
tracklets on each GT tracklet
Track Purityfraction of longest overlapping GT
tracklets on each prediction tracklet

Parameters:

matched_data (traccuracy.matchers.Matched) – Matched object for set of GT and Pred data
include_division_edges (bool, optional) – If True, include edges at division.

property info: dict[str, Any]: Dictionary with Metric name and any parameters

compute(matched: traccuracy.matchers._matched.Matched, override_matcher: bool = False, relax_skips_gt: bool = False, relax_skips_pred: bool = False) → traccuracy.metrics._results.Results

The compute methods of Metric objects return a Results object populated with results and associated metadata

Parameters:

matched (traccuracy.matchers.Matched) – Matched data object to compute metrics on
override_matcher (bool) – If True, the metric will not validate the matcher type
relax_skips_gt (bool) – If True, the metric will check if skips in the ground truth graph have an equivalent multi-edge path in predicted graph
relax_skips_pred (bool) – If True, the metric will check if skips in the predicted graph have an equivalent multi-edge path in ground truth graph

Returns:

Return type:

traccuracy.metrics._results.Results