bboxes_2d_tracker

Welcome to the documentation about the trackers for Bounding Boxes 2D.

All functions are defined in details further down the page.

centroid

Copyright (c) 2021-2022 UCLouvain, ICTEAM Licensed under GPL-3.0 [see LICENSE for details] Written by Jonathan Samelson (2021-2022)

class Centroid(proc_parameters: dict)[source]

Bases: pytb.tracking.bboxes.bboxes_2d_tracker.bboxes_2d_tracker.BBoxes2DTracker

__init__(proc_parameters: dict)[source]

Initializes a Centroid tracker with the given parameters.

Parameters

proc_parameters (dict) – A dictionary containing the Centroid parameters

track(detection: pytb.output.bboxes_2d.BBoxes2D) → pytb.output.bboxes_2d_track.BBoxes2DTrack[source]

Performs an inference on the given frame.

Parameters

detection (BBoxes2D) – The detection used to infer IDs.

Returns

A set of 2D bounding boxes identifying detected objects with the tracking information added.

Return type

BBoxes2DTrack

reset_state(reset_id: bool = False)[source]

Reset the current state of the tracker.

iou & kiou

Copyright (c) 2021-2022 UCLouvain, ICTEAM Licensed under GPL-3.0 [see LICENSE for details] Written by Jonathan Samelson (2021-2022)

class IOU(proc_parameters: dict)[source]

Bases: pytb.tracking.bboxes.bboxes_2d_tracker.bboxes_2d_tracker.BBoxes2DTracker

__init__(proc_parameters: dict)[source]

Initializes a IOU tracker with the given parameters.

Parameters

proc_parameters (dict) – A dictionary containing the related SORT’s parameters

track(detection: pytb.output.bboxes_2d.BBoxes2D) → pytb.output.bboxes_2d_track.BBoxes2DTrack[source]

Performs an inference on the given frame.

Parameters

detection (BBoxes2D) – The detection used to infer IDs.

Returns

A set of 2D bounding boxes identifying detected objects with the tracking information added.

Return type

BBoxes2DTrack

reset_state(reset_id: bool = False)[source]

Reset the current state of the tracker.

sort

Copyright (c) 2021-2022 UCLouvain, ICTEAM Licensed under GPL-3.0 [see LICENSE for details] Written by Jonathan Samelson (2021-2022)

class SORT(proc_parameters: dict)[source]

Bases: pytb.tracking.bboxes.bboxes_2d_tracker.bboxes_2d_tracker.BBoxes2DTracker

__init__(proc_parameters: dict)[source]

Initializes a SORT tracker with the given parameters.

Parameters

proc_parameters (dict) – A dictionary containing the related SORT’s parameters

track(detection: pytb.output.bboxes_2d.BBoxes2D) → pytb.output.bboxes_2d_track.BBoxes2DTrack[source]

Performs an inference on the given frame.

Parameters

detection (BBoxes2D) – The detection used to infer IDs.

Returns

A set of 2D bounding boxes identifying detected objects with the tracking information added.

Return type

BBoxes2DTrack

reset_state(reset_id: bool = False)[source]

Reset the current state of the tracker.

deepsort

Copyright (c) 2021-2022 UCLouvain, ICTEAM Licensed under GPL-3.0 [see LICENSE for details] Written by Jonathan Samelson (2021-2022)

class DeepSORT(proc_parameters: dict)[source]

Bases: pytb.tracking.bboxes.bboxes_2d_tracker.bboxes_2d_tracker.BBoxes2DTracker

__init__(proc_parameters: dict)[source]

Initializes a DeepSORT tracker with the given parameters.

Parameters

proc_parameters (dict) – A dictionary containing the related SORT’s parameters

track(detection: pytb.output.bboxes_2d.BBoxes2D, frame=<class 'numpy.ndarray'>) → pytb.output.bboxes_2d_track.BBoxes2DTrack[source]

Performs an inference on the given frame.

Parameters

  • detection (BBoxes2D) – The detection used to infer IDs.

  • frame (np.ndarray) – The frame where objects have to be tracked

Returns

A set of 2D bounding boxes identifying detected objects with the tracking information added.

Return type

BBoxes2DTrack

reset_state(reset_id: bool = False)[source]

Reset the current state of the tracker.