Publication Database

Upper bound tracker:
a multi-animal tracking solution for closed laboratory settings (2023)

Art

Buchbeitrag

Autoren

Dolokov, Alexander

Andersen, Niek

Hohlbaum, Katharina

Thöne-Reineke, Christa (WE 11)

Lewejohann, Lars (WE 11)

Hellwich, Olaf

Quelle

Proceedings of the 18th international joint conference on computer vision, imaging and computer graphics theory and applications — edited by Petia Radeva, Giovanni Maria Farinella, Kadi Bouatouch (Hrsg.)

Setúbal, Portugal: SCITEPRESS, 2023; Volume 4 : February 19-21, 2023, in Lisbon, Portugal — S. 945–952

ISBN: 978-989-758-634-7

Sprache

Englisch

Verweise

URL (Volltext): https://www.scitepress.org/Link.aspx?doi=10.5220/0011609500003417

DOI: 10.5220/0011609500003417

Kontakt

Institut für Tierschutz, Tierverhalten und Versuchstierkunde

Königsweg 67
14163 Berlin
+49 30 838 61146
tierschutz@vetmed.fu-berlin.de

Abstract / Zusammenfassung

When tracking multiple identical objects or animals in video, many erroneous results are implausible right away, because they ignore a fundamental truth about the scene. Often the number of visible targets is bounded. This work introduces a multiple object pose estimation solution for the case that this upper bound is known. It dismisses all detections that would exceed the maximally permitted number and is able to re-identify an individual after an extended period of occlusion including the re-appearance in a different place. An example dataset with four freely interacting laboratory mice is additionally introduced and the tracker’s performance demonstrated on it. The dataset contains various conditions ranging from almost no opportunity to hide for the mice to a fairly cluttered environment. The approach is able to significantly reduce the occurrences of identity switches - the error when a known individual is suddenly identified as a different one - compared to other current solutions.