Volltext-Downloads (blau) und Frontdoor-Views (grau)
The search result changed since you submitted your search request. Documents might be displayed in a different sort order.
  • search hit 5 of 5
Back to Result List

A Two-Stage Minimum Cost Multicut Approach to Self-Supervised Multiple Person Tracking

  • Multiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowledge or supervision to associate data correctly into tracks. In this work, we present a self-supervised multiple object tracking approach based on visual features and minimum cost lifted multicuts. Our method is based onMultiple Object Tracking (MOT) is a long-standing task in computer vision. Current approaches based on the tracking by detection paradigm either require some sort of domain knowledge or supervision to associate data correctly into tracks. In this work, we present a self-supervised multiple object tracking approach based on visual features and minimum cost lifted multicuts. Our method is based on straight-forward spatio-temporal cues that can be extracted from neighboring frames in an image sequences without supervision. Clustering based on these cues enables us to learn the required appearance invariances for the tracking task at hand and train an AutoEncoder to generate suitable latent representations. Thus, the resulting latent representations can serve as robust appearance cues for tracking even over large temporal distances where no reliable spatio-temporal features can be extracted. We show that, despite being trained without using the provided annotations, our model provides competitive results on the challenging MOT Benchmark for pedestrian tracking.show moreshow less

Export metadata

Statistics

frontdoor_oas
Metadaten
Document Type:Conference Proceeding
Conference Type:Konferenzartikel
Zitierlink: https://opus.hs-offenburg.de/4412
Bibliografische Angaben
Title (English):A Two-Stage Minimum Cost Multicut Approach to Self-Supervised Multiple Person Tracking
Conference:Asian Conference on Computer Vision (15. : November 30-December 4, 2020 : Kyoto, Japan)
Author:Kalun Ho, Amirhossein Kardoost, Franz-Josef Pfreundt, Janis KeuperStaff MemberORCiDGND, Margret Keuper
Date of Publication (online):2020/02/27
Place of publication:Cham
Publisher:Springer
First Page:539
Last Page:557
Parent Title (English):ACCV 2020: Computer Vision – ACCV 2020
Volume:LNCS 12623
ISBN:978-3-030-69531-6 (Print)
ISBN:978-3-030-69532-3 (Online)
URL:https://link.springer.com/chapter/10.1007%2F978-3-030-69532-3_33
Language:English
Inhaltliche Informationen
Institutes:Fakultät Elektrotechnik, Medizintechnik und Informatik (EMI) (ab 04/2019)
Institutes:Bibliografie
Formale Angaben
Open Access: Open Access 
Licence (German):License LogoUrheberrechtlich geschützt