Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 23 of 70
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
Author:Kalun Ho, Amirhossein Kardoost, Franz-Josef Pfreundt, Janis KeuperORCiDGND, Margret Keuper
Publisher:CVF
Year of Publication:2020
Pagenumber:8
Language:English
Parent Title (English):Proceedings of the Asian Conference on Computer Vision
Document Type:Conference Proceeding
Open Access:Frei zugänglich
Institutes:Bibliografie
Release Date:2021/01/07
Licence (German):License LogoEs gilt das UrhG
Note:
15th Asian Conference on Computer Vision, Nov 30 - Dec 4, 2020
URL:https://openaccess.thecvf.com/content/ACCV2020/html/Ho_A_Two-Stage_Minimum_Cost_Multicut_Approach_to_Self-Supervised_Multiple_Person_ACCV_2020_paper.html