Volltext-Downloads (blau) und Frontdoor-Views (grau)
  • search hit 20 of 452
Back to Result List

Unsupervised Multiple Person Tracking using AutoEncoder-Based Lifted Multicuts

  • 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 an unsupervised 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 an unsupervised 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 superivison. 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 representation. Thus, the resulting latent representations can serve as robust appearance cues for tracking even over large temporal distances where no reliable spatio-temporal features could 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:Janis KeuperORCiDGND, Kalun Ho, Margret Keuper
Year of Publication:2020
Page Number:9
Language:English
Document Type:Article (unreviewed)
Open Access:Frei zugänglich
Institutes:Bibliografie
Release Date:2021/01/05
Licence (German):License LogoEs gilt das UrhG
ArXiv Id:http://arxiv.org/abs/2002.01192