KIT | KIT-Bibliothek | Impressum | Datenschutz

Temporal Smoothing for Joint Probabilistic People Detection in a Depth Sensor Network

Wetzel, Johannes; Laubenheimer, Astrid; Heizmann, Michael

Abstract (englisch):
Wide-area indoor people detection in a network of depth sensors is the basis for many applications, e.g. people counting or customer behavior analysis. Existing probabilistic methods use approximative stochastic inference to estimate the marginal probability distribution of people present in the scene for a single time step. In this work we investigate how the temporal context, given by a time series of multi-view depth observations, can be exploited to regularize a mean-field variational inference optimization process. We present a probabilistic grid based dynamic model and deduce the corresponding mean-field update regulations to effectively approximate the joint probability distribution of people present in the scene across space and time. Our experiments show that the proposed temporal regularization leads to a more robust estimation of the desired probability distribution and increases the detection performance.

Open Access Logo

Postprint §
DOI: 10.5445/IR/1000125569
Frei zugänglich ab 27.09.2021
DOI: 10.1109/MFI49285.2020.9235267
Zugehörige Institution(en) am KIT Institut für Industrielle Informationstechnik (IIIT)
Publikationstyp Proceedingsbeitrag
Publikationsdatum 26.09.2020
Sprache Englisch
Identifikator ISBN: 978-1-72816-422-9
KITopen-ID: 1000125569
Erschienen in IEEE International Conference onMultisensor Fusion and Integration for Intelligent Systems (MFI) Virtual Conference, Sept. 14-16, 2020
Veranstaltung IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI 2020), online, 14.09.2020 – 16.09.2020
Verlag IEEE, Piscataway, NJ
Seiten 140–145
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page