TU Darmstadt / ULB / TUbiblio

People-Tracking-by-Detection and People-Detection-by-Tracking

Andriluka, Mykhaylo and Roth, Stefan and Schiele, Bernt (2008):
People-Tracking-by-Detection and People-Detection-by-Tracking.
IEEE, New York, In: IEEE Conference on Computer Vision and Pattern Recognition, [Conference or Workshop Item]

Abstract

Both detection and tracking people are challenging problems, especially in complex real world scenes that commonly involve multiple people, complicated occlusions, and cluttered or even moving backgrounds. People detectors have been shown to be able to locate pedestrians even in complex street scenes, but false positives have remained frequent. The identification of particular individuals has remained challenging as well. Tracking methods are able to find a particular individual in image sequences, but are severely challenged by real-world scenarios such as crowded street scenes. In this paper, we combine the advantages of both detection and tracking in a single framework. The approximate articulation of each person is detected in every frame based on local features that model the appearance of individual body parts. Prior knowledge on possible articulations and temporal coherency within a walking cycle are modeled using a hierarchical Gaussian process latent variable model (hGPLVM). We show how the combination of these results improves hypotheses for position and articulation of each person in several subsequent frames. We present experimental results that demonstrate how this allows to detect and track multiple people in cluttered scenes with reoccurring occlusions.

Item Type: Conference or Workshop Item
Erschienen: 2008
Creators: Andriluka, Mykhaylo and Roth, Stefan and Schiele, Bernt
Title: People-Tracking-by-Detection and People-Detection-by-Tracking
Language: English
Abstract:

Both detection and tracking people are challenging problems, especially in complex real world scenes that commonly involve multiple people, complicated occlusions, and cluttered or even moving backgrounds. People detectors have been shown to be able to locate pedestrians even in complex street scenes, but false positives have remained frequent. The identification of particular individuals has remained challenging as well. Tracking methods are able to find a particular individual in image sequences, but are severely challenged by real-world scenarios such as crowded street scenes. In this paper, we combine the advantages of both detection and tracking in a single framework. The approximate articulation of each person is detected in every frame based on local features that model the appearance of individual body parts. Prior knowledge on possible articulations and temporal coherency within a walking cycle are modeled using a hierarchical Gaussian process latent variable model (hGPLVM). We show how the combination of these results improves hypotheses for position and articulation of each person in several subsequent frames. We present experimental results that demonstrate how this allows to detect and track multiple people in cluttered scenes with reoccurring occlusions.

Publisher: IEEE, New York
Uncontrolled Keywords: Forschungsgruppe Visual Inference (VINF), People tracking, People detection, Computer vision
Divisions: UNSPECIFIED
20 Department of Computer Science
20 Department of Computer Science > Interactive Graphics Systems
Event Title: IEEE Conference on Computer Vision and Pattern Recognition
Date Deposited: 16 Apr 2018 09:03
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item