Who is where: Matching People in Video to Wearable Acceleration During Crowded Mingling Events

Research output: Chapter in Book/Conference proceedings/Edited volumeConference contributionScientificpeer-review

11 Citations (Scopus)

Abstract

We address the challenging problem of associating acceleration data from a wearable sensor with the corresponding spatio-temporal region of a person in video during crowded mingling scenarios. This is an important first step for multisensor behavior analysis using these two modalities. Clearly, as the numbers of people in a scene increases, there is also a need to robustly and automatically associate a region of the video with each person’s device. We propose a hierarchical association approach which exploits the spatial context of the scene, outperforming the state-of-the-art approaches significantly. Moreover, we present experiments on matching from 3 to more than 130 acceleration and video streams which, to our knowledge, is significantly larger than prior works where only up to 5 device streams are associated.
Original languageEnglish
Title of host publicationProceedings of the 2016 ACM Multimedia Conference, MM 2016
Place of PublicationNew York, NY
PublisherAssociation for Computing Machinery (ACM)
Pages267-271
Number of pages5
ISBN (Electronic)978-1-4503-3603-1
DOIs
Publication statusPublished - 2016
EventMM'16 the ACM Multimedia Conference: 24th ACM Multimedia Conference - Amsterdam, Netherlands
Duration: 15 Oct 201619 Oct 2016

Conference

ConferenceMM'16 the ACM Multimedia Conference
Country/TerritoryNetherlands
CityAmsterdam
Period15/10/1619/10/16

Keywords

  • Mingling
  • wearable sensor
  • computer vision
  • association

Fingerprint

Dive into the research topics of 'Who is where: Matching People in Video to Wearable Acceleration During Crowded Mingling Events'. Together they form a unique fingerprint.

Cite this