Unsupervised analysis of activity sequences using event-motifs

  • Raffay Hamid
  • , Siddhartha Maddi
  • , Aaron Bobick
  • , Irfan Essa

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

17 Scopus citations

Abstract

We present an unsupervised framework to discover characterizations of everyday human activities, and demonstrate how such representations can be used to extract points of interest in event-streams. We begin with the usage of Suffix Trees as an efficient activity-representation to analyze the global structural information of activities, using their local event statistics over the entire continuum of their temporal resolution. Exploiting this representation, we discover characterizing event-subsequences and present their usage in an ensemble-based framework for activity classification. Finally, we propose a method to automatically detect subsequences of events that are locally atypical in a structural sense. Results over extensive data-sets, collected from multiple sensor-rich environments are presented, to show the competence and scalability of the proposed framework.

Original languageEnglish
Title of host publicationProceedings of the 4th ACM International Workshop on Video Surveillance and Sensor Networks, VSSN'06
Pages71-78
Number of pages8
DOIs
StatePublished - 2006
Event4th ACM International Workshop on Video Surveillance and Sensor Networks, VSSN'06, co-located with the 2006 ACM International Multimedia Conference - Santa Barbara, CA, United States
Duration: Oct 27 2007Oct 27 2007

Publication series

NameProceedings of the ACM International Multimedia Conference and Exhibition

Conference

Conference4th ACM International Workshop on Video Surveillance and Sensor Networks, VSSN'06, co-located with the 2006 ACM International Multimedia Conference
Country/TerritoryUnited States
CitySanta Barbara, CA
Period10/27/0710/27/07

Fingerprint

Dive into the research topics of 'Unsupervised analysis of activity sequences using event-motifs'. Together they form a unique fingerprint.

Cite this