Recognizing human activities

Research output: Chapter in Book/Report/Conference proceedingConference contribution

38 Scopus citations

Abstract

The paper deals with the problem of classification of human activities from video as one way of performing activity monitoring. Our approach uses motion features that are computed very efficiently and subsequently projected into a lower dimension space where matching is performed. Each action is represented as a manifold in this lower dimension space and matching is done by comparing these manifolds. To demonstrate the effectiveness of this approach, it was used on a large data set of similar actions, each performed by many different actors. Classification results are accurate and show that this approach can handle many challenges such as variations in performers' physical attributes, color of clothing, and style of motion. An important result is that the recovery of three-dimensional properties of a moving person, or even two-dimensional tracking of the person's limbs, is not a necessary step that must precede action recognition.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages157-162
Number of pages6
ISBN (Electronic)0769519717, 9780769519715
DOIs
StatePublished - Jan 1 2003
EventIEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003 - Miami, United States
Duration: Jul 21 2003Jul 22 2003

Publication series

NameProceedings - IEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003

Other

OtherIEEE Conference on Advanced Video and Signal Based Surveillance, AVSS 2003
CountryUnited States
CityMiami
Period7/21/037/22/03

Keywords

  • Computer science
  • Hidden Markov models
  • Humans
  • IIR filters
  • Performance evaluation
  • Shape
  • Surveillance
  • Testing
  • Tracking
  • Videoconference

Fingerprint Dive into the research topics of 'Recognizing human activities'. Together they form a unique fingerprint.

Cite this