Human activity detection in MPEG sequences

B. Ozer, W. Wolf, A. N. Akansu

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

27 Scopus citations

Abstract

We propose a hierarchical method for human detection and activity recognition in MPEG sequences. The algorithm consists of three stages at different resolution levels. The first step is based on the principal component analysis of MPEG motion vectors of macroblocks grouped according to velocity, distance and human body proportions. This step reduces the complexity and amount of processing data. The DC DCT components of luminance and chrominance are the input for the second step, to be matched to activity templates and a human skin template. A more detailed analysis of the uncompressed regions extracted in previous steps is done at the last step via model-based segmentation and graph matching. This hierarchical scheme enables working at different levels, from low complexity to low false rates. It is important and interesting to realize that significant information can be obtained from the compressed domain in order to connect to high level semantics.

Original languageEnglish (US)
Title of host publicationProceedings - Workshop on Human Motion, HUMO 2000
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages61-66
Number of pages6
ISBN (Electronic)0769509398, 9780769509396
DOIs
StatePublished - 2000
EventWorkshop on Human Motion, HUMO 2000 - Austin, United States
Duration: Dec 7 2000Dec 8 2000

Publication series

NameProceedings - Workshop on Human Motion, HUMO 2000

Other

OtherWorkshop on Human Motion, HUMO 2000
Country/TerritoryUnited States
CityAustin
Period12/7/0012/8/00

All Science Journal Classification (ASJC) codes

  • Computer Vision and Pattern Recognition
  • Signal Processing

Fingerprint

Dive into the research topics of 'Human activity detection in MPEG sequences'. Together they form a unique fingerprint.

Cite this