Abnormal activity recognition in office based on ℜ transform

Ying Wang*, Kaiqi Huang, Tieniu Tan

*Corresponding author for this work

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

23 Citations (Scopus)

Abstract

This paper introduces an abnormal activity recognition method based on a new feature descriptor for human silhouette. For a binary human silhouette, an extended radon transform, ℜ transform, is employed to represent low-level features. The information that the initial silhouette carries is transformed in a compact way preserving important spatial information of the activities. Then a set of HMMs based on the features extracted by our method are trained to recognize abnormal activities. Experiments have proved the accuracy and efficiency of the proposed method, and the comparison with Fourier descriptor illustrates its robustness to disjoint shapes and shapes with holes.

Original languageEnglish
Title of host publication2007 IEEE International Conference on Image Processing, ICIP 2007 Proceedings
Place of PublicationPiscataway, NJ
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages341-344
Number of pages4
Volume1
ISBN (Print)1424414377, 9781424414376
DOIs
Publication statusPublished - 2006
Externally publishedYes
Event14th IEEE International Conference on Image Processing, ICIP 2007 - San Antonio, TX, United States
Duration: 16 Sep 200719 Sep 2007

Other

Other14th IEEE International Conference on Image Processing, ICIP 2007
CountryUnited States
CitySan Antonio, TX
Period16/09/0719/09/07

Keywords

  • Abnormality recognition
  • Feature descriptor
  • HMM
  • Surveillance
  • Transform

Fingerprint Dive into the research topics of 'Abnormal activity recognition in office based on ℜ transform'. Together they form a unique fingerprint.

Cite this