Sciweavers

15 search results - page 2 / 3
» Hidden Markov Models for Optical Flow Analysis in Crowds
Sort
View
CVPR
2009
IEEE
14 years 12 months ago
Observe Locally, Infer Globally: a Space-Time MRF for Detecting Abnormal Activities with Incremental Updates
We propose a space-time Markov Random Field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video fra...
Jaechul Kim (University of Texas at Austin), Krist...
FGR
2006
IEEE
163views Biometrics» more  FGR 2006»
13 years 11 months ago
Human Action Recognition Using Multi-View Image Sequences Features
Recognizing human action from image sequences is an active area of research in computer vision. In this paper, we present a novel method for human action recognition from image se...
Mohiuddin Ahmad, Seong-Whan Lee
CEE
2010
119views more  CEE 2010»
13 years 5 months ago
Block-matching-based motion field generation utilizing directional edge displacement
A motion field generation algorithm using block matching of edge-flag histograms has been developed aiming at its application to motion recognition systems. Use of edge flags inste...
Hitoshi Hayakawa, Tadashi Shibata
ICPR
2006
IEEE
13 years 11 months ago
HMM-based Human Action Recognition Using Multiview Image Sequences
In this paper, we present a novel method for human action recognition from any arbitrary view image sequence that uses the Cartesian component of optical flow velocity and human ...
Mohiuddin Ahmad, Seong-Whan Lee
SIGMOD
2008
ACM
162views Database» more  SIGMOD 2008»
14 years 5 months ago
Event queries on correlated probabilistic streams
A major problem in detecting events in streams of data is that the data can be imprecise (e.g. RFID data). However, current state-ofthe-art event detection systems such as Cayuga ...
Christopher Ré, Dan Suciu, Julie Letchner, ...