Sciweavers

1283 search results - page 29 / 257
» Locally Monotonic Models for Image and Video Processing
Sort
View
ICIP
2004
IEEE
14 years 9 months ago
Simultaneous background and foreground modeling for tracking in surveillance video
We present a stochastic tracking algorithm for surveillance video where targets are dim and at low resolution. The algorithm builds motion models for both background and foregroun...
Jie Shao, Shaohua Kevin Zhou, Rama Chellappa
ICASSP
2008
IEEE
14 years 1 months ago
Distributed multi-dimensional hidden Markov models for image and trajectory-based video classifications
In this paper, we propose a novel multi-dimensional distributed hidden Markov model (DHMM) framework. We first extend the theory of 2D hidden Markov models (HMMs) to arbitrary ca...
Xiang Ma, Dan Schonfeld, Ashfaq A. Khokhar
ICIP
2008
IEEE
14 years 1 months ago
An adaptive background model initialization algorithm with objects moving at different depths
Background subtraction is an essential element in most object tracking and video surveillance systems. The success of this low-level processing step is highly dependent on the qua...
Chia-Chih Chen, J. K. Aggarwal
MM
2010
ACM
127views Multimedia» more  MM 2010»
13 years 7 months ago
Mining and cropping common objects from images
Discovering common objects that appear frequently in a number of images is a challenging problem, due to (1) the appearance variations of the same common object and (2) the enormo...
Gangqiang Zhao, Junsong Yuan
BMVC
2010
13 years 5 months ago
Local Gaussian Processes for Pose Recognition from Noisy Inputs
Gaussian processes have been widely used as a method for inferring the pose of articulated bodies directly from image data. While able to model complex non-linear functions, they ...
Martin Fergie, Aphrodite Galata