Sciweavers

3593 search results - page 387 / 719
» A Generative Model Based Approach to Motion Segmentation
Sort
View
EMMCVPR
2011
Springer
14 years 4 months ago
Data-Driven Importance Distributions for Articulated Tracking
Abstract. We present two data-driven importance distributions for particle filterbased articulated tracking; one based on background subtraction, another on depth information. In ...
Søren Hauberg, Kim Steenstrup Pedersen
CVPR
2010
IEEE
15 years 10 months ago
Novel Observation Model for Probabilistic Object Tracking
Treating visual object tracking as foreground and background classification problem has attracted much attention in the past decade. Most methods adopt mean shift or brute force s...
Dawei Liang, Qingming Huang, Hongxun Yao, Shuqiang...
TSP
2011
151views more  TSP 2011»
14 years 11 months ago
Stochastic Models for Sparse and Piecewise-Smooth Signals
Abstract—We introduce an extended family of continuous-domain stochastic models for sparse, piecewise-smooth signals. These are specified as solutions of stochastic differential...
Michael Unser, Pouya Dehghani Tafti
CODES
2007
IEEE
15 years 11 months ago
A code-generator generator for multi-output instructions
We address the problem of instruction selection for Multi-Output Instructions (MOIs), producing more than one result. Such inherently parallel hardware instructions are very commo...
Hanno Scharwächter, Jonghee M. Youn, Rainer L...
CVIU
2007
121views more  CVIU 2007»
15 years 4 months ago
Background estimation under rapid gain change in thermal imagery
We consider detection of moving ground vehicles in airborne sequences recorded by a thermal sensor with automatic gain control, using an approach that integrates dense optic flow...
Hulya Yalcin, Robert T. Collins, Martial Hebert