Sciweavers

116 search results - page 6 / 24
» Towards using multiple cues for robust object recognition
Sort
View
ICIP
2001
IEEE
14 years 9 months ago
A robust motion detection and estimation filter for video signals
The problem of detecting areas of motion in video sequences and estimating parameters such as speed, direction and dynamics is addressed in many applications of image processing s...
Markus Latzel, John K. Tsotsos
CVPR
2007
IEEE
14 years 5 months ago
Partially Occluded Object-Specific Segmentation in View-Based Recognition
We present a novel object-specific segmentation method which can be used in view-based object recognition systems. Previous object segmentation approaches generate inexact results ...
Minsu Cho (Seoul National University), Kyoung Mu L...
ICCS
2005
Springer
14 years 1 months ago
Towards a Bayesian Approach to Robust Finding Correspondences in Multiple View Geometry Environments
Abstract. This paper presents a new Bayesian approach to the problem of finding correspondences of moving objects in a multiple calibrated camera environment. Moving objects are d...
Cristian Canton-Ferrer, Josep R. Casas, Montse Par...
BMVC
2010
13 years 5 months ago
Manifold Learning for ToF-based Human Body Tracking and Activity Recognition
In this paper, we propose a method for simultaneous human full-body pose tracking and activity recognition from time-of-flight (ToF) camera images. Simple and sparse depth cues ar...
Loren Arthur Schwarz, Diana Mateus, Victor Castane...
ICIP
2006
IEEE
14 years 9 months ago
Recognition of Multi-Object Events Using Attribute Grammars
* We present a method for representing and recognizing visual events using attribute grammars. In contrast to conventional grammars, attribute grammars are capable of describing fe...
Seong-Wook Joo, Rama Chellappa