Sciweavers

CVIU
2006
222views more  CVIU 2006»
13 years 11 months ago
Conditional models for contextual human motion recognition
We present algorithms for recognizing human motion in monocular video sequences, based on discriminative Conditional Random Field (CRF) and Maximum Entropy Markov Models (MEMM). E...
Cristian Sminchisescu, Atul Kanaujia, Dimitris N. ...
CVIU
2006
104views more  CVIU 2006»
13 years 11 months ago
A unifying geometric representation for central projection systems
In this paper we study projection systems with a single effective viewpoint, including combinations of mirrors and lenses (catadioptric) as well as just lenses with or without rad...
João P. Barreto
CVIU
2006
169views more  CVIU 2006»
13 years 11 months ago
A generic structure-from-motion framework
We introduce a generic structure-from-motion approach based on a previously introduced, highly general imaging model, where cameras are modeled as possibly unconstrained sets of p...
Srikumar Ramalingam, Suresh K. Lodha, Peter F. Stu...
CVIU
2006
168views more  CVIU 2006»
13 years 11 months ago
Automated camera layout to satisfy task-specific and floor plan-specific coverage requirements
In many multi-camera vision systems the effect of camera locations on the task-specific quality of service is ignored. Researchers in Computational Geometry have proposed elegant ...
Ugur Murat Erdem, Stan Sclaroff
CVIU
2006
86views more  CVIU 2006»
13 years 11 months ago
A paintbrush laser range scanner
Lyubomir Zagorchev, A. Ardeshir Goshtasby
CVIU
2006
142views more  CVIU 2006»
13 years 11 months ago
Robust target detection and tracking through integration of motion, color, and geometry
Vision-based tracking is a basic elementary task in many computer vision-based applications such as video surveillance and monitoring, sensing and navigation in robotics, video co...
Harini Veeraraghavan, Paul R. Schrater, Nikolaos P...
CVIU
2006
129views more  CVIU 2006»
13 years 11 months ago
Integrating multiple levels of zoom to enable activity analysis
In this paper, we present a multi-zoom framework for activity analysis in situations requiring combinations of both detailed and coarse views of the scene. The epipolar geometry i...
Paul Smith, Mubarak Shah, Niels da Vitoria Lobo
CVIU
2006
105views more  CVIU 2006»
13 years 11 months ago
The representation and matching of categorical shape
We present a framework for categorical shape recognition. The coarse shape of an object is captured by a multiscale blob decomposition, representing the compact and elongated part...
Ali Shokoufandeh, Lars Bretzner, Diego Macrini, M....
CVIU
2006
209views more  CVIU 2006»
13 years 11 months ago
Joint optical flow estimation, segmentation, and 3D interpretation with level sets
This paper describes a variational method with active curve evolution and level sets for the estimation, segmentation, and 3D interpretation of optical flow generated by independe...
Hicham Sekkati, Amar Mitiche
CVIU
2006
107views more  CVIU 2006»
13 years 11 months ago
Testing new variants of the Beckmann-Kirchhoff model against radiance data
In this paper, we explore whether the Fresnel term can be used to improve the predictions of the Beckmann
Hossein Ragheb, Edwin R. Hancock