Search For:

Displaying 1-13 out of 13 total
Dependent Multiple Cue Integration for Robust Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris Samaras
Issue Date:April 2008
pp. 670-685
We propose a new technique for fusing multiple cues to robustly segment an object from itsbackground in video sequences that suffer from abrupt changes of both illumination and position ofthe target. Robustness is achieved by the integration of appearance ...
 
Simultaneous pose, correspondence and non-rigid shape
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jordi Sanchez-Riera, Jonas Ostlund, Pascal Fua, Francesc Moreno-Noguer
Issue Date:June 2010
pp. 1189-1196
Recent works have shown that 3D shape of non-rigid surfaces can be accurately retrieved from a single image given a set of 3D-to-2D correspondences between that image and another one for which the shape is known. However, existing approaches assume that su...
 
Simultaneous correspondence and non-rigid 3D reconstruction of the coronary tree from single X-ray images
Found in: Computer Vision, IEEE International Conference on
By Eduard Serradell,Adriana Romero,Ruben Leta,Carlo Gatta,Francesc Moreno-Noguer
Issue Date:November 2011
pp. 850-857
We present a novel approach to simultaneously reconstruct the 3D structure of a non-rigid coronary tree and estimate point correspondences between an input X-ray image and a reference 3D shape. At the core of our approach lies an optimization scheme that i...
 
Shared Random Ferns for Efficient Detection of Multiple Categories
Found in: Pattern Recognition, International Conference on
By Michael Villamizar, Francesc Moreno-Noguer, Juan Andrade-Cetto, Alberto Sanfeliu
Issue Date:August 2010
pp. 388-391
We propose a new algorithm for detecting multiple object categories that exploits the fact that different categories may share common features but with different geometric distributions. This yields an efficient detector which, in contrast to existing appr...
 
Efficient rotation invariant object detection using boosted Random Ferns
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Michael Villamizar, Francesc Moreno-Noguer, Juan Andrade-Cetto, Alberto Sanfeliu
Issue Date:June 2010
pp. 1038-1045
We present a new approach for building an efficient and robust classifier for the two class problem, that localizes objects that may appear in the image under different orientations. In contrast to other works that address this problem using multiple class...
 
Accurate Non-Iterative O(n) Solution to the PnP Problem
Found in: Computer Vision, IEEE International Conference on
By Francesc Moreno-Noguer, Vincent Lepetit, Pascal Fua
Issue Date:October 2007
pp. 1-8
We propose a non-iterative solution to the PnP problem┬┐the estimation of the pose of a calibrated camera from n 3D-to-2D point correspondences┬┐whose computational complexity grows linearly with n. This is in contrast to state-of-the-art methods that are O(...
 
A Target Dependent Colorspace for Robust Tracking
Found in: Pattern Recognition, International Conference on
By Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris Samaras
Issue Date:August 2006
pp. 43-46
The selection of the appropriate colorspace for tracking applications has not been an issue previously considered in the literature. Many color representations have been suggested, based on the invariance to illumination changes. Nevertheless, none of them...
 
Integration of Conditionally Dependent Object Features for Robust Figure/Background Segmentation
Found in: Computer Vision, IEEE International Conference on
By Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris Samaras
Issue Date:October 2005
pp. 1713-1720
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and position of the target. Robustness is achieved by the integration of appearanc...
 
Integration of Shape and a Multihypotheses Fisher Color Model for Figure-Ground Segmentation in Non-Stationary Environments
Found in: Pattern Recognition, International Conference on
By Francesc Moreno-Noguer, Alberto Sanfeliu
Issue Date:August 2004
pp. 771-774
In this paper a new technique to perform figure-ground segmentation in image sequences of scenarios with varying illumination conditions is proposed. The set of color points of both the target and background are modelled with Mixture of Gaussians (MoG), wh...
 
Non-Rigid Graph Registration using Active Testing Search
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Eduard Serradell,Miguel Pinheiro,Raphael Sznitman,Jan Kybic,Francesc Moreno-Noguer,Pascal Fua
Issue Date:August 2014
pp. 1
We present a new approach for matching sets of branching curvilinear structures that form graphs embedded in R2 or R3 and may be subject to deformations. Unlike earlier methods, ours does not rely on local appearance similarity nor does require a good init...
 
Dense Segmentation-Aware Descriptors
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Eduard Trulls,Iasonas Kokkinos,Alberto Sanfeliu,Francesc Moreno-Noguer
Issue Date:June 2013
pp. 2890-2897
In this work we exploit segmentation to construct appearance descriptors that can robustly deal with occlusion and background changes. For this, we downplay measurements coming from areas that are unlikely to belong to the same region as the descriptor's c...
 
A Joint Model for 2D and 3D Pose Estimation from a Single Image
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Edgar Simo-Serra,Ariadna Quattoni,Carme Torras,Francesc Moreno-Noguer
Issue Date:June 2013
pp. 3634-3641
We introduce a novel approach to automatically recover 3D human pose from a single image. Most previous work follows a pipelined approach: initially, a set of 2D features such as edges, joints or silhouettes are detected in the image, and then these observ...
 
Active refocusing of images and videos
Found in: ACM Transactions on Graphics (TOG)
By Francesc Moreno-Noguer, Peter N. Belhumeur, Shree K. Nayar
Issue Date:July 2007
pp. 1-35
We present a system for refocusing images and videos of dynamic scenes using a novel, single-view depth estimation method. Our method for obtaining depth is based on the defocus of a sparse set of dots projected onto the scene. In contrast to other active ...
     
 1