Paulo F. U. Gotardo
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Paulo F. U. Gotardo has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Aleix M. Martinez
The Ohio State University, USA
3 shared publications - C.F. Benitez-Quiroz
Computational Biology and Cognitive Science Laboratory, The Ohio State University, 469 Dresse Laboratories, 2015 Neil Avenue, Columbus, Ohio, 43210
1 shared publication K.L. Boyer
1 shared publicationL. Silva
1 shared publicationO.R.P. Bellon
IMAGO Res. Group, Univ. Fed. do Parana, Curitiba, Brazil
1 shared publication- Onur C. Hamsici
Qualcomm Research
1 shared publication
Latest Publications
- 1 January 2014
- Published by Elsevier in Pattern Recognition
- Vol. 47 (1) , 208-215
Salient and non-salient fiducial detection using a probabilistic graphical model
- 1 January 2014
- Published by Elsevier in Pattern Recognition
- Vol. 47 (1) , 208-215
Salient and non-salient fiducial detection using a probabilistic graphical model
- 1 January 2012
- Published by Springer Nature
- Vol. 7575, 260-273
Learning Spatially-Smooth Mappings in Non-Rigid Structure From Motion
Non-rigid structure from motion (NRSFM) is a classical underconstrained problem in computer vision. A common approach to make NRSFM more tractable is to constrain 3D shape deformation to be smooth over time. This constraint has been used to compress the deformation model and reduce the number of unknowns that are estimated. However, temporal smoothness cannot be enforced when the data lacks temporal ordering and its benefits are less evident when objects undergo abrupt deformations. This paper proposes a new NRSFM method that addresses these problems by considering deformations as spatial variations in shape space and then enforcing spatial, rather than temporal, smoothness. This is done by modeling each 3D shape coefficient as a function of its input 2D shape. This mapping is learned in the feature space of a rotation invariant kernel, where spatial smoothness is intrinsically defined by the mapping function. As a result, our model represents shape variations compactly using custom-built coefficient bases learned from the input data, rather than a pre-specified set such as the Discrete Cosine Transform. The resulting kernel-based mapping is a by-product of the NRSFM solution and leads to another fundamental advantage of our approach: for a newly observed 2D shape, its 3D shape is recovered by simply evaluating the learned function.
- 1 January 2012
- Published by Springer Nature
- Vol. 7575, 260-273
Learning Spatially-Smooth Mappings in Non-Rigid Structure From Motion
Non-rigid structure from motion (NRSFM) is a classical underconstrained problem in computer vision. A common approach to make NRSFM more tractable is to constrain 3D shape deformation to be smooth over time. This constraint has been used to compress the deformation model and reduce the number of unknowns that are estimated. However, temporal smoothness cannot be enforced when the data lacks temporal ordering and its benefits are less evident when objects undergo abrupt deformations. This paper proposes a new NRSFM method that addresses these problems by considering deformations as spatial variations in shape space and then enforcing spatial, rather than temporal, smoothness. This is done by modeling each 3D shape coefficient as a function of its input 2D shape. This mapping is learned in the feature space of a rotation invariant kernel, where spatial smoothness is intrinsically defined by the mapping function. As a result, our model represents shape variations compactly using custom-built coefficient bases learned from the input data, rather than a pre-specified set such as the Discrete Cosine Transform. The resulting kernel-based mapping is a by-product of the NRSFM solution and leads to another fundamental advantage of our approach: for a newly observed 2D shape, its 3D shape is recovered by simply evaluating the learned function.
- 1 November 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 802-809
Kernel non-rigid structure from motion
Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear combination of K basis shapes; the solution is then obtained as the low-rank factorization of an input observation matrix. An important but overlooked problem with this approach is that non-linear deformations are often observed; these deformations lead to a weakened low-rank constraint due to the need to use additional basis shapes to linearly model points that move along curves. Here, we demonstrate how the kernel trick can be applied in standard NRSFM. As a result, we model complex, deformable 3D shapes as the outputs of a non-linear mapping whose inputs are points within a low-dimensional shape space. This approach is flexible and can use different kernels to build different non-linear models. Using the kernel trick, our model complements the low-rank constraint by capturing non-linear relationships in the shape coefficients of the linear model. The net effect can be seen as using non-linear dimensionality reduction to further compress the (shape) space of possible solutions.
- 1 November 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 802-809
Kernel non-rigid structure from motion
Non-rigid structure from motion (NRSFM) is a difficult, underconstrained problem in computer vision. The standard approach in NRSFM constrains 3D shape deformation using a linear combination of K basis shapes; the solution is then obtained as the low-rank factorization of an input observation matrix. An important but overlooked problem with this approach is that non-linear deformations are often observed; these deformations lead to a weakened low-rank constraint due to the need to use additional basis shapes to linearly model points that move along curves. Here, we demonstrate how the kernel trick can be applied in standard NRSFM. As a result, we model complex, deformable 3D shapes as the outputs of a non-linear mapping whose inputs are points within a low-dimensional shape space. This approach is flexible and can use different kernels to build different non-linear models. Using the kernel trick, our model complements the low-rank constraint by capturing non-linear relationships in the shape coefficients of the linear model. The net effect can be seen as using non-linear dimensionality reduction to further compress the (shape) space of possible solutions.
- 15 November 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Vol. 34 (6) , 2303-2316
Range Image Segmentation Into Planar and Quadric Surfaces Using an Improved Robust Estimator and Genetic Algorithm
This paper presents a novel range image segmentation method employing an improved robust estimator to iteratively detect and extract distinct planar and quadric surfaces. Our robust estimator extends M-estimator Sample Consensus/Random Sample Consensus (MSAC/RANSAC) to use local surface orientation information, enhancing the accuracy of inlier/outlier classification when processing noisy range data describing multiple structures. An efficient approximation to the true geometric distance between a point and a quadric surface also contributes to effectively reject weak surface hypotheses and avoid the extraction of false surface components. Additionally, a genetic algorithm was specifically designed to accelerate the optimization process of surface extraction, while avoiding premature convergence. We present thorough experimental results with quantitative evaluation against ground truth. The segmentation algorithm was applied to three real range image databases and competes favorably against eleven other segmenters using the most popular evaluation framework in the literature. Our approach lends itself naturally to parallel implementation and application in real-time tasks. The method fits well into several of today's applications in man-made environments, such as target detection and autonomous navigation, for which obstacle detection, but not description or reconstruction, is required. It can also be extended to process point clouds resulting from range image registration.
- 15 November 2004
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics)
- Vol. 34 (6) , 2303-2316
Range Image Segmentation Into Planar and Quadric Surfaces Using an Improved Robust Estimator and Genetic Algorithm
This paper presents a novel range image segmentation method employing an improved robust estimator to iteratively detect and extract distinct planar and quadric surfaces. Our robust estimator extends M-estimator Sample Consensus/Random Sample Consensus (MSAC/RANSAC) to use local surface orientation information, enhancing the accuracy of inlier/outlier classification when processing noisy range data describing multiple structures. An efficient approximation to the true geometric distance between a point and a quadric surface also contributes to effectively reject weak surface hypotheses and avoid the extraction of false surface components. Additionally, a genetic algorithm was specifically designed to accelerate the optimization process of surface extraction, while avoiding premature convergence. We present thorough experimental results with quantitative evaluation against ground truth. The segmentation algorithm was applied to three real range image databases and competes favorably against eleven other segmenters using the most popular evaluation framework in the literature. Our approach lends itself naturally to parallel implementation and application in real-time tasks. The method fits well into several of today's applications in man-made environments, such as target detection and autonomous navigation, for which obstacle detection, but not description or reconstruction, is required. It can also be extended to process point clouds resulting from range image registration.