Procházení katedra kybernetiky dle data publikování
Zobrazují se záznamy 61-80 z 1383
-
Dense Linear-Time Correspondences for Tracking
(IEEE, 2008-06)A novel method is proposed for the problem of frame-to-frame correspondence search in video sequences. The method, based on hashing of low-dimensional image descriptors, establishes dense correspondences and allows large ... -
Parallel integral projection transform for straight electrode localization in 3-D ultrasound images
(IEEE, 2008-07)In surgical practice, small metallic instruments are frequently used to perform various tasks inside the human body. We address the problem of their accurate localization in the tissue. Recent experiments using medical ... -
Optimal Randomized RANSAC
(IEEE, 2008-08)A randomized model verification strategy for RANSAC is presented. The proposed method finds, like RANSAC, a solution that is optimal with user-specified probability. The solution is found in time that is close to the ... -
Marginal Consistency: Unifying Constraint Propagation on Commutative Semirings
(Institute National de la Recherche Agronomique, 2008-09)We generalise the linear programming relaxation approach to Weighted CSP by Schlesinger and the max-sum diffusion algorithm by Koval and Kovalevsky twice: from Weighted CSP to Semiring CSP, and from binary networks to ... -
Guest Editors’ Introduction to the Special Section on CVPR Papers
(IEEE, 2008-10) -
Tracking by an Optimal Sequence of Linear Predictors
(IEEE, 2009-04)We propose a learning approach to tracking explicitly minimizing the computational complexity of the tracking process subject to user-defined probability of failure (loss-of-lock) and precision. The tracker is formed by a ... -
Revisiting the Decomposition Approach to Inference in Exponential Families and Graphical Models
(Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, 2009-05) -
Geometric min-Hashing: Finding a (Thick) Needle in a Haystack
(IEEE, 2009-06)We propose a novel hashing scheme for image retrieval, clustering and automatic object discovery. Unlike commonly used bag-of-words approaches, the spatial extent of image features is exploited in our method. The geometric ... -
Efficient Representation of Local Geometry for Large Scale Object Retrieval
(IEEE, 2009-06)State of the art methods for image and object retrieval exploit both appearance (via visual words) and local geometry (spatial extent, relative pose). In large scale problems, memory becomes a limiting factor - local ... -
Line filtering for detection of microtools in 3D ultrasound data
(IEEE, 2009-09)We propose a robust method for localization of elongated surgical tools in 3D ultrasound data based on shape analysis. The tubular structures in input data are enhanced by a line filter in the pre-processing phase. A new ... -
Online learning of robust object detectors during unstable tracking
(IEEE, 2009-09)This work investigates the problem of robust, longterm visual tracking of unknown objects in unconstrained environments. It therefore must cope with frame-cuts, fast camera movements and partial/total object occlusions/d ... -
Discrete curvature calculation for fast level set segmentation
(IEEE, 2009-11)Fast level set methods replace continuous PDEs by a discrete formulation, improving the execution times. The regularization in fast level set methods was so far handled indirectly via level set function smoothing. We propose ... -
Revisiting the Linear Programming Relaxation Approach to Gibbs Energy Minimization and Weighted Constraint Satisfaction
(IEEE, 2010)We present a number of contributions to the LP relaxation approach to weighted constraint satisfaction (= Gibbs energy minimization). We link this approach to many works from constraint programming, which relation has so ... -
Efficient Structure from Motion by Graph Optimization
(Springer Berlin, 2010)We present an efficient structure from motion algorithm that can deal with large image collections in a fraction of time and effort of previous approaches while providing comparable quality of the scene and camera ... -
Bootstrap Resampling for Image Registration Uncertainty Estimation Without Ground Truth
(IEEE, 2010-01)We address the problem of estimating the uncertainty of pixel based image registration algorithms, given just the two images to be registered, for cases when no ground truth data is available. Our novel method uses bootstrap ... -
Fixed Points of Loopy Belief Propagation as Zero Gradients of a Function of Reparameterizations
(Center for Machine Perception, Department of Cybernetics, Faculty of Electrical Engineering, Czech Technical University, 2010-02)The existing view on loopy belief propagation sees it as an algorithm to nd a common zero of a system of non-linear functions, not explicitly related to each other. We show that these functions are in fact related { they ... -
Large-Scale Discovery of Spatially Related Images
(IEEE, 2010-02)We propose a randomized data mining method that finds clusters of spatially overlapping images. The core of the method relies on the min-Hash algorithm for fast detection of pairs of images with spatial overlap, the so-called ... -
A voting strategy for visual ego-motion from stereo
(IEEE, 2010-06)We present a procedure for egomotion estimation from visual input of a stereo pair of video cameras. The 3D egomotion problem, which has six degrees of freedom in general, is simplified to four dimensions and further ... -
Unsupervised Discovery of Co-occurrence in Sparse High Dimensional Data
(IEEE, 2010-06)An efficient min-Hash based algorithm for discovery of dependencies in sparse high-dimensional data is presented. The dependencies are represented by sets of features co-occurring with high probability and are called ... -
P-N Learning: Bootstrapping Binary Classifiers by Structural Constraints
(IEEE, 2010-06)This paper shows that the performance of a binary classifier can be significantly improved by the processing of structured unlabeled data, i.e. data are structured if knowing the label of one example restricts the labeling ...