Prohlížení Publikační činnost - 13133 dle autora "Chum, Ondřej"

Zobrazují se záznamy 1-16 z 16

    • Construction of Precise Local Affine Frames 

      Autor: Mikulik, Andrej; Matas, Jiří; Perd’och, Michal; Chum, Ondřej
      (IEEE, 2010-08)
      We propose a novel method for the refinement of Maximally Stable Extremal Region (MSER) boundaries to sub-pixel precision by taking into account the intensity function in the 2 × 2 neighborhood of the contour points. The ...

    • Efficient Representation of Local Geometry for Large Scale Object Retrieval 

      Autor: Perd’och, Michal; Chum, Ondřej; Matas, Jiří
      (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 ...

    • Epipolar Geometry Estimation via RANSAC Benefits from the Oriented Epipolar Constraint 

      Autor: Chum, Ondřej; Werner, Tomáš; Matas, Jiří
      (IEEE, 2004-08)
      The efficiency of epipolar geometry estimation by RANSAC is improved by exploiting the oriented epipolar constraint. Performance evaluation shows that the enhancement brings up to a two-fold speed-up. The orientation test ...

    • Epipolar Geometry from Two Correspondences 

      Autor: Perd’och, Michal; Matas, Jiří; Chum, Ondřej
      (IEEE, 2006)
      A novel algorithm for robust RANSAC-like estimation of epipolar geometry (of uncalibrated camera pair) from two correspondences of local affine frames (LAFs) is presented. Each LAF is constructed from three points independently ...

    • Geometric Hashing with Local Af ne Frames 

      Autor: Chum, Ondřej; Matas, Jiří
      (IEEE, 2006-06)
      We propose a novel representation of local image structure and a matching scheme that are insensitive to a wide range of appearance changes. The representation is a collection of local affine frames that are constructed ...

    • Geometric min-Hashing: Finding a (Thick) Needle in a Haystack 

      Autor: Chum, Ondřej; Perd’och, Michal; Matas, Jiří
      (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 ...

    • Image Matching and Retrieval by Repetitive Patterns 

      Autor: Doubek, Petr; Matas, Jiří; Perd’och, Michal; Chum, Ondřej
      (IEEE, 2010-08)
      Detection of repetitive patterns in images has been studied for a long time in computer vision. This paper discusses a method for representing a lattice or line pattern by shift-invariant descriptor of the repeating element. ...

    • Joint Orientation of Epipoles 

      Autor: Chum, Ondřej; Werner, Tomáš; Pajdla, Tomáš
      (British Machine Vision Association, 2003-09)
      It is known that epipolar constraint can be augmented with orientation by formulating it in the oriented projective geometry. This oriented epipolar constraint requires knowing the orientations (signs of overall scales) ...

    • Large-Scale Discovery of Spatially Related Images 

      Autor: Chum, Ondřej; Matas, Jiří
      (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 ...

    • Local Affine Frames for Wide-Baseline Stereo 

      Autor: Matas, Jiří; Obdržálek, Štěpán; Chum, Ondřej
      (IEEE, 2002)
      A novel procedure for establishing wide-baseline correspondence is introduced. Tentative correspondences are established by matching photometrically normalised colour measurements represented in a local affine frame. The ...

    • Matching with PROSAC – Progressive Sample Consensus 

      Autor: Chum, Ondřej; Matas, Jiří
      (IEEE, 2005-06)
      A new robust matching method is proposed. The progressive sample consensus (PROSAC) algorithm exploits the linear ordering defined on the set of correspondences by a similarity function used in establishing tentative ...

    • On the Interaction between Object Recognition and Colour Constancy 

      Autor: Obdržálek, Štěpán; Matas, Jiří; Chum, Ondřej
      (IEEE, 2003)
      In this paper we investigate some aspects of the interaction between colour constancy and object recognition. We demonstrate that even under severe changes of illumination, many objects are reliably recognised if relying ...

    • Optimal Randomized RANSAC 

      Autor: Chum, Ondřej; Matas, Jiří
      (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 ...

    • Randomized RANSAC with Sequential Probability Ratio Test 

      Autor: Matas, Jiří; Chum, Ondřej
      (IEEE, 2005-10)
      A randomized model verification strategy for RANSAC is presented. The proposed method finds, like RANSAC, a solution that is optimal with user-controllable probability n. A provably optimal model verification strategy is ...

    • Two-view Geometry Estimation Unaffected by a Dominant Plane 

      Autor: Chum, Ondřej; Werner, Tomáš; Matas, Jiří
      (IEEE, 2005-06)
      A RANSAC-based algorithm for robust estimation of epipolar geometry from point correspondences in the possible presence of a dominant scene plane is presented. The algorithm handles scenes with (i) all points in a single ...

    • Unsupervised Discovery of Co-occurrence in Sparse High Dimensional Data 

      Autor: Chum, Ondřej; Matas, Jiří
      (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 ...