1 Ocak 2016 Dergi makalesi Açık Erişim

Altinoklu, Burak; Ulusoy, Ilkay; Tari, Sibel

JSON-LD (schema.org)

{
  "@context": "https://schema.org/", 
  "@id": 55801, 
  "@type": "ScholarlyArticle", 
  "creator": [
    {
      "@type": "Person", 
      "affiliation": "Middle East Tech Univ, Dept Elect & Elect Engn, TR-06800 Ankara, Turkey", 
      "name": "Altinoklu, Burak"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Middle East Tech Univ, Dept Elect & Elect Engn, TR-06800 Ankara, Turkey", 
      "name": "Ulusoy, Ilkay"
    }, 
    {
      "@type": "Person", 
      "affiliation": "Middle East Tech Univ, Dept Comp Engn, TR-06800 Ankara, Turkey", 
      "name": "Tari, Sibel"
    }
  ], 
  "datePublished": "2016-01-01", 
  "description": "We present a Markov Random Field (MRF) based skeleton model for object shape and employ it in a probabilistic chamfer-matching framework for shape based object detection. Given an object category, shape hypotheses are generated from a set of sparse (coarse) skeletons guided by suitably defined unary and binary potentials at and between shape parts. The Markov framework assures that the generated samples properly reflect the observed or desired shape variability. As the model employs a sparsely sampled skeleton, the shape hypotheses are in the form of linear boundary segments; hence, matching can be performed using Directional Chamfer Matching. As the number of states that each MRF node can take is small, the matching process is efficient. Experiments with giraffe and swan categories of the ETHZ Dataset demonstrate that the method perform well in the case of articulated objects. (C) 2016 Elsevier B.V. All rights reserved.", 
  "headline": "A probabilistic sparse skeleton based object detection", 
  "identifier": 55801, 
  "image": "https://aperta.ulakbim.gov.tr/static/img/logo/aperta_logo_with_icon.svg", 
  "license": "http://www.opendefinition.org/licenses/cc-by", 
  "name": "A probabilistic sparse skeleton based object detection", 
  "url": "https://aperta.ulakbim.gov.tr/record/55801"
}