<?xml version="1.0" encoding="UTF-8"?>
<?xml-stylesheet type="text/xsl" href="/sponet/themes/root/assets/xsl/rss.xsl"?>
<rss version="2.0" xmlns:opensearch="http://a9.com/-/spec/opensearch/1.1/" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:slash="http://purl.org/rss/1.0/modules/slash/">
  <channel>
    <title>Ergebnis für Versionen - 4038879</title>
    <description>Treffer 1 - 2 von 2</description>
    <generator>Laminas_Feed_Writer 2 (https://getlaminas.org)</generator>
    <link>https://sponet.de/sponet/Search/Versions?sort=first_indexed+desc%2Cfirst_indexed+desc&amp;limit=50&amp;id=4038879&amp;search=versions&amp;lng=de</link>
    <opensearch:totalResults>2</opensearch:totalResults>
    <opensearch:startIndex>0</opensearch:startIndex>
    <opensearch:itemsPerPage>50</opensearch:itemsPerPage>
    <opensearch:Query role="request" searchTerms="4038879" startIndex="0"/>
    <atom:link rel="first" type="application/rss+xml" title="Zur ersten Seite springen" href="https://sponet.de/sponet/Search/Versions?sort=first_indexed+desc%2Cfirst_indexed+desc&amp;limit=50&amp;view=rss&amp;id=4038879&amp;search=versions&amp;lng=de"/>
    <atom:link rel="last" type="application/rss+xml" title="Zur letzten Seite springen" href="https://sponet.de/sponet/Search/Versions?sort=first_indexed+desc%2Cfirst_indexed+desc&amp;limit=50&amp;view=rss&amp;id=4038879&amp;search=versions&amp;lng=de&amp;page=1"/>
    <atom:link rel="self" type="application/rss+xml" href="https://sponet.de/sponet/Search/Versions?sort=first_indexed+desc%2Cfirst_indexed+desc&amp;limit=50&amp;view=rss&amp;id=4038879&amp;search=versions&amp;lng=de"/>
    <item>
      <title>Objektverfolgung durch Okklusionsdetektion mittels strukturiertem Sparse Learning</title>
      <pubDate>Tue, 01 Jan 2013 05:23:45 +0100</pubDate>
      <link>https://sponet.de/sponet/Record/4051089</link>
      <guid>https://sponet.de/sponet/Record/4051089</guid>
      <author>Zhang, T.</author>
      <author>Ghanem, B.</author>
      <author>Xu, C.</author>
      <author>Ahuja, N.</author>
      <dc:format>Kongressband, Tagungsbericht</dc:format>
      <dc:subject>Software</dc:subject>
      <dc:subject>Video</dc:subject>
      <dc:subject>Fußball</dc:subject>
      <dc:subject>Analyse</dc:subject>
      <dc:subject>Bewegung</dc:subject>
      <dc:subject>Motion Capturing</dc:subject>
      <dc:format>Kongressband, Tagungsbericht</dc:format>
      <dc:creator>Zhang, T.</dc:creator>
      <dc:creator>Ghanem, B.</dc:creator>
      <dc:creator>Xu, C.</dc:creator>
      <dc:creator>Ahuja, N.</dc:creator>
      <content:encoded><![CDATA[Sparse representation based methods have recently drawn much attention in visual tracking due to good performance against illumination variation and occlusion. They assume the errors caused by image variations can be modeled as pixel-wise sparse. However, in many practical scenarios these errors are not truly pixel-wise sparse but rather sparsely distributed in a structured way. In fact, pixels in error constitute contiguous regions within the object's track. This is the case when significant occlusion occurs. To accommodate for non-sparse occlusion in a given frame, we assume that occlusion detected in previous frames can be propagated to the current one. This propagated information determines which pixels will contribute to the sparse representation of the current track. In other words, pixels that were detected as part of an occlusion in the previous frame will be removed from the target representation process. As such, this paper proposes a novel tracking algorithm that models and detects occlusion through structured sparse learning. We test our tracker on challenging benchmark sequences, such as sports videos, which involve heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that our tracker consistently outperforms the state-of-the-art.]]></content:encoded>
      <slash:comments>0</slash:comments>
    </item>
    <item>
      <title>Objektverfolgung durch Okklusionserkennung über strukturiertes Sparse-Learning</title>
      <pubDate>Tue, 01 Jan 2013 05:23:45 +0100</pubDate>
      <link>https://sponet.de/sponet/Record/4038879</link>
      <guid>https://sponet.de/sponet/Record/4038879</guid>
      <author>Zhang, T.</author>
      <author>Ghanem, B.</author>
      <author>Xu, C.</author>
      <author>Ahuja, N.</author>
      <dc:format>elektronische Publikation</dc:format>
      <dc:subject>Mess- und Informationssystem</dc:subject>
      <dc:subject>Spielsportart</dc:subject>
      <dc:subject>Software</dc:subject>
      <dc:subject>Analyse</dc:subject>
      <dc:subject>Messverfahren</dc:subject>
      <dc:subject>Sensor</dc:subject>
      <dc:subject>Tracking</dc:subject>
      <dc:format>elektronische Publikation</dc:format>
      <dc:creator>Zhang, T.</dc:creator>
      <dc:creator>Ghanem, B.</dc:creator>
      <dc:creator>Xu, C.</dc:creator>
      <dc:creator>Ahuja, N.</dc:creator>
      <content:encoded><![CDATA[Sparse representation based methods have recently drawn much attention in visual tracking due to good performance against illumination variation and occlusion. They assume the errors caused by image variations can be modeled as pixel-wise sparse. However, in many practical scenarios these errors are not truly pixel-wise sparse but rather sparsely distributed in a structured way. In fact, pixels in error
constitute contiguous regions within the object`s track. This is the case when significant occlusion occurs. To accommodate for non-sparse occlusion in a given frame, we assume that occlusion detected in previous frames can be propagated to the current one. This propagated information determines which pixels will contribute to the sparse representation of the current track. In other words, pixels that were detected as part of an occlusion in the previous frame will be removed from the target representation process. As such, this paper proposes a novel tracking algorithm that models and detects occlusion through structured sparse learning. We test our tracker on challenging benchmark sequences, such as sports videos, which involve heavy occlusion, drastic illumination changes, and large pose variations. Experimental results show that our tracker consistently outperforms the state-of-the-art.]]></content:encoded>
      <slash:comments>0</slash:comments>
    </item>
  </channel>
</rss>
