<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic yes, this example contains in Intel® Integrated Performance Primitives</title>
    <link>https://community.intel.com/t5/Intel-Integrated-Performance/OpticalFlowPyrLK-feature-points/m-p/1183733#M27259</link>
    <description>&lt;P&gt;yes, this example contains some of the inconsistencies with the actual implementation and has to be redeveloped. We will try fix all of them.&lt;/P&gt;&lt;P&gt;Actually, the&amp;nbsp;pPrev is in and out parameters and has to be initialized at the input to this function.&lt;/P&gt;</description>
    <pubDate>Thu, 13 Feb 2020 04:21:14 GMT</pubDate>
    <dc:creator>Gennady_F_Intel</dc:creator>
    <dc:date>2020-02-13T04:21:14Z</dc:date>
    <item>
      <title>OpticalFlowPyrLK feature points</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/OpticalFlowPyrLK-feature-points/m-p/1183732#M27258</link>
      <description>&lt;P&gt;The docs for&amp;nbsp;OpticalFlowPyrLK don't explicitly state whether the&amp;nbsp;pPrev array of&amp;nbsp;initial coordinates of the feature-points is an input parameter or not. My impression however is that&amp;nbsp;pPrev must be specified by the caller. The IPPI demo code in&amp;nbsp;OpticalFlowPyrLK.c on the other hand, simply sets the&amp;nbsp;pPrev array to zero values.&lt;/P&gt;&lt;P&gt;My questions:&lt;/P&gt;&lt;P&gt;1. So, is this just bad sample code or an undocumented something&amp;nbsp;where OpticalFlowPyrLK figures out good feature points&amp;nbsp;itself ?&lt;/P&gt;&lt;P&gt;2.&amp;nbsp;OpticalFlowPyrLK is based on "Pyramidal Implementation of the Lucas Kanade Feature Tracker" by Jean-Yves Bouguet, of the Intel Corporation Microprocessor Research Labs. Chapter 3 "Feature Selection" of this document describes an the algorithm to select feature-points. How does that algorithm translate into IPPI calls ?&lt;/P&gt;&lt;P&gt;Regards,&lt;/P&gt;&lt;P&gt;Adriaan van Os&lt;/P&gt;</description>
      <pubDate>Sun, 09 Feb 2020 13:56:16 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/OpticalFlowPyrLK-feature-points/m-p/1183732#M27258</guid>
      <dc:creator>Adriaan_van_Os</dc:creator>
      <dc:date>2020-02-09T13:56:16Z</dc:date>
    </item>
    <item>
      <title>yes, this example contains</title>
      <link>https://community.intel.com/t5/Intel-Integrated-Performance/OpticalFlowPyrLK-feature-points/m-p/1183733#M27259</link>
      <description>&lt;P&gt;yes, this example contains some of the inconsistencies with the actual implementation and has to be redeveloped. We will try fix all of them.&lt;/P&gt;&lt;P&gt;Actually, the&amp;nbsp;pPrev is in and out parameters and has to be initialized at the input to this function.&lt;/P&gt;</description>
      <pubDate>Thu, 13 Feb 2020 04:21:14 GMT</pubDate>
      <guid>https://community.intel.com/t5/Intel-Integrated-Performance/OpticalFlowPyrLK-feature-points/m-p/1183733#M27259</guid>
      <dc:creator>Gennady_F_Intel</dc:creator>
      <dc:date>2020-02-13T04:21:14Z</dc:date>
    </item>
  </channel>
</rss>

