<?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 Have the 415 and 435 plug straight into the Movidius Stick in Items with no label</title>
    <link>https://community.intel.com/t5/Items-with-no-label/Have-the-415-and-435-plug-straight-into-the-Movidius-Stick/m-p/590117#M11240</link>
    <description>&lt;P&gt;Make a new version of the Movidius Compute stick which has the 415 or 435 cameras plug straight into the stick to eliminate&lt;/P&gt;&lt;P&gt;throughput issues on slower micro PC devices.  The Stick itself still plugs into the PC USB port.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;If you dont want to use the 415 or 435 cameras Intel could also sell the hardware that would allow any camera to interface to the stick directly.&lt;/P&gt;&lt;P&gt;Or maybe just offer the hardware to do this and the port on the Compute stick.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;WHY?&lt;/P&gt;&lt;P&gt;From this wonderful marriage you can develop the nirvana of an SDK which can deliver the BOXES names and the percentages,&lt;/P&gt;&lt;P&gt;Optionally you can deliver the actual images, and the distances and or heat maps via the USB to applications. &lt;/P&gt;&lt;P&gt;Using just the info with no pictures greatly reduces the data size.&lt;/P&gt;&lt;P&gt;This would make it NIRVANA .&lt;/P&gt;&lt;P&gt;You can concentrate on developing the business logic and neural network aka deep learning code on a more powerful box&lt;/P&gt;&lt;P&gt;and when complete stick it onto a small micro device that needs just the  business logic and not the image information.&lt;/P&gt;&lt;P&gt;Taking a huge burden off the IOT device. Think of simple things like facial recognition etc.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;If someone doesn't want to use this option no problem have the stick work as it has but PLEASE have it directly support and optimize&lt;/P&gt;&lt;P&gt;Tiny Yolo. Most Demos I have seen show this off now.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Hopefully getting the low cost disconnected Deep Learning device of my dreams.&lt;/P&gt;&lt;P&gt;Happy analyzing&lt;/P&gt;</description>
    <pubDate>Fri, 27 Apr 2018 15:17:47 GMT</pubDate>
    <dc:creator>RTasa</dc:creator>
    <dc:date>2018-04-27T15:17:47Z</dc:date>
    <item>
      <title>Have the 415 and 435 plug straight into the Movidius Stick</title>
      <link>https://community.intel.com/t5/Items-with-no-label/Have-the-415-and-435-plug-straight-into-the-Movidius-Stick/m-p/590117#M11240</link>
      <description>&lt;P&gt;Make a new version of the Movidius Compute stick which has the 415 or 435 cameras plug straight into the stick to eliminate&lt;/P&gt;&lt;P&gt;throughput issues on slower micro PC devices.  The Stick itself still plugs into the PC USB port.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;If you dont want to use the 415 or 435 cameras Intel could also sell the hardware that would allow any camera to interface to the stick directly.&lt;/P&gt;&lt;P&gt;Or maybe just offer the hardware to do this and the port on the Compute stick.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;WHY?&lt;/P&gt;&lt;P&gt;From this wonderful marriage you can develop the nirvana of an SDK which can deliver the BOXES names and the percentages,&lt;/P&gt;&lt;P&gt;Optionally you can deliver the actual images, and the distances and or heat maps via the USB to applications. &lt;/P&gt;&lt;P&gt;Using just the info with no pictures greatly reduces the data size.&lt;/P&gt;&lt;P&gt;This would make it NIRVANA .&lt;/P&gt;&lt;P&gt;You can concentrate on developing the business logic and neural network aka deep learning code on a more powerful box&lt;/P&gt;&lt;P&gt;and when complete stick it onto a small micro device that needs just the  business logic and not the image information.&lt;/P&gt;&lt;P&gt;Taking a huge burden off the IOT device. Think of simple things like facial recognition etc.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;If someone doesn't want to use this option no problem have the stick work as it has but PLEASE have it directly support and optimize&lt;/P&gt;&lt;P&gt;Tiny Yolo. Most Demos I have seen show this off now.&lt;/P&gt;&lt;P&gt;&lt;/P&gt;&lt;P&gt;Hopefully getting the low cost disconnected Deep Learning device of my dreams.&lt;/P&gt;&lt;P&gt;Happy analyzing&lt;/P&gt;</description>
      <pubDate>Fri, 27 Apr 2018 15:17:47 GMT</pubDate>
      <guid>https://community.intel.com/t5/Items-with-no-label/Have-the-415-and-435-plug-straight-into-the-Movidius-Stick/m-p/590117#M11240</guid>
      <dc:creator>RTasa</dc:creator>
      <dc:date>2018-04-27T15:17:47Z</dc:date>
    </item>
    <item>
      <title>Re: Have the 415 and 435 plug straight into the Movidius Stick</title>
      <link>https://community.intel.com/t5/Items-with-no-label/Have-the-415-and-435-plug-straight-into-the-Movidius-Stick/m-p/590118#M11241</link>
      <description>&lt;P&gt;Hello ChicagoBob123, &lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;Thanks for posting your opinion in the RealSense community. The community will analyze your idea which sounds really interesting.&lt;P&gt;&amp;nbsp;&lt;/P&gt;&lt;P&gt;&amp;nbsp;&lt;/P&gt;Best Regards, &lt;P&gt;&amp;nbsp;&lt;/P&gt;Juan N.</description>
      <pubDate>Fri, 27 Apr 2018 19:55:16 GMT</pubDate>
      <guid>https://community.intel.com/t5/Items-with-no-label/Have-the-415-and-435-plug-straight-into-the-Movidius-Stick/m-p/590118#M11241</guid>
      <dc:creator>idata</dc:creator>
      <dc:date>2018-04-27T19:55:16Z</dc:date>
    </item>
  </channel>
</rss>

