<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
  <head>
    <meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
  </head>
  <body bgcolor="#ffffff" text="#000000">
    On 23/05/2017 01:15 p.m., Ben Coman wrote:<br>
    <blockquote
cite="mid:CAProBTkpJd_MmeJJcA3+WkNkqdWazTCY_HO5_wn2cjv5LwmUMw@mail.gmail.com"
      type="cite">
      <div dir="ltr">
        <div class="gmail_extra"><br>
          <div class="gmail_quote">On Tue, May 23, 2017 at 11:47 PM,
            Juan Vuletich <span dir="ltr"><<a moz-do-not-send="true"
                href="mailto:JuanVuletich@zoho.com" target="_blank">JuanVuletich@zoho.com</a>></span>
            wrote:<br>
            <blockquote class="gmail_quote" style="margin: 0px 0px 0px
              0.8ex; border-left: 1px solid rgb(204, 204, 204);
              padding-left: 1ex;"><br>
              Hi Folks,<br>
              <br>
              Satellogic was featured today at Nature News! <a
                moz-do-not-send="true"
href="http://www.nature.com/news/earth-observing-companies-push-for-more-advanced-science-satellites-1.22034"
                rel="noreferrer" target="_blank">http://www.nature.com/news/ear<wbr>th-observing-companies-push-<wbr>for-more-advanced-science-<wbr>satellites-1.22034</a><br>
              <br>
              I helped design and build the hyperspectral cameras in our
              satellites Fresco and Batata. And I wrote the geometric
              and spectral processing software for that image. This is
              not completely off topic, though: The geometric software
              (image rectification and correction), the most complex
              part of the processing, was written by me in Cuis
              Smalltalk, and runs in a Cuis Smalltalk + OpenCL
              application.<br>
              <br>
              Please share my joy today!<span class="gmail-HOEnZb"><font
                  color="#888888"><br>
                  <br>
                  -- <br>
                  Juan Vuletich<br>
                  <a moz-do-not-send="true"
                    href="http://www.cuis-smalltalk.org"
                    rel="noreferrer" target="_blank">www.cuis-smalltalk.org</a><br>
                  <a moz-do-not-send="true"
                    href="https://github.com/Cuis-Smalltalk/Cuis-Smalltalk-Dev"
                    rel="noreferrer" target="_blank">https://github.com/Cuis-Smallt<wbr>alk/Cuis-Smalltalk-Dev</a><br>
                  @JuanVuletich<br>
                  <br>
                  <br>
                </font></span></blockquote>
          </div>
          <br class="gmail-Apple-interchange-newline">
          Its great to hear of joy in work.  It was interesting to read
          "The company announced in January that it would give
          researchers free access to its 30-metre-resolution
          hyperspectral data. These span optical and near-infrared
          wavelengths and can help track water pollution and oil spills,
          and monitor the health of forests and crops." <br>
        </div>
      </div>
    </blockquote>
    <br>
    Yes. We hope to make a difference.<br>
    <br>
    <blockquote
cite="mid:CAProBTkpJd_MmeJJcA3+WkNkqdWazTCY_HO5_wn2cjv5LwmUMw@mail.gmail.com"
      type="cite">
      <div dir="ltr">
        <div>Is your geometric software useful dataset users?  Or is it
          just for preprocessing to prepare saleable data?</div>
        <div>Is its available to end-users?  Or is it secret sauce?</div>
        <div><br>
        </div>
        <div>cheers -ben </div>
      </div>
    </blockquote>
    <br>
    The image rectification and geolocation is used to produce the
    images most people can use. The idea is to go from pictures taken
    from the point of view of the satellite at the moment they were
    taken (each with a different perspective) and turn them into a
    map-like (or Google Maps like) geometry. This is especially
    important to be able to track the evolution of stuff at some point
    on Earth: you need images from different points in time, and they
    need to be able to "stack" them. You also need to know exactly where
    each pixel is located (i.e. latitude and longitude). End users don't
    need this software: the images we provide are already corrected.<br>
    <br>
    There are various ways to do this in the industry. We are using a
    rather unusual approach and I have developed some novel techniques,
    that lets us do this with far less computational cost that usual.
    These is currently proprietary technology. I intend to be able to
    publish them as part of a Ph.D. thesis on C.S. in a not too distant
    future. I talked about all this at
    <a class="moz-txt-link-freetext" href="https://www.youtube.com/watch?v=bgIwbx-eDcI&index=44&list=PLCGAAdUizzH027lLWKXh_44cGuEsay7-R">https://www.youtube.com/watch?v=bgIwbx-eDcI&index=44&list=PLCGAAdUizzH027lLWKXh_44cGuEsay7-R</a>
    and
    <a class="moz-txt-link-freetext" href="https://www.youtube.com/watch?v=fx9dgLW9m7w&t=8s&list=PLCGAAdUizzH06AkHg6_UxZ6QZBgz84yAc&index=30">https://www.youtube.com/watch?v=fx9dgLW9m7w&t=8s&list=PLCGAAdUizzH06AkHg6_UxZ6QZBgz84yAc&index=30</a>
    .<br>
    <br>
    Cheers,<br>
    <pre class="moz-signature" cols="72">-- 
Juan Vuletich
<a class="moz-txt-link-abbreviated" href="http://www.cuis-smalltalk.org">www.cuis-smalltalk.org</a>
<a class="moz-txt-link-freetext" href="https://github.com/Cuis-Smalltalk/Cuis-Smalltalk-Dev">https://github.com/Cuis-Smalltalk/Cuis-Smalltalk-Dev</a>
@JuanVuletich</pre>
  </body>
</html>