<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Event Camera on Fabrizio Ottati</title><link>https://fabrizio-ottati.github.io/tags/event-camera/</link><description>Recent content in Event Camera on Fabrizio Ottati</description><generator>Hugo</generator><language>en-US</language><lastBuildDate>Tue, 28 Feb 2023 00:00:00 +0000</lastBuildDate><atom:link href="https://fabrizio-ottati.github.io/tags/event-camera/index.xml" rel="self" type="application/rss+xml"/><item><title>Efficient compression for event-based data</title><link>https://fabrizio-ottati.github.io/blog/file-reading-benchmark/</link><pubDate>Tue, 28 Feb 2023 00:00:00 +0000</pubDate><guid>https://fabrizio-ottati.github.io/blog/file-reading-benchmark/</guid><description>&lt;h1 id="efficient-compression-for-event-based-data"&gt;Efficient compression for event-based data&lt;/h1&gt;&#10;&lt;h2 id="datasets-grow-larger-in-size"&gt;Datasets grow larger in size&lt;/h2&gt;&#10;&lt;p&gt;As neuromorphic algorithms tackle more complex tasks that are linked to bigger datasets, and event cameras mature to have higher spatial resolution, it is worth looking at how to encode that data efficiently when storing it on disk. To give you an example, Prophesee&amp;rsquo;s latest automotive &lt;a href="https://docs.prophesee.ai/stable/datasets.html"&gt;object detection dataset&lt;/a&gt; is some 3.5 TB in size for under 40h of recordings with a single camera.&lt;/p&gt;</description></item></channel></rss>