<?xml version="1.0" encoding="UTF-8"?><oembed><type>video</type><version>1.0</version><html>&lt;iframe src=&quot;https://www.loom.com/embed/22c4fe38076a49eb9eead93cb142dc3c&quot; frameborder=&quot;0&quot; width=&quot;1234&quot; height=&quot;925&quot; webkitallowfullscreen mozallowfullscreen allowfullscreen&gt;&lt;/iframe&gt;</html><height>925</height><width>1234</width><provider_name>Loom</provider_name><provider_url>https://www.loom.com</provider_url><thumbnail_height>925</thumbnail_height><thumbnail_width>1234</thumbnail_width><thumbnail_url>https://cdn.loom.com/sessions/thumbnails/22c4fe38076a49eb9eead93cb142dc3c-c6e95f495208b6f5.gif</thumbnail_url><duration>253.037</duration><title>NVG Calibration Rig Demo on Raspberry Pi 5 🎥</title><description>In this video, I demonstrate the NVG calibration rig currently running on a Raspberry Pi 5, which processes feeds from two cameras simulating left and right eyes. The CV algorithm detects the night vision goggles and measures alignment and focus metrics, revealing a misalignment score of about 63 and focus scores around 80. I adjusted the focus using the goggles&apos; knurling, which improved the focus scores back to good levels. I encourage you to take a closer look at the alignment and focus metrics as we continue to refine this calibration process.</description></oembed>