<?xml version="1.0" encoding="utf-8" standalone="yes"?>
<rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom">
  <channel>
    <title>CV on Roman Hrabkov</title>
    <link>https://romanhrabkov.me/tags/cv/</link>
    <description>Recent content in CV on Roman Hrabkov</description>
    <generator>Hugo</generator>
    <language>en-US</language>
    <lastBuildDate>Sun, 15 Jun 2025 00:00:00 +0000</lastBuildDate>
    <atom:link href="https://romanhrabkov.me/tags/cv/index.xml" rel="self" type="application/rss+xml" />
    <item>
      <title>Aerial Imagery Object Detection</title>
      <link>https://romanhrabkov.me/projects/aerial-imagery-object-detection/</link>
      <pubDate>Sun, 15 Jun 2025 00:00:00 +0000</pubDate>
      <guid>https://romanhrabkov.me/projects/aerial-imagery-object-detection/</guid>
      <description>01. The Challenge High-resolution aerial and drone imagery presents significant computer vision challenges due to extreme object scale variance, dense clustering, occlusions, and diverse lighting conditions across geographic regions.&#xA;The objective was to evaluate, benchmark, and optimize modern deep learning object detection models (YOLOv8 variants) to perform real-time inference on geospatial datasets with minimal false positives.&#xA;02. Vision Pipeline Flow cv_pipeline_flow.svg [ Raw Aerial Imagery (GeoTIFF) ]&#xA;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;&amp;nbsp;│&#xA;&amp;nbsp;&amp;nbsp;[ Slicing &amp;amp; Data Augmentation (SAHI) ]</description>
    </item>
  </channel>
</rss>
