<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>DeepSORT | Jay Polra</title><link>https://jaypolra.github.io/tags/deepsort/</link><atom:link href="https://jaypolra.github.io/tags/deepsort/index.xml" rel="self" type="application/rss+xml"/><description>DeepSORT</description><generator>Hugo Blox Builder (https://hugoblox.com)</generator><language>en-us</language><lastBuildDate>Wed, 01 Jan 2025 00:00:00 +0000</lastBuildDate><image><url>https://jaypolra.github.io/media/icon_hu_3943bc2ea2cd9fa1.png</url><title>DeepSORT</title><link>https://jaypolra.github.io/tags/deepsort/</link></image><item><title>AI Hazard Recognition System</title><link>https://jaypolra.github.io/project/ai-hazard-recognition/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://jaypolra.github.io/project/ai-hazard-recognition/</guid><description>&lt;p>The core research problem: how does a detection-based safety system stay reliable when part of the physical environment is physically invisible to the camera?&lt;/p>
&lt;p>Detection alone fails here. A vehicle that disappears into a blind spot does not mean the zone is safe. Built entry-exit state tracking as a conservative safety heuristic: assume worst case until exit is confirmed by a boundary camera.&lt;/p>
&lt;p>Built blocker-aware zone isolation across 4 sequential camera feeds. Real-time pipeline runs YOLO detection and DeepSORT tracking at 8 FPS with under 50ms zone state updates. Full React dashboard for safety officer monitoring.&lt;/p></description></item></channel></rss>