Maintenancedemo-0012

Live Video Analytics

Real-time object detection, people counting, and zone monitoring with YOLO running on local GPU. Bounding boxes at 15-30fps on any camera feed.

gpucomputesecuritynvidiahpaihpzgxn001in-progress

Not available to book

This demo is under maintenance and cannot be booked. It will reopen once its owner marks it ready.

Watch lab overview (21 sec)
Run Count0
Student MaterialsPublic Repo
Admin / CI-CDPrivate Repo

Lab overview

No walkthrough is recorded for this demo yet, so this is a 21 sec tour of the lab and how to use it.

Trouble playing? Download the file.

Overview

Point any camera at a scene and watch AI identify objects in real time. YOLO object detection runs on the GPU, producing bounding boxes, class labels, and confidence scores at frame rate. Define monitoring zones and set occupancy alerts.

What You'll Learn

  • Real-time object detection with YOLOv8 on GPU
  • People and vehicle counting at scale
  • Zone-based monitoring with configurable alert thresholds
  • WebSocket frame streaming architecture

Key Capabilities

  • 80 object classes detected at 15-30fps
  • User-defined monitoring zones with occupancy alerts
  • 5-minute analytics timeline with per-class tracking
  • Multiple YOLO model sizes (nano, small, medium)
  • Image upload alternative for demos without a camera