Getting Started Reference¶

Quick reference for new users of Home Security Intelligence.

This page provides a quick overview and links to the detailed getting started documentation.

Quick Links¶

System Overview¶

Home Security Intelligence is an AI-powered home security monitoring dashboard that:

• Processes camera feeds using YOLO26 object detection
• Analyzes detections with Nemotron LLM for risk assessment
• Provides real-time alerts via WebSocket connections
• Tracks entities (people, vehicles, pets) across cameras
• Maintains activity baselines for anomaly detection

Architecture Components¶

Camera Images
      |
      v
+-------------+      +-------------+      +-------------+
|   YOLO26    |----->|  Enrichment |----->|  Florence-2 |
|   (8095)    |      |   (8094)    |      |   (8092)    |
+-------------+      +-------------+      +-------------+
      |                    |                    |
      v                    v                    v
+-----------------------------------------------------------+
|                    Nemotron (8091)                        |
|              Risk Analysis & Scoring                      |
+-----------------------------------------------------------+
                          |
                          v
                    Risk Events

Minimum Requirements¶

Hardware¶

Software¶

Quick Start (5 Minutes)¶

# 1. Clone repository
git clone https://github.com/your-org/home-security-intelligence.git
cd home-security-intelligence

# 2. Run setup
./setup.sh

# 3. Download AI models
./ai/download_models.sh

# 4. Start services
podman-compose -f docker-compose.prod.yml up -d

# 5. Open dashboard
open http://localhost:3000

Key Concepts¶

Risk Scoring¶

The system assigns risk scores (0-100) to events:

Detection Classes¶

YOLO26 detects security-relevant objects:

SECURITY_CLASSES = {
    "person", "car", "truck", "dog", "cat",
    "bird", "bicycle", "motorcycle", "bus"
}

Entity Types¶

The system tracks these entity types:

Keyboard Navigation¶

Press ? anywhere to see keyboard shortcuts.

See Keyboard Shortcuts for complete reference.

Configuration Files¶

Common Tasks¶

View Live Events¶

1. Open Dashboard (g d)
2. Activity feed shows real-time detections
3. Click event for details

Check System Health¶

1. Navigate to System page (g y)
2. View GPU utilization, service status
3. Check AI model performance

Configure Cameras¶

1. Go to Settings (g s)
2. Camera Management section
3. Add FTP upload paths

Review Analytics¶

1. Open Analytics (g n)
2. View detection trends
3. Filter by date range

Troubleshooting¶

See Troubleshooting Guide for detailed solutions.

Next Steps¶

After initial setup:

1. Configure zones - Set up detection zones for each camera
2. Add household members - Register known people for smart alerts
3. Set up notifications - Configure webhook integrations
4. Review baselines - Let the system learn normal patterns (7 days)

Related Documentation¶

• Full Getting Started Guide
• AI Models Reference
• Environment Variables
• Accessibility Features

Back to Reference Hub