> ## Documentation Index
> Fetch the complete documentation index at: https://rtsp-human-capture.docs.itsyourap.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# RTSP Human Capture

> Detect and capture people from RTSP camera streams using YOLOv4/YOLOv3 with GPU acceleration

## Welcome

RTSP Human Capture is a powerful CLI tool for real-time person detection and capture from RTSP camera streams. Built on YOLOv4/YOLOv3 with automatic HOG fallback, it supports GPU acceleration, multi-stream concurrent processing, and configurable snapshot or video recording.

<CardGroup cols={2}>
  <Card title="Quick Start" icon="rocket" href="/quickstart">
    Get up and running in minutes with our quickstart guide
  </Card>

  <Card title="Installation" icon="download" href="/installation">
    Install dependencies and set up your environment
  </Card>

  <Card title="Model Setup" icon="brain" href="/guides/model-setup">
    Download and configure YOLOv4/YOLOv3 models
  </Card>

  <Card title="CLI Commands" icon="terminal" href="/api/cli-commands">
    Explore all available commands and options
  </Card>
</CardGroup>

## Key Features

<CardGroup cols={2}>
  <Card title="Advanced Detection" icon="user-check">
    YOLOv4/YOLOv3 person detection with automatic HOG fallback when model files are unavailable
  </Card>

  <Card title="GPU Acceleration" icon="bolt">
    CUDA GPU acceleration automatically detected and enabled for fast inference
  </Card>

  <Card title="Multi-Stream Support" icon="video">
    Process multiple RTSP streams concurrently with threaded architecture
  </Card>

  <Card title="Flexible Recording" icon="camera">
    Save annotated snapshots (JPEG) or video clips (MP4) when people are detected
  </Card>

  <Card title="Live Display" icon="tv">
    Real-time grid display for monitoring multiple camera streams simultaneously
  </Card>

  <Card title="Auto Reconnect" icon="arrows-rotate">
    Automatic reconnection with retry logic for reliable long-term operation
  </Card>
</CardGroup>

## Use Cases

<AccordionGroup>
  <Accordion title="Security and Surveillance" icon="shield-halved">
    Monitor multiple camera feeds for security purposes, automatically capturing snapshots or video clips when people enter the frame. Perfect for building security, perimeter monitoring, and access control.
  </Accordion>

  <Accordion title="Retail Analytics" icon="store">
    Track customer foot traffic and movement patterns in retail environments. Capture data on when and where people appear in your store for business intelligence.
  </Accordion>

  <Accordion title="Smart Home Automation" icon="house">
    Integrate with home automation systems to trigger actions based on person detection from security cameras. Record events when motion is detected.
  </Accordion>

  <Accordion title="Research and Development" icon="flask">
    Use as a foundation for computer vision research projects involving person detection, tracking, and analysis from video streams.
  </Accordion>
</AccordionGroup>

## Get Started

<Steps>
  <Step title="Install Dependencies">
    Install Python 3.12+ and uv package manager, then sync project dependencies
  </Step>

  <Step title="Download Models">
    Download YOLOv4 weights, config, and COCO class names from the official sources
  </Step>

  <Step title="Configure Settings">
    Edit config.cfg to set detection thresholds and output directories
  </Step>

  <Step title="Run Detection">
    Start processing your RTSP streams with a single command
  </Step>
</Steps>

<Card title="Ready to begin?" icon="arrow-right" href="/installation" horizontal>
  Follow the installation guide to get started
</Card>