Detects people in images, recorded video, or live streams and returns structured bounding box coordinates with confidence scores. No training. No configuration. Just provide an image or stream and your API key.

This model is optimized for:

• Low latency inference
  
• High precision person localization
  
• Cloud or On-Prem deployment
  
• Edge-friendly real-time processing
  
  

Why This Model Exists

Most “person detection” workflows fail for one of two reasons:

1. They require custom training and dataset prep.
   
2. They are too slow for real-time applications.
   
   

This model removes both constraints. The goal is simple:

Give developers reliable person localization immediately, without ML overhead.

Bounding boxes are the atomic unit of many higher-order systems:

• Counting
  
• Tracking
  
• Behavior analysis
  
• Access control
  
• Safety monitoring
  

This model provides that atomic unit.

‍

Key Capabilities

Input Types

• Single images
  
• Video files
  
• RTSP / livestream feeds
  
• Webcam streams
  
  

Output

• JSON with bounding box coordinates
  
• Confidence scores
  
• Frame-level detections (for video)
  
  

Deployment

• EyePop Cloud
  
• On-Premise AI Application Runtime
  
• Edge devices with GPU or CPU
  
  

Setup

• Create account
  
• Get API key
  
• Send media
  
• Receive structured results
  

No hyperparameters. No labels. No model tuning.

‍

Example Output

{
  "objects": [
    {
      "category": "person",
      "classLabel": "person",
      "confidence": 0.8572,
      "height": 250.598,
      "id": 1,
      "orientation": 0,
      "width": 200.833,
      "x": 0,
      "y": 0
    }
  ],
  "source_height": 251,
  "source_width": 201  
}

‍

Practical Use Cases

Below are applications where bounding-box-level person detection is sufficient and powerful.

Security & Access Control

• Intrusion detection
  
• Restricted zone monitoring
  
• After-hours occupancy alerts
  
• Perimeter breach detection
  

Retail & Physical Spaces

• Foot traffic counting
  
• Queue length estimation
  
• Heatmap generation (with tracking layer)
  
• Store occupancy analytics
  

Workplace Safety

• Restricted equipment proximity alerts
  
• Construction site monitorin
  
• Warehouse compliance auditing
  

Live Production & Media

• Auto-cropping livestreams
  
• Camera framing automation
  
• Dynamic speaker focus
  
• Sports sideline tracking
  

Smart Buildings

• Room occupancy detection
  
• HVAC optimization inputs
  
• Emergency evacuation monitoring
  

Robotics & Automation

• Human-aware robot navigation
  
• Safety buffer detection
  
• Human-robot interaction gating
  

Healthcare & Senior Care

• Fall detection systems (with additional logic)
  
• Room presence monitoring
  
• Assisted living oversight
  

Transportation & Smart Cities

• Platform crowd monitoring
  
• Transit occupancy analysis
  
• Crosswalk monitoring
  
  

Why Bounding Boxes Matter

A bounding box is not just a rectangle. It gives you:

• Position
  
• Scale
  
• Motion vector (when tracked over time)
  
• Relative distance proxy (via pixel size)
  
• Region-of-interest cropping
  

If you know where a person is in pixel space, you can derive everything else with additional logic.

‍

Deployment Options

EyePop Cloud

• Scalable
  
• Managed infrastructure
  
• Ideal for web apps and SaaS
  

On-Premise Runtime

• Data never leaves your network
  
• Ideal for regulated industries
  
• Compatible with GPU or CPU servers
  
• Edge inference capable
  
  

Who This Is For

• Developers who need instant person detection
  
• Teams building safety or compliance tools
  
• Startups prototyping vision features
  
• Enterprises integrating vision into existing systems
  
  

If your system depends on knowing where people are, this model is the fastest way to get there.