📜
Developer Documentation
  • 👋EyePop.ai Introduction
  • 🎯Getting Started
    • 👨‍💻Pop Quick Start
    • 💪Low Code Examples
  • 🗝️API Key
  • 🏷️Finding People & Objects
  • SDKs
    • ☁️React/Node SDK
      • Render 2D (Visualization)
    • 🐍Python SDK
  • Self Service Training
    • Dataset SDK (Node)
    • 🏋️How To Train a Model
      • Defining Your Computer Vision Model
      • Example Use Case: Detecting Eyeglasses
      • Preparing & Uploading Data
      • Using EyePop.ai’s AutoLabeler
      • Human Review
      • Data Augmentation Setup
      • Training in Progress
      • Deployment
        • Deploy to Windows Runtime
      • Previewing Results
      • Iterative Training
      • Deep Dives (FAQ)
  • EyePop.ai Visual Intelligence
    • Reports
Powered by GitBook
On this page
  • People Category
  • Person
  • Person w/ Demographic Data (Age, Gender, Expression)
  • Person w/ 2D Body Points + Demographic Data
  • Person w/ 3D Face, Body & Hands
  • Common Objects Category
  • Person + Common Objects
  • Expert Detection Category
  • People + Animals
  • People + Devices
  • Person + Sports Equipment
  • Person + Vehicles
  • Labels

Finding People & Objects

EyePop.ai has predefined logic to help you find people and objects in common settings. Take a look at the below list to get started.

PreviousAPI KeyNextReact/Node SDK

Last updated 2 months ago

Interested in running or training your own custom model? You can with no AI experience. Need help? Please contact us.


People Category

Person

Basic model for individual person detection. Works great for finding 1-5 people in a variety of scenes.

Output:

  • Bounding Boxes, Trace ID

  • Detected object labels:

    • People Labels

Person w/ 2D Body Points

Detects a person and identifies key 2D body points for posture and movement analysis.

Output:

  • Bounding Boxes, Trace ID, Body Points

  • Detected object labels:

    • People Labels

    • 2D Body Parts Labels

Person w/ Demographic Data (Age, Gender, Expression)

Enhances person detection with demographic insights, including age, gender, and facial expressions.

Output:

  • Bounding Boxes, Trace ID

  • Detected object labels:

    • People Labels

    • Gender Labels

    • Age Labels

    • Expression Labels

Person w/ 2D Body Points + Demographic Data

Combines 2D body point detection with demographic data for a comprehensive analysis of individuals.

Output:

  • Bounding Boxes, Trace ID, Body Points

  • Detected object labels:

    • People Labels

    • Gender Labels

    • Age Labels

    • Expression Labels

    • 2D Body Parts Labels

Person w/ 3D Face, Body & Hands

Advanced model capturing detailed 3D mapping of a person's face, body, and hand movements.

Output:

  • Bounding Boxes, Trace ID, 3D Body Points, 3D Face Points, 3D Hand Points

  • Detected object labels:

    • People Labels

    • Expression Labels

    • 3D Body Parts Labels


Common Objects Category

Person + Common Objects

Identifies a person in the context of surrounding common objects, enhancing interaction analysis.

Output:

  • Bounding Boxes, Trace ID,

  • Detected object labels:

    • People Labels

    • People & Common Objects Labels


Expert Detection Category

People + Animals

Detects both people and animals, useful for scenarios involving human-animal interactions.

Output: Bounding Boxes, Trace ID

Output:

  • Bounding Boxes, Trace ID,

  • Detected object labels:

    • People Labels

    • Animal Labels

People + Devices

Focuses on the interaction between people and various electronic devices.

Output: Bounding Boxes, Trace ID

  • Bounding Boxes, Trace ID,

  • Detected object labels:

    • People Labels

    • Device Labels

Person + Sports Equipment

Specialized in identifying sports-related activities and equipment handled by individuals.

Output: Bounding Boxes, Trace ID

  • Bounding Boxes, Trace ID,

  • Detected object labels:

    • People Labels

    • Sport Labels

Person + Vehicles

Designed for scenarios where individuals interact with various types of vehicles.

Output: Bounding Boxes, Trace ID

  • Bounding Boxes, Trace ID,

  • Detected object labels:

    • People Labels

    • Vehicle Labels


Labels

The following labels are recognized by the EyePop.ai Computer Vision API and provided as prediction results. All models include the label for detecting people under the label of person.

People Labels

person

People & Common Objects Labels

eyepop logo, bicycle, car, motorcycle, airplane, bus, train, truck, boat, traffic light, fire hydrant, stop sign, parking meter, cat, dog, horse, umbrella, handbag, suitcase, sports ball, baseball bat, baseball glove, skateboard, surfboard, tennis racket, bottle, wine glass, cup, bowl, hot dog, chair, couch, potted plant, bed, dining table, toilet, tv, laptop, mouse, keyboard, cell phone, microwave, sink, refrigerator, book, clockEPDevice, laptop, mouse, remote, keyboard, cell phone, clock, scissors, hair drier, toothbrush

Expression Labels

Happy, Neutral, Sad, Surprise, Angry, Fear, Disgust

Animal Labels

bird, cat, dog, horse, sheep, cow, elephant, bear, zebra, giraffe

Sport Labels

frisbee, skis, snowboard, sports ball, kite, baseball bat, baseball glove, skateboard, surfboard, tennis racket

Vehicle Labels

bicycle, car, motorcycle, bus, train, truck

Age Labels

0-2, 3-9, 10-19, 20-29, 30-39, 40-49, 50-59, 60+

Gender Labels

Male, Female

Device Labels

laptop, mouse, remote, keyboard, cell phone, clock, scissors, hair drier, toothbrush

2D Body Parts Labels

left eye, left ear, left shoulder, left hip, left elbow, left wrist, left knee, left ankle, right eye, right ear, right shoulder, right hip, right elbow, right wrist, right knee, right ankle, nose, midpoint_lowest, midpoint_highest

3D Body Parts Labels

mouth (right), mouth (left), right ear, right eye (outer), right eye, right eye (inner), nose, left eye (inner), left eye, left eye (outer), left ear, right shoulder, left shoulder, left hip, right hip, right elbow, right wrist, right thumb, right pinky, right index, left elbow, left wrist, left thumb, left pinky, left index, right knee, right ankle, right foot index, right heel, left knee, left ankle, left foot index, left heel
🏷️
train your own model
help@eyepop.ai