Image Segmentation

Note

If you haven’t set up the SDK yet, make sure to go through those directions first. You’ll need to add the Core library to the app before using the specific feature API or custom model. Follow iOS setup or Android setup directions.

Image Segmentation In Action

Image Segmentation allows developers to partition a video or image into multiple segments that represent everyday things. As an example, image segmentation can help identify the outline of people walking in the street or discern the shapes of everyday things in your living room like couches and chairs.

Runs On-Device

Image Segmentation runs completely on-device. No internet connection required.

Live Video Performance (iOS Only)

Image Segmentation is designed to run on live video with a fast frame rate. Exact FPS performance varies depending on device, but it should be possible to run this feature on live video on modern mobile devices.

3 Different Segmentation Scenes

Use Image Segmentation to recognize different objects in one of 3 scenes:

  • Outdoor - Identify different objects when you’re exploring the city or your neighborhood.
    • Building / Edifice
    • Sky
    • Tree
    • Sidewalk / Pavement
    • Earth / Ground
    • Car
    • Water
    • House
    • Fence, Fencing
    • Signboard, Sign
    • Skyscraper
    • Bridge, Span
    • River
    • Bus
    • Truck / Motortruck
    • Van
    • Minibike / Motorbike
    • Bicycle
    • Traffic Light
    • Person
  • Living Room - Identify different objects when you’re at home.
    • Chair
    • Wall
    • Coffee Table
    • Ceiling
    • Floor
    • Bed
    • Lamp
    • Sofa
    • Window
    • Pillow
  • People - Identify people specifically.