LogoLogo
  • Getting started with Keylabs
  • Application overview
    • Application navigation
    • Application toolbar
      • Informative panel
      • Panel
      • View
      • Edit
      • File
      • Tools
      • Frame location buttons
      • 🔧Tool buttons in the Merge Editor
    • Model Assisted Labeling
      • Segment Anything 2 model
    • Setting up your custom workflow
  • Release Notes
    • Release notes 2.0 - 2.3-1
      • Release notes 2.0
      • Release notes 2.1
      • Release notes 2.2
      • Release notes 2.3
      • Release notes 2.3-1
    • Release notes 1.90 - 1.92
      • Release notes 1.90
      • Release notes 1.91
      • Release notes 1.92
    • Release notes 1.80-1.89
      • Release notes 1.89
        • Release notes 1.89-2
      • Release notes 1.88
        • Release notes 1.88-1
      • Release notes 1.87
      • Release notes 1.86
      • Release notes 1.85
      • Release notes 1.84
      • Кelease notes 1.83
      • Release notes 1.82
      • Release notes 1.81
      • Release notes 1.80
  • HOW TO START
    • Project creation
    • Files uploading
    • Classes
      • Setting up classes
        • Bounding box
        • Oriented Bounding Box
        • Cuboid
        • Polygon
        • Multiline
        • Skeleton
        • Mesh
        • Bitmap
      • Setting up attributes
        • Select
        • Mugshot
        • String
        • Boolean
        • Separator
  • HOW TO ANNOTATE
    • ⚙️Annotation shapes
      • 🦲Bounding Box object annotation
      • 〰️Multiline and Polygon objects annotation
      • 💀Annotation of Skeleton object
      • 👾Annotation of Bitmap object
      • 🔘Mesh object annotation
    • Stacking order
    • Video annotation
      • Interpolation function
        • Attribute interpolation
  • HOW TO MANAGE
    • 🛠️Setting up a Project
      • Project types
      • Stages
      • Merge project creation
      • Configuration
    • ⚡Project Management
      • Project Status
      • Clone project creation
      • Files filtering
    • 👷User Management
      • User roles
        • Worker
        • Project Manager
        • Super User
        • Admin
        • Customer
      • Locations
    • 👨‍💻Arranging the workflow
      • Adding a user
      • Files management
    • 📣Audit
      • Changelog
      • Reports usage for audit
    • 📊Reports
      • Whole platform reports
        • Velocity reports
        • Timetable reports
          • TimeTable Aggregated
          • TimeTable raw data
          • Timetable current state
      • Per project reports
        • Velocity reports - by date
        • Velocity reports - by user
        • Worklog Aggregated
        • Worklog - Raw data
        • Worklog Time by File
  • TIPS AND TRICKS
    • ▶️Shortcuts
  • HOW TO INTEGRATE
    • Export
    • Files Storage
      • Platform storage
      • External storage
    • 🗒️Keylabs Export Format
      • ZIP archive structure
      • JSON File Structure
    • CLI/SDK
      • CLI
      • SDK
Powered by GitBook
On this page

Was this helpful?

  1. Application overview
  2. Model Assisted Labeling

Segment Anything 2 model

Artificial intelligence - AI

PreviousModel Assisted LabelingNextSetting up your custom workflow

Last updated 4 months ago

Was this helpful?

Image segmentation is a technology used in computer vision to improve the classification of images. It allows for the analysis and identification of objects and their positions at the individual pixel level, providing more detailed information.

The process of image segmentation involves identifying object boundaries in order to define their position and shape, which then allows for the labeling of different regions in the image.

The AI Annotation feature is available on any project that has "Segment anything" selected in the ML model selection field in the Configuration tab. This feature makes it easy to segment an image in just a few clicks.

The Segment Anything algorithm is specifically designed to segment objects in images. When this feature is selected, the following tools are available in the AI annotation configuration window:

Foreground Points: Select the pixels in the image that belong to the object you want to highlight (foreground). This helps the algorithm understand which parts of the image should be marked as foreground.

When you define an annotation point, make sure to add more points until the object is annotated as accurately as possible. If needed, you can manually adjust the annotation using the Lasso and Auto Select tools.

To define the background points, select points in the image that belong to the background. These points indicate what should be marked as the background and what area has extra pixels that the system accepts as the object you want.

You can also adjust the image manually using the Lasso and Auto Select subtraction tools.

To select a Bounding Box around an object in the image, use the Containing Box tool. This rectangle also helps define the boundaries of the object. Once you have added AI annotations, evaluate the segmentation result. If you are not satisfied with the result, you can continue to manually tweak the annotation using the tools: add lasso, subtract lasso, add auto-selection, and subtract auto-selection.

If you want to remove necessary parts of the annotation that belong to the annotated object, use the AI annotation subtraction tool. To do this, select the object, then select the "Subtract AI annotation" icon in the tool window that opens. Finally, select the tooltip: Foreground points, Background points, or Containing box, and mark the necessary section to be removed with a dot or frame.

Tracking objects

The platform's object tracking function supports only specific annotation types: Bitmap and Bounding box. This enables the automatic platform's object tracking function to support only tracking of object movement across a sequence of frames and is applicable exclusively to these two types of annotation.

To track an object over multiple frames, first select the object, then click the “Track Object” button.

Segments anything model also provides a .

Tracking options toolbar will appear, that lets you select the number of frames on which the object needs to be tracked following the current frame by dragging a slider.

tracking function
An example of segmentation that predicts class labels for each pixel in an image.
Example of AI annotation while adding foreground points
Using background points to adjust AI annotation
Example of AI annotation while using Containing box tool
Example of AI substruction using Foreground points