Skip to main content

Labellerr: Segment Anything Model 2 (SAM 2) Video Object Tracking Documentation

Introduction

Labellerr’s SAM 2 enables 10x faster video object tracking compared to manual annotation, making it ideal for annotating moving objects—such as players and balls in sports videos—across frames with minimal effort. This AI-powered tool streamlines the process, saving significant time and ensuring high-accuracy results in sports analytics, robotics, retail, and agriculture.

Key Features

  • AI-driven, frame-by-frame object tracking
  • Compatible with multiple label types (player, ball, etc.)
  • Combines manual annotation, point prompts, and automated tracking
  • Efficiently handles occlusions and out-of-frame moments

Step-by-Step Guide: Using SAM 2 for Video Object Tracking

1. Preparing the Video and Labels

  • Upload your video to the Labellerr platform.
  • Play the video briefly to familiarize yourself with its content.
  • Create labels for each object you want to track (e.g., player, ball).

2. Annotating Key Frames with SAM 2

a. Select Object and Annotation Tool

  • Select the relevant label (e.g., ball).
  • Click the Magic Brush and choose Segment Anything Model 2 (SAM 2) from the dropdown menu.

b. Add Point Prompts

  • Click the interact icon to begin.
  • Place point prompts on the object to help the model segment it accurately.
  • Confirm the segmentation by clicking the tick icon.

c. Track Object Across Video

  • Right-click on the object and select SAM 2 Tracking.
  • SAM 2 automatically tracks and segments the object across the entire video timeline.
  • Repeat for additional objects (e.g., select player and follow the same steps).

3. Reviewing and Adjusting Tracks

a. Timeline Visualization

  • Tracked objects appear on a colored timeline.
  • Colored dots indicate present, absent, or segmentation error.
  • Gaps in the timeline indicate occlusion or the object moving out of frame.

b. Handling Occlusions & Errors

  • If SAM 2 misses a frame:
    • Right-click and select Mark Out of View (if object is absent).
    • Right-click and select Mark in View (if object is present).

c. Seamless Results

  • Play the labeled video to preview accurate object tracking across all frames.

4. Customizing Annotations (Optional)

  • Use bounding boxes for simple shapes (e.g., players).
  • Use polygons for small or irregular objects (e.g., balls).
  • Add attributes (e.g., player activity, jersey color) and video-wide classifications for detailed datasets.

5. Firing Multiple Annotation Jobs

Labellerr supports running multiple annotation jobs simultaneously, speeding up large-scale video annotation.

How It Works

  1. Upload your videos and create object labels.
  2. Select objects to annotate.
  3. Click the SAM 2 button in the object header.
  4. Choose the object for this job.
  5. Click Run to automatically track and segment the object across all frames.

6. Running SAM 2 on a Single Timeline

You can track multiple objects continuously in a single workflow.

How It Works

  • Upload your video and create labels for all objects.
  • Select each object to include in the timeline job.
  • Right-click on the timeline, choose SAM 2 Tracking, and select Run SAM 2.
  • Monitor progress in the Timeline section, where colored dots indicate object presence, absence, or segmentation errors.

Benefits

  • Dramatically faster: Reduces hours of manual tracking to just a few clicks.
  • High accuracy: AI leverages previous frame information to minimize drift and errors.
  • Flexible: Suitable for any moving object in videos—sports, robotics, animals, retail, etc.
  • Easy error correction: Quick manual fixes via right-click if predictions are off.