z-x-yang/Segment-and-Track-Anything

Health v2 · maintenance only

Adoption not part of the score

3134 stars · 355 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

An open-source pipeline (SAM-Track) that segments and tracks arbitrary objects in videos using the Segment Anything Model for key-frame segmentation and DeAOT for multi-object tracking and mask propagation. It supports automatic and interactive workflows, including a Gradio WebUI and Colab demo.

Use cases

• segment and track objects in a video
• interactive video object segmentation
• automatically detect and segment new objects in video frames
• propagate segmentation masks across video frames
• track multiple objects in drone footage
• build a video annotation pipeline for autonomous driving datasets

When to choose

• you need open-vocabulary segmentation and tracking of arbitrary objects in videos
• you want interactive click/brush-based segmentation with automatic propagation
• you need a research baseline combining SAM and AOT/DeAOT
• you want a WebUI or Colab demo for video segmentation without writing code

When to avoid

• you need real-time tracking on CPU-only hardware
• you require a lightweight production tracker with minimal dependencies
• you only need simple bounding-box tracking without pixel-level masks
• you need a commercially permissive license (project is AGPL-3.0)

Facets

library · maturity active

computer-vision image-processing video-processing machine-learning deep-learning computer-vision machine-learning artificial-intelligence python cross-platform segment-anything video-object-segmentation object-tracking sam deaot interactive-segmentation webui video gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="z-x-yang/Segment-and-Track-Anything")