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

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

Repository: https://github.com/z-x-yang/Segment-and-Track-Anything
Canonical: https://ross.abutalabs.com/products/segment-and-track-anything
Language: Jupyter Notebook
License: AGPL-3.0
License Family: copyleft
Topics: interactive-segmentation, segment-anything, segment-anything-model, video-object-segmentation, visual-object-tracking
Last push: 2026-07-03T21:59:37+00:00

## Health v2 (maintenance only)
Score: 61/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 90, release rhythm 8, longevity 88
- inputs: {"age_days": 1235, "days_push": 61, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 3134, forks 355 (observed 2026-08-28T04:07:45.610245+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: computer-vision, image-processing, video-processing, machine-learning, deep-learning
- domain: computer-vision, machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: segment-anything, video-object-segmentation, object-tracking, sam, deaot, interactive-segmentation, webui, video, gpu

## Member repositories
- z-x-yang/Segment-and-Track-Anything (main) score 61

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:45.610245+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:26:07.055930+00:00, confidence not recorded.
  - readme: https://github.com/z-x-yang/Segment-and-Track-Anything (fetched 2026-08-28T04:07:45.610245+00:00, sha f226aaf5b50a)
- Data as of 2026-08-30T08:39:29.467469+00:00.