Aral Sea

sam2_aral_sea.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Segmenting objects from timeseries images with SAM 2\n",
    "\n",
    "[![image](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/gist/giswqs/8225768307a2aa503144ae7be2ec5a3a)\n",
    "\n",
    "\n",
    "This notebook shows how to segment objects from timeseries with the [samgeo](https://github.com/opengeos/segment-geospatial) package.\n",
    "\n",
    "Make sure you use GPU runtime for this notebook. For Google Colab, go to `Runtime` -> `Change runtime type` and select `GPU` as the hardware accelerator. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Install dependencies\n",
    "\n",
    "Uncomment and run the following cell to install the required dependencies."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# %pip install -U segment-geospatial"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from samgeo import SamGeo2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Segment the objects from a video"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor = SamGeo2(\n",
    "    model_id=\"sam2-hiera-large\",\n",
    "    video=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://github.com/opengeos/datasets/releases/download/videos/aral_sea.mp4\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "video_path = url\n",
    "predictor.set_video(video_path)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor.show_images()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "prompts = {\n",
    "    1: {\n",
    "        \"points\": [[213, 350], [530, 382], [325, 260]],\n",
    "        \"labels\": [1, 1, 0],\n",
    "        \"frame_idx\": 0,\n",
    "    },\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor.show_prompts(prompts, frame_idx=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor.predict_video(prompts)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predictor.save_video_segments_blended(\"sea\", output_video=\"aral_sea_blended.mp4\", fps=5)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "sam",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.11.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}