https://github.com/aliaksandr960/segment-anything-eo

Earth observation tools for Meta AI Segment Anything
https://github.com/aliaksandr960/segment-anything-eo

Last synced: about 2 months ago
JSON representation

Earth observation tools for Meta AI Segment Anything

• Host: GitHub
• URL: https://github.com/aliaksandr960/segment-anything-eo
• Owner: aliaksandr960
• Created: 2023-04-08T21:37:59.000Z (almost 2 years ago)
• Default Branch: main
• Last Pushed: 2023-06-30T07:11:24.000Z (over 1 year ago)
• Last Synced: 2024-08-03T23:23:58.965Z (5 months ago)
• Language: Jupyter Notebook
• Size: 27.3 MB
• Stars: 396
• Watchers: 9
• Forks: 39
• Open Issues: 8
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-segment-anything-extensions - Repo
• Awesome-Segment-Anything - Code - | The tools are developed to ease the processing of spatial data (GeoTIFF and TMS) with SAM using sliding window algorithm for big files. | (Open Source Projects / Follow-up Papers)
• Awesome-Segment-Anything - [**Segment Anything EO tools**

README

        
***I suggest you use https://github.com/opengeos/segment-geospatial instead of this repo. It was the first successful attempt to join SAM and EO data, but now there are much better documented and much better maintained options.***

![Automatic segmentation example](title_sameo.png?raw=true "Automatic segmentation example")

# Segment Anything EO tools

Earth observation tools for Meta AI Segment Anything

## This tools are developed to ease the processing of spatial data (GeoTIFF and TMS) with Meta AI Segment Anything models using sliding window algorithm for big files

### You can:

- download TMS data (including OpenAerialMap and Mapbox Maxar) as GeoTIFF files

- process GeoTIFF files with Meta AI Segment Anything models

- save predicted segments as GeoTIFF raster data and GPKG vector data

and a little bit more

### Usage:

- colab notebook https://colab.research.google.com/drive/1RC1V68tD1O-YissBq9nOvS2PHEjAsFkA?usp=share_link

- jupyter notebook in the repo https://github.com/aliaksandr960/segment-anything-eo/blob/main/basic_usage.ipynb

### Technical details:

- Using a sliding window algorithm to process large images

- In order to separate instances, every instance gets surrounded by 1px width spare space, so it is not the same as how original Segment Anything works

***Segment Anything was released less than a week ago, and these are the first experiments with it. I don't know how paramters affect perfomance — feel free to change everything.***

# Licensing

[Facebook Research Segment Anything](https://github.com/facebookresearch/segment-anything) — Apache-2.0 license 

[Gumblex tms2geotiff](https://github.com/gumblex/tms2geotiff) — BSD-2-Clause license 

Other code — MIT license

***Segment Anything and tms2geotiff were copied to this repo 9 Apr 2022, you can update them to more recent versions if needed***