Meta AI' Segment Anything Model (SAM) for Geospatial Data
Project description
segment-geospatial
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
The segment-geospatial package draws its inspiration from segment-anything-eo repository authored by Aliaksandr Hancharenka. To facilitate the use of the Segment Anything Model (SAM) for geospatial data, I have developed the segment-anything-py and segment-geospatial Python packages, which are now available on PyPI and conda-forge. My primary objective is to simplify the process of leveraging SAM for geospatial data analysis by enabling users to achieve this with minimal coding effort. I have adapted the source code of segment-geospatial from the segment-anything-eo repository, and credit for its original version goes to Aliaksandr Hancharenka.
- Free software: MIT license
- Documentation: https://samgeo.gishub.org
Features
- Download map tiles from Tile Map Service (TMS) servers and create GeoTIFF files
- Segment GeoTIFF files using the Segment Anything Model (SAM)
- Save segmentation results as common vector formats (GeoPackage, Shapefile, GeoJSON, etc.)
- Visualize segmentation results on interactive maps
Examples
- Segmenting satellite imagery
- Automatically generating object masks
- Segmenting satellite imagery with input prompts
Demos
- Automatic mask generator
- Interactive segmentation with input prompts
Tutorials
Video tutorials are available on my YouTube Channel.
Acknowledgements
This package was made possible by the following open source projects. Credit goes to the developers of these projects.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file segment-geospatial-0.5.0.tar.gz
.
File metadata
- Download URL: segment-geospatial-0.5.0.tar.gz
- Upload date:
- Size: 24.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 5457cde290203bd1279f30824834103516b015fdee0ac3d72a14eaea5799cdcf |
|
MD5 | d2ea0dcac6cc4e85bf28e365374c7802 |
|
BLAKE2b-256 | 3f5cc0d2b3e2a1977acb7d21381b3fbe4830d45811506afa6e69b7ed22b0e71e |
File details
Details for the file segment_geospatial-0.5.0-py2.py3-none-any.whl
.
File metadata
- Download URL: segment_geospatial-0.5.0-py2.py3-none-any.whl
- Upload date:
- Size: 23.5 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.2 CPython/3.11.3
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c063773a68a229e47e34913c924696317e582a7973367df8446bf4c0e74931fc |
|
MD5 | 7c1ccbe53173496c63b53ea8035f289d |
|
BLAKE2b-256 | fba16e91eab78062175cd1e1b9e299d94d37d872175de8097518122c25efa996 |