segment-geospatial and SAMRS
These two tools are complements: "opengeos/segment-geospatial" provides a Python package for applying SAM to geospatial data, while "ViTAE-Transformer/SAMRS" introduces a dataset created using SAM for remote sensing segmentation, which could be utilized by or contribute to the further development of the former.
About segment-geospatial
opengeos/segment-geospatial
A Python package for segmenting geospatial data with the Segment Anything Model (SAM)
This tool helps geospatial analysts and remote sensing specialists automatically identify and outline features like buildings, roads, or land cover in satellite imagery and other geospatial data. You input aerial photos or satellite images, and it outputs precise digital maps with these features segmented and ready for further analysis. This is ideal for anyone working with satellite imagery or geographic information systems (GIS) who needs to quickly extract specific objects or areas of interest.
About SAMRS
ViTAE-Transformer/SAMRS
The official repo for [NeurIPS'23] "SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model"
This project helps remote sensing analysts and researchers create large, detailed datasets for image segmentation tasks. It takes existing aerial or satellite imagery with object detection labels and automatically generates precise segmentation masks for objects like cars, ships, planes, and dams. The output is a significantly expanded dataset ready for training advanced machine learning models for tasks like environmental monitoring or urban planning.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work