# Raster Vision

Canonical: https://gisforweb.com/tools/raster-vision/

Open-source Python framework for deep learning on satellite and aerial imagery.

Raster Vision is a Python framework for applying deep learning to satellite, aerial, and other large geospatial imagery. It provides configurable pipelines for chip classification, object detection, and semantic segmentation, with georeferenced raster and vector predictions. Its integrations cover STAC, object storage, and execution on AWS Batch or SageMaker.

## Details

- Type: library

- Categories: analysis, data-processing, satellite

- Open source: Yes

- Pricing model: open-source

- License: Apache-2.0

- Platforms: linux, macos, docker

## Features

- Supports chip classification and semantic segmentation

- Builds object detection training pipelines

- Reads georeferenced raster and vector data

- Produces georeferenced raster and vector predictions

- Loads imagery from STAC APIs and object storage

- Runs pipelines on AWS Batch and SageMaker

- Defines reusable YAML training pipelines

## Project sources

- Website: https://rastervision.io/

- Documentation: https://docs.rastervision.io/en/stable/

- Repository: https://github.com/azavea/raster-vision

Directory descriptions are summaries. Verify current capabilities and terms with the project sources.