OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Developer Tools & SDKs

Raster Vision

Raster Vision is an open-source Python library and low-code framework for building deep-learning computer-vision workflows on satellite, aerial, oblique drone and other large imagery sets. It supports image-chip classification, object detection and semantic segmentation through PyTorch backends, with utilities for georeferenced data, model training, prediction and georeferenced outputs.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

Raster Vision — OpenViST project profile in AI Developer Tools & SDKs.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Raster Vision when building a deep-learning computer-vision workflow for large geospatial imagery and when its classification, detection or segmentation tasks fit the project. The low-code framework is a documented starting point for configuring experiments; the library suits developers who want to combine its utilities with their own code.

Who it is for

  • Remote-sensing practitioners building image-analysis workflows.
  • Users who want to configure repeatable experiments through a low-code framework.
  • Developers combining geospatial deep learning with their own Python code.

Documented uses

  • Classify satellite or aerial image chips into categories such as land use.
  • Detect objects in aerial imagery.
  • Segment imagery into labeled regions.
  • Read georeferenced data and write predictions in georeferenced formats.
  • Configure a repeatable pipeline for preparing training chips, training and evaluating models, and generating predictions.
Before you choose

Requirements & limits

The project is open source under the Apache 2.0 license. The documentation describes pip installation and pre-built Docker images.

  • The supported computer-vision tasks are chip classification, object detection and semantic segmentation.
  • PyTorch is the listed model backend ecosystem.
  • The framework covers multiple pipeline stages, from training-data analysis through model evaluation and deployment bundling.
  • Cloud experiment support is documented for AWS Batch and AWS SageMaker.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Set up Raster Vision for development

Prepare a local development environment with the repository's plugins and dependencies.

Before you start

  • A clone of the Raster Vision repository
  • A Python virtual-environment manager such as mamba, uv or pyenv

Steps

  1. Clone the repository and navigate to it.

  2. Create and activate a Python virtual environment.

  3. Run scripts/setup_dev_env.sh to install the Raster Vision plugins in editable mode along with dependencies.

Expected outcome

A development environment with the project's plugins and dependencies installed.

Guide limitations

  • This documented procedure covers environment setup, not running a model or workflow.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
13 October 2026
Original website title
azavea/raster-vision · Official homepage title · retained in its source language
How we review sourcesSuggest a correction