Welcome to the [ Raven Scan ] platform documentation

Overview

The Raven Scan platform harnesses advanced drone and satellite imagery to revolutionize waste management and environmental monitoring.

By integrating high-resolution imagery with precision image annotation, AI-powered object detection models, and geospatial analysis, our solution delivers powerful tools for identifying illegal dump sites and optimizing the management of regulated landfills.

User Guides and Documentation

Guides

Explore each feature through our User Guides

Feature Documentation

Learn more from our detailed Feature Documentation

📝Table of Contents

Overview	Getting Started	Licensing
Guides and Docs	Dependencies	Open-Sourced
Key Features	Raven Scan Showcase	Acknowledgments
Map | Datasets | Annotation	Development	Venture Fund
Orthophoto Inputs | Landfill Management | 3D Point-Cloud Scans	Code of Conduct	MMDetection
AI Model Training | Waste Detection and Monitoring	Contributing	Third-Party

Key Features

Map View Detected Dumpsites on Map Open-Layers, layer switcher, view terrain, adjust coloring Direct GeoTiff Injection, review historical scans of areas Guide Docs	Dataset Management Manage extensive Datasets of Drone and Satellite images Tools for uploading, categorizing, and maintaining image data Features include tagging, filtering, and robust data integrity checks Guide Docs
Image Annotation Annotate High-Resolution imagery Draw, adjust, enable and disable bounding boxes Guide Docs	Detection Input Images Reuse Input Images and save space View input images as Map Layers Guide Docs
Landfill Management Advanced tools for legal landfill management Waste Form Submission integration, types, trucks, imports Guide Docs	3D Point-Cloud 3D Point-Cloud scan integration View and Compare, Measure Height, Distance, Volume Guide Docs
AI Model Training Train proven AI model architectures with your custom datasets Reinforce your custom-trained models as more data comes in Guide Docs	Waste Detection and Monitoring of Dumpsites Detect using Custom-Trained AI Models Visualize Results on Georeferenced Map Guide Docs

This repository aims to equip researchers, environmental agencies, and policymakers with the tools needed to monitor and respond to environmental challenges efficiently.

Join us in leveraging these capabilities to maintain ecological integrity and promote sustainable practices in waste management.

Our complete Project Charter.

Our official Documentation Page.

Getting Started

We provide a guide that will help you set up and run the [ Raven Scan ] platform on your local development environment.

• The complete installation guide can be found on our official documentation page

Dependencies

Dependency Type	Technology / Tool	Dependency Type	Technology / Tool
MVC Dependencies		AI Dependencies
Web Framework	.NET 8	AI Platform	MMDetection 3.3
ORM	Entity Framework	AI Processing Library	Pytorch (CUDA)
Package Manager	NuGet	Package Manager	Miniconda 3
Package Manager	npm	Programming Language	Python 3.8
Frontend Library	Open Layers	Programming Language	C++ 14
Geographic Library	NetTopologySuite
Geographic Library	GDAL
3D Point-Cloud Library	PoTree
Database	PostgreSQL 16
Database Extension	PostGIS
Scheduling Library	Hangfire

• See all Project Dependencies

Raven Scan Showcase

Below are screenshots demonstrating Raven Scan's key capabilities in action:

Dataset Management Overview of Dataset Images and their statuses

Detected Dumpsites show on Map

3D Point-Cloud Volume Calculation of a Landfill's Waste Heap

Development

Support & Issues

Check the detailed documentation for troubleshooting
Create an issue in the GitHub repository

If you are ready to contribute, experiencing a bug, or just curious

• Check out the Development Documentation

Code of Conduct

We are committed to fostering a welcoming and inclusive community.

Our project adheres to a Code of Conduct that outlines expectations for participation and community standards for behavior.

We encourage all contributors and participants to review and adhere to these guidelines.

By participating in this project, you agree to abide by its terms.

• Full Code of Conduct

Contributing

We welcome contributions from the community.

Whether you're fixing bugs, adding new features, or improving documentation, your help is greatly appreciated.

For detailed instructions on how to contribute, please see our

• Complete Contributing Guidelines

Licensing

This project is licensed under the Apache License 2.0.
This license allows for a great deal of freedom in both academic and commercial use of this software.

• See the Complete License Text.

Open-Sourced

Collected Dataset

Contains 2115 drone images of illegal waste dumpsites

• 1280 x 1280 px resolution

• Nadir perspective (camera pointing straight down at a 90-degree angle to the ground)

• Hugging Face Dataset

Trained Models

• Hugging Face Models

Acknowledgments

We would like to extend our deepest gratitude to the following organizations and platforms for their invaluable support

UNICEF Venture Fund

We express our profound gratitude to the UNICEF Venture Fund for their generous support of our project. Their commitment to fostering innovation and sponsoring projects that utilize frontier technology is truly commendable and instrumental in driving positive change.

MMDetection

A special thanks to the open-source AI training platform MMDetection. Your robust tools and extensive resources have significantly accelerated our development process.

Third Party Notices

Our project would not have been possible without the myriad of libraries and frameworks that have empowered us along the way. We owe a great debt of gratitude to all the contributors and maintainers of these projects.

Thank you to everyone who has made this project possible. We couldn't have done it without you!

Raven Scan uses third-party libraries or other resources that may be distributed under licenses different than the Raven Scan software.

In the event that we accidentally failed to list a required notice, please bring it to our attention by posting an issue on out GitHub Page.

Each team member has played a pivotal role in bringing this project to fruition, and we are immensely thankful for their hard work and dedication.

• All Project Dependencies