Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/WildMeOrg/scout
https://github.com/WildMeOrg/scout
Last synced: about 2 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/WildMeOrg/scout
- Owner: WildMeOrg
- License: mit
- Created: 2022-11-03T03:56:31.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-10-28T17:52:44.000Z (2 months ago)
- Last Synced: 2024-10-30T01:34:15.671Z (2 months ago)
- Language: JavaScript
- Size: 49 MB
- Stars: 8
- Watchers: 6
- Forks: 5
- Open Issues: 26
-
Metadata Files:
- Readme: README.md
- Funding: .github/FUNDING.yml
- License: LICENSE
Awesome Lists containing this project
- open-sustainable-technology - Wild Me Scout - Provides structure data processing and management for photographs from aerial surveys in support of animal census efforts, combining machine learning and expertise to get to accurate animal counts as quickly as possible. (Biosphere / Terrestrial Wildlife)
README
# Scout
Scout is a software application designed to support annotators and lab leads processing imagery for the Kavango–Zambezi Transfrontier Conservation Area (KAZA TFCA) aerial survey of animals.
With Scout, you can:
* Ingest high volumes of .ARW and .JPG images collected from survey cameras
* Group images as "Tasks" that can be assigned to other users (e.g., image annotators) or machine learning (ML) models for bounding box creation and species labeling
* Review and ground truth annotated images for accuracy
* Draw division lines for overlapping image sequences with annotations
* Export CSV data files for statistical analysis
## System Requirements
**NOTE**: This software is designed to run on an air-gapped private network only. (Significant security modifications are needed before this platform is suitable for installation on a public network or cloud).
* A fast and stable internet connection.
* An 8GB-minimum thumbdrive.
* A dedicated, powerful laptop with a graphics processing unit (GPU) to run solely as the Scout server.
* Laptops with the Chrome web browser to connect to the Scout server for lab leads and annotators.
## Installation
For installation and first-time configuration steps, follow our [Server System Setup](https://scout.docs.wildme.org/system-administrators/server-system-setup.html) documentation guide.
**NOTE**: Following full installation instructions will remove all data and any operating system from the Scout Server laptop and Ubuntu Linux will be installed as the operating system. Skip Ubuntu installation to run on a different OS.
## Important Links & Documentation
Use our [Help Documentation](https://scout.docs.wildme.org/) to learn how to use Scout.
Visit [Wild Me Professional Services](https://www.wildme.org/services) to view the range of services we can offer.
## Support
For assistance with setup and installation, or for interest in development, join our [Wild Me Development Discord](https://discord.gg/zw4tr3RE4R).
For usage issues and customer support, visit our [Community page](https://community.wildme.org).
## Usage
Scout supports three user roles:
* System Administrators install and run Scout.
* Lab leads create and manage user accounts, upload images, coordinate tasks, review and ground truth annotations, draw division lines, and export data.
* Annotators draw and label bounding boxes representing animals on images.
Lab leads view, filter, manage, and export Tasks using the Task table:
Annotators and ML models use bounding boxes, species labels, and annotation labels to indicate animals in images:
## Techstack and Features
Scout uses Javascript (Sails.js) and integrated machine learning provided by [Scoutbot](https://github.com/WildMeOrg/scoutbot).
## License
Scout is licensed under the [MIT open source license](https://opensource.org/license/mit/).