https://github.com/kitware/adapt
An open source platform for deploying state of the art deep-neural-network computer vision in real time on small unmanned aircraft systems (sUAS)
https://github.com/kitware/adapt
ai computer-vision deep-learning diy-ai drone geospatial hardware hardware-designs ml mlops real-time ros
Last synced: about 1 month ago
JSON representation
An open source platform for deploying state of the art deep-neural-network computer vision in real time on small unmanned aircraft systems (sUAS)
- Host: GitHub
- URL: https://github.com/kitware/adapt
- Owner: Kitware
- License: apache-2.0
- Created: 2021-08-06T18:08:53.000Z (about 4 years ago)
- Default Branch: main
- Last Pushed: 2023-01-31T14:39:23.000Z (over 2 years ago)
- Last Synced: 2025-05-08T20:14:07.188Z (5 months ago)
- Topics: ai, computer-vision, deep-learning, diy-ai, drone, geospatial, hardware, hardware-designs, ml, mlops, real-time, ros
- Homepage:
- Size: 73.4 MB
- Stars: 5
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# ADAPT Multi-Mission Payload
### An open source platform for deploying state of the art deep-neural-network computer vision in real time on small unmanned aircraft systems (sUAS).
* Optimized drone-based collection of imagery and geospatial metadata with live feedback to maintain quality control.
* Integration with the open source do-it-yourself AI toolkit [VIAME](https://www.viametoolkit.org/) to annotate data and train mission-specific image-processing models.
* Upload your models for aerial deployment with real-time, georegistered analytics wirelessly transmitted to a ground station computer and beyond for rapid dissemination.
* Commodity [hardware components](https://kitware.github.io/adapt/parts), [CAD models](https://github.com/Kitware/adapt/tree/main/cad), and [open-source software](https://gitlab.kitware.com/adapt/adapt_ros_ws) allows organizations to cheaply and easily build their own payloads
## Supports a variety of unique missions
* [Sea and River Ice Monitoring](https://kitware.github.io/adapt/ice_monitor)
* [Monitoring Arctic Mammal Populations](https://kitware.github.io/adapt/ice_seal)
* [Person Search and Rescue](https://kitware.github.io/adapt/search_and_rescue)
* [Wild Fire Monitoring](https://kitware.github.io/adapt/fire_monitoring)
* [Coastline Erosion Monitoring](https://kitware.github.io/adapt/coastline_monitoring)
Ongoing work on the ADAPT project is funded by [NOAA](https://www.noaa.gov/) to support [key missions](https://uas.noaa.gov/Portals/5/Docs/NOAA%20UAS%20Program%20Overview%2019Apr2019.pdf?ver=2019-04-22-144716-137).
## Source Code
The ADAPT payload source code is hosted here: [https://gitlab.kitware.com/adapt/adapt_ros_ws](https://gitlab.kitware.com/adapt/adapt_ros_ws) or
[Try the simulator with docker](https://gitlab.kitware.com/adapt/adapt/-/tree/master/AirSim). Please use the Issue Tracker on Gitlab or contact us [here](https://kitware.github.io/adapt/contact/).
## License
This repository is under the Apache 2.0 license, see NOTICE and LICENSE file.
## Documentation
Documentation: [https://kitware.github.io/adapt/](https://kitware.github.io/adapt/)
## Events
* [Kitware and ACUASI September 2021 data collection in Fairbanks Alaska](https://kitware.github.io/adapt/sept_2021_collects).
* [The 3rd NOAA Workshop on Leveraging AI in Environmental Sciences](https://2021noaaaiworkshop.sched.com/info)
## Papers / Presentations
* (2022) National Innovation Center Seminar: [Slides](https://docs.google.com/presentation/d/1Z0FEdAjt3vTNZYKwsOXEP_GBd8f6RWV7H0KD1kT_Cfg/edit?usp=sharing)
* (2022) Ocean Sciences Meeting: [Slides](https://docs.google.com/presentation/d/15Ib9vKES6aAzlCuejUdRuDkyPnBcADa_OHr9GyepWBY/edit?usp=sharing)
* (2022) 1st International Workshop on Practical Deep Learning in the Wild at AAAI Conference on Artificial Intelligence: [Paper](https://arxiv.org/abs/2201.10366)
* (2021) NOAA Innovators Series: [Slides](https://docs.google.com/presentation/d/1Bp65DTJMgateIyRNzrCvjfHrLshqS3AUaba3lLGbTts/edit?usp=sharing), [Recording](https://www.youtube.com/watch?v=eD95Di6B5wo&t=1735s)
* (2021) The 3rd NOAA Workshop on Leveraging AI in Environmental Sciences: [Slides](https://docs.google.com/presentation/d/1PMgJrYxrqMtuJYR-xiAdFsjSSQt90_XOcYZ5pRXP4sk/edit#slide=id.p), [Recording](https://drive.google.com/file/d/1BI0qeIOw7TK262lNJzK_m3XIJd-RSvQn/view?usp=sharing)
## Site
For more information go to [https://kitware.github.io/adapt/](https://kitware.github.io/adapt/)