arplaboratory/STHN
[RA-L 2024] Official repository for "STHN: Deep Homography Estimation for UAV Thermal Geo-localization with Satellite Imagery"
This project helps operations engineers and first responders accurately pinpoint the location of drones equipped with thermal cameras using satellite imagery, especially during nighttime or low-visibility conditions. It takes in thermal images captured by a drone and standard satellite maps, then outputs the precise geographic coordinates where the drone's thermal view aligns with the satellite map. This is useful for anyone needing to accurately track drones or assess ground situations from aerial thermal data.
Use this if you need to precisely geo-localize UAV thermal imagery in situations where GPS might be unreliable or insufficient, such as search and rescue operations, surveillance, or infrastructure inspection.
Not ideal if your primary need is for visible-light drone imagery geo-localization or if you do not have access to corresponding satellite imagery for the operational area.
Stars
79
Forks
7
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Feb 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/arplaboratory/STHN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
MarvinTeichmann/MultiNet
Real-time Joint Semantic Reasoning for Autonomous Driving
ternaus/TernausNetV2
TernausNetV2: Fully Convolutional Network for Instance Segmentation
WangLibo1995/GeoSeg
UNetFormer: A UNet-like transformer for efficient semantic segmentation of remote sensing urban...
cvjena/cn24
Convolutional (Patch) Networks for Semantic Segmentation
rankseg/rankseg
Boost segmentation model mIoU/Dice instantly WITHOUT retraining. A plug-and-play, training-free...