SlytherinGe/RSTeller
Vision-Language Dataset for Remote Sensing
This project offers a vast collection of satellite and aerial images, primarily from the United States, each with detailed descriptive captions. It helps remote sensing specialists, environmental analysts, and urban planners train specialized AI models to interpret complex geographic scenes. You input satellite imagery and get out rich textual descriptions, enabling more accurate scene understanding for various applications.
No commits in the last 6 months.
Use this if you need a large, pre-annotated dataset of remote sensing images and descriptions to train or evaluate AI models for scene understanding tasks.
Not ideal if you need imagery outside the United States or require very specific imagery capture dates not covered between August 2021 and November 2022.
Stars
40
Forks
4
Language
Python
License
—
Category
Last pushed
May 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/SlytherinGe/RSTeller"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KimMeen/Time-LLM
[ICLR 2024] Official implementation of " 🦙 Time-LLM: Time Series Forecasting by Reprogramming...
om-ai-lab/VLM-R1
Solve Visual Understanding with Reinforced VLMs
bytedance/SALMONN
SALMONN family: A suite of advanced multi-modal LLMs
NVlabs/OmniVinci
OmniVinci is an omni-modal LLM for joint understanding of vision, audio, and language.
fixie-ai/ultravox
A fast multimodal LLM for real-time voice