Satellite imagery object detection using text prompts
I built a browser-based tool for detecting objects in satellite imagery using vision-language models (VLMs). You draw a polygon on the map and enter a text prompt such as "swimming pools", "oil tanks", or "buses". The system scans the selected area tile-by-tile and returns detections projected back onto the map as GeoJSON. Pipeline: select area and zoom level, split the region into mercantile tiles, run each tile with the prompt through a VLM, convert predicted bounding boxes to geographic coordinates (WGS84), and render the results back on the map. It works reasonably well for distinct…
Satellite imagery object detection using text prompts launched on March 9, 2026 with 53 votes, #713 of 23,380 launches that month and more than 95% of that year's launches.
In plain words
A browser-based tool for finding objects in satellite imagery using text prompts. Users draw a polygon on a map, enter a search term like "swimming pools" or "oil tanks," and the system scans the area tile-by-tile using vision-language models, returning detected objects as geographic coordinates overlaid on the map. The tool works well for distinct structures and requires no login. It is designed for researchers, analysts, and anyone needing to identify specific features across geographic regions from satellite data.
written from the facts on this page · September 2026
From the sources
State-of-the-art satellite analysis and geospatial AI. Professional-grade object detection for real estate, logistics, agriculture, and urban planning. Try our free demo.
Try our interactive satellite analysis demo. Detect vehicles, shipping containers, and buildings on high-resolution maps using open-vocabulary AI models.
Welcome to the Satellite Analysis Workspace Demo . This interactive environment allows you to experience the power of our geospatial computer vision models without creating an account or providing any credentials. In this restricted demo environment, you can pan and zoom across a high-resolution map tile and execute real-time object detection . Simply type "vehicles", "storage tanks", or "bridges" into the scan tool to see our vision-language models identifying assets from above. We've optimized this demo to showcase the speed and precision of our cloud-based inference engine. While the demo area is limited, it provides a perfect look at the tool that professionals use for satellite…from useful-ai-tools.com
In the maker’s words, at launch
I built a browser-based tool for detecting objects in satellite imagery using vision-language models (VLMs). You draw a polygon on the map and enter a text prompt such as "swimming pools", "oil tanks", or "buses". The system scans the selected area tile-by-tile and returns detections projected back onto the map as…
Does a similar job
all alternatives →- UCUsing computer vision to detect birds in parks2014 · code.flickr.net · ▲195
- FPFrom Photos to Positions: Prototyping VLM-Based Indoor Maps2025 · arjo129.github.io · ▲55
Just a fun hack I did while bored over the weekend. My wife was busy shopping, it got me thinking that can VLMs solve the indoor location problem in a mall? Can I just show a VLM a map and an image and have it doa good enough job locating me? I hacked this P.O.C and it seems to work.
- UDUsing deep learning to detect objects from your webcam2018 · modeldepot.github.io · ▲95
- LWLearn where countries are on the world map with Spaced Repetition2025 · map.koljapluemer.com · ▲217
Hi HN, I made a web game to practice country locations a while ago and HN liked it, so I thought I'd post my updated version as well. As for how the game works and feels, I'd really recommend you checking it out for yourself, it's free, no signup, no ads. The tech stack is Vue + ts + Tailwind/Daisy for the looks. The learning algorithm is a slight modification of the ts version of FSRS. If you have anything to add, it's open source as well (https://github.com/koljapluemer/learn-worldmap), although not well documented yet. In the end it's just a little sideproject,…
- UYUsing YOLO to Detect Office Chairs in 40M Hotel Photos2025 · ▲222
I used the YOLO object detection library from Ultralytics to scan over 40 million hotel photos and identify images with office chairs. This helped me create a map showing hotels suitable for remote work. Map: https://www.tripoffice.com/maps Yolo: https://www.ultralytics.com/yolo The whole process was done on a home Mac without the use of any LLMs. It's based on traditional object detection technology.
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, March 2026
the whole month →
Switch from ChatGPT to Claude with import memory feature
AI · Mar 2026 · claude.com
Littlebird▲709Littlebird remembers everything across your meetings, messages, docs, and apps, then takes action so you can recall any detail and never lose context.
AI · Mar 2026 · littlebird.ai
