[HN Gopher] Show HN: Detect any object in satellite imagery usin...
___________________________________________________________________
Show HN: Detect any object in satellite imagery using a text prompt
I built a browser-based tool that uses Vision-Language Models
(VLMs) to detect objects in satellite imagery via natural language
prompts. Draw a polygon on the map, type what you want to find
(e.g., "swimming pools," "oil tanks," "solar panels"), and the
system scans tile-by-tile, projecting bounding boxes back onto the
globe as GeoJSON. The pipeline: pick zoom level + prompt - slice
map into mercantile tiles - feed each tile + prompt to VLM - create
bounding boxes - project to WGS84 coordinates - render on map. No
login required for the demo. Works well for distinct structures
zero-shot; struggles with dense/occluded objects where narrow YOLO
models still win.
Author : eyasu6464
Score : 8 points
Date : 2026-03-08 13:51 UTC (4 days ago)
(HTM) web link (www.useful-ai-tools.com)
(TXT) w3m dump (www.useful-ai-tools.com)
| fallingmeat wrote:
| did you just make Danti?
___________________________________________________________________
(page generated 2026-03-12 23:00 UTC)