Detect any object in satellite imagery using a text prompt
Get picks like this daily. Today's launch numbers, the top launches, AI and tech news, and a daily opportunity pick, straight to your inbox.
Want to reach these readers? Sponsor an issue.
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.
HN · launched Mar 8, 2026 · 22 upvotes (top 24%) · 0 views
Niche: computer vision software and models · 225 launches, 11 in the last 7 days ▼ -45% · Explore this niche →
Category and tags
- Horizontal
- Analytics & BI
- B2B
- AI-native
- Commercial product
Visit website ↗ Source listing ↗
More like this: all 225 launches in computer vision software and models →
Could you build this?
Yes It combines standard web mapping libraries with an existing Vision-Language Model or zero-shot object detection API running on sliced map tile images.
Discussion
7 comments analyzed.
Competitors mentioned: Danti
Concerns raised: Repeated submissions appearing as dishonest marketing strategy, Duplicate posting (posted yesterday with engagement)
Feature requests: Identify houses with rooftop solar installations
Competitors
Other products that read as similar to this one : 91 launches clear the similarity bar, closest 8 shown.
Attention rank: #17 of 92 (itself plus its competitors, highest first, normalized so YC and Product Hunt are compared fairly).
Launched 128 days after the earliest competitor.
- Satellite imagery object detection using text prompts · hn · 2026-03-09 · 53 upvotes · similarity 0.93
- DK-VLM · github · 2026-10-13 · 25 upvotes · similarity 0.48
- Chat with Orion · hn · 2025-11-13 · 22 upvotes · similarity 0.46
- ST-SAM3 · github · 2026-10-26 · 12 upvotes · similarity 0.44
- Vision-Based, Vectorless RAG for Long Douments · hn · 2025-10-31 · 6 upvotes · similarity 0.42
- Run open-weight OCR, VLM and vision models behind one API · hn · 2026-09-04 · 5 upvotes · similarity 0.42
- deepseek-vision-pro · github · 2026-10-13 · 21 upvotes · similarity 0.42
- ScaleScout · github · 2026-10-13 · 21 upvotes · similarity 0.40
The niche, labels, vibe code rating and competitor comparison on this page are analysis by Nicheloom. If you use them, please credit nicheloom.com. How you may use our data.