Picterra
No-code geospatial machine-learning platform for satellite, drone, and aerial imagery
About
Picterra lets analysts train custom deep-learning detectors on satellite, drone, and aerial imagery without writing code: annotate a few examples, and the platform finds similar objects at scale. It handles optical, multispectral, thermal, SAR, and height-map imagery, with change detection and GIS integrations.
The workflow suits teams that need object detection but lack ML engineers. Detection quality depends heavily on training examples and imagery resolution, and enterprise pricing is quote-based rather than published.
What it can do
- No-code custom detector training
- Object and change detection
- Multispectral and SAR imagery support
- API and GIS integrations
- Picterra Tracer for compliance monitoring
Setup
- Create a Picterra account (free trial available)
- Upload satellite, drone, or aerial imagery
- Annotate example objects with the smart annotation tools
- Train detectors and run them at scale via the API or dashboards
Prerequisites
Imagery to analyze; account with imagery credits
Use cases
Works with
Trust score — 7/10
Scored 7/10 (verified tier, metrics-v1). Evidence: Swiss company, $3.3M seed from Space Capital; No-code detector training documented across directories; Detection quality depends on training data and resolution; Pricing is quote-based. License: Proprietary SaaS platform.
How the trust score is built
Full methodology →- Adoption · stars/downloads, log-scaled vs peers
- 7.0/10
- Maintenance · recency, releases, issue load
- 7.0/10
- Openness · license + docs
- 5.0/10
- Manual review · sanity read + red-flag check
- 7.0/10
- · Swiss company, $3.3M seed from Space Capital
- · No-code detector training documented across directories
- · Detection quality depends on training data and resolution
- · Pricing is quote-based
Sources
Every fact above was checked against these sources. Where a claim comes from the provider and couldn't be independently verified, the text says so.