Location Estimation
Morrigan — Rigr AI's visual geolocation, ranked with confidence.
Overview
Rigr AI's Location Estimation capability, Morrigan, analyses visual cues in images and video to estimate likely capture locations, both indoors and outdoors.
Results are probabilistic and ranked with confidence scores, supporting lead generation rather than false certainty.
Reading the Whole Frame
Most geolocation tools wait for the obvious — a landmark, a street sign, a recognisable skyline. Investigative imagery rarely offers any of them.
Location Estimation reads the whole frame instead: architecture and building materials, signage and script, vegetation, terrain, the quality of the light, the layout and furnishings of a room, what people are wearing, even the view through a window. It reasons from the combination, not a single clue.
We had a case here where we were able to locate a picture of a person sitting in a restaurant, based on the view out of the window.
— Senior Officer, European Law Enforcement Agency
Try It
Upload an image to see location estimation in action.
Upload an image
Drag and drop or select a file
Images you submit are kept for up to 7 days for trust & safety review, then deleted. Do not upload images of identifiable people without their consent. How we handle demo data →
Or try an example
Operational Use
Location Estimation is used to:
- Support jurisdictional assessment
- Generate investigative leads from visual evidence
- Narrow a search from country to region
- Accelerate cross-border and time-sensitive investigations
The capability integrates directly into the platform and is also available as a standalone API.
Deployment and Control
- Fully containerised
- On-premise and air-gapped operation
- No external connectivity required
- Outputs remain under customer control
Frequently asked questions
What is Morrigan?
Morrigan is Rigr AI's visual geolocation capability (Location Estimation). It estimates likely capture locations from images and video, both indoors and outdoors.
How does it work without a landmark or street sign?
It reads the whole frame — architecture and building materials, signage and script, vegetation, terrain, the quality of the light, interior furnishings, what people are wearing, even the view through a window — and reasons from the combination rather than a single clue.
Are the location results definitive?
No. Results are probabilistic and ranked with confidence scores, returning multiple candidate locations to support lead generation rather than false certainty.
Can it process a whole case at once?
Within VST Teams, Location Estimation runs across every image in a case and surfaces the strongest geographic leads first. It is also available as a standalone API.