Annotating images based on multi-modal sensor data

This invention describes a drone equipped with both a regular camera and a thermal camera. It uses data from both cameras, captured at the same time, to identify objects more reliably than with just one camera. Once an object is confidently identified, that data can be used to teach an artificial intelligence system to recognize similar objects in the future.

Why it matters: AI models for object detection and classification have advanced significantly since 2018, making real-time multi-modal processing on drones more powerful. Training new classifiers from drone data is now much more efficient.

Status: Not in forceListed as no longer active. The specific reason is not in the record we hold.
How hard to build: SpecializedDrone, multi-sensor integration, real-time AI software

3 AI reinvention directions for this patent

See all three

AI gives you a few directions you could take this. Pick one, and we check whether your version is different enough to patent, then write the filing.

Reinvent this with AI

Where this one came from

Every morning we go through millions of abandoned patents and pick out 15 worth your time. This was one of today’s.

This one

+10