Visual Traffic Detection

Tracking all aerial objects, including non-cooperative

Based on certifiable AI, detects all airborne intruders, seeing far more than human eyes. Capable of identifying, categorizing, and tracking non-cooperative traffic such as birds and drones. Independent of any infrastructure, integrates into current and future flight deck instruments and advisory systems.

Get PDF
(Development view, not a pilot interface)

How We Use AI

We use a type of AI called machine learning to create a neural network—the core component responsible for recognition of objects appearing in the video stream.

Training machine learning models in the lab

Data from real flights
Data from simulated flights
Training
dataset
Testing
dataset
Validation
dataset

AI component within the airborne application

Input
Video stream from cameras
Pre-processing
Preparing frames for analysis (using classical software)
Algorithm frozen after training and testing, not evolving or learning in flight
Convolutional Neural Network
Identifying objects in each frame
Post-processing
Filtering and tracking detections, sending data output (using classical software)
Output
Identifying airborne traffic, e.g.: helicoper, fixed-wing, drones, birds, gliders, parachutes, etc.

Let’s connect!

Tell us about your use case and ask us anything. We're happy to discuss your needs and explore how we can help.
Leave your details, and we'll get back to you as soon as possible.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.