Dataiku and UAVIA have come together to push the boundaries of unmanned autonomous vehicles (read: drones) further towards ubiquitous AI and real-time aerial inspections. Sounds cool, but what does that process look like in practice?
How Dataiku was used to design and train a single shot detector (SSD) model that allows unmanned aerial vehicles to detect and track objects of interest
A technical description of the SSD model and the role of UAVIA's embedded intelligence
The method used to simplify the optimization of neural network models for inference within UAVIA DroneOS