Sign up to take part
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
Registered users can ask their own questions, contribute to discussions, and be part of the Community!
In the past we have been introduced to edge computing as a concept. Today, let's take it one step further!
In this post, we will detail how we designed and trained a single shot detector (SSD) model that allows unmanned aerial vehicles powered by UAVIA’s embedded intelligence to automatically detect and track objects of interest in the most hardware-optimized way. We also provide a technical description of the SSD model and present the method we’ve used to simplify the optimization of neural network models for inference within UAVIA DroneOS, using the drone’s specific System On Chip (SOC).
Additional Resources: Dataiku and UAVIA Collaboration Successfully Deploys Machine Learning Models for Edge Computing on D...