| Summary: | The deployment of deep learning algorithms on embedded devices has the
potential to unlock a wide range of applications in fields such as robotics,
healthcare, and autonomous systems. However, the limited computational
resources of these devices present a challenge, particularly for real-time
applications where both speed and accuracy are crucial. This paper
investigates the feasibility of running state-of-the-art deep learning models on
resource-constrained embedded devices, using drone control via hand
gestures as a case study for real-time, interactive applications.
|
|---|