The recent breakthrough of artificial intelligence (AI) in many fields has recently shown its impact on drone technology as well. However, most of the provided solutions either entirely rely on commercial software or provide a weak integration interface which denies the development of additional techniques. This leads us to propose a novel and efficient frame-work for the drone technology. Specifically, we introduce the multi-layer AI (MLAI) framework which allows easy integration of ad-hoc AI applications. To demonstrate the benefits of the proposed framework, we implemented deep learning models to track and detect objects based on MLAI.
An efficient artificial intelligence framework for UAV systems
Togootogtokh E.;Foresti G. L.;Micheloni C.;Maritnel N.
2019-01-01
Abstract
The recent breakthrough of artificial intelligence (AI) in many fields has recently shown its impact on drone technology as well. However, most of the provided solutions either entirely rely on commercial software or provide a weak integration interface which denies the development of additional techniques. This leads us to propose a novel and efficient frame-work for the drone technology. Specifically, we introduce the multi-layer AI (MLAI) framework which allows easy integration of ad-hoc AI applications. To demonstrate the benefits of the proposed framework, we implemented deep learning models to track and detect objects based on MLAI.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.