In this work we present how some state-of-the art action recognition techniques can be tailored to monitoring indoor human activities. At first, we analyze the most relevant algorithms and eventually we present an effective implementation based on the solely RGB input. Our preliminary results show that the proposed solution achieves competitive results with respect to other methods in the state of the art that take also advantage of multiple inputs.
Ciocca, G., Elmi, A., Napoletano, P., Schettini, R. (2018). Activity monitoring from RGB input for indoor action recognition systems. In 2018 IEEE 8th International Conference on Consumer Electronics - Berlin (ICCE-Berlin) (pp.1-4). IEEE Computer Society [10.1109/ICCE-Berlin.2018.8576233].
Activity monitoring from RGB input for indoor action recognition systems
Ciocca, G
;Napoletano, P;Schettini, R
2018
Abstract
In this work we present how some state-of-the art action recognition techniques can be tailored to monitoring indoor human activities. At first, we analyze the most relevant algorithms and eventually we present an effective implementation based on the solely RGB input. Our preliminary results show that the proposed solution achieves competitive results with respect to other methods in the state of the art that take also advantage of multiple inputs.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
