In this work we have introduced TDNN for surgical gestures and errors recognition based on kinematic data. We have evaluated the proposed method on novel VRASTED public dataset. The obtained results demonstrate state that TDNN applied to kinematic data can be very effective in modeling instrument movements, thus they are suitable for gesture recognition, but they need to be fused with other sensing modalities for obtaining error detection performance suitable for on-line situation awareness systems
Surgical Gesture and Error Recognition with Time Delay Neural Network on Kinematic Data
Giovanni Menegozzo;Diego Dall’Alba;Chiara Zandona;Paolo Fiorini
2019-01-01
Abstract
In this work we have introduced TDNN for surgical gestures and errors recognition based on kinematic data. We have evaluated the proposed method on novel VRASTED public dataset. The obtained results demonstrate state that TDNN applied to kinematic data can be very effective in modeling instrument movements, thus they are suitable for gesture recognition, but they need to be fused with other sensing modalities for obtaining error detection performance suitable for on-line situation awareness systems
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
