We present a novel method for monocular hand gesture recognition in ego-vision scenarios that deals with static and dynamic gestures and can achieve high accuracy results using a few positive samples. Specifically, we use and extend the dense trajectories approach that has been successfully introduced for action recognition. Dense features are extracted around regions selected by a new hand segmentation technique that integrates superpixel classification, temporal and spatial coherence. We extensively testour gesture recognition and segmentation algorithms on public datasets and propose a new dataset shot with a wearable camera. In addition, we demonstrate that our solution can work in near real-time on a wearable device.
Gesture Recognition in Ego-Centric Videos using Dense Trajectories and Hand Segmentation / Baraldi, Lorenzo; Paci, Francesco; Serra, Giuseppe; Benini, Luca; Cucchiara, Rita. - ELETTRONICO. - (2014), pp. 702-707. (Intervento presentato al convegno 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2014 tenutosi a Columbus, Ohio nel 23-28 June 2014) [10.1109/CVPRW.2014.107].
Gesture Recognition in Ego-Centric Videos using Dense Trajectories and Hand Segmentation
BARALDI, LORENZO;PACI, FRANCESCO;SERRA, GIUSEPPE;CUCCHIARA, Rita
2014
Abstract
We present a novel method for monocular hand gesture recognition in ego-vision scenarios that deals with static and dynamic gestures and can achieve high accuracy results using a few positive samples. Specifically, we use and extend the dense trajectories approach that has been successfully introduced for action recognition. Dense features are extracted around regions selected by a new hand segmentation technique that integrates superpixel classification, temporal and spatial coherence. We extensively testour gesture recognition and segmentation algorithms on public datasets and propose a new dataset shot with a wearable camera. In addition, we demonstrate that our solution can work in near real-time on a wearable device.File | Dimensione | Formato | |
---|---|---|---|
2014EVW.pdf
Open access
Tipologia:
Versione originale dell'autore proposta per la pubblicazione
Dimensione
739.65 kB
Formato
Adobe PDF
|
739.65 kB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I metadati presenti in IRIS UNIMORE sono rilasciati con licenza Creative Commons CC0 1.0 Universal, mentre i file delle pubblicazioni sono rilasciati con licenza Attribuzione 4.0 Internazionale (CC BY 4.0), salvo diversa indicazione.
In caso di violazione di copyright, contattare Supporto Iris