With the increasing popularity of wearable cameras, such as GoPro or Narrative Clip, research on continuous activity monitoring from egocentric cameras has received a lot of attention. Research in hardware and software is devoted to find new efficient, stable and long-time running solutions; however, devices are too power-hungry for truly always-on operation, and are aggressively duty-cycled to achieve acceptable lifetimes. In this paper we present a wearable system for context change detection based on an egocentric camera with ultra-low power consumption that can collect data 24/7. Although the resolution of the captured images is low, experimental results in real scenarios demonstrate how our approach, based on Siamese Neural Networks, can achieve visual context awareness. In particular, we compare our solution with hand-crafted features and with state of art technique and propose a novel and challenging dataset composed of roughly 30000 low-resolution images.
Context Change Detection for an Ultra-Low Power Low-Resolution Ego-Vision Imager / Paci, Francesco; Baraldi, Lorenzo; Serra, Giuseppe; Cucchiara, Rita; Benini, Luca. - 9913:(2016), pp. 589-602. (Intervento presentato al convegno First International Workshop on Egocentric Perception, Interaction and Computing tenutosi a Amsterdam, The Netherlands nel October 8-10, 2016) [10.1007/978-3-319-46604-0_42].
Context Change Detection for an Ultra-Low Power Low-Resolution Ego-Vision Imager
PACI, FRANCESCO;BARALDI, LORENZO;SERRA, GIUSEPPE;CUCCHIARA, Rita;
2016
Abstract
With the increasing popularity of wearable cameras, such as GoPro or Narrative Clip, research on continuous activity monitoring from egocentric cameras has received a lot of attention. Research in hardware and software is devoted to find new efficient, stable and long-time running solutions; however, devices are too power-hungry for truly always-on operation, and are aggressively duty-cycled to achieve acceptable lifetimes. In this paper we present a wearable system for context change detection based on an egocentric camera with ultra-low power consumption that can collect data 24/7. Although the resolution of the captured images is low, experimental results in real scenarios demonstrate how our approach, based on Siamese Neural Networks, can achieve visual context awareness. In particular, we compare our solution with hand-crafted features and with state of art technique and propose a novel and challenging dataset composed of roughly 30000 low-resolution images.File | Dimensione | Formato | |
---|---|---|---|
eccv2016submission.pdf
Open access
Tipologia:
Versione originale dell'autore proposta per la pubblicazione
Dimensione
4.87 MB
Formato
Adobe PDF
|
4.87 MB | 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