Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloDeep learning for decentralized parking lot occupancy detection
Anno di pubblicazione2017
Formato
  • Elettronico
  • Cartaceo
Autore/iAmato G.; Carrara F.; Falchi F.; Gennaro C.; Meghini C.; Vairo C.
Affiliazioni autoriCNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy
Autori CNR e affiliazioni
  • FABIO CARRARA
  • GIUSEPPE AMATO
  • CLAUDIO GENNARO
  • FABRIZIO FALCHI
  • CLAUDIO FRANCESCO VAIRO
  • CARLO MEGHINI
Lingua/e
  • inglese
AbstractA smart camera is a vision system capable of extracting application-specific information from the captured images. The paper proposes a decentralized and efficient solution for visual parking lot occupancy detection based on a deep Convolutional Neural Network (CNN) specifically designed for smart cameras. This solution is compared with state-of-the-art approaches using two visual datasets: PKLot, already existing in literature, and CNRPark-EXT. The former is an existing dataset, that allowed us to exhaustively compare with previous works. The latter dataset has been created in the context of this research, accumulating data across various seasons of the year, to test our approach in particularly challenging situations, exhibiting occlusions, and diverse and difficult viewpoints. This dataset is public available to the scientific community and is another contribution of our research. Our experiments show that our solution outperforms and generalizes the best performing approaches on both datasets. The performance of our proposed CNN architecture on the parking lot occupancy detection task, is comparable to the well-known AlexNet, which is three orders of magnitude larger.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da327
Pagine a334
Pagine totali-
RivistaExpert systems with applications
Attiva dal 1990
Editore: Pergamon, - Oxford
Paese di pubblicazione: Regno Unito
Lingua: inglese
ISSN: 0957-4174
Titolo chiave: Expert systems with applications
Titolo proprio: Expert systems with applications.
Titolo abbreviato: Expert syst. appl.
Numero volume della rivista72
Fascicolo della rivista-
DOI10.1016/j.eswa.2016.10.055
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)
  • Scopus (Codice:2-s2.0-85006097682)
  • ISI Web of Science (WOS) (Codice:000392770900028)
Parole chiaveMachine learning, Classification, Deep learning, Convolutional neural networks, Parking space dataset
Link (URL, URI)http://www.sciencedirect.com/science/article/pii/S095741741630598X
Titolo parallelo-
Licenza-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioniProgetto: ENERGIA, Renewable Energy and ICT for Sustainability Energy
Strutture CNR
  • ISTI — Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"
Moduli/Attività/Sottoprogetti CNR
  • ICT.P08.010.002 : Digital Libraries
Progetti Europei-
Allegati
Deep learning for decentralized parking lot occupancy detection (documento privato )
Descrizione: Codice Puma: cnr.isti/2017-A0-045
Tipo documento: application/pdf
Deep learning for decentralized parking lot occupancy detection
Descrizione: Preprint
Tipo documento: application/pdf