Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloA novel approach to train random forests on GPU for computer vision applications using local features
Anno di pubblicazione2015
Autore/iDaniele Pianu, Roberto Nerino, Claudia Ferraris, and Antonio Chimienti
Autori CNR e affiliazioni
  • inglese
AbstractThe random forests (RF) classifier has recently gained momentum in the computer vision field, thanks to its successful application in human body tracking, hand pose estimation and object detection. In this article, we present a novel approach to train RF on a graphics processing unit (GPU) for computer vision applications where simple per-pixel features are computed. Besides leveraging the processing power of the GPU to accelerate the training, we reformulate the training problem to limit costly image transfers when it is not possible to store the entire data set in GPU memory. Furthermore, our implementation supports arbitrary image types and allows the user to specify custom features. We extensively compare our approach with the state of the art on publicly available data sets, and we obtain a reduction in training time of up to 18 times. Finally, we train our implementation on a large data set (around 100 K images), demonstrating that our approach is suitable for training RF on the vast data sets typically used in computer vision.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da1
Pagine a15
Pagine totali15
RivistaInternational journal of high performance computing applications (Online)
Attiva dal 1999
Editore: Sage Publications. - London
Paese di pubblicazione: Regno Unito
Lingua: inglese
ISSN: 1741-2846
Titolo chiave: International journal of high performance computing applications (Online)
Titolo proprio: International journal of high performance computing applications. (Online)
Titolo abbreviato: Int. j. high perform. comput. appl. (Online)
Numero volume della rivista-
Fascicolo della rivista-
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)-
Parole chiaveRandom Forests, GPGPU, computer vision, local features, image segmentation, OpenCL
Link (URL, URI)
Titolo parallelo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • IEIIT — Istituto di elettronica e di ingegneria dell'informazione e delle telecomunicazioni
Moduli CNR-
Progetti Europei-
  • A novel approach to train random forests on GPU for computer visioni applications using local features
    Descrizione: Post Review version without publisher editing