CRIS Current Research Information System
IRIS è la soluzione IT che facilita la raccolta e la gestione dei dati relativi alle attività e ai prodotti della ricerca. Fornisce a ricercatori, amministratori e valutatori gli strumenti per monitorare i risultati della ricerca, aumentarne la visibilità e allocare in modo efficace le risorse disponibili.
EnglishConfidence measures aim at discriminating unreliable disparities inferred by a stereo vision system from reliable ones. A common and effective strategy adopted by most top-performing approaches consists in combining multiple confidence measures by means of an appropriately trained random-forest classifier. In this paper, we propose a novel approach by training an n-channel convolutional neural network on a set of feature maps, each one encoding the outcome of a single confidence measure. This strategy enables to move the confidence prediction problem from the conventional 1D feature maps domain, adopted by approaches based on random-forests, to a more distinctive 3D domain, going beyond single pixel analysis. This fact, coupled with a deep network appropriately trained on a small subset of images, enables to outperform top-performing approaches based on random-forests.
| Titolo: | Even More Confident Predictions with Deep Machine-Learning | |
| Autore/i: | Poggi, Matteo; Tosi, Fabio; Mattoccia, Stefano | |
| Autore/i Unibo: | ||
| Anno: | 2017 | |
| Serie: | ||
| Titolo del libro: | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops | |
| Pagina iniziale: | 393 | |
| Pagina finale: | 401 | |
| Digital Object Identifier (DOI): | http://dx.doi.org/10.1109/CVPRW.2017.54 | |
| Abstract: | Confidence measures aim at discriminating unreliable disparities inferred by a stereo vision system from reliable ones. A common and effective strategy adopted by most top-performing approaches consists in combining multiple confidence measures by means of an appropriately trained random-forest classifier. In this paper, we propose a novel approach by training an n-channel convolutional neural network on a set of feature maps, each one encoding the outcome of a single confidence measure. This strategy enables to move the confidence prediction problem from the conventional 1D feature maps domain, adopted by approaches based on random-forests, to a more distinctive 3D domain, going beyond single pixel analysis. This fact, coupled with a deep network appropriately trained on a small subset of images, enables to outperform top-performing approaches based on random-forests. | |
| Data stato definitivo: | 4-feb-2018 | |
| Appare nelle tipologie: | 4.01 Contributo in Atti di convegno |
File in questo prodotto:
http://hdl.handle.net/11585/619386
Copyright © 2022