Hand-Object Interaction Detection with Fully Convolutional Networks
Schröder M, Ritter H (2017)
In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 18-25.
Konferenzbeitrag
| Veröffentlicht | Englisch
Download
![Open access file OA](https://pub.uni-bielefeld.de/images/access_open.png)
Autor*in
Einrichtung
Abstract / Bemerkung
Detecting hand-object interactions is a challenging
problem with many applications in the human-computer interaction
domain. We present a real-time method that automatically
detects hand-object interactions in RGBD sensor
data and tracks the object’s rigid pose over time. The
detection is performed using a fully convolutional neural
network, which is purposefully trained to discern the relationship
between hands and objects and which predicts
pixel-wise class probabilities. This output is used in a probabilistic
pixel labeling strategy that explicitly accounts for
the uncertainty of the prediction. Based on the labeling of
object pixels, the object is tracked over time using modelbased
registration. We evaluate the accuracy and generalizability
of our approach and make our annotated RGBD
dataset as well as our trained models publicly available.
Erscheinungsjahr
2017
Titel des Konferenzbandes
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Seite(n)
18 - 25
Konferenz
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (ODAR)
Konferenzort
Honolulu, HI, USA
Konferenzdatum
2017-07-21 – 2017-07-26
Page URI
https://pub.uni-bielefeld.de/record/2911886
Zitieren
Schröder M, Ritter H. Hand-Object Interaction Detection with Fully Convolutional Networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 2017: 18-25.
Schröder, M., & Ritter, H. (2017). Hand-Object Interaction Detection with Fully Convolutional Networks. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 18-25.
Schröder, Matthias, and Ritter, Helge. 2017. “Hand-Object Interaction Detection with Fully Convolutional Networks”. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 18-25.
Schröder, M., and Ritter, H. (2017). “Hand-Object Interaction Detection with Fully Convolutional Networks” in The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops 18-25.
Schröder, M., & Ritter, H., 2017. Hand-Object Interaction Detection with Fully Convolutional Networks. In The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. pp. 18-25.
M. Schröder and H. Ritter, “Hand-Object Interaction Detection with Fully Convolutional Networks”, The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp.18-25.
Schröder, M., Ritter, H.: Hand-Object Interaction Detection with Fully Convolutional Networks. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. p. 18-25. (2017).
Schröder, Matthias, and Ritter, Helge. “Hand-Object Interaction Detection with Fully Convolutional Networks”. The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 2017. 18-25.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
Dieses Objekt ist durch das Urheberrecht und/oder verwandte Schutzrechte geschützt. [...]
Volltext(e)
Name
paper.pdf
3.25 MB
Access Level
![Open access file OA](https://pub.uni-bielefeld.de/images/access_open.png)
Zuletzt Hochgeladen
2019-09-06T09:18:49Z
MD5 Prüfsumme
11ffb53c4794dd569318ceb9e02bc33f