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.

Download
OA 3.25 MB
Konferenzbeitrag | Veröffentlicht | Englisch
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
Titel des Konferenzbandes
The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops
Seite
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
PUB-ID

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, 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:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Name
3.25 MB
Access Level
OA Open Access
Zuletzt Hochgeladen
2018-01-26T18:43:31Z

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar