2012
DOI: 10.1007/978-3-642-35749-7_24
|View full text |Cite
|
Sign up to set email alerts
|

Generalised Pose Estimation Using Depth

Abstract: Abstract. Estimating the pose of an object, be it articulated, deformable or rigid, is an important task, with applications ranging from HumanComputer Interaction to environmental understanding. The idea of a general pose estimation framework, capable of being rapidly retrained to suit a variety of tasks, is appealing. In this paper a solution is proposed requiring only a set of labelled training images in order to be applied to many pose estimation tasks. This is achieved by treating pose estimation as a clas… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
4
0
1

Year Published

2013
2013
2020
2020

Publication Types

Select...
3
2
1

Relationship

1
5

Authors

Journals

citations
Cited by 7 publications
(5 citation statements)
references
References 10 publications
0
4
0
1
Order By: Relevance
“…To this end, appearance is the only cue we can use to reimplement their methods on our datasets. It is more convenient to compare our method with [14] on our datasets since both of us use binocular cameras in office environment. The difference is that we have 15 classes of hand postures while they have only 3 classes.…”
Section: Methods Comparisonmentioning
confidence: 99%
See 2 more Smart Citations
“…To this end, appearance is the only cue we can use to reimplement their methods on our datasets. It is more convenient to compare our method with [14] on our datasets since both of us use binocular cameras in office environment. The difference is that we have 15 classes of hand postures while they have only 3 classes.…”
Section: Methods Comparisonmentioning
confidence: 99%
“…Many of them think that, even with a low quality disparity map, accurate hand segmentation could still be possible by combining appearance cues [14,15]. However, the perceived color of skin varies significantly depending on the user's skin color and the light condition of background.…”
Section: Introductionmentioning
confidence: 98%
See 1 more Smart Citation
“…Hong et al [47] and Grzeszcuk et al [37] used a stereo camera pair from which they generated depth images which were combined with other cues to build models of the person(s) in the image. Fujimura and Liu [32] and Hadfield and Bowden [38] segmented hands on the naive assumption that hands will be the closest objects to the camera.…”
Section: Tracking Basedmentioning
confidence: 99%
“…Algo muy usual es utilizar diversas cámaras para generar mapas de profundidad. Por ejemplo en [60] Hadfield y Bowden utilizan un sistema de visión estereoscópica (dos cámaras) para segmentar las manos de una persona, utilizando la asunción de que las manos son los objetos más cercanos a las cámaras. En [8] se utiliza un modelo de piel sumado a un sistema de tres cámaras para obtener información de profundidad.…”
Section: Segmentación Y Seguimientounclassified