Details
| Original language | English |
|---|---|
| Pages (from-to) | 19-24 |
| Number of pages | 6 |
| Journal | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Volume | 2 |
| Issue number | 3W2 |
| Publication status | Published - 2 Oct 2013 |
| Event | 2013 ISPRS Workshop on Image Sequence Analysis, ISA 2013 - Antalya, Turkey Duration: 11 Nov 2013 → 11 Nov 2013 |
Abstract
We present an interactive system to manipulate a virtual object by tracking multiple hands in 3D space using a Kinect device. The system segments hand shapes from a captured 3D scene by using depth information and active contours. A hand shape is recognized by a trained naive Bayes classifier, whether it belongs to a palm, a pointing hand form or both hands with simple occlusion. A plane is approximated by using RANSAC for a palm hand form, while a vector from the hand centroid to the fingertip is obtained for a pointing hand form by using ICP as tracking method. A shape of simple occluded two hands is split into a palm and an incomplete pointing hand form, whose missing data is estimated by using PCA. The system works in semi-real time.
Keywords
- 1D signature, Gesture recognition, ICP, Kinect, Multiple object tracking
ASJC Scopus subject areas
- Earth and Planetary Sciences(all)
- Earth and Planetary Sciences (miscellaneous)
- Environmental Science(all)
- Environmental Science (miscellaneous)
- Physics and Astronomy(all)
- Instrumentation
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 2, No. 3W2, 02.10.2013, p. 19-24.
Research output: Contribution to journal › Conference article › Research › peer review
}
TY - JOUR
T1 - Interactive multi-object tracking for virtual object manipulation
AU - Guo, Yibo
AU - Yang, Michael Ying
AU - Rosenhahn, Bodo
PY - 2013/10/2
Y1 - 2013/10/2
N2 - We present an interactive system to manipulate a virtual object by tracking multiple hands in 3D space using a Kinect device. The system segments hand shapes from a captured 3D scene by using depth information and active contours. A hand shape is recognized by a trained naive Bayes classifier, whether it belongs to a palm, a pointing hand form or both hands with simple occlusion. A plane is approximated by using RANSAC for a palm hand form, while a vector from the hand centroid to the fingertip is obtained for a pointing hand form by using ICP as tracking method. A shape of simple occluded two hands is split into a palm and an incomplete pointing hand form, whose missing data is estimated by using PCA. The system works in semi-real time.
AB - We present an interactive system to manipulate a virtual object by tracking multiple hands in 3D space using a Kinect device. The system segments hand shapes from a captured 3D scene by using depth information and active contours. A hand shape is recognized by a trained naive Bayes classifier, whether it belongs to a palm, a pointing hand form or both hands with simple occlusion. A plane is approximated by using RANSAC for a palm hand form, while a vector from the hand centroid to the fingertip is obtained for a pointing hand form by using ICP as tracking method. A shape of simple occluded two hands is split into a palm and an incomplete pointing hand form, whose missing data is estimated by using PCA. The system works in semi-real time.
KW - 1D signature
KW - Gesture recognition
KW - ICP
KW - Kinect
KW - Multiple object tracking
UR - http://www.scopus.com/inward/record.url?scp=85048919649&partnerID=8YFLogxK
U2 - 10.5194/isprsannals-II-3-W2-19-2013
DO - 10.5194/isprsannals-II-3-W2-19-2013
M3 - Conference article
AN - SCOPUS:85048919649
VL - 2
SP - 19
EP - 24
JO - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
JF - ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
SN - 2194-9042
IS - 3W2
T2 - 2013 ISPRS Workshop on Image Sequence Analysis, ISA 2013
Y2 - 11 November 2013 through 11 November 2013
ER -