Real-time Hand Pose Recognition Using Low-Resolution Depth Images

Authors:
Zhenyao Mo;Ulrich Neumann
Affiliations:
University of Southern California;University of Southern California
Venue:
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Year:
2006

Citing 0
Cited 10

Feature alignment approach for hand posture recognition based on curvature scale space

Neurocomputing
Robust hand detection for augmented reality interface

Proceedings of the 8th International Conference on Virtual Reality Continuum and its Applications in Industry
Improved object segmentation based on 2D/3D images

SPPRA '08 Proceedings of the Fifth IASTED International Conference on Signal Processing, Pattern Recognition and Applications
Sign recognition using constrained optimization

ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
American sign language recognition with the kinect

ICMI '11 Proceedings of the 13th international conference on multimodal interfaces
Hand pose estimation and hand shape classification using multi-layered randomized decision forests

ECCV'12 Proceedings of the 12th European conference on Computer Vision - Volume Part VI
Connecting users to virtual worlds within MPEG-V standardization

Image Communication
Generalised pose estimation using depth

ECCV'10 Proceedings of the 11th European conference on Trends and Topics in Computer Vision - Volume Part I
Model-based hand pose estimation via spatial-temporal hand parsing and 3D fingertip localization

The Visual Computer: International Journal of Computer Graphics
Octree segmentation based calling gesture recognition for elderly care robot

Proceedings of the 8th International Conference on Ubiquitous Information Management and Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gesture recognition methods based on intensity or color images often suffer from low efficiency and lack of robustness. In this paper, we employ a new laser-based camera that produces reliable low-resolution depth images at video rates. By decomposing and recognizing hand poses as finger states (finger poses and finger inter-relations), we achieve robust hand pose recognition in real-time (30 frames/second).