Improved object segmentation based on 2D/3D images

Authors:
Seyed Eghbal Ghobadi;Omar Edmond Loepprich;Oliver Lottner;Klaus Hartmann;Wolfgang Weihs;Otmar Loffeld
Affiliations:
University of Siegen, Siegen, Germany;University of Siegen, Siegen, Germany;University of Siegen, Siegen, Germany;University of Siegen, Siegen, Germany;University of Siegen, Siegen, Germany;University of Siegen, Siegen, Germany
Venue:
SPPRA '08 Proceedings of the Fifth IASTED International Conference on Signal Processing, Pattern Recognition and Applications
Year:
2008

Citing 5
Cited 0

Segmentation of Range and Intensity Image Sequences by Clustering

ICIIS '99 Proceedings of the 1999 International Conference on Information Intelligence and Systems
A Time-Of-Flight Depth Sensor - System Description, Issues and Solutions

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 3 - Volume 03
Real-time Hand Pose Recognition Using Low-Resolution Depth Images

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Pattern Recognition and Machine Learning (Information Science and Statistics)

Pattern Recognition and Machine Learning (Information Science and Statistics)
3D head tracking based on recognition and interpolation using a time-of-flight depth sensor

CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper addresses the solution to the problem of object segmentation based on the fusion of 2D/3D images. These images are provided by the novel monocular hybrid 2D/3D vision system which has been implemented at our research center. The proposed segmentation is based on the combination of edge detection and an unsupervised clustering technique. While the former is applied to the high resolution 2D Images, the latter is done based on the low resolution Time-of-Flight images. The experimental results show that the proposed solution improve the object segmentation.