Improved Object Segmentation based on 2D/3D Images

S.E. Ghobadi, O.E. Loepprich, O. Lottner, K. Hartmann, W. Weihs, and O. Loffeld (Germany)


Segmentation, 2D/3D Images, K-Means, Expectation Maximization, Edge Detection


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 com bination of edge detection and an unsupervised clustering technique. While the former is applied to the high resolu tion 2D Images, the latter is done based on the low resolu tion Time-of-Flight images. The experimental results show that the proposed solution improve the object segmentation.

Important Links:

Go Back