Superpixels Generation of RGB-D Images Based on Geodesic Distance

Pan, Xiao; Zhou, Yuanfeng; Liu, Shuwei; Zhang, Caiming

Superpixels Generation of RGB-D Images Based on Geodesic Distance

Files

071-076.pdf (19.63 MB)

Date

2015

Authors

Pan, Xiao
Zhou, Yuanfeng
Liu, Shuwei
Zhang, Caiming

Publisher

The Eurographics Association

Abstract

A novel algorithm for generating superpixels of RGB-D images is presented in this paper. A regular triangular mesh is constructed by the depth and a local geometric features sensitive initialization method is proposed for initializing seeds by a density function. Over-segmentation of the vertices on mesh can be generated by minimizing a new energy function defined by weighted geodesic distance which can be used for measuring the similarity of vertices with color information. At last, superpixels are generated by re-mapping the mesh over-segmentation to 2D image. During energy optimizing, we will check the topology correctness of the superpixels and refine the topology of the superpixels. Experiments on a large RGB-D images database show that the superpixels generated by the new method can adhere to the object boundaries well and outperform the state-of-the-art methods.

        @inproceedings{10.2312:pg.20151284
,
booktitle = {Pacific Graphics Short Papers
},
editor = {Stam, Jos and Mitra, Niloy J. and Xu, Kun
},
title = {{Superpixels Generation of RGB-D Images Based on Geodesic Distance
}},
author = {Pan, Xiao and 
Zhou, Yuanfeng and 
Liu, Shuwei and 
Zhang, Caiming
},
year = {2015
},
publisher = {The Eurographics Association
},
ISBN = {978-3-905674-96-5
},
DOI = {10.2312/pg.20151284
}
}