.png){kind=icon}
.png){kind=icon}
Return
A graph-based technique for semi-supervised segmentation of 3D surfaces
.png){kind=icon}
OA
AI
DOI：10.1016/j.patrec.2012.03.015.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
A wide range of cheap and simple to use 3D scanning devices has recently been introduced in the market. These tools are no longer addressed to research labs and highly skilled professionals, but rather, they are mostly designed to allow inexperienced users to acquire surfaces and whole objects easily and independently. In this scenario, the demand for automatic or semi-automatic algorithms for 3D data processing is increasing. In this paper we address the task of segmenting the acquired surfaces into perceptually relevant parts. Such a problem is well known to be ill-defined both for 2D images and 3D objects, as even with a perfect understanding of the scene, many different and incompatible semantic or syntactic segmentations can exist together. For this reason recent years have seen a great research effort into semi-supervised approaches, that can make use of small bits of information provided by the user to attain better accuracy. We propose a semi-supervised procedure that exploits an initial set of seeds selected by the user. In our framework segmentation happens by propagating part labels over a weighted graph representation of the surface directly derived from its triangulated Fresh. The assignment of each element is driven by a greedy approach that accounts for the curvature between adjacent triangles. The proposed technique does not require to perform edge detection or to fit propagating surfaces and its implementation is very straightforward. Still, despite its simplicity, tests trade on a standard database of scanned 3D objects show its effectiveness even with moderate user supervision. (C) 2012 Elsevier B.V. All rights reserved.
Keywords:
3D segmentation
Directional curvature metric
Greedy label propagation
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.3
Papers:
7.8K
Citations:
1.6W