Automatic Segmentation of Scanned Human Body Using Curve Skeleton Analysis

Lovato, Christian; Castellani, Umberto; Giachetti, Andrea

doi:10.1007/978-3-642-01811-4_4

Cited by 14 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We apply the method described in [20] providing a smooth and centered connected tree, and also the estimated values computed at the skeletal points. If the legs are not in contact under the knee and arms are not adherent to the trunk under the elbow, this curve skeleton allows the recognition of limbs and of the head without further constraints on subject's pose.…”

Section: Proposed Systemmentioning

confidence: 99%

Robust Automatic Measurement of 3D Scanned Models for the Human Body Fat Estimation

Giachetti

Lovato

Piscitelli

et al. 2015

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

In this paper, we present an automatic tool for estimating geometrical parameters from 3-D human scans independent on pose and robustly against the topological noise. It is based on an automatic segmentation of body parts exploiting curve skeleton processing and ad hoc heuristics able to remove problems due to different acquisition poses and body types. The software is able to locate body trunk and limbs, detect their directions, and compute parameters like volumes, areas, girths, and lengths. Experimental results demonstrate that measurements provided by our system on 3-D body scans of normal and overweight subjects acquired in different poses are highly correlated with the body fat estimates obtained on the same subjects with dual-energy X-rays absorptiometry (DXA) scanning. In particular, maximal lengths and girths, not requiring precise localization of anatomical landmarks, demonstrate a good correlation (up to 96%) with the body fat and trunk fat. Regression models based on our automatic measurements can be used to predict body fat values reasonably well.

show abstract

Section: Proposed Systemmentioning

confidence: 99%

Robust Automatic Measurement of 3D Scanned Models for the Human Body Fat Estimation

Giachetti

Lovato

Piscitelli

et al. 2015

IEEE J. Biomed. Health Inform.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another skeleton‐based segmentation was proposed by Lovato et al . [LCG09], in particular for human bodies and the like. This algorithm incorporates a skeleton extraction method that takes advantage of voxel coding and active contours.…”

Section: Skeleton‐based Segmentationmentioning

confidence: 99%

Part‐Based Mesh Segmentation: A Survey

Rodrigues

Morgado

Gomes

2018

Computer Graphics Forum

View full text Add to dashboard Cite

This paper surveys mesh segmentation techniques and algorithms, with a focus on part‐based segmentation, that is, segmentation that divides a mesh (featuring a 3D object) into meaningful parts. Part‐based segmentation applies to a single object and also to a family of objects (i.e. co‐segmentation). However, we shall not address here chart‐based segmentation, though some mesh co‐segmentation methods employ such chart‐based segmentation in the initial step of their pipeline. Finally, the taxonomy proposed in this paper is new in the sense that one classifies each segmentation algorithm regarding the dimension (i.e. 1D, 2D and 3D) of the representation of object parts. The leading idea behind this survey is to identify the properties and limitations of the state‐of‐the‐art algorithms to shed light on the challenges for future work.

show abstract

“…Given a low resolution and watertight representation of the body, we apply a procedure to obtain a pose estimation and rough segmentation of the mesh through the extraction and labeling of the curve skeleton of the mesh and an optimization step finding a symmetric and reasonable stick figure adapted to the skeleton. The procedure has been described in [9] and consists of extracting a curve skeleton of the mesh with an efficient method based on voxel coding and active contours. Starting from the head salient point extracted on the surface we can compute the shortest path from the farthest inner point and the selected point.…”

Section: Skeletonization and Partitioningmentioning

confidence: 99%

“…The algorithm is able to compute a limited number of external branches of the tree, number that is finally reduced to five with a simple cleaning procedure removing smaller leaves of the skeletal tree. With simple heuristics based on skeletal branches lengths and directions, and a consistency check related to the extracted surface salient points, it is possible to recognize head, trunk and limbs from the skeleton (see [9] for details). Associating then scalar values on the skeleton points (e.g.…”

Section: Skeletonization and Partitioningmentioning

confidence: 99%

Geometrical Processing of 3D Body Scanner Data for Anthropometric Applications

Lovato¹,

Castellani²,

Zancanaro³

et al. 2010

Proceedings of the 1st International Conference on 3D Body Scanning Technologies, Lugano, Switzerland, 19-20 October 2010

Self Cite

View full text Add to dashboard Cite

In this paper we describe a pipeline for the geometric processing of 3D meshes obtained by whole body scanners, aimed at providing support for anthropometric measurements. The output of whole body scanners is a cloud of points, usually transformed in a triangulated mesh through the use of specific algorithms in order to support the 3D visualization of the surface and the extraction of meaningful anthropometric landmarks and measurements. Anthropometric analysis is usually performed by using device specific and closed software solutions provided by scanner manufacturers, and requires often a careful acquisition, with strong constraints on subject pose. This may create problems in comparing data acquired in different places and performing large-scale multi-centric studies as well as in applying advanced shape analysis tools on the captured models. The aim of our work is to overcome these problems by selecting and customizing geometrical processing tools able to create an open and device-independent pipeline for the analysis of body scanner data. We also aim at developing and validating methods to extract automatically feature points, body segments and relevant measurements that can be used in anthropometric and metabolic research. The paper presents a general description of the proposed processing pipeline and the currently developed modules (hole filling, skeleton-based segmentation, heat kernel based landmark location), showing their usefulness in the automatic and computer assisted evaluation of anthropometric data.

show abstract

Automatic Segmentation of Scanned Human Body Using Curve Skeleton Analysis

Cited by 14 publications

References 13 publications

Robust Automatic Measurement of 3D Scanned Models for the Human Body Fat Estimation

Robust Automatic Measurement of 3D Scanned Models for the Human Body Fat Estimation

Part‐Based Mesh Segmentation: A Survey

Geometrical Processing of 3D Body Scanner Data for Anthropometric Applications

Contact Info

Product

Resources

About