Yijun Xiao

A discrete Reeb graph approach for the segmentation of human body scans

Segmentation of 3D human body (HB) scan is a very challenging problem in applications exploiting human scan data. To tackle this problem, we propose a topological approach based on discrete Reeb graph (DRG) which is an extension of the classical Reeb graph to unorganized cloud of 3D points. The essence of the approach is detecting critical nodes in the DRG thus permitting the extraction of branches that represent the body parts. Because the human body shape representation is built upon global topological features that are preserved so long as the whole structure of the human body does not change, our approach is quite robust against noise, holes, irregular sampling, moderate reference change and posture variation. Experimental results performed on real scan data demonstrate the validity of our method.

A functional-based segmentation of human body scans in arbitrary postures

This paper presents a general framework that aims to address the task of segmenting three-dimensional (3-D) scan data representing the human form into subsets which correspond to functional human body parts. Such a task is challenging due to the articulated and deformable nature of the human body. A salient feature of this framework is that it is able to cope with various body postures and is in addition robust to noise, holes, irregular sampling and rigid transformations. Although whole human body scanners are now capable of routinely capturing the shape of the whole body in machine readable format, they have not yet realized their potential to provide automatic extraction of key body measurements. Automated production of anthropometric databases is a prerequisite to satisfying the needs of certain industrial sectors (e.g., the clothing industry). This implies that in order to extract specific measurements of interest, whole body 3-D scan data must be segmented by machine into subsets corresponding to functional human body parts. However, previously reported attempts at automating the segmentation process suffer from various limitations, such as being restricted to a standard specific posture and being vulnerable to scan data artifacts. Our human body segmentation algorithm advances the state of the art to overcome the above limitations and we present experimental results obtained using both real and synthetic data that confirm the validity, effectiveness, and robustness of our approach.

Topological segmentation of discrete human body shapes in various postures based on geodesic distance

This paper extends our previous Reeb graph approach based on a new Morse function, namely geodesic distance, to segment whole body scan data into primary body parts in various postures. Because of the bending invariance of geodesic distance, the resulting Reeb graph can remain stable in a large range of postures. Consequently, the approach is capable of segmenting data within the posture range. The application of geodesic distance also brings the independence of coordinate frame selection. We present a number of experiments conducted on both real body 3D scan samples and simulated datasets to demonstrate the validity of the approach.

Recognition of human body posture from a cloud of 3D data points using wavelet transform coefficients

Addresses the problem of recognizing a human body posture from a cloud of 3D points acquired by a human body scanner. Motivated by finding a representation that embodies a high discriminatory power between posture classes, a new type of feature is suggested, namely the wavelet transform coefficients (WTC) of the 3D data-point distribution projected on to the space of spherical harmonics. A feature selection technique is developed to find those features with high discriminatory power. Integrated within a Bayesian classification framework and compared with other standard features, the WTC showed great capability in discriminating between close postures. The qualities of the WTC features were also reflected in the experimental results carried out with artificially generated postures, where the WTC obtained the best classification rate.

Posture recognition and segmentation from 3D human body scans

This paper addresses the problem of segmenting 3D scan data of human body (HB) into sets corresponding to the HB parts, where the posture of the body is unknown. The approach consists of recognizing first the posture, then exploiting the information retrieved from the posture recognition into the segmentation process. For the recognition, the wavelet transform coefficients are suggested as new 3D shape descriptors. Then segmentation technique integrating the model posture information is presented. The segmentation results are illustrated on human body scans of different postures.

Wavelet moments for recognizing human body posture from 3D scans

This paper addresses the problem of recognizing a human body (HB) posture from a cloud of 3D points acquired by a human body scanner It suggests the wavelet transform coefficients (WTC) as 3D shape descriptors of the HB posture. The WTC showed to have a high discrimination power between posture classes. Integrated within a Bayesian classification framework and compared with other standard moments, the WTC showed great capabilities in discriminating between close postures. The qualities of the WTC features were also reflected on its classification rate, ranked first when compared with other 3D features.

LABELLING OF THREE DIMENSIONAL HUMAN BODY SCANS: A TOPOLOGICAL APPROACH

Whole human body scanners are 3D imaging devices which are capable of capturing a computerized format of whole body shape, thus permitting automatic extraction of the different body measurements. This requires the segmentation of scan data into subsets corresponding to the functional human body parts. Such a task is quite challenging due to the articulated and the deformable aspects of the human body shape. The attempts made so far suffer from various limitations, such as being restricted to standard specific posture and vulnerability to scan data corruption. This paper proposes a general framework that aims towards overcoming these challenges. One of the salient features of this framework is that it can cope with moderate posture variations around the standard posture, in addition of being quite robust against noise, holes and irregular sampling. Experimental results performed on real and synthetic data confirmed the validity, effectiveness and robustness of our framework.