Skeletal Graphs Research Articles

Learning articulated appearance models for tracking humans: A spectral graph matching approach

Tracking an unspecified number of people in real-time is one of the most challenging tasks in computer vision. In this paper, we propose an original method to achieve this goal, based on the construction of a 2D human appearance model. The general framework, which is a region-based tracking approach, is applicable to any type of object. We show how to specialize the method for taking advantage of the structural properties of the human body. We segment its visible parts by using a skeletal graph matching strategy inspired by the shock graphs. Only morphological and topological information is encoded in the model graph, making the approach independent of the pose of the person, the viewpoint, the geometry or the appearance of the limbs. The limbs labeling makes it possible to build and update an appearance model for each body part. The resulting discriminative feature, that we denote as an articulated appearance model, captures both color, texture and shape properties of the different limbs. It is used to identify people in complex situations (occlusion, field of view exit, etc.), and maintain the tracking. The model to image matching has proved to be much more robust and better-founded than with existing global appearance descriptors, specifically when dealing with highly deformable objects such as humans. The only assumption for the recognition is the approximate viewpoint correspondence between the different models during the matching process. The method does not make use of skin color detection, which allows us to perform tracking under any viewpoint. Occlusions can be detected by the generic part of the algorithm, and the tracking is performed in such cases by means of a particle filter. Several results in complex situations prove the capacity of the algorithm to learn people appearance in unspecified poses and viewpoints, and its efficiency for tracking multiple humans in real-time using the specific updated descriptors. Finally, the model provides an important clue for further human motion analysis process.

Shape-based searching for product lifecycle applications

Estimates suggest that more than 75% of engineering design activity comprises reuse of previous design knowledge to address a new design problem. Reusing design knowledge has great potential to improve product quality, shorten lead time, and reduce cost. However, PLM systems, which address the issue of reuse by searching for keywords in filenames, part numbers or context attached to CAD models, do not provide a robust tool to search reusable knowledge. This paper presents a brief overview of a novel approach to search for 3D models. The system is built on a client–server–database architecture. The client takes in the query input from the user along with his search preferences and passes it to the server. The server converts the shape input into feature vectors and a unique skeletal graph representation. Details of the algorithms to perform these steps are presented here. Principal advantages of our graph representation are: (i) it preserves geometry and topology of the query model, (ii) it is considerably smaller than the B-Rep graph, and (iii) it is insensitive to minor perturbations in shape, but sensitive enough to capture the major features of a shape. The combined distance of feature vectors and skeletal graphs in the database provide an indirect measure of shape similarity between models. Critical database issues such as search system efficiency, semantic gap reduction and the subjectivity of the similarity definition are addressed. This paper reports our initial results in designing, implementing and running the shape search system.

Recognition of shapes by attributed skeletal graphs

In this paper, we propose a framework to address the problem of generic 2-D shape recognition. The aim is mainly on using the potential strength of skeleton of discrete objects in computer vision and pattern recognition where features of objects are needed for classification. We propose to represent the medial axis characteristic points as an attributed skeletal graph to model the shape. The information about the object shape and its topology is totally embedded in them and this allows the comparison of different objects by graph matching algorithms. The experimental results demonstrate the correctness in detecting its characteristic points and in computing a more regular and effective representation for a perceptual indexing. The matching process, based on a revised graduated assignment algorithm, has produced encouraging results, showing the potential of the developed method in a variety of computer vision and pattern recognition domains. The results demonstrate its robustness in the presence of scale, reflection and rotation transformations and prove the ability to handle noise and occlusions.

Photonic band gaps in materials with triply periodic surfaces and related tubular structures

We calculate the photonic band gap of triply periodic bicontinuous cubic structures and of tubular structures constructed from the skeletal graphs of triply periodic minimal surfaces. The effect of the symmetry and topology of the periodic dielectric structures on the existence and the characteristics of the gaps is discussed. We find that the $\mathrm{C}({\mathrm{I}}_{2}\ensuremath{-}{\mathrm{Y}}^{**})$ structure with $\mathrm{Ia}3\ifmmode\bar\else\textasciimacron\fi{}d$ symmetry, a symmetry which is often seen in experimentally realized bicontinuous structures, has a photonic band gap with interesting characteristics. For a dielectric contrast of 11.9 the largest gap is approximately 20% for a volume fraction of the high dielectric material of 25%. The midgap frequency is a factor of 1.5 higher than the one for the (tubular) D and G structures. For a volume fraction of 25% the smallest dielectric contrast required to open a gap for the $\mathrm{C}({\mathrm{I}}_{2}\ensuremath{-}{\mathrm{Y}}^{**})$ structure is 4.5. A gap of width larger than 10% is obtained with dielectric contrasts of 7 and higher.

Skeletal graphs — a new class of perfect graphs

Let S be an arbitrary collection of stars in a graph G such that there is no chain of length <3 joining the centers of (any) two stars in G . We consider the graphs that can be obtained by deleting in a parity graph all the edges of such a set S . These graphs will be called skeletal graphs and we prove that they are strict quasi-parity graphs and hence perfect graphs.

MATURATION OF BONE CENTERS IN HAND AND WRISTOF CHILDREN WITH CHRONIC NUTRITIVE FAILURE&lt;subtitle&gt;Effect of Dietary Supplements of Reconstituted Milk Solids&lt;/subtitle&gt;

AS PREVIOUSLY reported from this clinic, 1 the administration of a dietary supplement of reconstituted milk solids produced a significant increase in the rate of skeletal maturation in children with nutritive and growth failure. The overall increase in rate of skeletal maturation as measured by skeletal age (Todd 2 ) and Red Graph (bone developmental age graph 3 ) was obtained only when the level of supplementation was sufficient to overcome the deficiencies accumulated prior to giving the added milk. In making the assessments, it was noted that the growth response to the milk supplements was not equal in all bone centers. The skeletal growth progress of these children was characterized by a pronounced degree of asymmetry. It seemed of interest, therefore, to determine whether there was a differential utilization of the nutrients contained in the milk supplements by ossification centers in a selected skeletal area. In the present report, an analysis