By Topic

Nonrigid and Articulated Motion Workshop, 1997. Proceedings., IEEE

Date 16-16 June 1997

Filter Results

Displaying Results 1 - 18 of 18
  • Proceedings IEEE Nonrigid and Articulated Motion Workshop

    Publication Year: 1997
    Save to Project icon | Request Permissions | PDF file iconPDF (137 KB)  
    Freely Available from IEEE
  • Author index

    Publication Year: 1997 , Page(s): 145
    Save to Project icon | Request Permissions | PDF file iconPDF (32 KB)  
    Freely Available from IEEE
  • A three-dimensional model of human lip motions trained from video

    Publication Year: 1997 , Page(s): 46 - 53
    Cited by:  Papers (11)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (720 KB)  

    We present a 3D model of human lips and develop a framework for training it from real data. The model starts off with generic physics specified with the finite element method and “learns” the correct physics through observations. The model's physics allow physically-based regularization between sparse observation points and the resulting set of deformations are used to derive the correct physical modes of the model. Preliminary results showing the model's ability to reconstruct lip shapes from sparse data are shown. The resulting model can be used for both analysis and synthesis View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Tracking of persons in monocular image sequences

    Publication Year: 1997 , Page(s): 2 - 9
    Cited by:  Papers (17)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (824 KB)  

    We present an approach to extract quantitative geometric descriptions of the movements of persons by fitting the projection of a 3-dimensional human model to consecutive frames of an image sequence. The kinematics of the human model is given by a homogeneous transformation tree and its body parts are modeled by right-elliptical cones. The proposed approach can determine the values of a varying number of degrees of freedom (DOFs; body joints, position and orientation of the person relative to the camera) according to the application and the kind of image sequence. The determination of the DOFs is understood as an estimation problem which is solved by an iterated extended Kalman filter (IEKF). For this purpose, the human model is augmented by a simple motion model of constant velocity for all DOFs which is used in the prediction step of the IEKF. In the update step both region and edge information is used View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modeling spatial-temporal patterns in facial articulation

    Publication Year: 1997 , Page(s): 54 - 60
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (668 KB)  

    In this paper, a new method of modeling human facial articulation is proposed. The approach contains three major parts: the spatial dimension reduction through principal component analysis; the temporal function approximation using the sample basis function which is similar to the facial articulation process; and the learning algorithm which can improve the recognition and the compression capability. This scheme is also used for encoding facial articulation parameter sequences. Though developed based on FAPS (MPEG4 facial animation parameter set), the algorithm can be easily applied to other parameter representations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Measuring lesion growth from 3D medical images

    Publication Year: 1997 , Page(s): 112 - 119
    Cited by:  Papers (1)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (648 KB)  

    Evaluating precisely the temporal variations of lesion volumes is very important for at least three types of practical applications: pharmaceutical trials, decision making for drug treatment or surgery and patient follow-up. The authors present a volumetric analysis technique, combining precise rigid registration of 3D medical images, nonrigid deformation computation and flowfield analysis. Their analysis technique has two outcomes: the detection of evolving lesions and the quantitative measurement of volume variations. The originality of their approach is that no precise segmentation of the lesion is needed but the approximative designation of a region of interest, which can be automatized. They distinguish between tissue transformation (image intensity changes without deformation) and expansion or contraction effects reflecting a change of mass within the tissue; a real lesion being generally the combination of both effects. The method is tested with synthesized 3D image sequences and applied, in a first attempt to quantify in vivo a mass effect, to the analysis of a patient with multiple sclerosis (MS) View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Estimation of articulated motion using kinematically constrained mixture densities

    Publication Year: 1997 , Page(s): 10 - 17
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (804 KB)  

    We address the problem of articulated posture estimation in its general form. Namely, the recovery of full 3D articulated posture parameters from an uncontrolled scene. Stochastic modeling of low-level segmented image data is unified with models of object kinematic structure through a constrained mixture of observation processes. A modified expectation-maximization algorithm is proposed for this purpose. Early experiments qualitatively demonstrate the efficacy of our approach, and provide a context for integration for more sophisticated image cues View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Global versus structured interpretation of motion: moving light displays

    Publication Year: 1997 , Page(s): 18 - 25
    Cited by:  Papers (7)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (880 KB)  

    Moving light displays (MLDs) have been used extensively to study motion perception and perception of the human gait in particular. MLD perception is largely considered to be structural, i.e., perception depends on identification of human kinematic structure. However, work by Little and Boyd (1996) has shown that it is possible to recognize individual people, from their gaits, by non-structural means. They use global shape-of-motion features derived from optical flow in a sequence of gray-scale images. Our goal is to show that shape-of-motion features can be derived equally well from MLD images as from gray-scale images, and to compare the recent results obtained for shape-of-motion recognition with psychophysical observations about MLD perception. The implication is that non-structural shape-of-motion interpretation of gait can be applied to MLDs, allowing us to interpret significant MLD results in the context of a known algorithm. Our results shed light on the validity of shape-of-motion features from the psychophysical standpoint as well as suggest an alternative approach to understanding MLD perception. In particular we find that characterizing movement in a gait may be treated as the sum of a set of moving points (if this is true then MLD lights need not be placed right at joints). Changes to a subset of the points affect the sum and consequently affect the perception of the whole View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Virtual humans for animation, ergonomics, and simulation

    Publication Year: 1997 , Page(s): 28 - 36
    Cited by:  Papers (8)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1008 KB)  

    The last few years have seen great maturation in the computation speed and control methods needed to portray 3D virtual humans suitable for real interactive applications. We first describe the state of the art, then focus on the particular approach taken at the University of Pennsylvania with the Jack system. Various aspects of real-time virtual humans are considered such as appearance and motion, interactive control, autonomous action, gesture, attention, locomotion, and multiple individuals. The underlying architecture consists of a sense-control-act structure that permits reactive behaviors to be locally adaptive to the environment, and a “PaT-Net” parallel finite-state machine controller that can be used to drive virtual humans through complex tasks. Finally, we argue for a deep connection between language and animation and describe current effects in linking them through the JacMOO extension to lambdaMOO View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Elastic spline models for human cardiac motion estimation

    Publication Year: 1997 , Page(s): 120 - 127
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (748 KB)  

    Elastic splines (including dynamic “snakes” and elastic contours), minimising an energy norm of the membrane and/or thin-plate types, have been used to model many surfaces in visual reconstruction and related biomedical applications. The authors model the displacement of the material between successive cardiac images using vector splines. They define a family of elastic splines. These splines can be tuned to enforce different types and different degrees of smoothness. They assess how well these splines can be used to reconstruct human cardiac motion. The proposed method has been implemented based on MRI projection data View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human motion analysis: a review

    Publication Year: 1997 , Page(s): 90 - 102
    Cited by:  Papers (99)  |  Patents (149)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1100 KB)  

    Human motion analysis is receiving increasing attention from computer vision researchers. This interest is motivated by a wide spectrum of applications, such as athletic performance analysis, surveillance, man-machine interfaces, content-based image storage and retrieval, and video conferencing. The paper gives an overview of the various tasks involved in motion analysis of the human body. The authors focus on three major areas related to interpreting human motion: 1) motion analysis involving human body parts, 2) tracking of human motion using single or multiple cameras, and 3) recognizing human activities from image sequences. Motion analysis of human body parts involves the low-level segmentation of the human body into segments connected by joints, and recovers the 3D structure of the human body using its 2D projections over a sequence of images. Tracking human motion using a single or multiple camera focuses on higher-level processing, in which moving humans are tracked without identifying specific parts of the body structure. After successfully matching the moving human image from one frame to another in image sequences, understanding the human movements or activities comes naturally, which leads to a discussion of recognizing human activities. The review is illustrated by examples View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Frame-based 4D interactive modeling of heart motion

    Publication Year: 1997 , Page(s): 128 - 135
    Cited by:  Patents (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (812 KB)  

    Temporal abnormalities in heart wall motion are important diagnostic indicators of cardiac disease. Limitations in cardiac image quality and resolution necessitate the guidance of an experienced user or clinician to define the inside and outside boundaries of the heart. The authors describe methods for reconstructing the spatio-temporal behavior of the heart from magnetic resonance cine images in an interactive setting. A finite element model of the time-varying geometry, incorporating both spatial and temporal coherence constraints, was fitted to image-derived data by minimising an objective function. Interaction was facilitated by a small number of user controlled “guide points” included in the objective function. A frame-based solution procedure was developed allowing the user to interact with the solution via the position of the guide points. The method was applied to patients imaged shortly after a heart attack (myocardial infarction). The inclusion of temporal coherence in the model allowed the influence of spatial smoothing constraints to be reduced, enabling more accurate description of time-dependent regional variations View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human skin and hand motion analysis from range image sequences using nonlinear FEM

    Publication Year: 1997 , Page(s): 80 - 88
    Cited by:  Papers (10)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1280 KB)  

    We propose new methods for human tissue motion analysis from range image sequences using the nonlinear finite element method (FEM). The approach combines range data, mechanics of human tissues, and dynamics of their motion using nonlinear finite element models. We are able to evaluate the changes in strain distribution over time. Given images at two time instances and their corresponding features, we use FEM to synthesize intermediate images not only of the displacement fields, but also of the strains of the underlying tissues. This results in a physically-based framework for motion and strain analysis. The results from the skin elasticity experiments show promise of detecting differences in elasticity between normal and abnormal tissue. The results from the hand motion experiments indicate the level of strain that could be causing repetitive stress injury (RSI) View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A configuration space approach for efficient animation of human figures

    Publication Year: 1997 , Page(s): 38 - 45
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (824 KB)  

    We propose an efficient method for animation of virtual human models in an environment of obstacles. A nearby target location reachable by a human figure is given and a search is performed in the object space encompassing obstacles to obtain an optimum configuration. The goal is realized by simplifying the configuration space of a human model into two dimensions and then projecting a discretized object space onto it. The discretization is carried out using DDA (digital differential analyzer used in fast line drawing) or high speed frame buffer hardware. Further gains in speed are obtained by precalculating certain basic human configurations and attaining required postures in advance. We discuss walking over obstacles, reaching a given target by hand and a combination of these. The animation of human figures is very efficient permitting real-time performance of multiple human figures View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Dynamic simulation of the jaw and chewing muscles for maxillofacial surgery

    Publication Year: 1997 , Page(s): 104 - 111
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (832 KB)  

    The need for simulation in medical environments increases with the complexity and risks of operations. Exact geometric planning is one of the main problems a surgeon has to deal with. The goal of the authors' research is the development of a graphical simulation of the human mastication system. Therefore, they are developing an integrated model of the jaw by parameterizing the bones (maxilla and mandible) and modeling the motion capabilities as well as the mastication muscles. The main focus of the paper is the introduction of a kinematic model of the temporomandibular joint and modeling of the mastication muscles. The kinematic model describes the geometrical and analytical movement of the jaw by specially defined axes. By modifying the axes or the geometrical model of the mandible, a surgeon can get a first impression of the post-operative result of, for example, a repositioning. Through integration of the muscles and muscle forces, one can even obtain a dynamic simulation of the whole mastication system View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Segmentation of range data for the automatic construction of models of articulated objects

    Publication Year: 1997 , Page(s): 62 - 69
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (676 KB)  

    We consider the problem of automatically constructing geometric models of articulated objects from example range data. The problem of automatic model construction has been investigated in some depth for rigid objects but these do not extend easily to the articulated case. The problem arises because of the need to register surface measurements taken from different viewpoints into a common reference frame. Registration algorithms generally assume that an object does not change shape from one view to the next but when building a model of an articulated object it is necessary for the modes of articulation to be present in the example data. To avoid this problem we propose that raw surface data of articulated objects is first segmented into rigid subsets which correspond to rigid subcomponents of the object. This allows a model of each subcomponent to be constructed using the conventional approach and a final, articulated model to be constructed by assembling each of the subcomponent models View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A 3D optical flow approach to addition of deformable PET volumes

    Publication Year: 1997 , Page(s): 136 - 143
    Cited by:  Papers (5)  |  Patents (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1072 KB)  

    A method for combining datasets from gated cardiac PET acquisitions is described. Optical flow techniques are used to accurately model non-rigid motion present during the cardiac cycle so that a one-to-one mapping is found between each voxel of two gated volumes. Using this mapping, images can be combined to produce a composite dataset with improved statistics and reduced motion induced blur. Like recent past efforts in deformable motion, an image similarity measure is combined with elastic constraints to obtain a valid flow field. Additionally, because of the noisy characteristics of individual reconstructed volumes in a gated PET study, 4D and multiscale techniques were used to obtain more accurate motion estimates. Results using data from gated cardiac studies on canine and human subjects are presented View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The velocity snake

    Publication Year: 1997 , Page(s): 70 - 79
    Cited by:  Papers (10)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (736 KB)  

    We present a new active contour model for boundary tracking and motion estimation of non-rigid objects, which results from applying a velocity control to the class of elastodynamical contour models, known as snakes. The proposed control term is the outcome of an energy dissipation function which measures the difference between the contour velocity and the apparent velocity of the image (optical flow). Treating the image video-sequence as continuous measurements along time, it is shown that the proposed control results in an unbiased tracking, provided the initial contour is sufficiently close to the object boundary. This is in contrast to the original snake model which is proven to be biased due to the image (object) velocity; thus resulting in high sensitivity to clutter and numerical noise. The motion estimation further allows for position prediction of non-rigid boundaries. Based on the proposed control approach, we propose a new class of real time tracking contours, varying from models with batch-mode control estimation to models with real time adaptive controllers. The new tracking scheme was applied to boundary tracking of both rigid and non-rigid objects, resulting in unbiased tracking and robustness to image clutter and numerical noise View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.