We approach the task of human silhouette extraction from color and thermal image sequences using automatic image registration. Image registration between color and thermal images is a challenging problem due to the difficulties associated with finding correspondence. However, the moving people in a static scene provide cues to address this problem. In this paper, we propose a hierarchical schem...

In this paper, we propose spatio-temporal silhouette representations, called silhouette energy image (SEI) and silhouette history image (SHI) to characterize motion and shape properties for recognition of human movements such as human actions, activities in daily life. The SEI and SHI are constructed by using the silhouette image sequence of an action. The span or difference of the end time and...

ABSTRACT Objective To verify the factors associated with perception of current silhouette and body image dissatisfaction in adults obesity. Methods Cross-sectional study derived from baseline a randomized clinical trial. The image, defined by difference between ideal silhouette, were obtained scale that ranged one (smallest silhouette) to nine (largest silhouette). independent variables investi...

Ghost is a real time system for estimating human body posture and detecting body parts in monochromatic imagery. It constructs a silhouette based body model to determine the location of the body parts while people are in generic postures. It combines hierarchical body pose estimation, a convex hull analysis of the silhouette, and a partial mapping from the body parts to the silhouette segments ...

W e address the problem of estimating the structure and motion of a smooth curved object from its silhouettes observed over time by a trinocular imagery. W e first construct a model for the local structure along the silhouette for each frame in the temporal sequence. The local models are then integrated into a global surface description by estimating the motion between successive frames. The al...

Computing Silhouette View Poses Mirror normals are computed from the epipoles, principal point and focal length. These allow the orientations of the virtual cameras to be specified in the reference frame of the real camera. Camera positions are computed using the : a silhouette tangent that passes through an epipole must be tangent to the corresponding point in its projection into the opposite ...

This paper addresses the problem of recovering the 3D shape of a surface of revolution from a single uncalibrated perspective view. The algorithm introduced here makes use of the invariant properties of a surface of revolution and its silhouette to locate the image of the revolution axis, and to calibrate the focal length of the camera. The image is then normalized and rectified such that the r...

Outline shape carries a substantial part of the information present in an object view, and is more economical than classical representations such as geon-structural-descriptions or multiple-views. We demonstrate the utility of silhouette representations for a variety of visual tasks, ranging from basic-level categorization to nding the best view of an object. All these tasks necessitate the com...

OBJECTIVE To investigate the relationship between dietary patterns and self-perceived body shape silhouette and BMI in a sample of Mexican women. DESIGN A cross-sectional analysis of dietary habits from baseline data of a large cohort study (EsMaestra) conducted in 2006-2008. SETTING The state of Veracruz, Mexico. SUBJECTS Mexican teachers (n 20 330) provided information on body shape sil...

An ATR algorithm for low quality imagery is reported. Compact shaped targets are represented by their 2D silhouettes. Associated with each point on the silhouette, there is a direction roughly perpendicular to the local segment of the silhouette. The location of each silhouette point is assumed to be perturbed along that direction. A statistical technique is used to estimate the variance of tha...