An image is ideally a projection of the 3-D scene. However, the imaging process is always imperfect and constrained by the physical environment. This paper is concerned with image sequences acquired in such situations, the so-called transparency, for example, viewing through a window with reflections. When such situation occurs, the image sequence contains undesirable transparent motion, for ex...

In this paper we present a new method for extracting spatialtemporal features of dynamic gestures. We fully utilize the information of temporal motion and spatial luminance. In the first two consecutive frame the dominant motion model is used to calculate the gesturing motion, then it is combined with the result of static segmentation to segment the gesturing hand or arm from the background. Th...

OBJECT The objectives of this study were to compare the biomechanical effects of five lumbar reconstruction models on the adjacent segment and to analyze the effects of three factors: construct stiffness, sagittal alignment, and the number of fused segments. METHODS Nondestructive flexion-extension tests were performed by applying pure moments to 10 calf spinal (L3-S1) specimens. One-segment ...

We describe a method to segment and depth order motion layers simultaneously in an image sequence. Previous approaches have tended to ignore the depth ordering issue or treat it as a post-processing operation. We argue here that motion estimation and segmentation are crucially dependent on depth order and hence that the latter should form an integral part of any layering scheme. Using an explic...

Segment Cluster Tracking is a new approach of motion analysis in the class of mapping methods/algorithms. It solves the correspondence problem by matching image regions, resp. features of image regions. The image regions are created by combining color segments the result of a color segmentationto segment clusters. The tracking task is to find best correspondences between clusters of segments in...

A smooth surface imaged on the retina produces a smooth flow field. Thus, the visual system may group regions of smoothly varying flow to segment surfaces. We tested this idea by having observers perform a segmentation task on several stimuli that differed in their 3D interpretations but were all matched in the smoothness of their 2D flow fields. Performance varied across conditions with the be...

A smooth surface imaged on the retina produces a smooth flow field. Thus, the visual system may group regions of smoothly varying flow to segment surfaces. We tested this idea by having observers perform a segmentation task on several stimuli that differed in their 3D interpretations but were all matched in the smoothness of their 2D flow fields. Performance varied across conditions with the be...