The Guided Image Filter has recently been developed as an edge-preserving smoothing filter. It has proven to be effective in a wide range of applications, including noise reduction, haze removal, image matting, and others. In this paper, we propose an extension of the Guided Image Filter that takes advantage of confidence information associated with the filter input. Sometimes, such confidence information is generated in a preceding estimation stage in the processing pipeline, but is not considered by the classical Guided Image Filter. Taking the example of alpha matting, we show that our confidence aware Guided Image Filter can significantly increase the quality of the filter output with small computational overhead, and under maintenance of its O(N) time complexity.

In this paper we propose an algorithm for image segmentation using graph cuts which can be used to efficiently solve labeling problems on high resolution images or image sequences. The basic idea of our method is to group large homogeneous regions to one single variable. Therefore we combine the appearance and the task specific similarity with Dempster's theory of evidence to compute the basic belief that two pixels/groups will have the same label in the minimum energy state. Experiments on image and video segmentation show that our grouping leads to a significant speedup and memory reduction of the labeling problem. Thus large-scale labeling problems can be solved in an efficient manner with a low approximation loss.

A trend in the computer vision community is observed towards the simultaneous exploitation of color images and depth maps. In this context we propose a novel approach for bi-layer segmentation, whose main contribution is given by the integration of a color classifier based on color sampling, within a depth-based segmentation framework. We have run tests on datasets available online and the outcoming results pointed out the effectiveness of this approach and its suitability for integration in automatic segmentation systems.

BACKGROUND & OBJECTIVES:Mobile heart-lung-machines applied by percutaneous cannulation are mostly used in patients suffering from acute myocardial infarction (AMI). Whether patients with non-coronary reasons for circulatory arrest benefit of percutaneous emergency circulatory support (PECS) in the same way is still unclear.METHODS:We included 22 consecutive patients who were treated by PECS during a registry period of two years. Primary study endpoint was 30-day mortality rate.RESULTS:Circulatory arrest was caused by AMI in 14 patients (64%). The remaining 8 patients suffered from cardiomyopathy/myocarditis, 4; pulmonary embolism, 2; acute pulmonary failure, 1; and tumor lysis syndrome, 1. Revascularization rate was 93% in the AMI group under PECS support. Overall survival rate was 36.4% at one month: it reached 62.5% among non-coronary patients, but only 21.4% in the AMI group (P = 0.02). Weaning was possible by direct heart transplantation in two patients. Additional two patients required implantation of a left ventricular assist device. Pumpless extracorporeal lung assist was used in one case.CONCLUSION:In this small retrospective study percutaneous emergency circulatory support provided sufficient hemodynamic stabilization in emergency situations. One fifth of AMI patients were saved by immediate restoration of circulation and causal treatment when other means of resuscitation failed. Higher survival rates were noted in non-coronary patients.

Introduction: The purpose of our study was to prove the existence of the U wave using. magnetocardiograms (MCGs)Methods: The 31-channel MCGs of 25 healthy volunteers were recorded The onset of the U wave was defined by newly developed spatial con elation analysis, and the end, by different approachesResults: A U wave could be proved in all volunteers In 10 volunteers (heart rate, 57 +/- 19 beats/min) in whom the U wave was found to be separated from the following P wave, the U wave's end could be determined as a threshold value (U wave duration, 310 +/- 24 in In 15 volunteers (heart rate, 70 +/- 38 beats/min), the end of the U waves was concealed by a continuous transition of the U waves into the following P wavesConclusions: The U wave seems to be a regular phenomenon and has a distinct spatiotemporal assembly Crown Copyright (C) 2010 Published by Elsevier Inc All rights reserved

As local correspondence methods alone often do not achieve a sufficient robustness and accuracy, a subsequent refinement stage is commonly employed to improve upon the initial disparity estimates. In recent years, cross bilateral filters have already been successfully applied for this purpose. They do not only smooth the disparity maps but also help to better align the disparity values with the object edges resulting in an improved object segmentation. In this paper, a refinement step based on an extension of a cross bilateral filter is proposed that utilizes explicit reliability information in order to create robust and reliable disparity maps.