In many computer vision classification problems, both the error and time characterizes the quality of a decision. We show that such problems can be formalized in the framework of sequential decision-making. If the false positive and false negative error rates are given, the optimal strategy in terms of the shortest average time to decision (number of measurements used) is the Wald's sequential probability ratio test (SPRT). We built on the optimal SPRT test and enlarge its capabilities to problems with dependent measurements. We show how to overcome the requirements of SPRT -(i) a priori ordered measurements and (ii) known joint probability density functions. We propose an algorithm with near optimal time and error rate trade-off, called WaldBoost, which integrates the AdaBoost algorithm for measurement selection and ordering and the joint probability density estimation with the optimal SPRT decision strategy. The WaldBoost algorithm is tested on the face detection problem. The results are superior to the state-of-the-art methods in the average evaluation time and comparable in detection rates.

No abstract

Summary: Our previous experimental research and initial clinical observations regarding the use of N-acetylcysteine in the treatment of ischemic and reperfusion injury in acute myocardial infarction gave rise to a study entitled the Infarct Size Limitation: Acute N-acetylcysteine Defense (ISLAND) trial. Today, this randomized, echocardiographically and angiographically controlled study includes the first 30 patients with a first anterior wall myocardial infarction: Group A (n = 10) consisting of patients with successful recanalization of the infarct-related left anterior descending artery by streptokinase without any further treatment, Group B (n = 10) consisting of patients with failed infarct-related artery recanalization, and Group C (n = 10) comprising patients who had successful streptokinase-induced recanalization of the left anterior descending artery plus N-acetylcysteine administration at a dose of 100 mgkg body weight. The parameters monitored in our study include changes in global and regional left ventricular ejection fraction of the infarct-related segment using echocardiography and, using electrocardiograms and the Wagner QRS scoring system, the amounts of acutely jeopardized and finally infarcted myocardium. In Group A, global left ventricular ejection fraction rose nonsignificantly within 2 weeks from 37.5 ? 9.6% to 38.5 ? 13.8%; it declined significantly in Group B from 36.2 rt 6.1 % to 30.1 6 . 7 % (p < 0.05), while it

Social groups based on friendship or family relations are very common phenomena in human crowds and a valuable cue for a crowd activity recognition system. In this paper we present an algorithm for automatic on-line inference of social groups from observed trajectories of individual people. The method is based on the Social Force Model (SFM)widely used in crowd simulation applications -which specifies several attractive and repulsive forces influencing each individual relative to the other pedestrians and their environment. The main contribution of the paper is an algorithm for inference of the social groups (parameters of the SFM) based on analysis of the observed trajectories through attractive or repulsive forces which could lead to such behaviour. The proposed SFM-based method shows its clear advantage especially in more crowded scenarios where other state-of-the-art methods fail. The applicability of the algorithm is illustrated on an abandoned bag scenario.

Two optical flow estimation problems are addressed: i) occlusion estimation and handling, and ii) estimation from image sequences longer than two frames. The proposed ContinualFlow method estimates occlusions before flow, avoiding the use of flow corrupted by occlusions for their estimation. We show that providing occlusion masks as an additional input to flow estimation improves the standard performance metric by more than 25% on both KITTI and Sintel. As a second contribution, a novel method for incorporating information from past frames into flow estimation is introduced. The previous frame flow serves as an input to occlusion estimation and as a prior in occluded regions, i.e. those without visual correspondences. By continually using the previous frame flow, ContinualFlow performance improves further by 18% on KITTI and 7% on Sintel, achieving top performance on KITTI and Sintel.