Background foreground segmentation with RGB-D Kinect data: An efficient combination of classifiers

Low cost RGB-D cameras such as the Microsoft’s Kinect or the Asus’s Xtion Pro are completely changing the computer vision world, as they are being successfully used in several applications and research areas. Depth data are particularly attractive and suitable for applications based on moving objects detection through foreground/background segmentation approaches; the RGB-D applications proposed in literature employ, in general, state of the art foreground/background segmentation techniques based on the depth information without taking into account the color information. The novel approach that we propose is based on a combination of classifiers that allows improving background subtraction accuracy with respect to state of the art algorithms by jointly considering color and depth data. In particular, the combination of classifiers is based on a weighted average that allows to adaptively modifying the support of each classifier in the ensemble by considering foreground detections in the previous frames and the depth and color edges. In this way, it is possible to reduce false detections due to critical issues that can not be tackled by the individual classifiers such as: shadows and illumination changes, color and depth camouflage, moved background objects and noisy depth measurements. Moreover, we propose, for the best of the author’s knowledge, the first publicly available RGB-D benchmark dataset with hand-labeled ground truth of several challenging scenarios to test background/foreground segmentation algorithms.

Improving accuracy and speed of optimum-path forest classifier using combination of disjoint training subsets

The Optimum-Path Forest (OPF) classifier is a recent and promising method for pattern recognition, with a fast training algorithm and good accuracy results. Therefore, the investigation of a combining method for this kind of classifier can be important for many applications. In this paper we report a fast method to combine OPF-based classifiers trained with disjoint training subsets. Given a fixed number of subsets, the algorithm chooses random samples, without replacement, from the original training set. Each subset accuracy is improved by a learning procedure. The final decision is given by majority vote. Experiments with simulated and real data sets showed that the proposed combining method is more efficient and effective than naive approach provided some conditions. It was also showed that OPF training step runs faster for a series of small subsets than for the whole training set. The combining scheme was also designed to support parallel or distributed processing, speeding up the procedure even more. © 2011 Springer-Verlag.

A review on the combination of binary classifiers in multiclass problems

Several real problems involve the classification of data into categories or classes. Given a data set containing data whose classes are known, Machine Learning algorithms can be employed for the induction of a classifier able to predict the class of new data from the same domain, performing the desired discrimination. Some learning techniques are originally conceived for the solution of problems with only two classes, also named binary classification problems. However, many problems require the discrimination of examples into more than two categories or classes. This paper presents a survey on the main strategies for the generalization of binary classifiers to problems with more than two classes, known as multiclass classification problems. The focus is on strategies that decompose the original multiclass problem into multiple binary subtasks, whose outputs are combined to obtain the final prediction.

A novel MAP-MRF approach for multispectral image contextual classification using combination of suboptimal iterative algorithms

In this paper we present a novel approach for multispectral image contextual classification by combining iterative combinatorial optimization algorithms. The pixel-wise decision rule is defined using a Bayesian approach to combine two MRF models: a Gaussian Markov Random Field (GMRF) for the observations (likelihood) and a Potts model for the a priori knowledge, to regularize the solution in the presence of noisy data. Hence, the classification problem is stated according to a Maximum a Posteriori (MAP) framework. In order to approximate the MAP solution we apply several combinatorial optimization methods using multiple simultaneous initializations, making the solution less sensitive to the initial conditions and reducing both computational cost and time in comparison to Simulated Annealing, often unfeasible in many real image processing applications. Markov Random Field model parameters are estimated by Maximum Pseudo-Likelihood (MPL) approach, avoiding manual adjustments in the choice of the regularization parameters. Asymptotic evaluations assess the accuracy of the proposed parameter estimation procedure. To test and evaluate the proposed classification method, we adopt metrics for quantitative performance assessment (Cohen`s Kappa coefficient), allowing a robust and accurate statistical analysis. The obtained results clearly show that combining sub-optimal contextual algorithms significantly improves the classification performance, indicating the effectiveness of the proposed methodology. (C) 2010 Elsevier B.V. All rights reserved.

Digital subtraction radiographic analysis of the combination of bioabsorbable membrane and bovine morphogenetic protein pool in human periodontal infrabony defects

OBJECTIVES: This study assessed the bone density gain and its relationship with the periodontal clinical parameters in a case series of a regenerative therapy procedure. MATERIAL AND METHODS: Using a split-mouth study design, 10 pairs of infrabony defects from 15 patients were treated with a pool of bovine bone morphogenetic proteins associated with collagen membrane (test sites) or collagen membrane only (control sites). The periodontal healing was clinically and radiographically monitored for six months. Standardized pre-surgical and 6-month postoperative radiographs were digitized for digital subtraction analysis, which showed relative bone density gain in both groups of 0.034 ± 0.423 and 0.105 ± 0.423 in the test and control group, respectively (p>0.05). RESULTS: As regards the area size of bone density change, the influence of the therapy was detected in 2.5 mm² in the test group and 2 mm² in the control group (p>0.05). Additionally, no correlation was observed between the favorable clinical results and the bone density gain measured by digital subtraction radiography (p>0.05). CONCLUSIONS: The findings of this study suggest that the clinical benefit of the regenerative therapy observed did not come with significant bone density gains. Long-term evaluation may lead to a different conclusions.

A Comparison of Bimatoprost 0.03% Versus the Fixed-Combination of Latanotoprost 0.005% and Timolol 0.5% in Adult Patients With Elevated Intraocular Pressure: An Eight-Week, Randomized, Open-Label Trial

Introduction and Purpose: Bimatoprost and the fixed combination of latanoprost with timolol maleate are 2 medications widely used to treat glaucoma and ocular hypertension (OHT). The aim of the study is to compare the efficacy of these 2 drugs in reducing intraocular pressure (IOP) after 8 weeks of treatment in patients with primary open angle glaucoma (POAG) or OHT. Methods: In this randomized, open-label trial, 44 patients with POAG or OHT were allocated to receive either bimatoprost (1 drop QD) or latanoprost/timolol (1 drop QD). Primary outcome was the mean diurnal IOP measurement at the 8th week, calculated as the mean IOP measurements taken at 8:00 AM, 10: 00 AM, and 12: 00 PM Secondary outcomes included the baseline change in IOP measured 3 times a day, after the water-drinking test (performed after the last IOP measurement), and the assessment of side effects of each therapy. Results: The mean IOP levels of latanoprost/timolol (13.83, SD = 2.54) was significantly lower than of bimatoprost (16.16, SD = 3.28; P < 0.0001) at week 8. Also, the change in mean IOP values was significantly higher in the latanoprost/timolol group at 10:00 AM (P = 0.013) and 12:00 PM (P = 0.01), but not at 8: 00 AM (P = ns). During the water-drinking test, there was no signifi cant difference in IOP increase (absolute and percentage) between groups; however, there was a signifi cant decrease in mean heart rate in the latanoprost/timolol group. Finally, no signifi cant changes in blood pressure and lung spirometry were observed in either groups. Conclusions: The fixed combination of latanoprost/timolol was significantly superior to bimatoprost alone in reducing IOP in patients with POAG or OHT. Further studies with large sample sizes should be taken to support the superior efficacy of latanoprost/timolol, as well as to better assess its profile of side effects.

Selection of new glass-forming compositions in Al-La system using a combination of topological instability and thermodynamic criteria

A combination of an extension of the topological instability ""lambda criterion"" and a thermodynamic criterion were applied to the Al-La system, indicating the best range of compositions for glass formation. Alloy compositions in this range were prepared by melt-spinning and casting in an arc-melting furnace with a wedge-section copper mold. The GFA of these samples was evaluated by X-ray diffraction, differential scanning calorimetry and scanning electron microscopy. The results indicated that the gamma* parameter of compositions with high GFA is higher, corresponding to a range in which the lambda parameter is greater than 0.1, which are compositions far from Al solid solution. A new alloy was identified with the best GFA reported so far for this system, showing a maximum thickness of 286 mu m in a wedge-section copper mold. Crown Copyright (C) 2009 Published by Elsevier B.V. All rights reserved.

Combination of an anaerobic process with O(3), UV and O(3)/UV for cellulose pulp bleaching effluent treatment

Recent studies have shown that partial oxidation by advanced oxidation processes (AOP) is able to transform hard-to-degrade compounds and increase their biodegradability. In this work, anaerobic treatment was followed by ozonation, UV radiation and ozonation in the presence of UV radiation, to treat bleaching effluents from a cellulose kraft Pulp plant. The anaerobic reactor (horizontal anaerobic immobilized Sludge bed, HAISB) was Used as a pretreatment to reduce the efficient organic load before applying ACIP. The ozone treatments were applied in three different pH environments (3, 8 and 10) with retention times of 10, 30, 45 and 60 min. COD and adsorbable organic halogens (AOX) removal efficiencies at the HAISB were approximately 50%, while the BOD removal efficiency reached 80%. Ozonation promoted further removal of AOX and COD so that the combined efficiency reached 96% for AOX and 70% for COD. In the oxidation process, BOD was either removed in small quantities or actually increased, as intended, so that a second biological treatment would be able to complete the treatment. The maximum increase in the BOD(5)/COD ratio (biodegradability indicator) Occurred at pH 8, reaching 104% for ozonation at a dosage of 1540 mg(O3).L(-1). Applying UV radiation alone resulted in lower values: a 34% increase ill the BOD(5)/COD ratio and a 76% AOX removal efficiency. These results indicate that the combination of anaerobic treatment with ozonation or ozonation/UV radiation improves the treatability of cellulose pulp bleaching efficients and that the resulting wastewater is suitable for further biological treatment under aerobic conditions with a low level of toxic compounds from the halogenated family.

Transient and Steady-State Analysis of the Affine Combination of Two Adaptive Filters

In this paper, we propose an approach to the transient and steady-state analysis of the affine combination of one fast and one slow adaptive filters. The theoretical models are based on expressions for the excess mean-square error (EMSE) and cross-EMSE of the component filters, which allows their application to different combinations of algorithms, such as least mean-squares (LMS), normalized LMS (NLMS), and constant modulus algorithm (CMA), considering white or colored inputs and stationary or nonstationary environments. Since the desired universal behavior of the combination depends on the correct estimation of the mixing parameter at every instant, its adaptation is also taken into account in the transient analysis. Furthermore, we propose normalized algorithms for the adaptation of the mixing parameter that exhibit good performance. Good agreement between analysis and simulation results is always observed.

Stress cracking and photodegradation behavior of polycarbonate. The combination of two major causes of polymer failure

This work investigates the effects of photodegradation on the environmental stress cracking resistance of polycarbonate (PC). Injection molded samples were exposed to the ultraviolet (UV) light for various times in the laboratory prior to solvent contact. The bars were then stressed with two different loads in a tensile testing machine under the presence of ethanol. During this period, the stress relaxation was monitored and, after unloading, the ultimate properties were evaluated. Complementary tests were done by size exclusion chromatography, UV-visible spectroscopy, scanning electron microscopy, and light microscopy. The results indicated that ethanol causes significant modification in PC, with extensive surface crazing as well as reduction in mechanical properties. The previous degraded samples showed a higher level of stress relaxation and a greater loss in tensile strength in comparison with the undegraded ones. The synergist action of photodegradation and stress cracking in PC may be a consequence of the chemical changes caused by oxidation.

Re-description and new combination of five New World species of Chrysotus Meigen, with comments on the Neotropical genus Lyroneurus Loew (Diptera: Dolichopodidae)

Five New World species of Chrysotus Meigen are redescribed, four of them herein transferred from Diaphorus Meigen: C. angustifrons (Robinson), comb.nov., C. maculatus (Parent), comb.nov. (= D. maculipennis Robinson), C. robustus(Robinson), comb. nov., C. spectabilis (Loew) and C. wirthi (Robinson), comb. nov. The female of C. maculatus is described for the first time. Terminalia of both males and females are illustrated. The previous suggestion that C. angustifrons, C. robustus, C. wirthi, and C. spectabilis and the Neotropical genus Lyroneurus Loew are closely related based on wing venation similarities is analyzed and rejected.

Bleeding patterns and menstrual-related symptoms with the continuous use of a contraceptive combination of ethinylestradiol and drospirenone: a randomized study

Background: The objective of this study was to compare bleeding patterns of women using a contraceptive combination of 30 mcg ethinylestradiol (EE) and 3 mg drospirenone (DRSP) continuously or cyclically. Menstrual-related symptoms were also evaluated. Study Design: This open, prospective, randomized study evaluated 78 women using the EE/DRSP combination continuously for 168 days or for six 28-day cycles, each followed by a 7-day hormone-free interval. A diary with pre-established scales was used to assess the frequency and intensity of bleeding and menstrual-related symptoms. Results: Amenorrhea increased with continuous use; 62.2% of women with continuous use were amenorrheic at the end of treatment (95% CI: 46.6-77.8%). Dysmenorrhea, headache, acne, nausea, edema and increased appetite improved significantly in the continuous-use group, and mastalgia and edema in the cyclic-use group (p<.05). Six subjects in the continuous-use group (15.4%) and three in the cyclic-use group (7.7%) discontinued due to adverse events. Conclusions: Continuous use was associated with amenorrhea and fewer menstrual-related symptoms compared to cyclic use. (C) 2010 Elsevier Inc. All rights reserved.

Effect of a continuous regimen of contraceptive combination of ethinylestradiol and drospirenone on lipid, carbohydrate and coagulation profiles

Background: The objective of this study was to evaluate the effects of a contraceptive pill containing ethinylestradiol (30 mcg) and drospirenone (3 mg) in a continuous regimen on lipid, carbohydrate and coagulation parameters. Study Design: This open, prospective, randomized study included 78 participants (mean age 27.8 years) who were randomized into two groups to use the pill continuously for 168 days or for six 28-day cycles with a 7-day hormone-free interval between cycles. Markers of lipid, carbohydrate and coagulation profiles were measured prior to initiation and after the 6 months of pill use. Results: No statistically significant differences were found between the two contraceptive regimens with respect to carbohydrate or lipid profiles or in the parameters related to coagulation. Conclusions: The contraceptive combination of ethinylestradiol and drospirenone used in a continuous regimen was associated with metabolic alterations similar to those found during the traditional cyclic regimen of oral contraceptive use. (C) 2010 Elsevier Inc. All rights reserved.