Search

Visual object tracking is a fundamental component in many computer vision applications. Extracting robust features of object is one of the most important steps in tracking. As trackers, only formulated on RGB data, are usually affected by occlusions, appearance, or illumination variations, we propose a novel RGB-D tracking method based on genetic feature learning in this paper. Our approach addresses feature learning as an optimization problem. As owning the advantage of parallel computing, genetic algorithm (GA) has fast speed of convergence and excellent global optimization performance. At the same time, unlike handcrafted feature and deep learning methods, GA can be employed to solve the problem of feature representation without prior knowledge, and it has no use for a large number of parameters to be learned. The candidate solution in RGB or depth modality is represented as an encoding of an image in GA, and genetic feature is learned through population initialization, fitness evaluation, selection, crossover, and mutation. The proposed RGB-D tracker is evaluated on popular benchmark dataset, and experimental results indicate that our method achieves higher accuracy and faster tracking speed. [ABSTRACT FROM AUTHOR]

The article presents a study which proposes the online object tracking algorithm based on feature grouping. Observed is the grouping of object templates in template base while the variance of the pixels in multiple frames is computed. Results from comparisons indicate that the proposed method is robust to abnormal changes.

When occlusion between multiple objects is common, tracking of multiple objects is a difficult problem. In order to deal with this problem, a novel algorithm to localize and track multi-object on multiple planes is proposed. The foreground is detected by using codebook model. Then, the vanishing points of the vertical direction are computed and this information is used to compute homography matrix induced by multiple planes. Multiple objects are located at multiple planes. Finally, tracking is performed by graph cuts. The algorithm does not require fully camera calibration, and the complexity of the algorithm is reduced. The experimental results show that multiple objects can be tracked reliably and the algorithm has nice robustness to the occlusion in crowed environments. [ABSTRACT FROM AUTHOR]

Objective To evaluate the marginal microleakage of porcelain-fused-to-metal crown using four diffe-rent cements. Methods Sixteen porcelain-fused-to-metal crowns were built and randomly divided into 4 group, luted onto standard prepared human forward molars using four different cements (glass ionomer cement, resin-modified glass ionomer cement, PanaviaF, Super-Bond C&B adhesive luting system). After temperature cycling test, all the crowns were then submerged in 2% fuchsin for 24 h. The marginal microleakage at tooth cement interfaces was observed using light stereomicroscopy and evaluated in classification index. The marginal microleakage grade of 4 groups were analyzed by SPSS 13.0. Results The PanaviaF demonstrated the least marginal microleakage, Super-Bond C&B adhesive luting system, resin-modified glass ionomer cement showed an intermediate level of marginal microleakage, glass iono-mer cement was associated with severe marginal microleakage (total, %2=157.60, P<0.01; among the different groups, P<0.05). Conclusion Adhesive resin luting system which is the first selection in clinical is better than glass ionomer cement and is good at porcelain-fused-to-metal crown. [ABSTRACT FROM AUTHOR]

Aim: To establish a reversible porcine model of acute liver failure (ALF) and treat it with an artificial liver system., Methods: Sixteen pigs weighing 30-35 kg were chosen and administered with acetaminophen (APAP) to induce ALF. ALF pigs were then randomly assigned to either an experimental group ( n = 11), in which a treatment procedure was performed, or a control group ( n = 5). Treatment was started 20 h after APAP administration and continued for 8 h. Clinical manifestations of all animals, including liver and kidney functions, serum biochemical parameters and survival times were analyzed., Results: Twenty hours after APAP administration, the levels of serum aspartate aminotransferase, total bilirubin, creatinine and ammonia were significantly increased, while albumin levels were decreased ( P < 0.05). Prothrombin time was found to be extended with progression of ALF. After continuous treatment for 8 h (at 28 h), aspartate aminotransferase, total bilirubin, creatinine, and ammonia showed a decrease in comparison with the control group ( P < 0.05). A cross-section of livers revealed signs of vacuolar degeneration, nuclear fragmentation and dissolution. Concerning survival, porcine models in the treatment group survived for longer times with artificial liver system treatment ( P < 0.05)., Conclusion: This model is reproducible and allows for quantitative evaluation of new liver systems, such as a bioartificial liver. The artificial liver system (ZHJ-3) is safe and effective for the APAP-induced porcine ALF model., Competing Interests: Conflict-of-interest statement: The authors declare no conflicts of interest.

Objective: To evaluate the marginal microleakage of porcelain-fused-to-metal crown using four different cements., Methods: Sixteen porcelain-fused-to-metal crowns were built and randomly divided into 4 group, luted onto standard prepared human forward molars using four different cements (glass ionomer cement, resin-modified glass ionomer cement, PanaviaF, Super-Bond C&B adhesive luting system). After temperature cycling test, all the crowns were then submerged in 2% fuchsin for 24 h. The marginal microleakage at tooth cement interfaces was observed using light stereomicroscopy and evaluated in classification index. The marginal microleakage grade of 4 groups were analyzed by SPSS 13.0., Results: The PanaviaF demonstrated the least marginal microleakage, Super-Bond C&B adhesive luting system, resin-modified glass ionomer cement showed an intermediate level of marginal microleakage, glass ionomer cement was associated with severe marginal microleakage (total, Chi2 = 157.60, P < 0.01; among the different groups, P<0.05)., Conclusion: Adhesive resin luting system which is the first selection in clinical is better than glass ionomer cement and is good at porcelain-fused-to-metal crown.