Estimating Player Positions from Padel High-Angle Videos: Accuracy Comparison of Recent Computer Vision Methods

The estimation of player positions is key for performance analysis in sport. In this paper, we focus on image-based, single-angle, player position estimation in padel. Unlike tennis, the primary camera view in professional padel videos follows a de facto standard, consisting of a high-angle shot at about 7.6 m above the court floor. This camera angle reduces the occlusion impact of the mesh that stands over the glass walls, and offers a convenient view for judging the depth of the ball and the player positions and poses. We evaluate and compare the accuracy of state-of-the-art computer vision methods on a large set of images from both amateur videos and publicly available videos from the major international padel circuit. The methods we analyze include object detection, image segmentation and pose estimation techniques, all of them based on deep convolutional neural networks. We report accuracy and average precision with respect to manually-annotated video frames. The best results are obtained by top-down pose estimation methods, which offer a detection rate of 99.8% and a RMSE below 5 and 12 cm for horizontal/vertical court-space coordinates (deviations from predicted and ground-truth player positions). These results demonstrate the suitability of pose estimation methods based on deep convolutional neural networks for estimating player positions from single-angle padel videos. Immediate applications of this work include the player and team analysis of the large collection of publicly available videos from international circuits, as well as an inexpensive method to get player positional data in amateur padel clubs.

A Framework for Automatic Recognition of Cell Damage on Microscopic Images using Artificial Neural Networks

Despite several technological advances in the past years, the vast majority of microscopy examinations continue to be performed in a very laborious, time-consuming manner, requiring highly experienced personnel to spend several hours to visually examine each microscope slide. Due to recent improvements in modern Digital Image Processing, professionals that work on microscopic exams could benefit from new tools that can apply image processing possibilities to their specific field. We propose a framework consisting of an image segmentation stage, feature extraction, and then a Shallow Neural Network related to human perception. The framework is used to classify among 5 types of animal cell damage analyzed in a case study. The case study used applies the Single Cell Gel Electrophoresis assay (SCGE, also known as comet assay) to the cells of land mollusk Helix aspersa in order to measure the DNA damage caused by mutagenic agents. To train and analyze the performance of our approach, we used a dataset manually segmented by a biologist and comprised of 130 slide samples with labeled cells. Our framework proved to be robust, achieving an average accuracy of 88.3%.

Effect of ethanol on proteolysis in isolated liver cells

Ethanol, when tested alone, inhibited proteolysis by about 20%; however, no effect was detected when it was combined with exogenous oxidizable fuels which inhibited proteolysis by themselves. Ethanol was effective in inhibiting proteolysis in the presence of protease inhibitors like ammonia, leupeptin or methylamine, indicating that its mechanism of action involves a non-lysosomal pathway of degradation. Ethanol oxidation is mandatory for it to have effect on proteolysis, however, its action is not related to an increased state of reduction of the NAD system. In contrast to other reductants of the NAD system, ethanol effect is accompanied by a rise in the phosphorylation state of the adenine nucleotides, suggesting that its action might be related to the cellular energy state.

Acute effects of ethanol in the control of protein synthesis in isolated rat liver cells

The acute effect of ethanol on hepatic protein synthesis is a rather controversial issue. In view of the conflicting reports on this subject, the effect of ethanol on protein labeling from L-[3H]valine in isolated liver cells was studied under a variety of experimental conditions. When tracer doses of the isotope were utilized, ethanol consistently decreased the rate of protein labeling, regardless of the metabolic conditions of the cells. This inhibition was not prevented by doses of 4-methylpyrazole large enough to abolish all the characteristic metabolic effects of ethanol, and it was not related to perturbations on the rates of L-valine transport and/or proteolysis. When ethanol was tested in the presence of saturating doses of L-[3H]valine no effect on protein labeling was observed. These observations suggest that the ethanol effect in decreasing protein labelling from tracer doses of the radioactive precursor does not reflect variations in the rate of protein synthesis but reflects changes in the specific activity of the precursor. These changes probably are secondary to variations in the dimensions of the amino acid pool utilized for protein synthesis. Even though it showed a lack of effect when tested alone, in the presence of saturating doses of the radioactive precursor ethanol inhibited the stimulatory effects on protein synthesis mediated by glucose and several gluconeogenic substrates. This effect of ethanol was not prevented by inhibitors of alcohol dehydrogenase, indicating that a shift of the NAD system to a more reduced state is not the mediator of its action. It is suggested that ethanol probably acted by changing the steady-state levels of some common effector(s) generated from the metabolism of all these fuels or else by preventing the inactivation of a translational repressor.