Automatic player position detection in basketball games

This paper presents us with a framework for the automatic player position detection (APPD) in the game of basketball. Court players are detected in the images broadcasted via television stations. In them, at any point of time, the view is from only one camera. This makes the detection process much more difficult. The player detection is based on the mixture of non-oriented pictorial structures. The detection of body parts is performed by the Support Vector Machine (SVM) algorithm. The results of these detections are combined together with constraints on their locations, which specify the position of one body part with respect to the parent body part. In order to train the whole model, we used a latent form of SVM called the latent SVM (LSVM). Such approach generated the statistical accuracy of about 82 %, which represents one of the best results in basketball player detection framework. Beside players, the algorithm detected a certain number of false positive objects. These are mostly people from the audience and the referees as well. This paper contains a simple and robust solution to remove them all, based on the play court boundaries and the histogram comparison. Separating players in different teams is done by k-means clustering. The inputs to this algorithm are saturation histograms calculated on the jerseys. A spatial transformation is determined by the detected play court boundaries and the actual court measures. Using this transformation, points representing the location of detected players in TV images are mapped to the actual location of players on the court, which was the main goal of our research. The proposed solution is sound and efficient. In addition, it is backed up by the experimental results obtained using the model of the actual footage of basketball games.     

Synergistic toughening and electrical functionalization of an epoxy using MWCNTs and silane- /plasma-activated basalt fibers

This work studied the effects of adding short basalt fibers (BFs) and multi-walled carbon nanotubes (MWCNTs), both separately and in combination, on the mechanical properties, fracture toughness, and electrical conductivity of an epoxy polymer. The surfaces of the short BFs were either treated using a silane coupling agent or further functionalized by atmospheric plasma to enhance the adhesion between the BFs and the epoxy. The results of a single fiber fragmentation test demonstrated a significantly improved BF/epoxy adhesion upon applying the plasma treatment to the BFs. This resulted in better mechanical properties and fracture toughness of the composites containing the plasma-activated BFs. The improved BF/epoxy adhesion also affected the hybrid toughening performance of the BFs and MWCNTs. In particular, synergistic toughening effects were observed when the plasma-activated BFs/MWCNTs hybrid modifiers were used, while only additive toughening effects occurred for the silane-sized BFs/MWCNTs hybrid modifiers. This work demonstrated a potential to develop strong, tough, and electrically conductive epoxy composites by adding hybrid BF/MWCNT modifiers.     

A local modulus analysis of rapid crack propagation in polymers

This work is concerned with the analysis of rapid crack propagation (RCP) in Polymethylmethacrylate (PMMA), Polycarbonate (PC) and two-layer PMMA/PC systems. Remarkably constant crack speeds were observed, and higher crack speeds corresponded to the higher preloads. Uniform fracture surfaces were associated with these constant speed RCPs. An indirect method was used to characterise dynamic fracture properties of the materials. The method relies on the recorded crack length histories and boundary conditions which are incorporated in a dynamic Finite Element (FE) code to generate the crack resistance (G _ID). The numerical simulation of the constant speed RCPs generated highly scattered G _ID data. Very large variations of the computed G _ID with the crack length did not correspond to fracture surface appearances. Geometry dependent and multivalued crack resistance results with respect to the crack speed cast doubt on the uniqueness of G _ID. In this work, attempts were made to overcome these difficulties by exploring the concept that the anomalies arise from large local strains around the rapidly moving crack tip, resulting in the crack seeing a low local modulus. It is demonstrated that the critical source of error on the analysis of RCP, is the improper linear elastic representation of the material behaviour around the propagating crack tip. Since the parameters describing the behaviour of the materials near the propagating crack tip were unknown, local non-linear effects were approximated by a local low modulus strip along the prospective crack path. The choice of the local modulus was justified by measurements of the strain histories along the crack path during RCP. The local strip low modulus model generated a larger amount of the kinetic energy in the sample and the crack resistance was reduced compared to results from the single constant modulus approach. Most importantly, G _ID data were nearly independent of the crack length, crack speed and the specimen size. This local modulus concept was also successfully applied to the analysis of RCP in the duplex specimen configuration.     

[2.2]Paracyclophane as a Target of the Organic Solid State: Emergent Properties via Supramolecular Construction

In this account, we review the synthesis of [2.2]paracyclophanes in the organic solid state. Reactions in crystalline solids provide a means to obtain molecules with high degrees of stereocontrol that can also be unattainable in solution. We show that [2.2]paracyclophanes form in the solid state stereospecifically and in quantitative yield via intermolecular [2+2] double photodimerization reactions. The double cycloaddition that affords a paracyclophane in the solid state does not readily occur in solution. Small molecules in the form of hydrogen-bond-donor templates can provide access to [2.2]paracyclophanes in a solid by design. A [2.2]paracyclophane obtained using a hydrogen-bond template is shown to exhibit attractive optical properties and has been employed as a building block of a metal-organic framework (MOF).     

Visual Target Localization with the Spincopter

The goal of the Spincopter project was to design an energy efficient aircraft capable of autorotation glide that could be used for both indoor and outdoor surveillance. This paper demonstrates how to utilize the self-rotating capability of the Spincopter in order to acquire a 3D image of its environment and localize predefined object(s). The omnidirectional capabilities of such an UAV extends the otherwise very limited field of view of conventional cameras usually used for aerial photography and surveillance. The paper presents the theoretical background and the actual implementation of such a system. It presents the resulting images and offers a brief survey of the image quality.     

Prediction of diesel fuel cold properties using artificial neural networks

In this paper, two neural networks, multilayer perceptron and networks with radial-basis function, were used to predict important cold properties of commercial diesel fuels, namely cloud point and cold filter plugging point. The developed models predict the named properties using cetane number, density, viscosity, contents of total aromatics, and distillation temperatures at 10, 50, and 90 vol. % recovery as input data. The training algorithms, number of hidden layer neurons, and number of training data points were optimized in order to obtain a model with optimal predictive ability. The results indicated better prediction of cloud and cold filter plugging points in the case of multilayer perceptron networks. The obtained absolute error mean for the optimal neural network models (0.58°C for the cloud point and 1.46°C for the cold filter plugging point) are within the range of repeatability of standard cold properties determination methods.     

Relay-based critical point estimation of a process with the PID controller in the loop

The proposed procedure is implemented without breaking the loop with the controller in operation, by activating a cascade of band-pass filters in series with a relay in the inner loop and a notch filter in the outer loop. A highly accurate estimate of the critical point of a process G_p(s) is obtained in the presence of measurement noise and load disturbance. The effectiveness of the proposed procedure is illustrated using a test batch consisting of stable, integrating and unstable processes, including dead-time.     

Influence of Whey Protein Addition and Feed Moisture Content on Chosen Physicochemical Properties of Directly Expanded Corn Extrudates

Production of extrudates from cereals is an often-used technological process in today’s world food industry. Extrudates from corn flour produced using the twin-screw extrusion process and enriched with whey protein concentrate represent high-quality source of proteins and fats. Whey protein concentrate (WPC) as a valuable source of proteins and minerals is one of the highest-quality components for possible extrudate enrichment. In this paper, the influence of various WPC addition and some extrusion process parameters such as feed moisture content ( Q_{\textH\text2 \textO} Q_{{{\text{H}}_{\text{2}} {\text{O}}}} ) on physicochemical properties of directly expanded corn flour extrudates manufactured in twin-screw co-rotating extruder was investigated. Whey protein concentrate was added in the following ratios 7.5%, 15% and 22.5% and water in 10.08, 12.18 and 14.28 L/h. Final composition of products is determined with measuring of protein, fat and water shares, water absorption index (WAI) and water solubility index (WSI). With added WPC and with increase of water volume flow, there was a significant rise in total protein, fat and water content in final products, as well as lowering of WSI and rising of WAI indexes. The statistical analysis of the obtained data shows that the lowest WSI and the highest WAI had samples with the largest share of WPC (22.5%) and water volume flow of 14.28 L/h. Colour is measured for each sample, and results were represented with hue angle (H), chroma (C) and lightness (L) values. Process parameters, WPC and Q_{\textH\text2 \textO} Q_{{{\text{H}}_{\text{2}} {\text{O}}}} influence the increase of saturation of C and lightness of L colour value, while H value stays unchanged. Mean value of H was 90.14 ± 1.06, which corresponds to dominance of yellow colour of samples.