The ChaLearn gesture dataset (CGD 2011)

This paper describes the data used in the ChaLearn gesture challenges that took place in 2011/2012, whose results were discussed at the CVPR 2012 and ICPR 2012 conferences. The task can be described as: user-dependent, small vocabulary, fixed camera, one-shot-learning. The data include 54,000 hand and arm gestures recorded with an RGB-D \(\hbox {Kinect}^\mathrm{TM}\) camera. The data are organized into batches of 100 gestures pertaining to a small gesture vocabulary of 8–12 gestures, recorded by the same user. Short continuous sequences of 1–5 randomly selected gestures are recorded. We provide man-made annotations (temporal segmentation into individual gestures, alignment of RGB and depth images, and body part location) and a library of function to preprocess and automatically annotate data. We also provide a subset of batches in which the user’s horizontal position is randomly shifted or scaled. We report on the results of the challenge and distribute sample code to facilitate developing new solutions. The data, datacollection software and the gesture vocabularies are downloadable from http://gesture.chalearn.org. We set up a forum for researchers working on these data http://groups.google.com/group/gesturechallenge.     

Principal motion components for one-shot gesture recognition

This paper introduces principal motion components (PMC), a new method for one-shot gesture recognition. In the considered scenario a single training video is available for each gesture to be recognized, which limits the application of traditional techniques (e.g., HMMs). In PMC, a 2D map of motion energy is obtained per each pair of consecutive frames in a video. Motion maps associated to a video are processed to obtain a PCA model, which is used for recognition under a reconstruction-error approach. The main benefits of the proposed approach are its simplicity, easiness of implementation, competitive performance and efficiency. We report experimental results in one-shot gesture recognition using the ChaLearn Gesture Dataset; a benchmark comprising more than 50,000 gestures, recorded as both RGB and depth video with a Kinect?camera. Results obtained with PMC are competitive with alternative methods proposed for the same data set.     

Automated Meta-Control for Adaptable Real-Time Software

The software meta-controller is an online agent responsible for dynamically adapting an application's software configuration, e.g. altering operational modes and migrating tasks, to best accommodate varying runtime circumstances. In distributed real-time applications such adaptations must be carried out in a manner which maintains the schedulability of all critical tasks while maximizing some notion of system value for all other tasks. For large-scale real-time applications, considering all possible adaptations at the task-level is computationally intractable. This paper presents an automated aggregate approach to software meta-control, appropriate for large-scale distributed real-time systems. The aggregate automated meta-control problem is still NP-hard, but it has very practical approximate solutions. Introduced, here, are two very-effective approximation algorithms, QDP and GG, with very reasonable polynomial time complexity. Both algorithms also provide us with upper bounds for optimum system values, useful for deriving absolute, albeit somewhat pessimistic, measures of actual performance. Extensive Monte Carlo analysis is used to illustrate that expected performance for both algorithms is generally suboptimal by no more than a few percent. Our flexible software meta-control model is also shown to be readily applied to a wide range of time-sensitive applications.     

Analogue CMOS prototype vision chip with prewitt edge processing

In this study, the design and realization of an analogue CMOS prototype vision chip with Prewitt edge processing is presented. The chip is designed with voltage and current mode and the main parts are one 16?×?16 pixel array, one pair of absolute value circuits and two transimpedance amplifiers. The technology process is TSMC 0.35???m. The edge processing is performed parallely on pixel level. The performance of the sensor comprises a processing time of 450?ns; optical dynamic range of 53?dB; power consumption at 30 frames per second of 1.5?mW; peak signal to noise ratio of 44?dB.     

Effects of porosity,dry unit weight,cement content and void/cement ratio on unconfined compressive strength of roof tile waste-silty soil mixtures

One of the conventional ways to improve the mechanical behavior of soils is to mix them with cementing agents such as cement, lime and fly ash. Recently, introduction to alternative materials or sub-products that can be adopted to improve the soil strength is of paramount importance. Therefore, the present study aims to investigate the effects of porosity (η), dry unit weight (γ_d) of molding, cement content (C) and porosity/volumetric cement content ratio (η/C_iv) or void/cement ratio on the unconfined compressive strength (q_u or UCS) of silty soil–roof tile waste (RT) mixtures. Soil samples are molded into four different dry unit weights (i.e. 13 kN/m³, 13.67 kN/m³, 14.33 kN/m³ and 15 kN/m³) using 3%, 6% and 9% cement and 5%, 15% and 30% RT. The results show that with the addition of cement, the strength of the RT–soil mixtures increases in a linear manner. On the other hand, the addition of RT decreases q_u of the samples at a constant percentage of cement, and the decrease in porosity can increase q_u. A dosage equation is derived from the experimental data using the porosity/volumetric cement content ratio (η/C_iv) where the control variables are the moisture content, crushed tile content, cement content and porosity.     

Fisher’s decision tree

Univariate decision trees are classifiers currently used in many data mining applications. This classifier discovers partitions in the input space via hyperplanes that are orthogonal to the axes of attributes, producing a model that can be understood by human experts. One disadvantage of univariate decision trees is that they produce complex and inaccurate models when decision boundaries are not orthogonal to axes. In this paper we introduce the Fisher’s Tree, it is a classifier that takes advantage of dimensionality reduction of Fisher’s linear discriminant and uses the decomposition strategy of decision trees, to come up with an oblique decision tree. Our proposal generates an artificial attribute that is used to split the data in a recursive way.The Fisher’s decision tree induces oblique trees whose accuracy, size, number of leaves and training time are competitive with respect to other decision trees reported in the literature. We use more than ten public available data sets to demonstrate the effectiveness of our method.     

Solid-state NMR for the analysis of interface excesses in Li-doped MgAl2O4 nanocrystals

Interface segregation plays a governing role in nanocrystalline ceramics properties due to the relative increase in the interfacial volume fraction. However, due to the complexity of the detection and quantification of interfacial excesses at the nanoscale, the role of ionic dopants or additives on microstructural evolution and thermodynamics can be easily underestimated. In this work, we address the spatial distribution of Li⁺ as a dopant in magnesium aluminate spinel nanoparticles. This is achieved through a novel method for the detection and quantification of Li⁺ across the surface, grain boundary, and bulk (crystal lattice). Based on selective lixiviation combined with chemical analysis, we were able to quantify the amount of Li⁺ forming surface excess, whereas the quantitative solid-state nuclear magnetic resonance technique enabled the quantification of Li⁺ segregated in the grain boundaries and dissolved in the lattice. This comprehensive understanding of the Li⁺ distribution across the nanoparticles makes possible an unprecedented interpretation of coarsening and sintering, with a clear correlation between the microstructure and the Li⁺ distribution. Although the work focuses on MgAl₂O₄, the proposed combination of techniques is expected to have a positive impact on the understanding of other multicomponent nanoscale systems.     

The influence of mineralogical,chemical and physical properties on grindability of commercial clinkers with high MgO level

This research investigates various methods able to identify possible mineralogical, physical and chemical influences on the grindability of commercial clinkers with high MgO level. The aim of the study is to evaluate the hardness and elastic modulus of the clinker mineral phases and their fracture strength during the comminution processes, comparing samples from clinkers with low MgO level (0.5%) and clinkers with elevated MgO levels (> 5.0%). The study of the influence of mineralogical, chemical and physical properties was carried out using several analytical techniques, such as: optical microscopy, X-ray diffraction with Rietveld refinement (XRD) and X-ray fluorescence (XRF). These techniques were useful in qualifying the different clinker samples. The drop weight test (DWT) and the Bond ball mill grindability test were performed to characterize the mechanical properties of clinkers. Nanoindentation tests were also carried out. Results from the Bond ball mill grindability test were found to be related to the hardness of the mineral phase and to mineralogical characteristics, such as type and amount of inclusions in silicates, belite and alite crystals shape, or microcracked alites. In contrast, the results obtained by the DWT were associated to the macro characteristics of clinkers, such as porosity, as well as to the hardness and mineralogical characteristics of belite crystals in clusters. Hardness instrumented tests helped to determine the Vickers hardness and elastic modulus from the mineral phases in commercial clinkers and produced different values for the pure phases compared to previous publications.     

Lessons Learned from the Two Major Tailings Dam Accidents in Brazil

Mine Water and the Environment - The failures of the Mariana and Brumadinho tailings dams in Minas Gerais, Brazil, had severe environmental repercussions and caused many fatalities. What should or...