Rao-blackwellized particle filter for human appearance and position tracking

In human motion analysis, the joint estimation of appearance, body pose and location parameters is not always tractable due to its huge computational cost. In this paper, we propose a Rao-Blackwellized Particle Filter for addressing the problem of human pose estimation and tracking. The advantage of the proposed approach is that Rao-Blackwellization allows the state variables to be splitted into two sets, being one of them analytically calculated from the posterior probability of the remaining ones. This procedure reduces the dimensionality of the Particle Filter, thus requiring fewer particles to achieve a similar tracking performance. In this manner, location and size over the image are obtained stochastically using colour and motion clues, whereas body pose is solved analytically applying learned human Point Distribution Models.

2D silhouette and 3D skeletal models for human detection and tracking

In this paper we propose a statistical model for detection and tracking of human silhouette and the corresponding 3D skeletal structure in gait sequences. We follow a point distribution model (PDM) approach using a Principal Component Analysis (PCA). The problem of non-lineal PCA is partially resolved by applying a different PDM depending of pose estimation; frontal, lateral and diagonal, estimated by Fisher's linear discriminant. Additionally, the fitting is carried out by selecting the closest allowable shape from the training set by means of a nearest neighbor classifier. To improve the performance of the model we develop a human gait analysis to take into account temporal dynamic to track the human body. The incorporation of temporal constraints on the model increase reliability and robustness.

Calibrated CFD simulation to evaluate thermal comfort in a highly-glazed naturally ventilated room

Natural ventilation is a sustainable solution to maintaining healthy and comfortable environmental conditions in buildings. However, the effective design, construction and operation of naturally ventilated buildings require a good understanding of complex airflow patterns caused by the buoyancy and wind effects.The work presented in this article employed a 3D computational fluid dynamics (CFD) analysis in order to investigate environmental conditions and thermal comfort of the occupants of a highly-glazed naturally ventilated meeting room. This analysis was facilitated by the real-time field measurements performed in an operating building, and previously developed formal calibration methodology for reliable CFD models of indoor environments. Since, creating an accurate CFD model of an occupied space in a real-life scenario requires a high level of CFD expertise, trusted experimental data and an ability to interpret model input parameters; the calibration methodology guided towards a robust and reliable CFD model of the indoor environment. This calibrated CFD model was then used to investigate indoor environmental conditions and to evaluate thermal comfort indices for the occupants of the room. Thermal comfort expresses occupants' satisfaction with thermal environment in buildings by defining the range of indoor thermal environmental conditions acceptable to a majority of occupants. In this study, the thermal comfort analysis, supported by both field measurements and CFD simulation results, confirmed a satisfactory and optimal room operation in terms of thermal environment for the investigated real-life scenario. © 2013 Elsevier Ltd.

CCN2/CTGF increases expression of miR-302 microRNAs, which target the TGF beta type II receptor with implications for nephropathic cell phenotypes

Signalling interplay between transforming growth factor-beta (TGF beta) and CCN2 [also called connective tissue growth factor (CTGF)] plays a crucial role in the progression of diabetic nephropathy and has been implicated in cellular differentiation. To investigate the potential role of microRNAs (miRNAs) in the mediation of this signalling network, we performed miRNA screening in mesangial cells treated with recombinant human CCN2. Analysis revealed a cohort of 22 miRNAs differentially expressed by twofold or more, including members of the miR-302 family. Target analysis of miRNA to 3'-untranslated regions (3'-UTRs) identified TGF beta receptor II (T beta RII) as a potential miR-302 target. In mesangial cells, decreased T beta RII expression was confirmed in response to CCN2 together with increased expression of miR-302d. T beta RII was confirmed as an miR-302 target, and inhibition of miR-302d was sufficient to attenuate the effect of CCN2 on T beta RII. Data from the European Renal cDNA Biopsy Bank revealed decreased T beta RII in diabetic patients, suggesting pathophysiological significance. In a mouse model of fibrosis (UUO), miR-302d was increased, with decreased T beta RII expression and aberrant signalling, suggesting relevance in chronic fibrosis. miR-302d decreased TGF beta-induced epithelial mesenchymal transition (EMT) in renal HKC8 epithelial cells and attenuated TGF beta-induced mesangial production of fibronectin and thrombospondin. In summary, we demonstrate a new mode of regulation of TGF beta by CCN2, and conclude that the miR-302 family has a role in regulating growth factor signalling pathways, with implications for nephropathic cell fate transitions.

Kernelized structural classification for 3D dogs body parts detection

Despite pattern recognition methods for human behavioral analysis has flourished in the last decade, animal behavioral analysis has been almost neglected. Those few approaches are mostly focused on preserving livestock economic value while attention on the welfare of companion animals, like dogs, is now emerging as a social need. In this work, following the analogy with human behavior recognition, we propose a system for recognizing body parts of dogs kept in pens. We decide to adopt both 2D and 3D features in order to obtain a rich description of the dog model. Images are acquired using the Microsoft Kinect to capture the depth map images of the dog. Upon depth maps a Structural Support Vector Machine (SSVM) is employed to identify the body parts using both 3D features and 2D images. The proposal relies on a kernelized discriminative structural classificator specifically tailored for dogs independently from the size and breed. The classification is performed in an online fashion using the LaRank optimization technique to obtaining real time performances. Promising results have emerged during the experimental evaluation carried out at a dog shelter, managed by IZSAM, in Teramo, Italy.

Kinetic analysis of the cleavage of human protease-activated receptor-1/2/3 and 4 using quenched-fluorescent peptide substrates

Protease-activated receptors [PARs] are a family of G-protein-coupled seven-transmembrane domain receptors that are activated by proteolytic cleavage of their amino-terminal exodomain. To characterize the cleavage rate of human PAR-1 / 2 / 3 and 4 by trypsin and thrombin, four synthetic quenched-fluorescent peptide substrates have been synthesized. Each substrate consisted of a ten-residue peptide spanning the receptor activation cleavage site and using progress-curve kinetics, k(cat)/K-m values were determined.