Adaptive moving shadow detection and removal by new semi-supervised learning technique

The efficient application of current methods of shadow detection in video is hindered by the difficulty in defining their parameters or models and/or their application domain dependence. This paper presents a new shadow detection and removal method that aims to overcome these inefficiencies. It proposes a semi-supervised learning rule using a new variant of co-training technique for shadow detection and removal in uncontrolled scenes. The new variant both reduces the run-time through a periodical execution of a co-training process according to a novel temporal framework, and generates a more generic prediction model for an accurate classification. The efficiency of the proposed method is shown experimentally on a testbed of videos that were recorded by a static camera and that included several constraints, e.g., dynamic changes in the natural scene and various visual shadow features. The conducted experimental study produced quantitative and qualitative results that highlighted the robustness of our shadow detection method and its accuracy in removing cast shadows. In addition, the practical usefulness of the proposed method was evaluated by integrating it in a Highway Control and Management System software called RoadGuard.     

On line background modeling for moving object segmentation in dynamic scenes

Fast and accurate moving object segmentation in dynamic scenes is the first step in many computer vision applications. In this paper, we propose a new background modeling method for moving object segmentation based on dynamic matrix and spatio-temporal analyses of scenes. Our method copes with some challenges related to this field. A new algorithm is proposed to detect and remove cast shadow. A comparative study by quantitative evaluations shows that the proposed approach can detect foreground robustly and accurately from videos recorded by a static camera and which include several constraints. A Highway Control and Management System called RoadGuard is proposed to show the robustness of our method. In fact, our system has the ability to control highway by detecting strange events that can happen like vehicles suddenly stopped in roads, parked vehicles in emergency zones or even illegal conduct such as going out from the road. Moreover, RoadGuard is capable of managing highways by saving information about the date and time of overloaded roads.     

Supervisory control based on minimal cuts and Petri net sub-controllers coordination

This paper addresses the synthesis of Petri net (PN) controller for the forbidden state transition problem with a new utilisation of the theory of regions. Moreover, as any method of control synthesis based on a reachability graph, the theory of regions suffers from the combinatorial explosion problem. The proposed work minimises the number of equations in the linear system of theory of regions and therefore one can reduce the computation time. In this paper, two different approaches are proposed to select minimal cuts in the reachability graph in order to synthesise a PN controller. Thanks to a switch from one cut to another, one can activate and deactivate the corresponding?PNcontroller. An application is implemented in a flexible manufacturing system to illustrate the present method. Finally, comparison with previous works with experimental results in obtaining a maximally permissive controller is presented.     

Effect of Multi-Wall Carbon Nanotubes on the Mechanical Properties of Natural Rubber

Multi-walled carbon nanotubes (MWNTs) were used to prepare natural rubber (NR) nanocomposites. Our first efforts to achieve nanostructures in MWNTs/NR nanocomposites were formed by incorporating carbon nanotubes in a polymer solution and subsequently evaporating the solvent. Using this technique, nanotubes can be dispersed homogeneously in the NR matrix in an attempt to increase the mechanical properties of these nanocomposites. The properties of the nanocomposites such as tensile strength, tensile modulus, elongation at break and hardness were studied. Mechanical test results show an increase in the initial modulus for up to 12 times in relation to pure NR. In addition to mechanical testing, the dispersion state of the MWNTs into NR studied by Transmission Electron Microscopy (TEM) in order to understand the morphology of the resulting system     

Studies on pore blocking mechanism and technical feasibility of a hybrid PAC-MF process for reclamation of irrigation water from biotreated POME

An integrated low-cost adsorption (with powdered activated carbon, PAC) and cross-flow membrane filtration (with microfiltration membranes of 0.1 and 0.2 μm pore sizes) process was employed for the treatment of biotreated palm oil mill effluent (POME) to produce irrigation water that is fully benchmarked with water-quality standards. The permeate quality was within the recommended standard for irrigation water, as the concentrations of all critical constituents were well below their recommended values. Sustainability of the process integration was further confirmed with the domination of cake filtration over other blocking mechanisms with higher R² values at all trans-membrane pressures. Suitable extended usage of permeate was found for toilet/urinal flushing.     

A four year study to determine the optimal harvesting period for Tunisian Chemlali olives

Due to the importance of the stage of maturity on several olive pomological parameters and oil quality indices, and to the interest that Tunisian olive oil production has recently received, the optimal harvesting period for the main Tunisian olive cultivar, Chemlali, was assessed. For the first time, a four‐season crops study, carried out in three representative geographical areas, was focused on both olive fruit pomological parameters and oil chemical composition at different stages of maturity. The stage of maturity was the factor showing the highest influence on the major part of these parameters, followed by the crop year. To guarantee a reasonable fat content and a good chemical quality of oil, in particular a harmonious acidic composition, acceptable UV absorbance, and a content high of antioxidants, unsaponifiable matter and sterols, the optimal harvesting period for Chemlali olives would appears to be between the end of November to the middle of December, which corresponds to a maturity index between 2.5 and 3.5.     

Fabrication of CdSe‐Nanofibers with Potential for Biomedical Applications

The design and synthesis of nanostructured functional hybrid biomaterials are essential for the next generation of advanced diagnostics and the treatment of disease. A simple route to fabricate semiconductor nanofibers by self‐assembled, elastin‐like polymer (ELP)‐templated semiconductor nanoparticles is reported. Core–shell nanostructures of CdSe nanoparticles with a shell of ELPs are used as building blocks to fabricate functional one‐dimensional (1D) nanostructures. The CdSe particles are generated in situ within the ELP matrix at room temperature. The ELP controls the size and the size‐distribution of the CdSe nanoparticles in an aqueous medium and simultaneously directs the self‐assembly of core–shell building blocks into fibril architectures. It was found that the self‐assembly of core–shell building blocks into nanofibers is strongly dependent on the pH value of the medium. Results of cytotoxicity and antiproliferation of the CdSe‐ELP nanofibers demonstrate that the CdSe‐ELP does not exhibit any toxicity towards B14 cells. Moreover, these are found to be markedly capable of crossing the cell membrane of B14. In contrast, unmodified CdSe nanoparticles with ELPs cause a strong toxic response and reduction in the cell proliferation. This concept is valid for the fabrication of a variety of metallic and semiconductor 1D‐architectures. Therefore, it is believed that these could be used not only for biomedical purposes but for application in a wide range of advanced miniaturized devices.     

Linear viscoelastic behavior of poly(ethylene terephtalate) above Tg amorphous viscoelastic properties Vs crystallinity: Experimental and micromechanical modeling

Linear viscoelastic behavior of amorphous and semicrystalline poly(ethylene terephtalate), (PET), was experimentally investigated. PET’s samples with different crystallinities (Xc) were prepared and viscoelastically characterized. Based on our experimental results (properties of the amorphous PET and semicrystalline polymers), micromechanical model was used to, first predict the viscoelastic properties of the semicrystalline polymers and second predict the changes on the viscoelastic properties of the amorphous phase when the crystallinity increases. For the micromechanical modeling of semicrystalline material’s viscoelastic properties, difficulties lie on the used numerical methods (Laplace-Carson transformation) and also on the actual physical and mechanical properties of the amorphous phase. In this paper we tried to simplify the Laplace-Carson-based method by using a pseudo-elastic one that avoids the numerical difficulties encountered before. The time-dependant problem is so replaced by a frequency-dependant set of elastic equations. Good agreement with low crystallinity fraction was found however large discrepancies appear for medium and high crystallinity. The poor agreement raises the issue of which amorphous mechanical properties should be taken as input in the micromechanical model? According to the dynamic mechanical analysis (DMA) experimental data, multiple amorphous phases with different glass transition temperatures were observed for each tested semicrystalline sample. For each sample, new glass transition temperature related to an equivalent amorphous phase was determined. DMA tests done at 1 Hz help estimating the mechanical properties of the new amorphous phase based on its new glass transition temperature. Using the new micromechanical approach developed in this paper, the changes occurring on the viscoelastic behavior of the amorphous phase upon crystallization were estimated. Good agreement was found after comparing the micromechanically estimated amorphous behavior with the experimentally estimated one leading to believe that the physical and mechanical properties of the amorphous phase change upon crystallization and taking on account this phenomenon is a key to a good prediction of the semicrystalline behavior using micromechanical models.