Change detection for moving object segmentation with robust background construction under Wronskian framework

Although background subtraction techniques have been used for several years in vision systems for moving object detection, many of them fail to provide good results in presence of noise, illumination variation, non-static background, etc. A basic requirement of background subtraction scheme is the construction of a stable background model and then comparing each incoming image frame with it so as to detect moving objects. The novelty of the proposed scheme is to construct a stable background model from a given video sequence dynamically. The constructed background model is compared with different image frames of the same sequence to detect moving objects. In the proposed scheme the background model is constructed by analyzing a sequence of linearly dependent past image frames in Wronskian framework. The Wronskian based change detection model is further used to detect the changes between the constructed background scene and the considered target frame. The proposed scheme is an integration of Gaussian averaging and Wronskian change detection model. Gaussian averaging uses different modes which arise over time to capture the underlying richness of background, and it is an approach for background building by considering temporal modes. Similarly, Wronskian change detection model uses a spatial region of support in this regard. The proposed scheme relies on spatio-temporal modes arising over time to build the appropriate background model by considering both spatial and temporal modes. The results obtained by the proposed model is found to provide accurate shape of moving objects. The effectiveness of the proposed scheme is verified by comparing the results with those of some of the existing state of the art background subtraction techniques on public benchmark databases. We found that the average F-measure is significantly improved by the proposed scheme from that of the state-of-the-art techniques.     

A Robust Extended Complex Kalman Filter and Sliding-mode Control Based Shunt Active Power Filter

Abstract—This article presents the design of a new shunt active power filter that employs a modified robust extended complex Kalman filter approach with an exponential robust term embedded for reference current estimation together with a current controller based on the sliding-mode control concept. The robust extended complex Kalman filter exploits a new weighted exponential function to handle these grid perturbations to estimate the reference signal in shunt active power filter system. The current controller in the proposed shunt active power filter has been designed using a sliding-mode control strategy because of its ability to handle parameter uncertainties and ease in implementation. To test the effectiveness of the proposed shunt active power filter, extensive simulations were performed using MATLAB/Simulink (The MathWorks, Natick, Massachusetts, USA), and real-time studies were made using OPAL-RT (Montreal, Quebec, Canada). Results obtained from the above studies using the proposed shunt active power filter together with the different variants of Kalman filter (Kalman filter, extended Kalman filter, extended complex Kalman filter) are analyzed, and it is observed that the proposed robust extended complex Kalman filter-sliding-mode control based shunt active power filter provides accurate and improved harmonics mitigation and reactive power compensation.     

Dictionary-based classifiers for exploiting feature sequence information and their application to hyperspectral remotely sensed data

The problem of classification is shared across various disciplines. Designing even less computationally demanding and more effective classifiers has been a key challenge for researchers for many years. No single classifier can be highly effective for all types of datasets and thus, depending on the data distribution, various classifiers have been proposed in the literature. To our knowledge, feature values have been vastly exploited as the base for discriminating classes, while feature sequence information has been somehow under-exploited so far. In the proposed approach normalised features are sorted and ranked, creating a sequence of finite numbers. The associated rank of the created sequence is used as an additional feature, which in a way defines the sample-specific intra-feature relationship. Three novel dictionary-based approaches such as Sequence Classifier (SC), Sequence-dictionary-based k-Nearest Neighbours Classifier (SDk-NN) and Combined-dictionary-based k-Nearest Neighbours Classifier (CDk-NN) are proposed in this paper.

In the case of remotely sensed data, and specifically in Hyper-Spectral Images (HSI), the spectral features (Spectral signatures) represent a strong, object-specific spectral relationship, which is a key point in our proposed approach. In this case, indeed, the proposed classifiers were tested over various (five) HS datasets and found to be effective. Based on the classifiers features, two derived distance measures are proposed and validated for the HS dataset, namely: the Normalised Sequence Distance (NSD) measure and Combined Distance (CD) measure. These measures appear to overperform the conventional Normalised Euclidean Distance (NED) in this context. Also, validation for both binary and multi-class datasets are experimented and their performances are evaluated in terms of accuracy and other standard measures. Experimental results over 21 datasets revealed that the proposed approaches perform comparably, and in some cases even better than other classifiers. Stack-operated, class-specific sparse dictionaries are also introduced in order to reduce the computational complexity, which can be used as an active learning-based approach for optimal training sample selection. Additional tests were performed with variable levels of dictionary sparsity for assessing its impact on accuracy.     

Combinatorial design of calcium meta phosphate poly(vinyl alcohol) bone-like biocomposites

The incidence of degenerative diseases and the ageing population have added to the growing demand for bone grafts. Although autologous bone continues to be the gold standard, limited yield and potential morbidity of the donor site pose considerable challenges. Currently, clinically used synthetic grafts based on calcium phosphates are mechanically brittle and not compliant hence composite scaffolds are expected to be provide viable solutions. In this study we report composites of calcium meta phosphate-poly (vinyl alcohol) with tunable mechanical properties, low swelling and excellent biocompatibility. The elastomeric nature of the composites resist brittle fracture and the scaffolds can be easily shaped to the bone defect by the surgeon. Testing on bone plug shaped specimens of the scaffolds, exhibited superior mechanical properties compared to currently commercially available bone plugs with additional advantages being the ability to increase porosity without compromising properties in compression and degree of swelling, which make these composites promising synthetic alternatives for bone grafts and bone tissue engineering.     

Polymerization behavior of an organophosphorus monomer for use in dental restorative materials

Vibrational overtone activated polymerization of acrylonitrile (AN) has been demonstrated using two initiators, benzoyl peroxide (BP), and 2,2′‐(azobis)isobutyronitrile (AIBN). Excitation of the fifth vibrational overtone of the CH stretch of AIBN at 627 nm and BP at 604 nm initiates the reaction. Monomer conversions were monitored by a gravimetric method. In both cases, the wavelength selectivity was investigated by irradiating the monomer/initiator mixtures at the absorption maximum of the initiator, the absorption maximum of the monomer, and at a wavelength (580 nm for AN/AIBN and 625 nm for AN/BP) where neither the initiator nor the monomer absorbs light. For the AN/AIBN mixture, after 48 h the monomer conversion for the irradiation on the peak absorption of AIBN (627 nm) is about twice as large as the irradiation at 580 nm. For the AN/BP mixture, after 48 h the monomer conversion for the irradiation on the peak absorption of BP (604 nm) is about a factor of 2.2 larger than for the irradiation at 625 nm. The overall quantum yields of both polymerizations were estimated. After 48 h the overall quantum yield for the AN/AIBN mixture irradiated at the initiator absorption (Φ₆₂₇ = 21083) is about 10 times larger than for the sample irradiated at the pure monomer absorption (Φ₅₉₅ = 1942). For the AN/BP mixture, the 604 nm quantum yield (Φ₆₀₄ = 1096) is about 2.4 times larger than the 595 nm quantum yield (Φ₅₉₅ = 448). The influence of the initiator concentration is also presented. © 2003 Wiley Periodicals, Inc. J Appl Polym Sci 90: 565–571, 2003     

The preparation of high conversion polymeric systems containing eugenol residues and their rheological characterization

Copolymeric systems bearing eugenol covalently linked to the macromolecular chains have been prepared and characterised in terms of thermal, rheological and in vitro behaviour. Eugenyl methacrylate (EgMA) and ethoxyeugenyl methacrylate (EEgMA) were polymerized and copolymerized with ethyl methacrylate (EMA) in a wide range of feed composition by bulk at high conversion. Glass transition temperature (T_g) increased with the content of EgMA in the copolymer whereas T_g decreased with the content of EEgMA. The presence of any of the eugenyl monomers in the copolymer increased the thermal stability of the materials. Rheological analysis showed that EMA-co-EgMA copolymers present a higher density of crosslinking or entanglements among the chains compared with EMA-co-EEgMA materials, and copolymers containing more than 40% EgMA exhibited a pseudo-solid like behaviour with G′ relatively independent of the frequency. The average molecular weight between cross-links (M_c) for the latter copolymers was in the order of 10⁴ Da. For EEgMA copolymers, tan δ was lower than unity and G′ showed a gradual and slight dependency with frequency over the whole range of composition. In vitro behaviour showed a higher hydrophilicity of the EEgMA containing copolymers manifested in higher water sorption values, lower water contact angle values and higher surface free energy due to an increase in polarity. All systems presented a good cytocompatibility with human fibroblasts assessed through direct and indirect assays.     

In vitro antioxidant activity of different cultivars of banana flower (Musa paradicicus L.) extracts available in India

Abstract: Six different cultivars of banana flowers (Musa paradicicus) (Kathali, Bichi, Shingapuri, Kacha, Champa, and Kalabou) were analyzed for the content of polyphenol expressed as gallic acid equivalent and flavonoid expressed as quercetein equivalent, and the in vitro total antioxidative activities of the flower extracts were compared with standard and expressed as trolox equivalent. The reducing power, 1,1‐diphenyl‐2‐picrylhydrazyl (DPPH) and 2,2‐azinobis(3‐ethylbenzothiazoline‐6‐sulfonic acid) radical cation (ABTS?⁺) scavenging activities, inhibition of lipid peroxidation in a linoleic acid emulsion system, and liposome peroxidation system were measured and compared with respective standard antioxidants. Iron‐mediated Fenton reaction was carried out to evaluate the protective effect of the extract of banana flower (Kacha cultivar) against H₂O₂‐induced DNA damage. The Kacha variety contains the maximum amount of polyphenol (11.94 ± 0.03 mg of gallic acid equivalent/g of dry weight) and flavonoid (0.174 ± 0.001 g of quercetin equivalent/g of polyphenol). It also has the highest total antioxidant capacity, DPPH radical scavenging activity, and ABTS?⁺ radical scavenging activity with a least EC₅₀ value of 0.051 mg/mL. Hepatic cell damage in iron‐mediated Fenton reaction caused by free radicals is reduced by the banana flower extract. On the basis of the results obtained, the banana flowers are found to be a potential source of natural antioxidants. This is the first report on the antioxidant properties of the extracts from banana flowers. The study suggests that the flowers of M. paradicicus that are found in India and consumed as vegetable can provide valuable functional ingredients that help in the prevention of oxidative stress.     

An improved differential evolution trained neural network scheme for nonlinear system identification

This paper presents an improved nonlinear system identification scheme using di？erential evolution （DE）, neural network （NN） and Levenberg Marquardt algorithm （LM）. With a view to achieve better convergence of NN weights optimization during the training, the DE and LM are used in a combined framework to train the NN. We present the convergence analysis of the DE and demonstrate the efficacy of the proposed improved system identification algorithm by exploiting the combined DE and LM training of the NN and suitably implementing it together with other system identification methods, namely NN and DE＋NN on a number of examples including a practical case study. The identification results obtained through a series of simulation studies of these methods on different nonlinear systems demonstrate that the proposed DE and LM trained NN approach to nonlinear system identification can yield better identification results in terms of time of convergence and less identification error.     

Exploration of photoreduction ability of reduced graphene oxide–cadmium sulphide hetero-nanostructures and their intensified activities against harmful microbes

Journal of Materials Science - Fabrication of effective photocatalyst using semiconductors and graphene or reduced graphene oxide has been regarded as one of the most promising task to attenuate...     

Moving object detection using spatio-temporal multilayer compound Markov Random Field and histogram thresholding based change detection

Multimedia Tools and Applications - In this article, we propose a Multi Layer Compound Markov Random Field (MLCMRF) Model to spatially segment different image frames of a given video sequence. The...