Human action recognition in H.264/AVC compressed domain using meta-cognitive radial basis function network

In this paper, we propose a H.264/AVC compressed domain human action recognition system with projection based metacognitive learning classifier (PBL-McRBFN). The features are extracted from the quantization parameters and the motion vectors of the compressed video stream for a time window and used as input to the classifier. Since compressed domain analysis is done with noisy, sparse compression parameters, it is a huge challenge to achieve performance comparable to pixel domain analysis. On the positive side, compressed domain allows rapid analysis of videos compared to pixel level analysis. The classification results are analyzed for different values of Group of Pictures (GOP) parameter, time window including full videos. The functional relationship between the features and action labels are established using PBL-McRBFN with a cognitive and meta-cognitive component. The cognitive component is a radial basis function, while the meta-cognitive component employs self-regulation to achieve better performance in subject independent action recognition task. The proposed approach is faster and shows comparable performance with respect to the state-of-the-art pixel domain counterparts. It employs partial decoding, which rules out the complexity of full decoding, and minimizes computational load and memory usage. This results in reduced hardware utilization and increased speed of classification. The results are compared with two benchmark datasets and show more than 90% accuracy using the PBL-McRBFN. The performance for various GOP parameters and group of frames are obtained with twenty random trials and compared with other well-known classifiers in machine learning literature. (C) 2015 Elsevier B.V. All rights reserved.

Compressed domain human action recognition in H.264/AVC video streams

This paper discusses a novel high-speed approach for human action recognition in H.264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of the proposed work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can result in reduced hardware utilization and faster recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust to outdoor as well as indoor testing scenarios. We have evaluated the performance of the proposed method on two benchmark action datasets and achieved more than 85 % accuracy. The proposed algorithm classifies actions with speed (> 2,000 fps) approximately 100 times faster than existing state-of-the-art pixel-domain algorithms.

Sparse Representation based Anomaly Detection using HOMV in H.264 Compressed Videos

In this paper, we have proposed an anomaly detection algorithm based on Histogram of Oriented Motion Vectors (HOMV) 1] in sparse representation framework. Usual behavior is learned at each location by sparsely representing the HOMVs over learnt normal feature bases obtained using an online dictionary learning algorithm. In the end, anomaly is detected based on the likelihood of the occurrence of sparse coefficients at that location. The proposed approach is found to be robust compared to existing methods as demonstrated in the experiments on UCSD Ped1 and UCSD Ped2 datasets.

Anomaly detection in compressed H.264/AVC video

Real time anomaly detection is the need of the hour for any security applications. In this article, we have proposed a real time anomaly detection for H.264 compressed video streams utilizing pre-encoded motion vectors (MVs). The proposed work is principally motivated by the observation that MVs have distinct characteristics during anomaly than usual. Our observation shows that H.264 MV magnitude and orientation contain relevant information which can be used to model the usual behavior (UB) effectively. This is subsequently extended to detect abnormality/anomaly based on the probability of occurrence of a behavior. The performance of the proposed algorithm was evaluated and bench-marked on UMN and Ped anomaly detection video datasets, with a detection rate of 70 frames per sec resulting in 90x and 250x speedup, along with on-par detection accuracy compared to the state-of-the-art algorithms.

A survey on compressed domain video analysis techniques

Image and video analysis requires rich features that can characterize various aspects of visual information. These rich features are typically extracted from the pixel values of the images and videos, which require huge amount of computation and seldom useful for real-time analysis. On the contrary, the compressed domain analysis offers relevant information pertaining to the visual content in the form of transform coefficients, motion vectors, quantization steps, coded block patterns with minimal computational burden. The quantum of work done in compressed domain is relatively much less compared to pixel domain. This paper aims to survey various video analysis efforts published during the last decade across the spectrum of video compression standards. In this survey, we have included only the analysis part, excluding the processing aspect of compressed domain. This analysis spans through various computer vision applications such as moving object segmentation, human action recognition, indexing, retrieval, face detection, video classification and object tracking in compressed videos.

Case studies on the formation of chalcogenide self-assembled monolayers on surfaces and dissociative processes

This report examines the assembly of chalcogenide organic molecules on various surfaces, focusing on cases when chemisorption is accompanied by carbon-chalcogen atom-bond scission. In the case of alkane and benzyl chalcogenides, this induces formation of a chalcogenized interface layer. This process can occur during the initial stages of adsorption and then, after passivation of the surface, molecular adsorption can proceed. The characteristics of the chalcogenized interface layer can be significantly different from the metal layer and can affect various properties such as electron conduction. For chalcogenophenes, the carbon-chalcogen atombond breaking can lead to opening of the ring and adsorption of an alkene chalcogenide. Such a disruption of the pi-electron system affects charge transport along the chains. Awareness about these effects is of importance from the point of view of molecular electronics. We discuss some recent studies based on X-ray photoelectron spectroscopy that shed light on these aspects for a series of such organic molecules.

Advancing Edge Speeds of Epithelial Monolayers Depend on Their Initial Confining Geometry

Collective cell migrations are essential in several physiological processes and are driven by both chemical and mechanical cues. The roles of substrate stiffness and confinement on collective migrations have been investigated in recent years, however few studies have addressed how geometric shapes influence collective cell migrations. Here, we address the hypothesis that the relative position of a cell within the confinement influences its motility. Monolayers of two types of epithelial cells-MCF7, a breast epithelial cancer cell line, and MDCK, a control epithelial cell line-were confined within circular, square, and cross-shaped stencils and their migration velocities were quantified upon release of the constraint using particle image velocimetry. The choice of stencil geometry allowed us to investigate individual cell motility within convex, straight and concave boundaries. Cells located in sharp, convex boundaries migrated at slower rates than those in concave or straight edges in both cell types. The overall cluster migration occurred in three phases: an initial linear increase with time, followed by a plateau region and a subsequent decrease in cluster speeds. An acto-myosin contractile ring, present in the MDCK but absent in MCF7 monolayer, was a prominent feature in the emergence of leader cells from the MDCK clusters which occurred every similar to 125 mu m from the vertex of the cross. Further, coordinated cell movements displayed vorticity patterns in MDCK which were absent in MCF7 clusters. We also used cytoskeletal inhibitors to show the importance of acto-myosin bounding cables in collective migrations through translation of local movements to create long range coordinated movements and the creation of leader cells within ensembles. To our knowledge, this is the first demonstration of how bounding shapes influence long-term migratory behaviours of epithelial cell monolayers. These results are important for tissue engineering and may also enhance our understanding of cell movements during developmental patterning and cancer metastasis.

CROWD FLOW SEGMENTATION IN COMPRESSED DOMAIN USING CRF

Crowd flow segmentation is an important step in many video surveillance tasks. In this work, we propose an algorithm for segmenting flows in H.264 compressed videos in a completely unsupervised manner. Our algorithm works on motion vectors which can be obtained by partially decoding the compressed video without extracting any additional features. Our approach is based on modelling the motion vector field as a Conditional Random Field (CRF) and obtaining oriented motion segments by finding the optimal labelling which minimises the global energy of CRF. These oriented motion segments are recursively merged based on gradient across their boundaries to obtain the final flow segments. This work in compressed domain can be easily extended to pixel domain by substituting motion vectors with motion based features like optical flow. The proposed algorithm is experimentally evaluated on a standard crowd flow dataset and its superior performance in both accuracy and computational time are demonstrated through quantitative results.

Preparation and Tribological Studies of Stearic Acid Self-Assembled Monolayers on Polymer-Coated Silicon Surface

We present a good alternative method to improve the tribological properties of polymer films by chemisorbing a long-chain monolayer on the functional polymer surface. Thus, a novel self-assembled monolayer is successfully prepared on a silicon substrate coated with amino-group-containing polyethyleneimine (PEI) by the chemical adsorption of stearic acid (STA) molecules. The formation and structure of the STA-PEI film are characterized by means of contact-angle measurement and ellipsometric thickness measurement, and of Fourier transformation infrared spectrometric and atomic force microscopic analyses. The micro- and macro-tribological properties of the STA-PEI film are investigated on an atomic force microscope (AFM) and a unidirectional tribometer, respectively. It has been found that the STA monolayer about 2.1-nm thick is produced on the PEI coating by the chemical reaction between the amino groups in the PEI and the carboxyl group in the STA molecules to form a covalent amide bond in the presence of N,N'-dicyclohexylcarbodiimide (DCCD) as a dehydrating regent. By introducing the STA monolayer, the hydrophilic PEI polymer surface becomes hydrophobic with a water contact angle to be about 105degrees. Study of the time dependence of the film formation shows that the adsorption of PEI is fast, whereas at least 24 h is needed to generate the saturated STA monolayer. Whereas the PEI coating has relatively high adhesion, friction, and poor anti-wear ability, the STA-PEI film possesses good adhesive resistance and high load-carrying capacity and anti-wear ability, which could be attributed to the chemical structure of the STA-PEI thin film. It is assumed that the hydrogen bonds between the molecules of the STA-PEI film act to stabilize the film and can be restored after breaking during sliding. Thus, the self-assembled STA-PEI thin film might find promising application in the lubrication of micro-electromechanical systems (MEMS).

Electrochemical, spectroscopic and SPM evidence for the controlled formation of self-assembled monolayers and organised multilayers of ferrocenyl alkyl thiols on Au(111)

Organised multilayers were formed from the controlled self-assembly of ferrocene alkyl thiols on Au(111) surfaces. The control was accomplished by increasing the concentration of the thiol solutions used for the assembly. Cyclic voltammetry, ellipsometry, scanning probe microscopy (STM and AFM) and in situ FTIR spectroscopy were used to probe the differences between mono- and multilayers of the same compounds. Electrochemical desorption studies confirmed that the multilayer structure is attached to the surface via one monolayer. The electrochemical behaviour of the multilayers indicated the presence of more than one controlling factor during the oxidation step, whereas the reduction was kinetically controlled which contrasts with the behaviour of monolayers, which exhibit kinetic control for the oxidation and reduction steps. Conventional and imaging ellipsometry confirmed that multilayers with well-defined increments in thickness could be produced. However, STM indicated that at the monolayer stage, the thiols used promote the mobility of Au atoms on the surface. It is very likely that the multilayer structure is held together through hydrogen bonding. To the best of out knowledge, this is the first example of a controlled one-step growth of multilayers of ferrocenyl alkyl thiols using self-assembly techniques.

Asymptotic analysis based on K-S constitutive law for a rubber wedge compressed by a line load at its tip

In the present paper, a rubber wedge compressed by a line load at its tip is asymptotically analyzed using a special constitutive law proposed by Knowles and Sternberg (K-S elastic law) [J. Elasticity 3 (1973) 67]. The method of dividing sectors proposed by Gao [Theoret. Appl. Fract, Mech. 14 (1990) 219] is used. Domain near the wedge tip can be divided into one expanding sector and two narrowing sectors. Asymptotic equations of the strain-stress field near the wedge tip are derived and solved numerically. The deformation pattern near a wedge tip is completely revealed. A special case. i.e. a half space compressed by a line load is solved while the wedge angle is pi.

Immunosensor Interface Based on Physical and Chemical Immunogylobulin G Adsorption onto Mixed Self-Assembled Monolayers

An immunosensor interface based on mixed hydrophobic self-assembled monolayers (SAMs) of methyl and carboxylic acid terminated thiols with covalently attached human Immunoglobulin G (hIgG), is investigated. The densely packed and organised SAMs were characterised by contact angle measurements and cyclic voltammetry. The effect of the non-ionic surfactant, Tween 20, in preventing nonspecific adsorption is addressed by ellipsometry during physical and covalent hIgG immobilization on pure and mixed SAMs, respectively. It is clearly demonstrated that nonspecific adsorption due to hydrophobic interactions of hIgG on methyl ended groups is totally inhibited, whereas electrostatic/hydrogen bonding interactions with the exposed carboxylic groups prevail in the presence of surfactant. Results of ellipsometry and Atomic Force Microscopy, reveal that the surface concentration of covalently immobilized hIgG is determined by the ratio of COOH/CH3-terminated thiols in SAM forming solution. Moreover, the ellipsometric data demonstrates that the ratio of bound anti-hIgG/hIgG depends on the density of hIgG on the surface and that the highest ratio is close to three. We also report the selectivity and high sensitivity achieved by chronoamperometry in the detection of adsorbed hIgG and the reaction with its antibody.

Functionalization of Si(111) surfaces and the formation of mixed monolayers for the covalent attachment of molecular catalysts in photoelectrochemical devices

The functionalization of silicon surfaces with molecular catalysts for proton reduction is an important part of the development of a solar-powered, water-splitting device for solar fuel formation. The covalent attachment of these catalysts to silicon without damaging the underlying electronic properties of silicon that make it a good photocathode has proven difficult. We report the formation of mixed monolayer-functionalized surfaces that incor- porate both methyl and vinylferrocenyl or vinylbipyridyl (vbpy) moieties. The silicon was functionalized using reaction conditions analogous to those of hydrosilylation, but instead of a H-terminated Si surface, a chlorine-terminated Si precursor surface was used to produce the linked vinyl-modified functional group. The functionalized surfaces were characterized by time-resolved photoconductivity decay, X-ray photoelectron spectroscopy (XPS), electro- chemical, and photoelectrochemical measurements. The functionalized Si surfaces were well passivated, exhibited high surface coverage and few remaining reactive Si atop sites, had a very low surface recombination velocity, and displayed little initial surface oxidation. The surfaces were stable toward atmospheric and electrochemical oxidation. The surface coverage of ferrocene or bipyridine was controllably varied from 0 up to 30% of a monolayer without loss of the underlying electronic properties of the silicon. Interfacial charge transfer to the attached ferrocene group was relatively rapid, and a photovoltage of 0.4 V was generated upon illumination of functionalized n-type silicon surfaces in CH₃CN. The immobilized bipyridine ligands bound transition metal ions, and thus enabled the assembly of metal complexes on the silicon surface. XPS studies demonstrated that [Cp∗Rh(vbpy)Cl]Cl, [Cp∗Ir(vbpy)Cl]Cl, and Ru(acac)₂vbpy were assembled on the surface. For the surface prepared with iridium, x-ray absorption spectroscopy at the Ir L_III edge showed an edge energy and post-edge features virtually identical to a powder sample of [Cp∗Ir(bipy)Cl]Cl (bipy is 2,2 ́-bipyridyl). Electrochemical studies on these surfaces confirmed that the assembled complexes were electrochemically active.