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.

Mean field approach for tracking similar objects

In this paper, we consider the problem of tracking similar objects. We show how a mean field approach can be used to deal with interacting targets and we compare it with Markov Chain Monte Carlo (MCMC). Two mean field implementations are presented. The first one is more general and uses particle filtering. We discuss some simplifications of the base algorithm that reduce the computation time. The second one is based on suitable Gaussian approximations of probability densities that lead to a set of self-consistent equations for the means and covariances. These equations give the Kalman solution if there is no interaction. Experiments have been performed on two kinds of sequences. The first kind is composed of a single long sequence of twenty roaming ants and was previously analysed using MCMC. In this case, our mean field algorithms obtain substantially better results. The second kind corresponds to selected sequences of a football match in which the interaction avoids tracker coalescence in situations where independent trackers fail.

Gaussian Approximation for Tracking Occluding and Interacting Targets

In this paper, we show how interacting and occluding targets can be tackled successfully within a Gaussian approximation. For that purpose, we develop a general expansion of the mean and covariance of the posterior and we consider a first order approximation of it. The proposed method differs from EKF in that neither a non-linear dynamical model nor a non-linear measurement vector to state relation have to be defined, so it works with any kind of interaction potential and likelihood. The approach has been tested on three sequences (10400, 2500, and 400 frames each one). The results show that our approach helps to reduce the number of failures without increasing too much the computation time with respect to methods that do not take into account target interactions.

FhCaBP4: A Fasciola hepatica calcium binding protein with EF-hand and dynein light chain domains

In trematodes, there is a family of proteins which combine EF-hand-containing domains with dynein light chain (DLC)-like domains. A member of this family from the liver fluke, Fasciola hepatica-FhCaBP4-has been identified and characterised biochemically. FhCaBP4 has an N-terminal domain containing two imperfect EF-hand sequences and a C-terminal dynein light chain-like domain. Molecular modelling predicted that the two domains are joined by a flexible linker. Native gel electrophoresis demonstrated that FhCaBP4 binds to calcium, manganese, barium and strontium ions, but not to magnesium or zinc ions. The hydrophobic, fluorescent probe 8-anilinonaphthalene-1-sulphonate bound more tightly to FhCaBP4 in the presence of calcium ions. This suggests that the protein undergoes a conformational change on ion binding which increases the number of non-polar residues on the surface. FhCaBP4 was protected from limited proteolysis by the calmodulin antagonist W7, but not by trifluoperazine or praziquantel. Protein-protein cross-linking experiments showed that FhCaBP4 underwent calcium ion-dependent dimerisation. Since DLCs are commonly dimeric, it is likely that FhCaBP4 dimerises through this domain. The molecular model reveals that the calcium ion-binding site is located close to a key sequence in the DLC-like domain, suggesting a plausible mechanism for calcium-dependent dimerisation.

A sequential algorithm for sparse support vector classifiers

Support vector machines (SVMs), though accurate, are not preferred in applications requiring high classification speed or when deployed in systems of limited computational resources, due to the large number of support vectors involved in the model. To overcome this problem we have devised a primal SVM method with the following properties: (1) it solves for the SVM representation without the need to invoke the representer theorem, (2) forward and backward selections are combined to approach the final globally optimal solution, and (3) a criterion is introduced for identification of support vectors leading to a much reduced support vector set. In addition to introducing this method the paper analyzes the complexity of the algorithm and presents test results on three public benchmark problems and a human activity recognition application. These applications demonstrate the effectiveness and efficiency of the proposed algorithm.


--------------------------------------------------------------------------------

Gender Classification via Lips: Static and Dynamic Features

Automatic gender classification has many security and commercial applications. Various modalities have been investigated for gender classification with face-based classification being the most popular. In some real-world scenarios the face may be partially occluded. In these circumstances a classification based on individual parts of the face known as local features must be adopted. We investigate gender classification using lip movements. We show for the first time that important gender specific information can be obtained from the way in which a person moves their lips during speech. Furthermore our study indicates that the lip dynamics during speech provide greater gender discriminative information than simply lip appearance. We also show that the lip dynamics and appearance contain complementary gender information such that a model which captures both traits gives the highest overall classification result. We use Discrete Cosine Transform based features and Gaussian Mixture Modelling to model lip appearance and dynamics and employ the XM2VTS database for our experiments. Our experiments show that a model which captures lip dynamics along with appearance can improve gender classification rates by between 16-21% compared to models of only lip appearance.

Comparison of frequency-selective screen-based linear to circular split-ring polarisation convertors

This study presents the use of periodic arrays of freestanding slot frequency-selective screens (FSS) as a means for generating circularly polarised signals from an incident linearly polarised signal at normal incidence to the structure. Measured and simulated results for crossed, linear and various ring slot element shapes in single and double-layer polarisation convertor structures are presented for 10 GHz operation. It is shown that 3 dB axial ratio (AR) bandwidths of 21% can be achieved with the one-layer perforated screen design and that the rate of change is lower than the double-layer structures. An insertion loss of 0.34 dB can be achieved for the split circular ring double-layer periodic array, and of the three topologies presented the hexagonal split-ring polarisation convertor gives the lowest variation of AR with angle of incidence 1.8 dB/45° and 3.6 dB/45° for the single and double-screen FSS, respectively. In addition, their tolerance to angle of incidence variation is presented. The capability of the surfaces reported here as twist polariser or spatial isolator components has been demonstrated with up to -30 dB isolation between incident and re-reflected signals for the double-layer designs being measured. © 2010 The Institution of Engineering and Technology.

Laughter Induction Techniques Suitable for Generating Motion Capture Data of Laughter Associated Body Movements

Laughter is a frequently occurring social signal and an important part of human non-verbal communication. However it is often overlooked as a serious topic of scientific study. While the lack of research in this area is mostly due to laughter’s non-serious nature, it is also a particularly difficult social signal to produce on demand in a convincing manner; thus making it a difficult topic for study in laboratory settings. In this paper we provide some techniques and guidance for inducing both hilarious laughter and conversational laughter. These techniques were devised with the goal of capturing mo- tion information related to laughter while the person laughing was either standing or seated. Comments on the value of each of the techniques and general guidance as to the importance of atmosphere, environment and social setting are provided.

An Investigation Into Features For Multi-View Lipreading

For the first time in this paper we present results showing the effect of speaker head pose angle on automatic lip-reading performance over a wide range of closely spaced angles. We analyse the effect head pose has upon the features themselves and show that by selecting coefficients with minimum variance w.r.t. pose angle, recognition performance can be improved when train-test pose angles differ. Experiments are conducted using the initial phase of a unique multi view Audio-Visual database designed specifically for research and development of pose-invariant lip-reading systems. We firstly show that it is the higher order horizontal spatial frequency components that become most detrimental as the pose deviates. Secondly we assess the performance of different feature selection masks across a range of pose angles including a new mask based on Minimum Cross-Pose Variance coefficients. We report a relative improvement of 50% in Word Error Rate when using our selection mask over a common energy based selection during profile view lip-reading.